From graham@gnelson.demon.co.uk Sun Jan 19 14:47:13 MET 1997
Article: 21404 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!newsfeed.uk.ibm.net!arclight.uoregon.edu!feed1.news.erols.com!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!EU.net!uknet!usenet1.news.uk.psi.net!uknet!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform library criticism (was: [INFORM] Takeable actors?)
Date: Wed, 15 Jan 1997 20:48:09 +0000 (GMT)
Organization: none
Lines: 38
Message-ID: <ant152009f7fM+4%@gnelson.demon.co.uk>
References: <5b6ivg$thv@bartlet.df.lth.se> <erkyrathE3wqrL.MAs@netcom.com> <5bbn05$bbo@bartlet.df.lth.se> <erkyrathE3xL4H.1ow@netcom.com> <erkyrathE3xLnA.31z@netcom.com> <5bdu63$p75@milo.vcn.bc.ca> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]

In article <5bdu63$p75@milo.vcn.bc.ca>, Neil K. Guy
<URL:mailto:nkg@vcn.bc.ca> wrote:
> 
> Andrew Plotkin (erkyrath@netcom.com) wrote:
> : Andrew Plotkin (erkyrath@netcom.com) wrote:
> : > Also, evil lurks everywhere, so keep your Uzi loaded.
> : 
> : In retrospect, a better conclusion is "...so give in to the Dark Side, 
> : buster."

Evil I may be, but at least I post to the newsgroup these days,
so I'm not quite so much of a lurker.

The substance of this thread is that the Inform library may be
practical and highly evolved, but has a few very murky corners from
a conceptual point of view, and in general isn't what we would
write if we were going to start all over again.  I think this
fair comment (though one should distinguish between the parser
and the verb library: the parser's not bad at all, I think).

I have occasionally thought that it would be nice to implement
an entirely new library in a proper object-oriented style.  But
I can't find a really convincingly OO way to implement the
typical problems confronting an IF model.  The classes of objects
interact too much.  Clashes of priority of different rules
(some methods in one class, some methods in another, etc.) have
to be resolved somewhere, and in an explicit way.  Not only
that, but objects in Inform basically change class dynamically
and often (as attributes are roughly used to indicate class
membership).

These are not insurmountable problems.  I'm just not sure that
I can see the "right" way to object-ify an IF world model.
Neither TADS nor Inform entirely convinces me.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From rglasser@penning.lanl.gov Sun Jan 19 14:47:20 MET 1997
Article: 21398 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!worldnet.att.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform library criticism (was: [INFORM] Takeable actors?)
Date: Thu, 16 Jan 1997 17:46:19 -0800
Organization: UCSD
Lines: 53
Message-ID: <32DED9EB.1BB5@penning.lanl.gov>
References: <5b6ivg$thv@bartlet.df.lth.se> <erkyrathE3wqrL.MAs@netcom.com> <5bbn05$bbo@bartlet.df.lth.se> <erkyrathE3xL4H.1ow@netcom.com> <32DD3B26.7922@penning.lanl.gov> <erkyrathE443F1.C13@netcom.com>
NNTP-Posting-Host: sdx-ca16-15.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Thu Jan 16  5:48:34 PM PST 1997
X-Mailer: Mozilla 2.0 (Win95; I)

Andrew Plotkin wrote:
> 
> Russell Glasser (rglasser@penning.lanl.gov) wrote:
> > Andrew Plotkin wrote:
> > >
> > > Magnus Olsson (mol@bartlet.df.lth.se) wrote:(regarding hacking the Inform libraries)
> > >
> > > > But this is _evil_.
> > >     <facetious>
> > > Of course it's evil. Computer languages are evil. Compilers are a
> > > terribly painful hack to get around the fact that computers aren't good
> > > enough to interpret English on the fly. The Z-machine is an evil hack to
> > > get around our unbelievably stupid policy of making computers that are
> > > incompatible with each other. Computer games are an attempt to take our
> > > minds off how lonely and miserable we all are because telepathy hasn't
> > > been invented yet.
> > >     </facetious>
> 
> First of all, I did not write the "facetious" tags. I was not being
> facetious. (Zen, maybe. Whap!)
> 

	Matter of fact I did not mean to put the "facetious" tags as if they 
were quoted text, it was a typo.  I take sole credit for adding them.

> I will restate my point now:
> 
> *The Inform libraries are what we have*. They are not the only compromises
> of elegance that I have in my life. Standing up and saying "Wait, this
> isn't perfect!" as if it's some vast revelation gets nothing from me but
> a disgusted glare.
> 	I respectfully withstand your disgusted glare.  However, I don't think 
the issue is whether Inform is perfect or not; I think it's an aesthetic 
preference regarding whether hacking the libraries is a good idea if it can 
possibly be avoided.
	Now, in Magnus' case, he offered a solution which, although he clearly 
said "I hate doing this", was apparently workable -- make the subject not a 
creature for the duration of one turn, then make it one again after taking it. 
This is bad because it's a kludge, but in my opinion it's STILL better than 
hacking the library... in fact, when I ask an Inform question, I'm always 
thinking of hacking the libraries as a last-last-last DESPERATE resort.  After 
all, I think one changes libraries more often than one changes the game 
they're writing; and when you do start a new game, you can easily cut n' paste 
things you wrote without having to comb through the old code to remember which 
is Graham's and which is yours.
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From d91frera@ida.liu.se Sun Jan 19 14:52:44 MET 1997
Article: 21384 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!data.ramona.vix.com!news1.digital.com!pa.dec.com!depot.mro.dec.com!news.jrd.dec.com!tbjnws.tbj.dec.com!tkonws.tko.dec.com!news.dec-j!cs.titech.ac.jp!tokyonet.ad.jp!sinfony-news01!news-jp-0.abone.net!np0.iij.ad.jp!nf0.iij.ad.jp!news.iij.ad.jp!linkclub.or.jp!inetc-news!aa.com!newsbase.nisiq.net!newsfeed.internetmci.com!feed1.news.erols.com!news.ecn.uoknor.edu!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: 10 Jan 1997 13:14:05 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 57
Message-ID: <5b5fat$jni@curofix.ida.liu.se>
References: <32b72f97@beachyhd.demon.co.uk> <59cimp$2hf@life.ai.mit.edu> <59uhn6$c0@mamba.cs.Virginia.EDU> <32c42118.5378687@news.one.net> <5a452b$kfh@life.ai.mit.edu> <32c6d623.12304274@news.one.net> <32cd1d9d.1222125@news.peinet.pe.ca> <32D12DF8.50C8A820@alcyone.com> <32d5942b.11742402@news.peinet.pe.ca>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)

tbarrie@cycor.ca (Trevor Barrie) writes:

>Erik Max Francis <max@alcyone.com> wrote:

>>> How on earth are either of those supposed to be more intuitive than the
>>> LISP example?
>>
>>I would say it's undeniably true that to people unfamiliar with computing,
>>LISP is far more hard to learn than a more English-like language like BASIC.

Some of the LISP functions have obscure names, granted. That is probably
because it has more built-in functions than say BASIC. The BASIC I've used
the most is Commodore 64 BASIC, which has about 60 keywords. The Common-LISP
I'm using has about 700 functions. The most basic ones are just as simple as
they are in BASIC. But then, when you want to do something complex in 
Common-LISP, you just find the function that does the job, you usually don't
have to write a lot yourself unless you want to.

Also, LISP has a very simple syntax. You use first paranthesis to say that
a new functioncall is beginning, then comes the function, then its arguments,
and a closing paranthesis to say that the functioncall is complete.
*Everyting* is separated by spaces, never commas, semicolons, colons, curly
brackets, square brackets or any other obscure,
hard-to-remember-when-to-use-what characters. In my experience, beginners
get started with real programming, as opposed to syntax guessing, much faster
with LISP than BASIC.

>>I wouldn't call it a matter of intuitiveness; it's just that BASIC (and even
>>Pascal or C) are more easily readable to people than LISP, particularly
>>without any prior experience with programming languages.

No matter what language you are trying to teach, you must start by explaining
something about the paradigm. The functional paradigm requires understanding
of recursion, which is something some people pick up in 5 seconds, while
others take 5 hours. Once you understand that, and the idea of prefix notation,
you are ready to go.

>Okay, that "particularly" seems pretty questionable to me... if anybody's
>going to have problems with LISP, it's those who _have_ prior experience
>with programming languages.

I definitely agree on this. I've been teaching both BASIC and LISP to
beginners as well as people with some experience in programming. It was
amazing how bad the C and Pascal hackers were doing with LISP at the start,
and how well the beginners were doing. A beginner would often come up with
a solution half as big and twice as elegant as the ones who had been
programming in procedural languages before. Then, after a while, when they got
the hang of it, the procedural programmers could benefit from their previous
experience.

/Fredrik

--
Fredrik Ramsberg, Comp Sci student, Linkoeping,                       SWEDEN
d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
----------------------------------------------------------------------------
Proud winner of the 1996 Humility World Championships!!!


From d91frera@ida.liu.se Sun Jan 19 14:58:49 MET 1997
Article: 21409 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: 15 Jan 1997 13:57:17 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 44
Message-ID: <5binnt$3da@curofix.ida.liu.se>
References: <32b72f97@beachyhd.demon.co.uk> <32D12DF8.50C8A820@alcyone.com> <32d5942b.11742402@news.peinet.pe.ca> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)

Erik Max Francis <max@alcyone.com> writes:

>Er, my wording suggested something I wasn't trying to indicate; I myself
>find LISP intriguing and have no problem with it (though I don't use it
>extensively).  However, arguing that it is just as easy for computer
>newcomers to learn as other languages such as BASIC is just plain false.

I plainly disagree. I have done about 100 hours of teaching in each of
these languages at beginner's level.

At the end of the BASIC course, the students had a pretty good grasp of the
language constructs, but little of more general principles in programming.
They knew about the data structures available in BASIC, but were certainly
not masters at using them. They could not have written a complex program,
like a text adventure or a simple editor.

The LISP students had a good grasp of the language _and_ of tree structures,
lists, records, property lists, higher order functions (functions taking
other functions as arguments), recursion, iteration, scope, interpretation,
macros and more. There was a project after that course, where the students
did things like symbolic derivation, natural language parsing, text
adventures(!), and a complete Commodore 64 emulator (OK, these last guys
were not beginners, but they were amusingly the ones who spent the first
10 hours of the course complaining about how bad LISP is, suggesting we
start with C instead, and coming up with lousy solutions to the exercises).

With LISP you get down to _programming_ very fast, instead of spending time
teaching syntax, ways of coping with the restrictions that the language
places upon you, how to emulate useful data structures using the limited
choice available etc.

In my work I use Prolog and C. For private projects I use Inform, C,
Pascal, LISP or Visual BASIC depending on the kind of project I'm doing.
I don't think I'm totally biased towards LISP, although I like it.
LISP has it's disadvantages, I'll definitely admit that. That it is hard
to understand for beginners is definitely not one of them, in my experience.

/Fredrik

--
Fredrik Ramsberg, Comp Sci student, Linkoeping,                       SWEDEN
d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
----------------------------------------------------------------------------
Proud winner of the 1996 Humility World Championships!!!


From max@alcyone.com Sun Jan 19 15:05:33 MET 1997
Article: 21401 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!news.bbnplanet.com!su-news-hub1.bbnplanet.com!news.sgi.com!news.spies.com!nixon.area.com!usenet
From: Erik Max Francis <max@alcyone.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: Thu, 16 Jan 1997 15:48:52 -0800
Organization: Alcyone Systems
Lines: 39
Message-ID: <32DEBE64.6B37240E@alcyone.com>
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se>
NNTP-Posting-Host: newton.alcyone.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.0 (X11; I; Linux 2.0.27 i686)

Magnus Olsson wrote:

> Would you care to substantiate that claim? Do you have experience
> teaching Lisp to beginners? Can you point to any research studies?

No, not really; I was merely expressing my opinion.  I was simply
suggesting that a more English-like language like BASIC is easier for a
completely programming newcomer to grasp than LISP.

I should point out that my original claim seemed to be scathing against
LISP, and I didn't mean it to be; I was merely suggesting that LISP is not
easy for beginners to wrap their heads around.

> From personal experience, I know thtat it's easy to get total beginners
> started in Basic, and Basic is easy as long as you're doing simple
> things and working on problems for which Basic is suitable.

Naturally.  BASIC is not one of the most powerful languages, and its only
real application in "real" applications programming is that of Visual
BASIC, and other languages such as Pascal, C, and C++ tend to be more
widely used than Visual BASIC for those kinds of applications.

The only suggestion I can come up with for validating my claim is that it's
BASIC (and sometimes Pascal or C) that is taught in introducing programming
courses, not LISP.  That doesn't necessarily imply that LISP is harder to
learn, though; it just demonstrates that BASIC (and others) are more common
for that sort of thing.

> However, if I were to teach beginners about list processing, recursion
> and self-reference, Basic would be a bad choice of language indeed.

Absolutely.

-- 
                             Erik Max Francis | max@alcyone.com
                              Alcyone Systems | http://www.alcyone.com/max/
                         San Jose, California | 37 20 07 N 121 53 38 W
                                 &tSftDotIotE | R^4: the 4th R is respect
     "You must surely know if man made heaven | Then man made hell"


From whizzard@uclink.berkeley.edu Sun Jan 19 16:15:07 MET 1997
Article: 21435 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!nntp.coast.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: I-F Contest Postmortem for 1996 (and some SPAG info.)
Date: 17 Jan 1997 22:37:46 GMT
Organization: University of California at Berkeley
Lines: 117
Message-ID: <5bouvq$qe0@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu


Okay, I've just about wrapped everything up for I-F Contest '96.  I still
have interviews to perform, and a few minor things, maybe some thank you
notes, etc.  I think that next year I'd like to get trophies made for
first-third place.  Honorable mention certificates for 4th-6th place.  You
know, some nice little ego strokers. :)

Activision is again showing some interest in the winners this year.  We
may have a repeat of last year's reprint-on-some-Activision-CD deal.  I've
sent them the first 6 placing games to look at.  Yeah, I know, it's a very
arbitrary place to cut things off.  It was more out of habit than
anything, since last year they took 6 games.  I swear Brian, I wasn't
picking on you, just trying to establish regular habits with them so they
might start factoring us into budgets or something like that.  Maybe
eventually I'll work them up to larger numbers of games, but its a fairly
complicated little bout of paper shuffling, getting all those releases and
such.  I dunno, we'll see.  Too much for one man to deal with in one day.

Anyways, Jason Melancon is now maintaining the SPAG web site.  I am going
to see about getting a page for the Contest up too.  It will be linked to
SPAG, but also to other interesting websites, and I will try and keep it
clear that SPAG and the contest are not affiliated to each other in any
way save that I manage them both. :P

Lemme find that URL...http://www.afn.org/~afn55673/spag.html

We hope to get it all spruced up with some CGI scripts for online score
submitting and such.  Same for next year's contest.  I dunno, I want to
see about making the contest look a bit more official without changing its
flavor too much.  Write up a press release for the game magazines, maybe a
mascot (Down! *crack! Down,  frothing raifers!  It was a joke!)  Anyways,
I want to get the anonymous thing automated to some degree to actually
make it not be a pain in der keister.

Oh yeah, I sent the addresses of prizewinners of to the donators of
prizes.  If you donated a prize and don't get a message titled
Distribution of Prizes or something similar soon, PLEASE let me know.
It's been awhile since I got the prize pledges, and email addresses are
known to go bad.

So, to sum up:

1. Prize donaters who do not get email from me need to contact me.
2. I obviously can't spell donat(e/o)r
3. SPAG magazine's website has moved to
	http://www.afn.org/~afn55673/spag.html
   We hope to add many features to it like:
   a. Letter to the editor submission box. (Okay, another mailto link, so
	sue me.)
   b. Automated SPAG rating submissions.  Type in name of game, assign
	scores using little slides or something, and hit submit.  The
	truly textual among you will probably prefer just typing it in and
	mailing it to me.
   c. Links to computer gaming magazines.  Not only XYZZYnews, but a bunch
	of the good commercial ones too, like CGW.
   d. Some select I-F links, that together cover all the important text
	adventure stuff.  I don't want too many links, and probably won't
	list any WWW hypertext novel sites, I don't care much for them.
   e. A breathers wall.  Those of you long-time readers of SPAG might have
	a clue what I mean.  Strictly for giggles.
   f. Easy subscribing to SPAG.  Click, confirm your subscription, wait
	for next issue.
   g. Prettified FAQ and reader's score chart, kept up to date.
   h. A new games section.  Since not everyone can keep up with the flood
	of new text adventures (cough cough, no really...) I think it
	would be crinkley to add links and authorr blurbs as games are
	released, assuming we are made aware of the games, that is.  Also,
	next time Eileen has the XYZZY awards, she can just raid our
	website to figure out which games are from 1997. :)


4. Next year's contest will maybe have a website housed on the same
account.  Features I'm thinking of are:
   a. Easy download of the entries (once they're in place.)  Hopefully a
	one click multi-meg download button as well, for the daring among
	us.
   b. Easy emailing of comments to the authors' anonymous accounts.
   c. A scoring form.  It will appear when voting opens, and disappear
	when it closes.  Strictly a Type in number 1-10 thing, since I
	don't want to force the SPAG system on anyone.
   d. Easy link to us page, with maybe some little thumbnail buttons for
	website maintainers to use.
   e. Grab press-release with a click feature.  For magazine folks and
	such.
   f. Any other stuff I think might be interesting.  I'm warning you all
	that most of this stuff is dependant on me or Jason learning
	CGI.

5. Those interested in helping to run next year's contest (and not
planning on entering) drop me a line.  I have job openings for people with
stable e-mail accounts and too much time on their hands.  I need a vote  
taker (Colin again?), and a press agent soft of thingy to contact
magazines, gather sponsorships, blah blah blah.  I have changed my mind on
official betatesters.  There will be none next year.  Zip.  Zero, kaput.
Maybe Michael Kinyon and the members of TABU will step in to fill the
void.  
	I am also removing the betatester voting restriction, and damn the
torpedoes.  There is no practical way to keep testers from voting in the
normal competition if they want, so the rule is silly and unenforceable as
well, so ZOOP, gone.  I'm going to try the author silence during voting
rule for one year and see how it goes.  If it becomes a Bad Thing (tm),
then it will go away.  People who have frothing fits over the rules, are,
as always, encouraged to organize their own bloody contest.

6. No, Avalon is not done.  (Thank god for backups.  Almost lost it this
morning.  "Yes yes, del *.*, sheesh, stupid warning message.  Wait a sec,
C:\TADS\AVALON\...yipe.")

Tap tap..anything else, brain?  No?  Good.  That's it.  Go away and leave
me to my programming....and my lunch.  Mmmm....lunch.  And no, you can't
have any.  Next thing you know the whole internet will want
some....sheesh.  </stupid rambling post>
-- 
=  SPAG Magazine  = Issues 1-9 at ftp.gmd.de:/if-archive/magazines/SPAG =
=       All       =  Ratings =     Issue 10 coming soon.  It's the      =
=      About      =  Reviews =        1996 I-F Competition Issue.       =
= Text Adventures =   News!  =        Editor: whizzard@pobox.com        =


From mol@bartlet.df.lth.se Sun Jan 19 16:22:10 MET 1997
Article: 21443 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform library criticism (was: [INFORM] Takeable actors?)
Date: 19 Jan 1997 15:53:19 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 38
Message-ID: <5btcgv$iju@bartlet.df.lth.se>
References: <5b6ivg$thv@bartlet.df.lth.se> <erkyrathE443F1.C13@netcom.com> <32DED9EB.1BB5@penning.lanl.gov> <32E025C2.8C5@globalserve.net>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <32E025C2.8C5@globalserve.net>,
Drone  <foxglove@globalserve.net> wrote:
>While I understand and agree with the philosophical underpinnings of avoiding 
>library hacks, in the case of Inform, it's really a trivial proposition. 

What's trivial? Avoiding library hacks or doing the library hacks? My critique was
that it should be - but isn't - trivial (or at least easy) to avoid hacking the library.

>I've only had the 
>libraries for a couple of months and I've already hacked them to include "viral" 
>(self-replicating) objects and to allow multiple third-person "self objects". 

Sounds interesting. Could you please tell us a little more?

>Sure I could have done somersaults to do these things and keep it 
>"library-friendly", but frankly, why bother? 

If you don't bother, fine, it's your code. 

>Nobody's going to compile my hacks but me, 

Other people _compiling_ your code is no problem anyway: just give
them a copy of your hacked library.

>porting is also trivial if you flag every hack with comments, as I have done. 

Hmm. Of course it depends on what kind of modifications you do make to the 
library, but you might be in for some unpleasant surprises when you upgrade
to 6.10 and library 6/3 - Graham has changed quite a few things.

Anyway, my point was simply this: even if it's not much work migrating your
library hacks to a new library version, a better library design would mean
that you wouldn't have to do any migration work at all.



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From Linards.Ticmanis@post.rwth-aachen.de Sun Jan 19 21:36:08 MET 1997
Article: 21452 of rec.arts.int-fiction
Path: news.lth.se!solace!umdac!umu.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!EU.net!Germany.EU.net!main.Germany.EU.net!news-koe1.dfn.de!news.rwth-aachen.de!not-for-mail
From: Linards Ticmanis <Linards.Ticmanis@post.rwth-aachen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers - LOGO/TCL
Date: Sat, 18 Jan 1997 22:48:27 +0100
Organization: RWTH Aachen, Germany
Lines: 57
Message-ID: <32E1452B.5F4D8820@post.rwth-aachen.de>
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se> <32DEBE64.6B37240E@alcyone.com>
NNTP-Posting-Host: s2m187.dialup.rwth-aachen.de
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.01 (X11; I; Linux 2.0.27 i486)

Erik Max Francis wrote:
> 
> Magnus Olsson wrote:
> 
> > Would you care to substantiate that claim? Do you have experience
> > teaching Lisp to beginners? Can you point to any research studies?
> 
> No, not really; I was merely expressing my opinion.  I was simply
> suggesting that a more English-like language like BASIC is easier for 
> a
> completely programming newcomer to grasp than LISP.
> 
...
> The only suggestion I can come up with for validating my claim is that 
> it's
> BASIC (and sometimes Pascal or C) that is taught in introducing
> programming
> courses, not LISP.  That doesn't necessarily imply that LISP is harder > to
> learn, though; it just demonstrates that BASIC (and others) are more
> common
> for that sort of thing.

Just for the record: I recall my informatics (is there such a word in
English? Well, basically it means computer science) teacher being angry
about the fact that he had to start with BASIC (since the German
curriculum for 9th grade seems to mandate that) and his preference for
LOGO. Once during a "Project week" he did a one-week all-day LOGO class
that got us (7th graders at the time) relatively far into advanced stuff
although none had too much experience before besides C64-Basic (or not
even that).
Personally, I find LOGO more intriguing than LISP: It gets rid of the
parentheses paradontosis usually associated with LISP (I played enough
of LISTS AND LISTS to really make my teeth hurt), has only one special
syntax form (TO defining Procedures/Functions or whatever you want to
call them) and doesn't run parameter lists unless told so, so the whole
business of when to "quote" and when not is pretty much gone.

Also to be mentioned is TCL, which is a lot more than just a basis of
the TK GUI library. A cleaned-up variant of its basic concept
(EVERYTHING is text) might make a very interesting, if not ideally
performing, tool for text-based computing, such as the stuff this group
is about. (e.g. get rid of "Variables" and replace them by an OO concept
that creates a new command with the name of the variable, so that
Variable substitution can be replaced by command substitution, so only
one kind of substitution is needed). IMHO TCL has managed to sucessfully
"steal" from compiled procedural languages, shell scripting, functional
as well as OO programming and integrated them into a whole that is much
more than the sum of independently-existing parts.

-- 

Linards Ticmanis

<A HREF="mailto:ticmani@reze-1.rz.rwth-aachen.de">
ticmani@reze-1.rz.rwth-aachen.de</A>

<BRIBE> me. I'll leave.


From 104312.2206@compuserve.com Mon Jan 20 09:10:57 MET 1997
Article: 21461 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!vixen.cso.uiuc.edu!chi-news.cic.net!news.compuserve.com!not-for-mail
From: Bryan Scattergood <104312.2206@compuserve.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: Sun, 19 Jan 1997 15:46:28 GMT
Organization: CompuServe Incorporated
Lines: 44
Message-ID: <VA.00000030.01856760@104312.2206>
References: <32b72f97@beachyhd.demon.co.uk>
 <32D12DF8.50C8A820@alcyone.com>
 <32d5942b.11742402@news.peinet.pe.ca>
 <32D93862.79B2A3DF@alcyone.com>
 <5bbmti$afl@bartlet.df.lth.se>
 <32DBD28D.713B5AF1@alcyone.com>
 <5binnt$3da@curofix.ida.liu.se>
Reply-To: 104312.2206@compuserve.com
NNTP-Posting-Host: ld01-039.compuserve.com
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-Newsreader: Virtual Access by Ashmount Research Ltd, http://www.ashmount.com

FReDRiK RaMSBeRG (WILdcARD) wrote:

>>Erik Max Francis <max@alcyone.com> writes:
>>Er, my wording suggested something I wasn't trying to indicate;
>>I myself find LISP intriguing and have no problem with it (though
>>I don't use it extensively).  However, arguing that it is just as 
>>easy for computer newcomers to learn as other languages such as
>>BASIC is just plain false.

> I plainly disagree. I have done about 100 hours of teaching in
> each of these languages at beginner's level.
>
> [snip]
>
> With LISP you get down to _programming_ very fast, instead of
> spending time teaching syntax, ways of coping with the
> restrictions that the language places upon you, how to emulate
> useful data structures using the limited choice available etc.
>
> In my work I use Prolog and C. For private projects I use Inform,
> C, Pascal, LISP or Visual BASIC depending on the kind of project
> I'm doing.  I don't think I'm totally biased towards LISP, although
> I like it.  LISP has it's disadvantages, I'll definitely admit that. 
> That it is hard to understand for beginners is definitely not one of 
> them, in my experience.

I agree with that wholeheartedly.  Lisp is fairly easy for beginners to 
pick up.  That those who have some BASIC experience find it *harder* 
than total beginners is more a problem with BASIC than anything to do 
with Lisp.

I suspect that BASIC has 'damaged' many programmers over the years, 
including myself.  Arrays and FOR/NEXT loops are not usually the best 
way to solve a problem.  For those of us who started with BASIC, they 
are often the first structures that spring to mind though.

Personally, I tend to use a mix of Gofer, Awk, C, C++ or assembler for 
projects based on their suitability.  Lisp's lack of a type-system 
means that I tend to use Gofer instead nowadays, but learning Lisp was 
still a good investment.

       Bryan




From d91frera@ida.liu.se Mon Jan 20 09:12:26 MET 1997
Article: 21457 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: 19 Jan 1997 13:21:03 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 39
Message-ID: <5bt73v$roa@curofix.ida.liu.se>
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se> <32deb932.803050@news.one.net>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)

wolf@one.net (Roger Plowman) writes:
>mol@bartlet.df.lth.se (Magnus Olsson) wrote:
>>The attraction of using Lisp for IF is that it's so flexible that you
>>can use it in all of these domains without having to add an awful lot
>>of ad-hoc features. Its compactness is also a plus.

><sigh> But the syntax breaths vacuum...

I don't understand the expression, but I assume it means that you don't
like the syntax of Lisp. Lisp has the simplest syntax of all languages I
have encountered. What can be wrong with that? Do you think complex syntax
is something to strive for? Well, try writing IF in Cobol then...

Lisp also has a richness in functions, which most languages lack. You have all
the functions that are available in procedural languages like Pascal or C, and
a few hundreds more. Many of these functions can be found in library-files
for other languages, but many of them could never be written and fitted into
these other languages in a natural way, unless they were made a part of the
language itself. Like, for instance, how do you make a new loop-construction
that iterates over all the elements in a linked list and applies a function
to each of them, in C? And make it fit into the language in a smooth way?
You don't. In Lisp, it already exists, but even if it didn't it would be
peanuts to write it.

All these functions need to have their arguments in a certain order, which is
of course a syntax issue as well. This order is quite consistent though, so
you can usually guess it easily, once you know the order of some other,
similar function. If you can't, you can always query the system for this
information, since Lisp is run in an incremental environment. That is,
you always get back to a command-line.

Respectfully as well,

/Fredrik
--
Fredrik Ramsberg, Comp Sci student, Linkoeping,                       SWEDEN
d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
----------------------------------------------------------------------------
Proud winner of the 1996 Humility World Championships!!!


From fake-mail@anti-spam.address Mon Jan 20 09:15:07 MET 1997
Article: 21470 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!news1.relcom.ru!EU.net!howland.erols.net!news.sprintlink.net!news-peer.sprintlink.net!uunet!in2.uu.net!199.60.229.3!newsfeed.direct.ca!van-as-08c02.direct.ca!user
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: TADS 2.2.1 ADV.T
Date: Sun, 19 Jan 1997 11:11:22 -0800
Organization: tela design
Lines: 29
Message-ID: <fake-mail-1901971111220001@van-as-08c02.direct.ca>
References: <5bhc6n$abq$1@news3.microserve.net> <19970115174701.MAA11889@ladder01.news.aol.com>
NNTP-Posting-Host: van-as-08c02.direct.ca
X-Newsreader: Yet Another NewsWatcher 2.0.1

In article <19970115174701.MAA11889@ladder01.news.aol.com>,
nulldogma@aol.com (Nulldogma) wrote:

> Yeah, I pointed this out to Mike back when he first uploaded 2.2.1, and he
> promised me he'd fix it. Apparently he still hasn't.
> 
> Anyway, here's the missing code in question. If Volker or anyone reading
> this would like to upload it to GMD (maybe as NUMBERED.T?), the world
> would be much appreciative.

 I added the missing adv.t code in question to my TADS tipsheet for the
meantime.

 http://www.tela.bc.ca/tela/tads/authoring/

 It's also in plain text form in:

 ftp://ftp.gmd.de/if-archive/programming/tads/examples/

 The code isn't *quite* the same as the code you posted, Neil... it may be
a slightly later rev or something as it adds an error message or two and a
new attribute.

 - Neil K.

-- 
--
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela@tela.bc.ca


From d91tan@minsk.docs.uu.se Mon Jan 20 09:15:30 MET 1997
Article: 21453 of rec.arts.int-fiction
Path: news.lth.se!solace!umdac!umu.se!newsfeed.sunet.se!news00.sunet.se!sunic!mn6.swip.net!plug.news.pipex.net!pipex!newsxfer3.itd.umich.edu!news.bbnplanet.com!su-news-hub1.bbnplanet.com!arclight.uoregon.edu!news.algonet.se!eua.ericsson.se!erinews.ericsson.se!news.seinf.abb.se!news.mdh.se!columba.udac.uu.se!news
From: Torbj|rn Andersson <d91tan@minsk.docs.uu.se>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] 6.10 another problem
Date: 17 Jan 1997 20:52:00 +0100
Organization: Uppsala University
Lines: 55
Sender: d91tan@Rama.DoCS.UU.SE
Message-ID: <uc9u3ogw04f.fsf@Rama.DoCS.UU.SE>
References: <y3ZmtMD4F2DaUz1@trib0029.tribal.line.org>
NNTP-Posting-Host: rama.docs.uu.se
Mime-Version: 1.0 (generated by tm-edit 7.85)
Content-Type: text/plain; charset=US-ASCII
X-Newsreader: Gnus v5.3/Emacs 19.34

omueller@tribal.line.org (Olav Mueller) wrote:

>     this time I am REALLY lost. Have a look at this small excerpt
> (I  removed  anything  remotely interesting ...) from some code I
> wrote (originally using Inform 6.03 with  library  6/1,  recently
> switched  to  6.10  with  library  6/3  ... and that is where the
> problems began!)

[Most of the code snipped]

> Extend "eat" replace
>     * edible                                -> Eat;

[snip]

>     Interestingly "go north" still works correctly, while "n"  or
> "north"  does  not  compute  ... can anyone help? What am I doing
> wrong?

This looks like another instance of the "Verb Problem" reported by
Rick Dague less than a week ago. Basically what seems to happen is
that when a command is parsed using an attribute token (e.g. edible),
the variable token_filter is set. As I understand it, this value is
later used to see if an object has the desired attribute.

This variable is cleared, and possible reset, by the ParseToken()
function. However, it appears that parsing of directions by their
names alone happens before this. Parsing any command which clears
this variable (e.g. "go north") will make "north", etc. work again.

The same phenomenon can be observed by making a piece of clothing,
e.g. a robe, wear it and then "take off robe". The action "take off"
uses - in this case - the attribute token worn.

Hopefully, Graham will have this fixed by the next library release.
(At least, assuming he has read these posts, and/or someone has
mailed him about it. I didn't.) In the meantime, Rick suggested the
following modification:

Rick Dague <bifurcate@geocities.com> wrote:

> I've inserted a line in parserm.h to reinitialize the variable
> token_filter before the parser checks to see if the command is movement.
> It's at (about) line 842.
>
> !  or REPARSE_CODE if it has restructured the parse table so the whole parse
> !  must be begun again...
>
>         token_filter=0;   ! this line added
>         wn=verb_wordnum;
>         l=NounDomain(compass,0,0); if (l==REPARSE_CODE) jump ReParse;

     _
Torbjorn



From graham@gnelson.demon.co.uk Mon Jan 20 09:41:06 MET 1997
Article: 21478 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!tank.news.pipex.net!pipex!netcom.net.uk!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: How long did it take to write 'Curses'?
Date: Wed, 15 Jan 1997 20:36:56 +0000 (GMT)
Organization: none
Lines: 44
Message-ID: <ant152056345M+4%@gnelson.demon.co.uk>
References: <01bc0032$0175e680$249c45cf@weissinger> <32d98698.79193032@news.gte.net> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]

> On 12 Jan 1997 02:41:12 GMT, "A. Keyton Weissinger"
> <keytonw@mindspring.com> wrote:
> > Does any one know how long it took for Graham Nelson to complete Curses?
> > It's fabulous and fairly large and I hope to do something about that size 
> > (and bigger) but am an IF authoring newbie and want some idea of how 
> > long such a thing takes for an expert...

I'm not sure myself.  "Curses" has a peculiar design history
and that accounts for some of its random eccentricities.
In particular, it has existed in about two substantially different
forms, with several intermediate states: basically it started out
Zork I-sized and then had about as much added again (about 7
months later).  The original took about a month to write (I was
just overflowing with silly ideas), but even that's hard to nail
down, because some of the time was spent debugging Inform and
the library.

So there you have it.  Any estimate between 1 month and 1 year
will have some truth to it.

"Balances" was written in a weekend (and it shows).  "Jigsaw"
took two years and a month or so, as I recall, but then
that was a project that I came back to and came back to.  (The
result is I think a better game, albeit one that's less fun.)

Angela M. Horns took something like a month to write "The Meteor,
The Stone and a Long Glass of Sherbet" (a three-week orgy of
creation plus a frantic week of tidying-up).  There's
really nothing else to do on the Isle of Eigg of an evening.

The trouble with rapid, random creation is that although it
makes sparky and puzzle-rich games (I think "Zork" and "Curses"
are cases in point), it also makes disconnected, disoriented
and generally amateurish games (I think "Zork" and "Curses"
are cases in point -- both have been tidied up and presented
nicely, but still...).

"Proper" games take longer to research and think through.
"Trinity" took just over a year of almost full-time work,
for instance.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Mon Jan 20 10:04:52 MET 1997
Article: 21482 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Inform library criticism (was: [INFORM] Takeable actors?)
Message-ID: <erkyrathE443F1.C13@netcom.com>
Organization: NETCOM On-line Communication Services (408 261-4700 guest)
X-Newsreader: TIN [version 1.2 PL1]
References: <5b6ivg$thv@bartlet.df.lth.se> <erkyrathE3wqrL.MAs@netcom.com> <5bbn05$bbo@bartlet.df.lth.se> <erkyrathE3xL4H.1ow@netcom.com> <32DD3B26.7922@penning.lanl.gov>
Date: Thu, 16 Jan 1997 17:33:00 GMT
Lines: 87
Sender: erkyrath@netcom.netcom.com

Russell Glasser (rglasser@penning.lanl.gov) wrote:
> Andrew Plotkin wrote:
> > 
> > Magnus Olsson (mol@bartlet.df.lth.se) wrote:(regarding hacking the Inform libraries)
> > 
> > > But this is _evil_.
> > 	<facetious>
> > Of course it's evil. Computer languages are evil. Compilers are a
> > terribly painful hack to get around the fact that computers aren't good
> > enough to interpret English on the fly. The Z-machine is an evil hack to
> > get around our unbelievably stupid policy of making computers that are
> > incompatible with each other. Computer games are an attempt to take our
> > minds off how lonely and miserable we all are because telepathy hasn't
> > been invented yet.
> > 	</facetious>

First of all, I did not write the "facetious" tags. I was not being 
facetious. (Zen, maybe. Whap!)

> 	Yeesh, get serious Andrew.  Magnus was talking about solid 
> programming style, and information hiding is the way good programming is 
> done.

That's what I said! Many parts of the Inform library implemenation are 
evil. RTakeSub is evil. Doors are really, really evil. Bad programming 
style is evil. I hate it.

Have I agreed with you loudly enough yet?

> 	Sure, it's all very well to say "_So Far_ is built under libraries 
> 5/12 and will remain so. This means that, sadly, it will never be translated 
> into another language using the 6/3 language system." 

What do you mean, it's all very well? It's *sad*! I just said so. It 
makes me sad.

> Speaking ad absurdam, 
> does that mean software developers have to dump all their old programs every 
> time their company upgrades to a new version of C++?

Wow, that would be *really* sad.

I will restate my point now:

*The Inform libraries are what we have*. They are not the only compromises
of elegance that I have in my life. Standing up and saying "Wait, this 
isn't perfect!" as if it's some vast revelation gets nothing from me but 
a disgusted glare.

Moreover, the *practical* consequences of this imperfection (*not* taking
it ad absurdem, but looking at my actual use of Inform in, y'know, real
life) are just not that big. If I *do* upgrade _So Far_ to libraries 6/3, 
it will be an extra fifteen minutes of work to transplant my hacks (and 
the hack we're arguing about here would be equally easy.) If the libraries 
6/4 involve a total reimplementation of RTakeSub, or some other thing I 
hacked, it would probably be an extra twenty minutes to upgrade to 
*that*. 

Compare this to, say, the effort it takes to port a new IF interpreter to
the Mac. It's just not a significant problem on my plate. It's *evil*,
because fifteen minutes times the number of authors who upgrade their
games will eventually equal a large amount of wasted effort. But it's not
a *big* evil. I choose to compromise my sense of programming elegance in 
order to work on bigger tasks. 

I will restate my point again, quoting from my earlier post:

> The Inform libraries are a pain in certain ways, which you can hack
> around, and this is not news. 
> [...]
> There ought to be a completely new set of libraries, which are not held to
> be compatible with any existing Inform code or the Designer's Manual. I'm
> not volunteering for the job.

(but, I should add, the existing libraries should not go away.)

Graham has posted in the interim saying that this job is more difficult 
than it looks. I certainly believe that. Nonetheless I will be happy if 
someone does it. I would, but I am fully booked with my own crusades to 
conquer evil.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From foxglove@globalserve.net Mon Jan 20 10:05:05 MET 1997
Article: 21475 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!newsxfer.itd.umich.edu!news.ececs.uc.edu!news.kei.com!news.thenet.net!uunet!in1.uu.net!204.191.213.61!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform library criticism (was: [INFORM] Takeable actors?)
Date: Sun, 19 Jan 1997 17:22:36 -0500
Organization: Envision This
Lines: 89
Message-ID: <32E29EAC.1AB0@globalserve.net>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin423.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)

I don't know if this is a duplicate, or if it will thread properly, but my news server was down 
and I used another to reply and then I wasn't sure if I really had access and then my real server 
went back up but it hasn't yet received the message this is replying to, and, well, obviously it 
is (er, was) a long story.

Magnus Olsson wrote:
>
> In article <32E025C2.8C5@globalserve.net>,
> Drone  <foxglove@globalserve.net> wrote:
> >While I understand and agree with the philosophical underpinnings of avoiding
> >library hacks, in the case of Inform, it's really a trivial proposition.
>
> What's trivial? Avoiding library hacks or doing the library hacks? My critique was
> that it should be - but isn't - trivial (or at least easy) to avoid hacking the library.
>
Doing and maintaining the library hacks is trivial, IMHO, meaning that I don't think it
really matters that *avoiding* this is non-trivial. And again, I agree in principle that
avoiding it should be easy.

> >I've only had the
> >libraries for a couple of months and I've already hacked them to include "viral"
> >(self-replicating) objects and to allow multiple third-person "self objects".
>
> Sounds interesting. Could you please tell us a little more?
>
It started off with how much I hated the implementation of the ASK/TELL paradigm in Inform.
It just looked to make my life incredibly difficult (I'm BIG on character interaction). I
looked over the libraries and decided that the problem was that they stubbornly refused to
allow the "concept" being asked about to have an object of its own. I considered the
problems inherent in implementing this, and decided that it called for a type of object
that can attach to an object, and replicate a copy of itself into the head of any
"sentient" that ever comes into scope, including NPCs.

So, for example, not only do you have a "rockfall" object, but you have an "idea of the
rockfall" object attached to it, with an each_turn routine that checks for sentients and
"infects" them with copies itself, meaning that sentients who see the rockfall, know about
it. Thus, a new type of object which I called a Viral. I implemented this, and changed the
ask and tell routines to make use of it, and to allow themselves to be overridden by "Ask"
and "Tell" routines either in a specific Sentient object or in a specific Concept object.
Added a few standard viral handling methods, such as x.infects(y), &c., and I had a
complete system which prevented me (I hope) from ever having to use a parse.word loop for
character interaction.

So now I've set about writing the game this depends upon. Working smoothly so far.

For reasons related to my emphasis on story (I was an English Lit major), I have never
liked second-person, and I also hacked the libraries to allow true multiple self-objects
rather than Inform's rather clumsy exception-style way of implementing multiple-character
control. Part of my take on this is changing all the standard library_messages to speak in
third person, and to allow any individual character object to override any particular
library_message (without overriding the whole routine), thus making the game respond to you
differently depending on your current "host". So in effect, my game is going to have a
partly new library_messages routine for each character you can control. This matches my
philosophy that the parsed commands should be directed "at" the main character, who
performs them, rather than at yourself. Just my personal preference, please. I realise that
plenty of excellent and very atmospheric games have been written in 2nd P. I'm not looking
for a paradigm war.

> >Sure I could have done somersaults to do these things and keep it
> >"library-friendly", but frankly, why bother?
>
> If you don't bother, fine, it's your code.
>
Just MHO. I'm not an Inform theorist. I'm just trying to write some games with it, so I
don't agonise over hacking the libraries if, as I said, I don't think it will come back and
bite me very hard. But again, this doesn't really match my general philosophy about
programming.

> >porting is also trivial if you flag every hack with comments, as I have done.
>
> Hmm. Of course it depends on what kind of modifications you do make to the
> library, but you might be in for some unpleasant surprises when you upgrade
> to 6.10 and library 6/3 - Graham has changed quite a few things.
>
Fair enough. Maybe I'll come back here with fresh bite marks on my butt and eat my words.

> Anyway, my point was simply this: even if it's not much work migrating your
> library hacks to a new library version, a better library design would mean
> that you wouldn't have to do any migration work at all.
>
Well, I certainly wouldn't complain if that were the case.

> --
> Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)

Drone.
--
"Esse Est Percipi."
foxglove@globalserve.net


From DaveK@soundcraft.co.uk.trim.these.last.five.words Mon Jan 20 11:23:15 MET 1997
Article: 21423 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!www.nntp.primenet.com!nntp.primenet.com!EU.net!uknet!usenet1.news.uk.psi.net!uknet!dispatch.news.demon.net!demon!fido.news.demon.net!demon!david.soundcraft.co.uk!not-for-mail
From: DaveK <DaveK@soundcraft.co.uk.trim.these.last.five.words>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform library criticism [medium long..]
Date: Thu, 16 Jan 1997 20:47:40 +0000
Organization: Soundcraft
Lines: 112
Message-ID: <32DE93EB.391C@soundcraft.co.uk.trim.these.last.five.words>
References: <5b6ivg$thv@bartlet.df.lth.se> <erkyrathE3wqrL.MAs@netcom.com> <5bbn05$bbo@bartlet.df.lth.se>
Reply-To: DaveK@soundcraft.co.uk.trim.these.last.five.words
NNTP-Posting-Host: david.soundcraft.co.uk
X-NNTP-Posting-Host: david.soundcraft.co.uk
X-Mailer: Mozilla 3.0Gold (Win95; I)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Hello, sailors!

 The issue of the library's default conditions and behaviour has been 
on my mind as well just lately, for a similar but different reason...

 In the alien spaceship that I'm coding at the moment, there's an
operating table (for doing those nasty examinations that aliens tend
to give you when you've been abducted, you know). As soon as you are
foolish enough to lie down on it, a bunch of straps and clamps shoot
out from the sides and hold you down. To stop you getting off the
table, I have a before condition which traps the ##GetOff and ##Exit
actions; if you haven't solved the puzzle of how to escape, they
prevent you leaving..... but look at this..... (transcript simulated,
>from  memory, so forgive the approximations to the output from Actions
and Routines trace...

> get on table
[Action ##Enter with noun table]
[Running before for table] (doesn't interfere)
[Running after for table] (does interfere, with the following message) 
As you climb on to the operating table, snake-like straps whip out
automatically from the sides and tie you firmly down!

> get off table
[Action ##GetOff with noun table]
[Running before for table] (does interfere: prevents it)
But you are held down by the straps!

> get off     (or Exit)
[Action ##Exit]  (...yep, no noun!, so table's before isn't run)
You get off the table.

 Similarly, at a later point, you may still be on the table, and have
a pebble in your hands. Then you may try...

> put pebble on table
[Action PutOn with noun pebble and second table]
[Running before for table with fake action ##Insert]
The straps wrap themselves around the pebble !

...but if you had tried (you are on/in the table, remember)

> drop pebble
[Action drop with noun pebble]
Dropped.

> x table
On the table is a pebble....

.. because the DropSub simply does

  move noun to parent(player)

.. when it should really send Insert messages if parent(player) is
a container/supporter. I'm willing to bet there's going to be a few
funnies relating to vehicles as well; if you're driving a Sinclair
C5, for example, you might well be unable to change your underwear
whilst in motion (not a lot of room in one of those, you know); but
<Wear noun> and <Disrobe noun> won't be passed to any before routines
except those of the <noun>. Using a react_before for the vehicle isn't
appropriate either, because it would have to repeat all the library's
checks for whether the object is held, wearable etc.

 Now I remember reading a textbook on adventure programming technique
a few years back (I've still got it around somewhere, it's an ancient
thing with code examples in IBM QBasic!), that had a very good and
object-oriented solution to exactly these sort of problems. Under the
system they recommended, all actions were passed all the way up the
object tree until they reached the root (generally the room/location
object), and any stage of the tree could interfere. I don't remember
if this process was recommended to stop at closed containers or not - 
although using the usual recursion rules might seem good, you might
want something different to happen in some cases; so I guess that each
object would decide for itself whether to abort the command, pass
it further up the tree, or accept it as definitely ok.

 So what I reckon is, that an entire re-write of the library structure
(with the possible exception of the parser, which is a) damn fine as it
stands, and b) damn complex to re-write) may be in order here.

 Specifically, the two biggest changes I'd like to implement are:

 i) Pass actions ALL the way up the tree in RunRoutines (or wherever),
 so as to avoid hideous react_before/react_after complications.
ii) BIG change: Implement a during [; ...] stage. I haven't thought
 this out in great detail yet: maybe it should be passed through the
 tree, or maybe just the player, noun and second should get to look at
 this; they could then either replace or OK the library's default
 behaviour for the given case. This means no need to hack the library
 nor yet to duplicate the xxxSub's in their entireity....

 Errmm. I do have a full time job, so I'm not quite volunteering to 
do this just yet. And I'm relying on pubnews severs for my usenet
access, so I can't even guarantee keeping up with discussions here!
Nonetheless, if anyone does have any contributions to this debate, 
please cc: me a copy in e-mail, and you never know for sure... just
maybe ....

 laters all,

    DaveK.



------------------------------------------------------------------------
Disclaimer: Guaranteed safe when used as directed. Some assembly may 
be required. Batteries not included. May cause drowsiness. Keep all
e-mail out of the reach of children. Not insured under the Export 
Credit Guarantee Scheme. Remember, the value of e-mail may go up as 
well as down. No more than 10 persons (1700 lbs) at one time. Contents
may have settled during shipping. Void where prohibited by law. 
------------------------------------------------------------------------


From nulldogma@aol.com Mon Jan 20 15:41:02 MET 1997
Article: 21485 of rec.arts.int-fiction
Path: news.lth.se!solace!umdac!umu.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!news.bbnplanet.com!su-news-hub1.bbnplanet.com!newsxfer3.itd.umich.edu!portc01.blue.aol.com!newstf02.news.aol.com!audrey01.news.aol.com!not-for-mail
From: nulldogma@aol.com (Nulldogma)
Newsgroups: rec.arts.int-fiction
Subject: Re: TADS 2.2.1 ADV.T
Date: 19 Jan 1997 21:24:33 GMT
Organization: AOL http://www.aol.com
Lines: 54
Message-ID: <19970119212400.QAA14510@ladder01.news.aol.com>
References: <fake-mail-1901971111220001@van-as-08c02.direct.ca>
NNTP-Posting-Host: ladder01.news.aol.com
X-Admin: news@aol.com

Here's what I had in mind. (Untested code, but it should work):

/*
* Further modifications to the numberedObject class introduced 
* in TADS 2.2.1.
*/

/*
* highNumberedObject is for sets of objects that are numbered
* beginning with a number other than one. (Example: Doors 
* numbered from 10-20.) Set minNum to the lowest number 
* allowed, and maxNum to the highest number allowed.
*/

class highNumberedObject: numberedObject
         num_is_valid( n ) =
         {
 if ( n < self.minNum or n > self.maxNum )
  {
  "The <<self.pluraldesc>> are numbered from <<self.minNum>> to
<<self.maxNum>>.";
  return nil;
  }
 else return true;
 }
 minNum=10
 maxNum=20
;

/*
* nonconsecutiveNumberedObjectis for sets of objects that are 
* numbered nonconsecutively. (Example: Channels on a TV that 
* can equal 2, 4, 5, 7, 9, etc.) List all the acceptable values in 
* numlist.
*/

class nonconsecutiveNumberedObject: numberedObject
         num_is_valid( n ) =
         {
 if ( not find ( self.numlist, n ))
  {
  "That is not an acceptable value."; //Customize this error
  return nil;     //message as need be.
  }
 else return true;
 }
 numlist=[]
;

Neil
---------------------------------------------------------
Neil deMause                            neild@echonyc.com
                  http://www.echonyc.com/~wham/neild.html
---------------------------------------------------------


From erkyrath@netcom.com Tue Jan 21 09:38:25 MET 1997
Article: 21498 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!nntp.uio.no!newsfeeds.sol.net!newspump.sol.net!howland.erols.net!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Questionable Languages & Compilers
Message-ID: <erkyrathE49n8B.7zq@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se> <32deb932.803050@news.one.net> <5bt73v$roa@curofix.ida.liu.se>
Date: Sun, 19 Jan 1997 17:28:59 GMT
Lines: 94
Sender: erkyrath@netcom19.netcom.com

FReDRiK RaMSBeRG (WILdcARD) (d91frera@ida.liu.se) wrote:
> wolf@one.net (Roger Plowman) writes:
> >mol@bartlet.df.lth.se (Magnus Olsson) wrote:
> >>The attraction of using Lisp for IF is that it's so flexible that you
> >>can use it in all of these domains without having to add an awful lot
> >>of ad-hoc features. Its compactness is also a plus.

> ><sigh> But the syntax breaths vacuum...

> I don't understand the expression, but I assume it means that you don't
> like the syntax of Lisp. Lisp has the simplest syntax of all languages I
> have encountered. What can be wrong with that? Do you think complex syntax
> is something to strive for? Well, try writing IF in Cobol then...

This is something of an ad absurdem argument both ways, since I like a
happy medium. Lisp's syntax is too simple for me. I like C syntax because
it's simple enough (except in a few places, like type names of complex
types.) It's easier on my eyes, because it uses different punctuation to
differentiate between different syntactic forms, as opposed to different
text strings within the same punctuation. 

After four years of using C++ professionally, I still do not know all of 
C++ syntax. I interpret this as a Big Fat Lose. :-)

> Lisp also has a richness in functions, which most languages lack.

Whoop! Whoop! Do not confuse Lisp's syntax with Lisp's power as a dynamic
language. There are now several languages which are (or are based on) 
the idea of Lisp in C syntax. (SML, Haskell, etc, the ones I keep bringing 
up.) 

Contrariwise, you could easily define a syntax for C made entirely of 
Lisp's parenthesis-and-atom notation. It would *be* C, line-for-line, but 
the "syntax" would be trivial. --Because all of the "hard stuff" would 
be off-loaded onto the semantics of the C-related forms. 

(define-struct-type flog (   ; struct flog {
  (int v1)                   ;   int v1;
  ((ptr char) str1)          ;   char *str1;
  ((ptr char) str2)          ;   char *str2;
))                           ; };

(function add                ; int add(int v1, int v2)
  int 
  ((int v1) (int v2))        
  (                          ; {
    (local (int res))        ;   int res;
    (set res (+ v1 v2))      ;   res = v1 + v2;
    (return res)             ;   return res;
  ))                         ; }

You know, this is a point I hadn't thought of. Lisp *does* have 
complicated syntax, in this sense; it's not made of complicated rules on 
how to arrange parentheses, but of complicated rules on the inputs to 
forms like "define" and "lambda" and "cond". I'll even say that it's as 
complicated as C.

Note that my silly-C example is very silly, because this C "syntax" 
doesn't take advantage of the big expressive win of Lisp -- that lists 
can be assembled at run-time and then executed. But that's a *semantic* 
fact. The whole point of distinguishing *syntax* is that you ignore 
meanings of things; and so I say that the syntax of silly-C is simple in 
exactly the same sense that the syntax of Lisp is simple.

> Like, for instance, how do you make a new loop-construction
> that iterates over all the elements in a linked list and applies a function
> to each of them, in C? And make it fit into the language in a smooth way?
> You don't.

But only because of certain assumptions of the C *language*, not the C 
syntax. You could do it in these other languages I noted.

> All these functions need to have their arguments in a certain order, which is
> of course a syntax issue as well. This order is quite consistent though, so
> you can usually guess it easily, once you know the order of some other,
> similar function.

Ok, this is part of what I was saying (I tend to start replying before I 
read the entire post :-)) I think you're weaseling, though, since there 
are more functions to learn in Lisp than there is syntax to learn in C. 
Heh. 

> If you can't, you can always query the system for this
> information, since Lisp is run in an incremental environment. That is,
> you always get back to a command-line.

Again, not a syntax issue.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From wolf@one.net Tue Jan 21 09:40:43 MET 1997
Article: 21514 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!worldnet.att.net!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!newsfeed.internetmci.com!newsfeed.one.net!news.one.net!news
From: wolf@one.net (Roger Plowman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: Mon, 20 Jan 1997 23:38:46 GMT
Organization: OneNet Communications HUB News Server
Lines: 76
Message-ID: <32e3fbe5.4389012@news.one.net>
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se> <32deb932.803050@news.one.net> <5bt73v$roa@curofix.ida.liu.se>
NNTP-Posting-Host: port-11-15.access.one.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent .99g/32.339


Hi Fredrik,

d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD)) wrote:

>I don't understand the expression, but I assume it means that you don't
>like the syntax of Lisp. Lisp has the simplest syntax of all languages I
>have encountered. What can be wrong with that? Do you think complex syntax
>is something to strive for? Well, try writing IF in Cobol then...

The problem with Lisp syntax is that *everything* is surrounded by
parentheses. There's also the prefix notation. And finally the problem
(one I never really saw satisfactorily solved) of creating write-only
code that's impossible to debug six months later.

Lisp is indeed simple to write in--but that's really a problem with
this particular language family, since moderately complex expressions
become unreadable. The eye tends to skip over the parentheses no
matter how carefully the code is formatted.

Even simple if tests become a challenge to express with clarity. And
tho it's been years since I've dealt with Lisp itself, I worked daily
with AdvSys for over a year. Reading the code now is somewhat
challenging, even though I put an english comment on every line,
including ending parentheses.

>Lisp also has a richness in functions, which most languages lack. You have all
>the functions that are available in procedural languages like Pascal or C, and
>a few hundreds more. Many of these functions can be found in library-files
>for other languages, but many of them could never be written and fitted into
>these other languages in a natural way, unless they were made a part of the
>language itself. Like, for instance, how do you make a new loop-construction
>that iterates over all the elements in a linked list and applies a function
>to each of them, in C? And make it fit into the language in a smooth way?
>You don't. In Lisp, it already exists, but even if it didn't it would be
>peanuts to write it.

This is, I think, an issue of quantity vs quality. I've dealt with
languages that were fairly sparse in terms of built-in functions and
statements and I've dealt with ones supplied with mega-libraries. 

The problem with mega-libraries is *learning* them. If I have a
function for every conceivable purpose I still have to know the
function exists, how to use it, and *why* to use it. I also have to
know about any inconsistancies or quirks, any limitations or side
effects (and every language has these, even OOP ones).

A steep learning curve is a detriment in an IF language, be it the
C-like TADS (and WorldClass) or Advsys or Inform. Most people using
them aren't programmers, they don't have a great deal of time to
devote to learning the language, and thus they can't take advantage of
all the nifty built-in stuff.

Alan has the advantage of being easier to learn, but lacks critical
language-extension functions, so unfortunately that isn't the answer
either.

What we need is a language/library combination that does complex
things easily, not one that has an embarassment of riches. To date I
haven't seen anything that qualifies.

Lisp definitely isn't the answer (in my opinion). Although every IF
language to date represents enourmous investments of time and effort
by their authors, and is light-years ahead of programming IF in Basic
(which I've done <shudder>) we're still in the dark ages when it comes
to languages and tools.

Visual tools might be the answer, and they might make language issues
secondary. To date there haven't been enough visual programming
environments for IF to hazard a guess about it.

Respectfully,

Wolf




From nkg@vcn.bc.ca Tue Jan 21 09:50:08 MET 1997
Article: 21502 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!news.maxwell.syr.edu!news.bc.net!unixg.ubc.ca!freenet.vancouver.bc.ca!not-for-mail
From: nkg@vcn.bc.ca (Neil K. Guy)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Inform vs. TADS look-and-feel
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Date: 20 Jan 1997 14:43:02 GMT
Organization: Vancouver CommunityNet
Lines: 31
Message-ID: <5c009m$gd5@milo.vcn.bc.ca>
References: <5avsi0$41i@bartlet.df.lth.se> <32D6B2AA.75B5F21E@post.rwth-aachen.de> <fake-mail-1901971123030001@van-as-08c02.direct.ca> <5buqpo$1jv@newsops.execpc.com>
NNTP-Posting-Host: opus.vcn.bc.ca
X-Newsreader: TIN [UNIX 1.3 BETA-950824-16colors PL0]
Xref: news.lth.se rec.arts.int-fiction:21502 rec.games.int-fiction:20296

Colm McCarthy (illusory@execpc.com) wrote:

: It's nitpicking, but I've always preferred TADS's default responses.
: Inform's "You can't see any such thing" always infuriated me.  I found
: it rather malicious in tone, but then that's me. [...]

 Hm... you bring up another interesting point. I guess I don't like
Inform's response because TADS' default response (I don't know the word
xxx) is more honest. The former implies Inform knows the word; the latter
basically admits that TADS doesn't. In addition, with the Inform system
you get exchanges like this:

   >take zxlkwdweio23898

   You can't see any such thing.

 And to me that breaks, uh, our good friend mimesis a bit.

 My understanding of the logic behind the Inform system is that it avoids
giving away to the player what words the game understands and what words
are unknown. But really, I don't see anything wrong with that. I think
it's quite fair for the player to know what vocabulary words are likely to
be understood. And if you really want to dupe the player then you can
simply stick in appropriate but unused vocabulary words so it's not
possible to guess anything useful that way.  :)

 - Neil K.

--
        the Vancouver CommunityNet   *   http://www.vcn.bc.ca/
              (formerly the Vancouver Regional FreeNet)


From mol@bartlet.df.lth.se Tue Jan 21 15:47:47 MET 1997
Article: 21517 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform vs. TADS look-and-feel
Date: 21 Jan 1997 12:17:23 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 72
Message-ID: <5c28k3$nko@bartlet.df.lth.se>
References: <5avsi0$41i@bartlet.df.lth.se> <5buqpo$1jv@newsops.execpc.com> <5c009m$gd5@milo.vcn.bc.ca> <erkyrathE4CBLH.69M@netcom.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <erkyrathE4CBLH.69M@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>Neil K. Guy (nkg@vcn.bc.ca) wrote:
>>  Hm... you bring up another interesting point. I guess I don't like
>> Inform's response because TADS' default response (I don't know the word
>> xxx) is more honest. The former implies Inform knows the word; the latter
>> basically admits that TADS doesn't. In addition, with the Inform system
>> you get exchanges like this:
>>    >take zxlkwdweio23898
>>    You can't see any such thing.
>>  And to me that breaks, uh, our good friend mimesis a bit.
>
>Whereas reality *does* sometimes stop you and say "The word 'XXX' does 
>not exist in this universe." I see...

I don't really think any of the systems is very good at maintaining
mimesis. There's a lot of scope for improvement - however, it is not at
all clear how to achieve that improvement in a reasonable simple way.

>>  My understanding of the logic behind the Inform system is that it avoids
>> giving away to the player what words the game understands and what words
>> are unknown. But really, I don't see anything wrong with that. I think
>> it's quite fair for the player to know what vocabulary words are likely to
>> be understood.
>
>I think it's totally unfair (and I speak as a player; it feels like 
>cheating when I can do this.)
>
>Can we say anything further on this subject?

Yes  (raising hand eagerly, desperate to get teacher's attention :-)),
I think we should think a little more about the effects on
gameplay. Suppose we have a puzzle of the kind we all love and enjoy
so much: a guess-the-correct-word puzzle. Or suppose just that the
first word that suggests itself to the player is one that the author
hadn't thought of. So suppose the player says "take snorkelwhacker",
when the intended syntax was "take potrzebie". 

In this case, Inform's response "You can't see any such thing" can be
more than a little confusing. There is IMHO a real risk that the player
will draw the conclusion that there really isn't any snorkelwhacker in
the game, but that the mysterious entity so eloquently described in
the room description really is something completely different.

When TADS replies that it doesn't understand the word
"snorkelwhacker", it is at least being completely honest. I think the
player is less likely to be misled and more likely to realize that he
should try all the synonyms he can think of.

At least that's how I work when I play IF.

Another case is this:

| Library.
| You uncle Zebrafax used to call this room his library, which is a bit
| odd since there is not a single book in sight. The only furniture is,
| in fact, a large safe.
| 
| The safe is open. Inside it is a ruby the size of a plover's egg.
| 
| > take all
| There is none at all available!

Which reply at least I find quite infuriating - the ruby is in plain
sight, yet the parser refuses to let "all" refer to things within
containers. (I'm sure Graham has good reasons for this; it's
irritating nevertheless).



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From d91frera@ida.liu.se Tue Jan 21 15:58:56 MET 1997
Article: 21520 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: Questionable Languages & Compilers
Date: 21 Jan 1997 09:15:36 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 145
Message-ID: <5c21fo$euv@curofix.ida.liu.se>
References: <32b72f97@beachyhd.demon.co.uk> <32D93862.79B2A3DF@alcyone.com> <5bbmti$afl@bartlet.df.lth.se> <32DBD28D.713B5AF1@alcyone.com> <5bik6u$r0g@bartlet.df.lth.se> <32deb932.803050@news.one.net> <5bt73v$roa@curofix.ida.liu.se> <32e3fbe5.4389012@news.one.net>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)

(Long post, but much of it is an example that can be skipped)

wolf@one.net (Roger Plowman) writes:

>>I don't understand the expression, but I assume it means that you don't
>>like the syntax of Lisp. Lisp has the simplest syntax of all languages I
>>have encountered. What can be wrong with that? Do you think complex syntax
>>is something to strive for? Well, try writing IF in Cobol then...

>The problem with Lisp syntax is that *everything* is surrounded by
>parentheses.

In a basically functional language, it's quite natural. It wouldn't work
very well in a procedural language.

>There's also the prefix notation. And finally the problem

No one needs more than 10 minutes to learn the prefix notation.

>Lisp is indeed simple to write in--but that's really a problem with
>this particular language family, since moderately complex expressions
>become unreadable. The eye tends to skip over the parentheses no
>matter how carefully the code is formatted.

The indentation is what primarily helps the eye in understanding the code,
not the parentheses. With a good Lisp-editor, like Emacs, the indentation is
done automatically, which is of course very valuable in such a language as
Lisp. As you say, counting parentheses isn't much fun.

>Even simple if tests become a challenge to express with clarity.

This is _very_ much a matter of coding style. Some people propose C as a
beginner's language. That's one of the best languages for writing unclear
code.

>The problem with mega-libraries is *learning* them. If I have a
>function for every conceivable purpose I still have to know the
>function exists, how to use it, and *why* to use it. I also have to
>know about any inconsistancies or quirks, any limitations or side
>effects (and every language has these, even OOP ones).

Not necessarily so. If you need a function that does something that could
be of general interest, it's very likely to exist. You just need to find it.
In my opinion, it takes only a short while to get used to the way the Common
Lisp functions work. As Andrew Plotkin pointed out in another reply to this,
there are a few 'special-forms', that don't follow the regular patterns
because it would be inconvenient. There are very few different kinds of
special-forms, though, so I don't think that's much of a problem. For
example, there are numerous special-forms for iteration over different
structures, but they all have a similar syntax.

I'll give you an example: I want to create an array, but can't remember
the command to do it or what arguments it takes.

(This is the actual interaction with the Lisp-environment - skip over it if
 you are not interested.)

> (apropos 'array)

*PRINT-ARRAY*    variable
CLOS::<ARRAY>    variable
ADJUST-ARRAY    function
ADJUSTABLE-ARRAY-P    function
:ARRAY    constant
ARRAY 
ARRAY-DIMENSION    function
ARRAY-DIMENSION-LIMIT    constant
ARRAY-DIMENSIONS    function
ARRAY-ELEMENT-TYPE    function
ARRAY-HAS-FILL-POINTER-P    function
ARRAY-IN-BOUNDS-P    function
ARRAY-RANK    function
ARRAY-RANK-LIMIT    constant
SYSTEM::ARRAY-READER    function
ARRAY-ROW-MAJOR-INDEX    function
ARRAY-TOTAL-SIZE    function
ARRAY-TOTAL-SIZE-LIMIT    constant
ARRAYP    function
FFI:C-ARRAY 
FFI:C-ARRAY-MAX 
FFI:C-ARRAY-PTR 
SYSTEM::C-TYPEP-ARRAY    function
SYSTEM::C-TYPEP-ARRAY-1 
MAKE-ARRAY    function
SIMPLE-ARRAY 
SYSTEM::SIMPLE-ARRAY-P    function
SYSTEM::TYPE-LIST-ARRAY 
SYSTEM::TYPE-LIST-ARRAY-1 
SYSTEM::TYPE-LIST-SIMPLE-ARRAY 
SYSTEM::TYPE-LIST-SIMPLE-ARRAY-1 
UPGRADED-ARRAY-ELEMENT-TYPE    function

> (describe 'make-array)

Description of
MAKE-ARRAY
This is the symbol MAKE-ARRAY, names a function.
The symbol lies in #<PACKAGE LISP> and is accessible in the packages CLOS, COMMON-LISP, COMMON-LISP-USER, FFI, LISP, SCREEN, STDWIN, SYSTEM, USER.
For more information, evaluate #'MAKE-ARRAY or (SYMBOL-FUNCTION 'MAKE-ARRAY).

> (describe #'make-array)

Description of
#<SYSTEM-FUNCTION MAKE-ARRAY>
This is a built-in system function.
argument list: (ARG1 &KEY :ADJUSTABLE :ELEMENT-TYPE :INITIAL-ELEMENT :INITIAL-CONTENTS :FILL-POINTER :DISPLACED-TO :DISPLACED-INDEX-OFFSET)

>

>A steep learning curve is a detriment in an IF language, be it the
>C-like TADS (and WorldClass) or Advsys or Inform. Most people using

I certainly agree that a steep learning curve is a bad idea in an IF language.
I am convinced that learning LISP is _much_ easier than learning, say Inform.

>them aren't programmers, they don't have a great deal of time to
>devote to learning the language, and thus they can't take advantage of
>all the nifty built-in stuff.

I hope my example helped to show that they can.

>What we need is a language/library combination that does complex
>things easily, not one that has an embarassment of riches. To date I
>haven't seen anything that qualifies.

Lisp with a good IF-writing library could serve that purpose.

>Visual tools might be the answer, and they might make language issues
>secondary. To date there haven't been enough visual programming
>environments for IF to hazard a guess about it.

I don't think visual tools will ever make language issues secondary. Most of
the coding involved in making a good game couldn't be done by drawing boxes
and lines.

Equally respectfully,

Fredrik


--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
I want to make it perfectly clear that I can't say I don't think people who
aren't avoiding using too many negations aren't putting things clearly enough.


From erkyrath@netcom.com Tue Jan 21 20:10:07 MET 1997
Article: 21530 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.mel.aone.net.au!grumpy.fl.net.au!news.webspan.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: suggested readings
Message-ID: <erkyrathE4DA2F.J7B@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5c1l6k$5b1@bard.edu>
Date: Tue, 21 Jan 1997 16:35:03 GMT
Lines: 86
Sender: erkyrath@netcom.netcom.com

Rodney Waldhoff (rw542@bard.edu) wrote:
> I have recently been reading the Whizzard's Guide to Text Adventure
> Authorship by G. Kevin Wilson (available from ftp.gmd.de) in which he
> suggests a number  of works that he considers to be "required reading" for
> would-be i-f authors. In particular, Mr. Wilson suggests:

>         * J.R.R. Tolkien's "The Hobbit"
>         * Douglas Adams' "The Hitchhiker's Guide to the Galaxy"
>         * Peter Beagle's "The Last Unicorn"
>         * William Gibson's "Neuromancer"
>         * Arthur Conan Doyle's "Sherlock Holmes" series

> Which seems to be representative of most i-f genres, including sword-and-
> sorcery/fantasy, humor/sci-fi, cyberpunk and detective/historical fiction.
> (I'm afraid I've never heard of Beagle or "The Last Unicorn"--fantasy,
> I gather?)

Yeah. Schmendrick the Magician! Read it.

I think this is more a reading list for would-be genre authors (mystery, 
fantasy, SF) *regardless* of whether it's IF or static fiction. And very 
minimal for that, of course. I'd add all my favorite authors, but I've 
listed them before.

> I was intrigued by these comments for I, as a would-be i-f author, have
> been doing a bit of research and searching for inspiration, and have
> discovered some works that seem to be particularly good examples of style,
> atmosphere, plot development, etc. for interactive fiction.

> I've primarily been looking at the detective genre, so of course we have
> Dolye's Sherlock Holmes series. To this I would add:

>      * Edgar Allen Poe's mysteries:
>         "The Murders in the Rue Morgue", "The Mystery of
>         Marie Roget", "The Gold Bug" and "The Purloined Letter"

Sure (actualy I'm a weasel, since I haven't read much Poe. But Poe's 
horror writing was excellently adapted to a graphic IF work, _The Dark 
Eye_.) 

> More importantly I think both these authors offer something to i-f writers
> in any genre. Specifically,
>      * Doyle's "The Adventure of Silver Blaze"
>         for its red herrings, excellent distribution of clues and an
>         ending that (imho) strikes a perfect balance between surprise and 
>         foreshadowing
>      * Poe's "The Man of the Crowd", "The Oblong Box", and above all, "The
>         Oval Portrait"
>          as examples of the power and depth of the description of objects

What, these are limited to IF? But the points are good. 

One of the reasons I keep recommending Cherryh and McKillip (ok, I gave 
in to temptation) is that they can pack tremendous amounts of information 
(and emotion) into single sentences. A useful talent in an IF work, where 
big screenfuls of text annoy the reader. ("reader" == "me".)

> Similarly, I would suggest that theater is (or should be) a closer
> relative of i-f than most novels, but maybe that's because I wish I could
> see more meaningful/useful dialogue. And of course we had interactive
> theater long before interactive novels...

My uncle is studying interactive theater in New York somewhere... I 
talked with him about it a little. Conclusion was that you can't transfer 
the good stuff to computers until we invent AI. Of course.

Everyone's going to hate me, but I think Piers Anthony is a great author
to read for IF writers. He's inexhaustibly fixated on puzzles,
*especially* IF-type puzzles, especially ones with clever,
hidden-but-logical solutions. And puzzle-oriented use of magic. And if he
preaches a lot, well, we've been talking about intertwining morality, IF,
and puzzles, haven't we? 

Mind you, I haven't read any Anthony myself for years. I got started
early, while he was still an original and creative writer. And I've done
my time reading his later stuff. :) But pull down, I don't know, the first
three or six Xanth books, the first three Proton/Phaze books, the first
three Incarnations books. (Ok, skip to the end of the third. It's got a
couple of good game scenarios.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From COP96RDF@shef.ac.uk Tue Jan 21 20:10:48 MET 1997
Article: 21531 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!news.ibm.net.il!arclight.uoregon.edu!enews.sgi.com!EU.net!uknet!usenet1.news.uk.psi.net!uknet!uknet!yama.mcc.ac.uk!bignews.shef.ac.uk!usenet
From: Roger Fredericks <COP96RDF@shef.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Source Posting
Date: Tue, 21 Jan 1997 17:39:14 +0000
Organization: Automatic Control & Systems Engineering, University of Sheffield, UK
Lines: 36
Message-ID: <32E4FF42.2F00@shef.ac.uk>
References: <01bc04f6$f2f464a0$129c45cf@weissinger>
NNTP-Posting-Host: pc006071.shef.ac.uk
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Win16; I)

A. Keyton Weissinger wrote:
> This is a plea on behalf of myself and (I'm sure) many other novice IF
> authors:
> 
> PLEASE FOLLOW GARETH REES' EXAMPLE AND POST YOUR SOURCE!!!! 

I agree.

To be quite honest, much of the source on GMD is pretty basic and not a lot of use. Advent, 
for instance, is very simplistic - most of the code is just room descriptions, and there's 
hardly anything in there that one couldn't soon work out alone. I don't wish to sound too 
harsh; I'd rather have the source to Advent than not, but there is a dearth of more advanced 
source. Balances is great for advanced parsing, but there isn't a lot else. Once one gets 
past the level of writing rooms and a few simple get-x-use-x puzzles, you're on your own. The 
programming of NPCs and sequences of events lasting many turns, for instance, is not well 
illustrated.

Gareth Rees' "Christminster" however, is different. It was fascinating (and very educational) 
for a non-programmer like me to see how a large and complex game should be put together. I've 
probably found it more useful than all the rest of the Inform source on gmd put together. 
(Don't worry Gareth, I haven't pinched anything from it!)

I don't want to discourage people from putting source code on gmd, but if you are going to, 
try and make it do something other people might not be able to work out themselves. If you've 
written a game and don't want to post the whole source (I can understand this up to a point) 
then why not rip out some of the slick routines you've come up with, change the text round a 
bit, and share it with the rest of us? Show off a bit! Things like this make good additions 
to the library. Many of these already exist of course, and are often cleverly written. I find 
that even if the module is no good to me as a whole, there's usually something to be learned 
by reading through it.

I don't know how many Inform novices have read through the standard library files themselves, 
but I recommend anyone learning the language to do so. They give the reader an understanding 
of Inform on every level.

Rob


From nulldogma@aol.com Tue Jan 21 22:09:02 CET 1997
Article: 21537 of rec.arts.int-fiction
Path: news.lth.se!solace!umdac!umu.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!eua.ericsson.se!news.algonet.se!news-feed.inet.tele.dk!mr.net!newsfeeds.sol.net!newspump.sol.net!howland.erols.net!newsxfer.itd.umich.edu!newsxfer3.itd.umich.edu!portc01.blue.aol.com!audrey01.news.aol.com!not-for-mail
From: nulldogma@aol.com (Nulldogma)
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform vs. TADS look-and-feel
Date: 19 Jan 1997 21:34:14 GMT
Organization: AOL http://www.aol.com
Lines: 47
Message-ID: <19970119213400.QAA15067@ladder01.news.aol.com>
References: <fake-mail-1901971123030001@van-as-08c02.direct.ca>
NNTP-Posting-Host: ladder01.news.aol.com
X-Admin: news@aol.com

Neil K. Guy wrote:
> At some point Magnus Olsson wrote:
> >
> > Last summer (I think), somebody mentioned on this newsgroup that he
> > didn't like the default TADS formatting of room descriptions etc, but
> > preferred that of Inform and the Infocom games instead.
>
> Actually... since nobody else has asked... what are the main differences
> between the TADS and Inform styles that people don't like?

For me it's mostly that Inform games have bold room titles, as well as
flush-left (i.e., not indented) first paragraphs for room descriptions.
These are easy enough to implement in TADS (see code below), but so long
as boldfacing wasn't recognized on Macs, it wasn't safe to do. (Flush-left
type below a non-bold heading looks icky.)

With MaxTADS, we are saved from that scourge. MaxTADS also allows
non-fixed-width fonts, which many people clamor for (though I don't
particularly care).

Now if you could add functionality in TADS to recognize both fixed-width
*and* non-fixed-width fonts in the same game, then you'd really be
talking...

Neil


/*   Code to "Informize" TADS room descriptions. */

modify room
    statusLine =
    {
        "\(<<self.sdesc>>\)"; "\n";
    }
;

modify nestedroom
    statusLine =
    {
 "\(<<self.location.sdesc>>, <<self.statusPrep>> <<self.thedesc>>\)";
"\n";
    }
;
---------------------------------------------------------
Neil deMause                            neild@echonyc.com
                  http://www.echonyc.com/~wham/neild.html
---------------------------------------------------------


From obrian@ucsu.Colorado.EDU Wed Jan 22 09:33:50 MET 1997
Article: 21556 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!mn6.swip.net!plug.news.pipex.net!pipex!oleane!pasteur.fr!jussieu.fr!math.ohio-state.edu!howland.erols.net!agate!boulder!ucsu.Colorado.EDU!obrian
From: Paul O'Brian <obrian@ucsu.Colorado.EDU>
Newsgroups: rec.arts.int-fiction
Subject: Re: suggested readings
Date: Tue, 21 Jan 1997 17:04:48 -0700
Organization: University of Colorado at Boulder
Lines: 29
Message-ID: <Pine.GSO.3.95.970121165811.21910A-100000@ucsu.Colorado.EDU>
References: <5c1l6k$5b1@bard.edu> <erkyrathE4DA2F.J7B@netcom.com>
NNTP-Posting-Host: ucsu.colorado.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
NNTP-Posting-User: obrian
In-Reply-To: <erkyrathE4DA2F.J7B@netcom.com>

On Tue, 21 Jan 1997, Andrew Plotkin wrote:

> Everyone's going to hate me, but I think Piers Anthony is a great author
> to read for IF writers. He's inexhaustibly fixated on puzzles,
> *especially* IF-type puzzles, especially ones with clever,
> hidden-but-logical solutions. And puzzle-oriented use of magic. And if he
> preaches a lot, well, we've been talking about intertwining morality, IF,
> and puzzles, haven't we? 

I concur. In fact, I mentioned at the end of "Claw" that the fortress'
three tests were Anthony-influenced. I was reading the "Incarnations"
series during the writing of "Claw" and was amazed at how closely some of
Anthony's work aligned with IF tropes. (For example, the incarnations in
the first few books get a magic object which symbolizes their power, and
which can influence the world when it is pushed, pulled, turned, spun,
etc.) They read almost like novels adapted from pieces of IF! (Now,
*there's* a genre we haven't yet seen revived.) 

I know there was a graphical IF game based on Anthony. Out of curiousity,
do those of you who've played it think it lived up to Anthony's potential
as a great author for adaptation into IF?

Paul O'Brian                                     obrian@ucsu.colorado.edu
"It makes no difference which one of us you vote for! Your planet is
doomed! DOOMED!"
							-- Kodos





From erkyrath@netcom.com Wed Jan 22 10:36:26 MET 1997
Article: 21530 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.mel.aone.net.au!grumpy.fl.net.au!news.webspan.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: suggested readings
Message-ID: <erkyrathE4DA2F.J7B@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5c1l6k$5b1@bard.edu>
Date: Tue, 21 Jan 1997 16:35:03 GMT
Lines: 86
Sender: erkyrath@netcom.netcom.com

Rodney Waldhoff (rw542@bard.edu) wrote:
> I have recently been reading the Whizzard's Guide to Text Adventure
> Authorship by G. Kevin Wilson (available from ftp.gmd.de) in which he
> suggests a number  of works that he considers to be "required reading" for
> would-be i-f authors. In particular, Mr. Wilson suggests:

>         * J.R.R. Tolkien's "The Hobbit"
>         * Douglas Adams' "The Hitchhiker's Guide to the Galaxy"
>         * Peter Beagle's "The Last Unicorn"
>         * William Gibson's "Neuromancer"
>         * Arthur Conan Doyle's "Sherlock Holmes" series

> Which seems to be representative of most i-f genres, including sword-and-
> sorcery/fantasy, humor/sci-fi, cyberpunk and detective/historical fiction.
> (I'm afraid I've never heard of Beagle or "The Last Unicorn"--fantasy,
> I gather?)

Yeah. Schmendrick the Magician! Read it.

I think this is more a reading list for would-be genre authors (mystery, 
fantasy, SF) *regardless* of whether it's IF or static fiction. And very 
minimal for that, of course. I'd add all my favorite authors, but I've 
listed them before.

> I was intrigued by these comments for I, as a would-be i-f author, have
> been doing a bit of research and searching for inspiration, and have
> discovered some works that seem to be particularly good examples of style,
> atmosphere, plot development, etc. for interactive fiction.

> I've primarily been looking at the detective genre, so of course we have
> Dolye's Sherlock Holmes series. To this I would add:

>      * Edgar Allen Poe's mysteries:
>         "The Murders in the Rue Morgue", "The Mystery of
>         Marie Roget", "The Gold Bug" and "The Purloined Letter"

Sure (actualy I'm a weasel, since I haven't read much Poe. But Poe's 
horror writing was excellently adapted to a graphic IF work, _The Dark 
Eye_.) 

> More importantly I think both these authors offer something to i-f writers
> in any genre. Specifically,
>      * Doyle's "The Adventure of Silver Blaze"
>         for its red herrings, excellent distribution of clues and an
>         ending that (imho) strikes a perfect balance between surprise and 
>         foreshadowing
>      * Poe's "The Man of the Crowd", "The Oblong Box", and above all, "The
>         Oval Portrait"
>          as examples of the power and depth of the description of objects

What, these are limited to IF? But the points are good. 

One of the reasons I keep recommending Cherryh and McKillip (ok, I gave 
in to temptation) is that they can pack tremendous amounts of information 
(and emotion) into single sentences. A useful talent in an IF work, where 
big screenfuls of text annoy the reader. ("reader" == "me".)

> Similarly, I would suggest that theater is (or should be) a closer
> relative of i-f than most novels, but maybe that's because I wish I could
> see more meaningful/useful dialogue. And of course we had interactive
> theater long before interactive novels...

My uncle is studying interactive theater in New York somewhere... I 
talked with him about it a little. Conclusion was that you can't transfer 
the good stuff to computers until we invent AI. Of course.

Everyone's going to hate me, but I think Piers Anthony is a great author
to read for IF writers. He's inexhaustibly fixated on puzzles,
*especially* IF-type puzzles, especially ones with clever,
hidden-but-logical solutions. And puzzle-oriented use of magic. And if he
preaches a lot, well, we've been talking about intertwining morality, IF,
and puzzles, haven't we? 

Mind you, I haven't read any Anthony myself for years. I got started
early, while he was still an original and creative writer. And I've done
my time reading his later stuff. :) But pull down, I don't know, the first
three or six Xanth books, the first three Proton/Phaze books, the first
three Incarnations books. (Ok, skip to the end of the third. It's got a
couple of good game scenarios.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Thu Jan 23 20:20:28 MET 1997
Article: 21606 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!eua.ericsson.se!cnn.exu.ericsson.se!uunet!in3.uu.net!205.252.116.190!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: suggested readings
Message-ID: <erkyrathE4H1q6.Iqt@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5c1l6k$5b1@bard.edu> <erkyrathE4DA2F.J7B@netcom.com> <32e6c2d9.13443443@hermes.rdrop.com>
Date: Thu, 23 Jan 1997 17:25:17 GMT
Lines: 35
Sender: erkyrath@netcom.netcom.com

Laurel Halbany (mythago@agora.rdrop.com) wrote:
> erkyrath@netcom.com (Andrew Plotkin) wrote:

> >Everyone's going to hate me, but I think Piers Anthony is a great author
> >to read for IF writers. He's inexhaustibly fixated on puzzles,
> >*especially* IF-type puzzles, especially ones with clever,
> >hidden-but-logical solutions. And puzzle-oriented use of magic. And if he
> >preaches a lot, well, we've been talking about intertwining morality, IF,
> >and puzzles, haven't we? 

> He's pretty awful when it comes to character development and
> motivation, though.

Simplistic, not necessarily awful, at least in the earlier stuff. 

> I wouldn't recommend anybody pick up an Anthony
> book when considering coding up an NPC.

Well, it depends what you mean. When you're *writing* an NPC, I'd want
something more interesting than Anthony's characters. When you're *coding*
an NPC, though, our technology is primitive enough that we have to do 
pretty mechanical, predictable behavior. Sound familiar? :-)

I'm not just being facile, here. Some kinds of puzzles (and other 
scripted events) have NPCs that act algorithmically -- either simple 
mechanism, or a predictable kind of reaction to story or player events. 
Anthony *does* do that kind of character in his books.

--Z


-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From goetz@cs.buffalo.edu Fri Jan 24 09:52:15 MET 1997
Article: 21601 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!hammer.uoregon.edu!news-xfer.netaxs.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!su-news-hub1.bbnplanet.com!newsxfer3.itd.umich.edu!portc01.blue.aol.com!newsstand.cit.cornell.edu!news.acsu.buffalo.edu!acsu.buffalo.edu!goetz
From: goetz@cs.buffalo.edu (Phil Goetz)
Newsgroups: rec.arts.int-fiction
Subject: Re: Um, what *is* Prolog?
Date: 21 Jan 1997 21:07:26 GMT
Organization: State University of New York at Buffalo/Computer Science
Lines: 9
Message-ID: <5c3b6e$ki0@prometheus.acsu.buffalo.edu>
References: <ant0220230b0c4bn@arnod.demon.co.uk> <5b0986$s28@bartlet.df.lth.se> <ant1020200b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: pollux.cs.buffalo.edu
NNTP-Posting-User: goetz

Check out my page at

http://www.cs.buffalo.edu/~goetz/prolog.html

This has pointers to free Prolog implementations, FAQs,
as well as a set of programming assignments that incrementally
develop an adventure game in Prolog, and their solutions.

Phil Goetz@cs.buffalo.edu


From gdr11@cl.cam.ac.uk Sun Jan 26 21:40:33 CET 1997
Article: 21630 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!uwm.edu!math.ohio-state.edu!howland.erols.net!EU.net!uknet!usenet1.news.uk.psi.net!uknet!uknet!lyra.csx.cam.ac.uk!news
From: Gareth Rees <gdr11@cl.cam.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: suggested readings
Date: 24 Jan 1997 14:30:49 +0000
Organization: Cambridge University Computer Lab
Lines: 19
Sender: gdr11@stint.cl.cam.ac.uk
Message-ID: <yxssp3rrvqe.fsf@stint.cl.cam.ac.uk>
References: <5c1l6k$5b1@bard.edu> <erkyrathE4DA2F.J7B@netcom.com>
	<32e6c2d9.13443443@hermes.rdrop.com> <erkyrathE4H1q6.Iqt@netcom.com>
NNTP-Posting-Host: stint.cl.cam.ac.uk
X-Newsreader: Gnus v5.3/Emacs 19.34

Andrew Plotkin <erkyrath@netcom.com> wrote:
> [Piers Anthony a good source of material for IF]

I agree with Andrew.  Piers Anthony's novels may be unreadably bad, but
precisely because of their poor characterisation and absurd wandering
puzzle-driven plots they would make good adventure-game fodder.

For example, in "With a Tangled Skein" (1985), the heroine saves the
universe by remembering how to find one crooked coin among twelve in
only three weighings on a set of balances; this is the kind of absurdity
one could only put up with in an adventure game.

(As the author of an adventure game in which you need to win a game of
two-by-two dots and boxes, I feel bound to point out that Anthony's
analysis of said game in the novel "Golem in the Gears" (1986) is
completely incorrect.  Why didn't he hire a consultant?)

-- 
Gareth Rees


From nkg@vcn.bc.ca Mon Jan 27 13:11:35 CET 1997
Article: 21682 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeeds.sol.net!hammer.uoregon.edu!arclight.uoregon.edu!news.bc.net!unixg.ubc.ca!freenet.vancouver.bc.ca!not-for-mail
From: nkg@vcn.bc.ca (Neil K. Guy)
Newsgroups: rec.arts.int-fiction
Subject: Re: I-F Contest Postmortem for 1996 (and some SPAG info.)
Date: 26 Jan 1997 20:15:57 GMT
Organization: Vancouver CommunityNet
Lines: 17
Message-ID: <5cge1t$j63@milo.vcn.bc.ca>
References: <5bouvq$qe0@agate.berkeley.edu> <5cd6b2$sbc@reader1.reader.news.ozemail.net> <erkyrathE4LGH9.K63@netcom.com> <5cfnf3$neo@reader1.reader.news.ozemail.net>
NNTP-Posting-Host: opus.vcn.bc.ca
X-Newsreader: TIN [UNIX 1.3 BETA-950824-16colors PL0]

James Cole (jrcole@ozemail.com.au) wrote:
 
: I agree that what I've said might seem a bit strange, but I do have a good
: reason.

 A desolation came unto the land. And the rivers did flow with blood. And
a foul pestilence filled the air. And locusts did scour the fields. And lo
the Lord spake, asking "Hast thou included thy game with the Activision CD
compilation?" And his voice was like thunder. And jrcole@ozemail.com.au
rose, and said "Nope." And the heavens opened, and the Lord replied "Jolly
good then, come on up."

 - Neil K. Guy

--
        the Vancouver CommunityNet   *   http://www.vcn.bc.ca/
              (formerly the Vancouver Regional FreeNet)


From mol@bartlet.df.lth.se Tue Jan 28 09:49:23 MET 1997
Article: 21714 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform .z8 question
Date: 28 Jan 1997 09:30:48 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 34
Message-ID: <5ckdfo$ecg@bartlet.df.lth.se>
References: <rbram-ya023580002201971617040001@news.concentric.net> <erkyrathE4LGML.Kon@netcom.com> <5cf1g0$qdn@cnn.Princeton.EDU> <32ED265E.10CF@worldnet.att.net>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <32ED265E.10CF@worldnet.att.net>,
David Speer  <speer@worldnet.att.net> wrote:
>Adam J. Thornton wrote:
>> 
>> In article <erkyrathE4LGML.Kon@netcom.com>,
>> Andrew Plotkin <erkyrath@netcom.com> wrote:
>> >> And yes, Andrew, I _know_ the Java VM is better ;)
>> >Dunno if it's better in general, but it already exists.
>> 
>> What we need are IF Java Class Libraries.
>> 
>> I say loudly as I being looking  the other way and whistling as someone
>> says, "well then, Adam, why don't you write us some?"
>> 
>What would actually go into writing JAVA IF libs?

Well, to start with a parser and disambiguator. That's really the most
important - and most difficult - bit. The basic classes for rooms,
takeable objects, static objects, scenery, light sources, doors,
containers, surfaces, actors. Methods for handling light, darkness,
line-of-sight, transparency, NPC interaction. More fancy classes for
things like settable dials, lockable things, food, clothes, you name
it. The grammar and default actions for a bunch of verbs. Bomb-proof
save, restore and undo commands.

It's really quite a lot, actually. Throwing together somethign for
writing small adventures - as proof-of-concept, perhaps - should not
be too difficult. But if you're aiming at a replacement for Inform or
TADS you should be prepared to invest quite a lot of time and
effort. The world is a complicated thing to simulate.


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From mdf@doc.ic.ac.uk Tue Jan 28 21:26:50 MET 1997
Article: 21733 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news-feed.inet.tele.dk!mr.net!arclight.uoregon.edu!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!rill.news.pipex.net!pipex!netcom.net.uk!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!doc.ic.ac.uk!doc.ic.ac.uk!not-for-mail
From: mdf@doc.ic.ac.uk (Martin Frost)
Newsgroups: rec.arts.int-fiction
Subject: Re: Which editor to use on inf files?
Date: 28 Jan 1997 13:12:55 -0000
Organization: Dept. of Computing, Imperial College, University of London, UK.
Lines: 24
Message-ID: <5cku0n$mjl@oak50.doc.ic.ac.uk>
References: <5cj1ch$4mc$1@neko.syix.com> <5cj6au$dkd@bartlet.df.lth.se> <5cjo0a$5sa@milo.vcn.bc.ca>
NNTP-Posting-Host: oak50.doc.ic.ac.uk

In article <5cjo0a$5sa@milo.vcn.bc.ca> nkg@vcn.bc.ca (Neil K. Guy) writes:

> Er, actually the filetype and creator codes are stored right in the file
>system, aren't they?

AFAIK, they are stored in different places on different filesystems. It is
only possible to easily examine the storage of such information when files are
stored on non-native filesystems, for example by using System 7.5 to write to
MSDOS floppies, or using a UNIX-based fileserver.

System 7.5, for example, writes a file called FINDER.DAT and a directory
called (IIRC) RESOURCE.FRK in each directory on an MSDOS disk. FINDER.DAT
contains a table associating MSDOS mangled filenames, Macintosh filenames, plus
file type info etc.

At the API level, they all appear to be in the filesystem itself, since the
only approved (== future-compatible) way of accesing them is through the
Mac equivalent of stat() (can't remember what it's called).

AFAIK, file comments are normally stored in the desktop file (this is why they
disappear if you rebuild the desktop).

Martin



From joe.mason@tabb.com Wed Jan 29 09:40:22 MET 1997
Article: 21744 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!super.zippo.com!zdc-e!uunet!in2.uu.net!142.77.1.4!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: Which editor to use o
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.7053.1727@tabb.com>
References: <1591.6961T979T2264@easynet.co.uk>
Date: Tue, 28 Jan 1997 15:40:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 32

"Re: Which editor to use o", declared Bill Hoggett from the Vogon ship:

BH>On 22-Jan-97 Sam A Hulick <shulick@cs.indiana.edu> wrote:

BH>>I just upgraded from an Amiga 3000 to a Cyrix 166MHz running Win95,
BH>and         ^^^^^^^^
BH>>I'm tossing up my hands wondering which editor would be good to edit
BH>>Inform .inf files.  Something that maybe handled indenting, etc.

I use the Turbo Pascal IDE - the editor that comes with Borland Turbo 
Pascal.  Unfortunately, you have to buy Turbo Pascal to get it.  When I 
don't use that, I use DOS Edit.

BH>>P.S.: .inf files on Win95 are registry information files.. is there
BH>a >way to make Win95 recognize both .inf files?

No, there's no way to make it recognize two different types.  What you 
*can* do is put the complete set of commands for both types in the one 
.inf description.  Just add an "Edit Z-Code" option to the end of the 
list, so you don't overwrite the commands used for setup information 
files.  (I think you can even set the Z-Code version to default without 
screwing anything up).

Another you can do is put a short-cut to your favourite editor in the 
"Send To" folder (\Windows\SendTo).  That way you can send *any* 
program, regardless of extension, to it by right-clicking on the icon 
(which is a big help with README files and stuff, where you get 
combinations like README., README.1ST, READ.ME, etc...)

Joe

 CMPQwk 1.42 9550 A good catchword can obscure analysis for fifty years.


From rhodri@wildebst.demon.co.uk Wed Jan 29 12:33:17 MET 1997
Article: 21761 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!eua.ericsson.se!news.algonet.se!hammer.uoregon.edu!news-xfer.netaxs.com!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!howland.erols.net!ix.netcom.com!netcom.net.uk!dispatch.news.demon.net!demon!wildebst.demon.co.uk!not-for-mail
From: rhodri@wildebst.demon.co.uk (Rhodri James)
Newsgroups: rec.arts.int-fiction
Subject: Re: Which editor to use on inf files?
Date: Wed, 29 Jan 1997 01:57:28 GMT
Organization: The Wildebestiary
Message-ID: <n53D59726@wildebst.demon.co.uk>
References: <5cj1ch$4mc$1@neko.syix.com> <5cj6au$dkd@bartlet.df.lth.se> <erkyrathE4oswG.93x@netcom.com> <5cjj63$cia@bartlet.df.lth.se>
NNTP-Posting-Host: wildebst.demon.co.uk
X-NNTP-Posting-Host: wildebst.demon.co.uk
X-Newsreader: Offlite 0.09 / Termite Internet for Acorn RISC OS
Lines: 16

mol@bartlet.df.lth.se (Magnus Olsson) wrote:

> On second thought, Micro$oft *could* of course have added a type
> information field when they designed the new file system for NT, still
> keeping the compatibility with DOS if you used a DOS filesystem, but for
> some reason they didn't.

Actually there is space to do this in the FAT (DOS) file format, and
Acorn/Aleph1 used this to preserve some RISC OS file type information on
files passed to DOS.  Unfortunately Win95 uses some of these bits for its
own ulterior purposes.  Sad, but that's what you get for fiddling with
undocumented features.

-- 
Rhodri James  *-*  Wildebeeste herder to the masses
If you don't know who I work for, you can't misattribute my words to them


From kfischer@greenhouse.llnl.gov Thu Jan 30 01:05:34 MET 1997
Article: 21773 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!mn6.swip.net!plug.news.pipex.net!pipex!newsxfer3.itd.umich.edu!howland.erols.net!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!su-news-hub1.bbnplanet.com!arclight.uoregon.edu!enews.sgi.com!lll-winken.llnl.gov!usenet
From: Kathleen Fischer <kfischer@greenhouse.llnl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform vs. TADS look-and-feel
Date: Wed, 29 Jan 1997 09:11:56 -0800
Organization: Lawrence Livermore National Laboratory
Lines: 57
Message-ID: <32EF84DC.446B@greenhouse.llnl.gov>
References: <5avsi0$41i@bartlet.df.lth.se> <32D6B2AA.75B5F21E@post.rwth-aachen.de> <fake-mail-1901971123030001@van-as-08c02.direct.ca> <5buqpo$1jv@newsops.execpc.com> <5c009m$gd5@milo.vcn.bc.ca> <erkyrathE4CBLH.69M@netcom.com> <32ee685d.5885814@news.peinet.pe.ca>
NNTP-Posting-Host: greenhouse.llnl.gov
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (X11; I; IRIX 5.3 IP22)

(Sorry... can't find who to attribute this to...)
>  Hm... you bring up another interesting point. I guess I don't like
> Inform's response because TADS' default response (I don't know the word
> xxx) is more honest. The former implies Inform knows the word; the latter
> basically admits that TADS doesn't. In addition, with the Inform system
> you get exchanges like this:
>    >take zxlkwdweio23898
>    You can't see any such thing.
>  And to me that breaks, uh, our good friend mimesis a bit.

The biggest gripe I have about "You can't see any such thing." is that I
get it most often when I'm trying to examine something listed in the
room description. Talking about breaking mimeses!

That said, I still prefer the Inform message to TADs because "The word
'XXX' does not exist in this universe." admits defeat right up front. 
At least Inform tries to keep the illusion going and in some
circumstances it works (ie, you try to pull your mint condition IF
compiler manual out of your daypack when in fact you lost it in an
malfunctioning avalanche several posts ago).

----
Test Room
You a standing in the middle of Kathleen's test room.  A thousand bugs
have been slayed here and their carcasses lie scattered about the floor.
Resting amoungst the rubble is a mint condition IF compiler manual. To
the north is a door leading to more interesting stuff.

> x bugs
You can't see any such thing.

A kunkel walks by, laughing his head off. "Mimesis?  You need a good
graphical interface for that, my friend." he smirks.

You patiently remind the kunkel that half the time in graphical games
you click on the book wanting to open it and instead your character lobs
it at some big green slobbery monster standing in the room with you.

"Books? We don't need no stinking books!" huffs the kunkel, warily
eyeing the mint condition IF compiler manual resting amongst the
carcasses.

> click on book
A disembodied hand appears from nowhere and presses on the book. The
mint condition IF compiler manual begins to rise slowly (ever so slowly)
>from  the ground and levitate toward the kunkel...

"Ahhhhh" he screams, scratching frantically at the concealed door that
doesn't seem to working at the moment...

Kathleen

-- 
*******************************************************************
*  Kathleen M. Fischer
*  kfischer@greenhouse.llnl.gov
** "Don't stop to stomp ants while the elephants are stampeding" **


From graham@gnelson.demon.co.uk Thu Jan 30 16:51:22 MET 1997
Article: 21794 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!erinews.ericsson.se!eua.ericsson.se!news.algonet.se!hammer.uoregon.edu!arclight.uoregon.edu!mr.net!netnews.com!howland.erols.net!EU.net!uknet!usenet1.news.uk.psi.net!uknet!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: New releases: Inform 6.11, Library 6/4
Date: Tue, 28 Jan 1997 01:20:01 +0000 (GMT)
Organization: none
Message-ID: <ant280101868M+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 135


  Updated releases: Inform 6.11 and Library 6/4
  =============================================

Inform 6.10 and library 6/3 were substantial upgrades, aimed mainly
at making a major overhaul of the parser (to support translation
to languages other than English) and improving debugging facilities.
Today's releases are strictly maintenance.

The compiler itself is in good shape and I wouldn't be upgrading
it except that one very serious bug has emerged: essentially an
optimisation of some "if" statements was optimising truth into
falsity.  This had been happening for a good nine months without
anyone noticing, but I am heartily ashamed.  Other alterations
include minor tweaks to assist the Mac port.  Still, porters should
find v6.11 easy to accommodate, since the code is hardly altered
>from  v6.10.

The "new model" parser, as premiered in library 6/3, has been
behaving in slightly quirky ways: well, after a month of
beta-testing by the unwitting denizens of rec.arts.int-fiction,
I've fixed some 17 bugs, listed below.  A few of these bugs
impact on game behaviour enough to annoy players seriously,
and I'd advise compiling "production copies" of games -- copies
intended for downloading or publication -- from library 6/4 rather
than 6/3.

Please note that 6/4, like 6/3, can be used with Inform 6.10 or
later (so you can use the upgraded library under v6.10 right away,
without waiting for ports of v6.11 to appear) but not with Inform
v6.0* or earlier.

As a temporary measure, you can get hold of the new material from the
Inform 6 Home Page:

    http://www.gnelson.demon.co.uk/inform.html

It will be filed in its proper place at ftp.gmd.de shortly, and then
the temporary uploads page will be taken out.

My thanks, as ever, to those who have emailed me bug reports.
I am always grateful for these, though it can sometimes take me
a couple of weeks to reply when I have a serious email backlog,
for which I apologise.  Please try to send me a short piece of
source code demonstrating what you think is wrong, if possible:
this saves on long explanations and makes it much easier for me
to find the problem.


    Graham Nelson
    27 January 1997

-----------------------------------------------------------------------------

Extracted from the 6-series library modification history, which
resides on the World Wide Web at:

   http://www.gnelson.demon.com/lhistory.html

-------------------------

188. The message "You can't, since the nothing leads nowhere" is no longer
    produced when the player tries to go through a door whose designer
    has forgotten to specify a "door_to" destination.
    
189. Singular and plural were the wrong way round for a few library
    messages in the 6/3 version of "English.h": thanks to Andreas Hoppler
    and Giovanni Riccardi for spotting this.

190. A minor correction has been made to get around a bug in v6.10 of the
    compiler (resulting in movement through darkness not properly working).
    Thus library 6/4 handles darkness movements properly even if you
    haven't got v6.11 or later of the compiler.

191. Likewise to prevent problems with the list manager printing unending
    sequences of spaces.  (Caused by a bug in Inform 6.10 that's fixed in
    6.11.)
    
192. A bug in disambiguation of "her" (possessive adjective) and "her"
    (pronoun) has been removed: it could cause crashes in some difficult
    cases, or more probably just a mysterious refusal to understand "her".

193. Commands like "someone, do something" resulted in the error
    "I only understood you as far as wanting to someone" (but only in
     certain circumstances).  Now fixed.

194. Two library messages about inserting X into Y now have X and Y the
    right way round.  (E.g., library 6/3 would sometimes print "The
    diamond is closed.", not "The Faberge diamond case is closed.", in
    response to "put diamond in case".)

195. Prepositions sometimes missed out when the parser is printing a
    command inferred for lack of input (e.g., "give" printing out
    "(the ball the dog)" instead of "(the ball to the dog)".  Fixed.

196. Spurious space removed from the message "The dog  doesn't seem
    interested.".

197. The disambiguator in the parser has been made a little less
    trigger-happy (it now asks questions like "Which do you mean...?"
    more often, rather than jumping too far to conclusions).

198. The grammar now finally makes "take" and "get" distinct Inform
    verbs: this should have no effect except to prevent the parser
    from confusing "take on..." with "get on...", "take out..." with
    "get out...", etc.

199. The NO_PLACES option works again.  (Sorry: I thought I'd fixed
    this back at 176 above.)

200. "Search" used to print an oddly truncated sentence when searching
    something all of whose contents were "scenery".  Fixed.

201. A minor bug in the list-writer to do with concealed and scenery
    objects being miscounted; and another bug to do with scenery but
    unconcealed contents of an object being listed if they're the
    first child of an unconcealed container or supporter, have both
    been fixed.

202. Action reversal not working when exactly one of the tokens being
    reversed is a "number" or "special".  Fixed.

203. Pronouns are quietly set to likely room contents when the player
    moves around, in the new parser (as in Infocom's parsers, but unlike
    the old Inform parser); in 6/3 this sometimes set them to "concealed"
    objects.  Fixed.

204. "Time:" being printed twice over on the status line in a
    time rather than score/turns game.  Fixed.

-----------------------------------------------------------------------------

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From kjahds@kjahds.com Thu Jan 30 19:52:28 MET 1997
Article: 21796 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!newsserver.jvnc.net!newsreader.jvnc.net!kjahds.com!not-for-mail
From: kjahds@kjahds.com (Kenneth Albanowski)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: 30 Jan 1997 11:07:21 -0500
Organization: None
Lines: 42
Message-ID: <5cqgvp$l7@kjahds.com>
References: <32EE2A79.41C6@greenhouse.llnl.gov> <5cpdva$jd6$1@news01a.micron.net>
NNTP-Posting-Host: prn-ts1-46.jvnc.net

In article <5cpdva$jd6$1@news01a.micron.net>,
Jay Goemmer  <jgoemmer@micron.net> wrote:
>Kathleen Fischer <kfischer@greenhouse.llnl.gov> wrote:
>>I'm trying to decide if I want the user to be able to select their
>>gender (all right, hold the wise-crack remarks... this is an honest
>>question!)
>
>   Since human personalities are fairly complex, and each of us has 
>a mixture of both "masculine" and "feminine" qualities (the quotation 
>marks are for the "Politically Correct"), I'm sure that concentrating 
>on the character's awareness of their surroundings, etc., would be a 
>good way to carry it off.

This sounds like a good approach, but perhaps could go farther then Jay was
thinking. LGOP had the relatively subtle bathroom choice. CosmoServe has the
explicit choice of (virtual!) body and orientation.

Might not it be possible to continue the idea of subtle choices and let the
player build up their visible persona? Instead of segregating into male and
female, have a series of properties, some boolean, others perhaps with more
flexibility. Obvious factors would be choice of clothing, choice (or lack
of) make-up, choice of bathroom (or, if we're being fancy, what they do in
the bathroom), choice of gender-stereotype (do they pick up the truck or the
doll first), choice of sexual orientation (given appropriate circumstances),
choice of sexual activity in general (do they read a tech book, or flirt?),
other choices like preferred reading material, etc.

Of course, great ingenuity would be needed, first of all to elicit the
information from the player, second of all to deal with the problem of
information that hasn't been collected yet (either do it all at the
beginning of the game, or the persona will have to be androgynous or in some
more complex Heisenburg-like undecided state) and third of all to deal with
all the possibilities of NPC interaction. If one wasn't careful, one might
have to deal with some, well, "uncommon" personas, unless there are limiting
factors on the choices.

I doubt any current I-F really needs or is up to dealing with all potential
in this, but I also have no doubt that some future work will do something
quite like this. The technique seems too powerful to ignore.
-- 
Kenneth Albanowski (kjahds@kjahds.com)



From gerlach7@nospam.address Sat Feb  1 01:50:26 MET 1997
Article: 21822 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!cdc2.cdc.net!news.texas.net!news-xfer.netaxs.com!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!howland.erols.net!math.ohio-state.edu!newsfeed.acns.nwu.edu!news.acns.nwu.edu!news	
From: Charles Gerlach <gerlach7@nospam.address>
Newsgroups: rec.arts.int-fiction
Subject: Re: how big is a competition game?
Date: Fri, 31 Jan 1997 15:26:39 -0600
Organization: Northwestern University, Evanston, IL, US
Lines: 38
Message-ID: <32F2638F.6F86@nospam.address>
References: <5ct80p$u4@nntp5.u.washington.edu>
NNTP-Posting-Host: tam7.mech.nwu.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (X11; I; HP-UX B.10.10 9000/715)

Mary K. Kuhner wrote:
> 
> Is there any consensus on approximately what size these competition
> games are supposed to be?  "Solvable in two hours" doesn't help me much.
> I can't solve *anything* in two hours.  I've been trying to proceed
> by comparison with previous games, but I'm looking at _Sherbet_ and
> _A Change in the Weather_ and getting rather confused.  Sherbet seems
> easily three times as big as Weather.   I haven't finished enough
> other games to have an idea about the range.
> 
> So, from a player's point of view, what's a good size?  Weather-sized?
> Sherbet-sized?  (Obviously both of those must have seemed good enough!)
> 
> Mary Kuhner mkkuhner@genetics.washington.edu

Well, many people commented that both Sherbet and Delusions were
just too darn big for a two hour game, unless you happened to be
a genius with excellent typing skills, speed reading abilities, and
large amounts of amphetamines in your blood stream.

My preference: the smaller the better. I've seen other people complain
about unrealistic minimalist settings, but I much prefer that to 
wading through hordes of locations with no real relevance to the game,
other than to make it feel bigger.

>From  the POV of an entrant, instead of a player, it struck me that
many games were judged by a bigger = better yardstick. Many people
seemed to give Aayela a low score with the comment "It was nice,
but I wanted more." I rated Aayela highly because it was well crafted
and well written, and was sorry to see others dismiss it based on 
size alone. 

-- 
**********************************************************************
Charles Gerlach does not speak for Northwestern, and can be mailed at: 
cagerlac  a t  merle  d o t  acns  d o t  nwu  d o t  edu
He hopes that placing his e-mail in this format did not seriously 
inconvenience anyone attempting to contact him (except for spam-bots).


From daly@PPD.Kodak.COM Sat Feb  1 01:50:54 MET 1997
Article: 21820 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!demos!news1.relcom.ru!EU.net!howland.erols.net!vixen.cso.uiuc.edu!sdd.hp.com!frankensun.altair.com!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: XYZZY Awards - down to the wire
Date: 31 Jan 1997 15:00:48 GMT
Organization: Eastman Kodak Company
Lines: 33
Message-ID: <5ct1f0$j1u@kodak.rdcs.Kodak.COM>
References: <32EDEE63.330A61F1@post.rwth-aachen.de> <5cllh4$6vh@life.ai.mit.edu> <5cn1pt$tr@news.lth.se>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com

In article <5cn1pt$tr@news.lth.se> mol@marvin.df.lth.se (Magnus Olsson) writes:
>
>Also, I have a strong feeling that the perceived parser "quality" is
>strongly dependent on the game.  What's a good parser? One that
>accepts all the commands that you want to input; one that doesn't get
>in the way of gameplay. So a game that doesn't require you to input
>complicated commands will be easier on the parser. 

This sounds like an argument for why a Best Parser award would be
appropriate instead of just a TADS vs. Inform thing.

IMHO, a game that makes you feel like you're interacting with a
story instead of with a parser is one that should be lifted up.
A seamless interface is a good thing whether the story is vast
or not.  I would presume, though, that if such a category were
established, people would vote for the most complex game with
a seamless interface.

To give an example from the yesterdays of I-F, Portal had a
superior interface.  You were an archaeologist from the far
future who came across a twentieth-century computer with a
built-in power supply, and you could use it to access the
planetary databases to see what caused a previously unexplained
mass exodus from Earth.  The interface was just a GUI database app.
Simple?  You bet.  Seamless?  Sure -- there is nothing you could do
there that wasn't anticipated.  But it was effective.

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From ats@hubert.wustl.edu Sat Feb  1 10:02:39 CET 1997
Article: 21834 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!news.starnet.net!news.starnet.net!newspump.wustl.edu!newsreader.wustl.edu!news
From: Alan Shutko <ats@hubert.wustl.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: XYZZY Awards - down to the wire
Date: 31 Jan 1997 14:13:46 -0600
Organization: Washington University in St. Louis, MO USA
Lines: 28
Message-ID: <m2afppvc05.fsf@hubert.wustl.edu>
References: <32EDEE63.330A61F1@post.rwth-aachen.de> <5cllh4$6vh@life.ai.mit.edu> <5cn1pt$tr@news.lth.se> <5ct1f0$j1u@kodak.rdcs.Kodak.COM>
NNTP-Posting-Host: wydo125.wustl.edu
Mime-Version: 1.0 (generated by tm-edit 7.93)
Content-Type: text/plain; charset=US-ASCII
X-Newsreader: Red Gnus v0.80/Emacs 19.34

>>>>> "MD" == Matthew Daly <daly@PPD.Kodak.COM> writes:

MD> To give an example from the yesterdays of I-F, Portal had a
MD> superior interface.  You were an archaeologist from the far future
MD> who came across a twentieth-century computer with a built-in power
MD> supply, and you could use it to access the planetary databases to
MD> see what caused a previously unexplained mass exodus from Earth.

Actually, I thought you were one a spaceship which had returned from
some voyage, only to discover that everyone was gone.  Can't check, my
aunt has the game (since it's hers, after all).  

But Portal was a good example of IF telling a story... it was not as
interactive as most of what we talk about here, but it had the
illusion of interaction.  All you did was read page after page of
story, but as you read different memos and stories, the computer
"found" more things in the decaying databases... it really seemed like
I was sitting at some old terminal trying to root through what records
remained.  It was more absorbing than most traditional IF.  Quite
similar in feeling to A Mind Forever Voyaging.

Now that you mention it, I have a great urge to play this game
again... it's a good thing my Amiga still runs.  I'll have to see if I
can get my aunt to send me the game.

-- 
Alan Shutko <ats@hubert.wustl.edu> - By consent of the corrupted
10.0 times 0.1 is hardly ever 1.0.


From mol@marvin.df.lth.se Sat Feb  1 10:03:19 CET 1997
Article: 21842 of rec.arts.int-fiction
Path: news.lth.se!mol
From: mol@marvin.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Inform games list
Date: 1 Feb 1997 09:02:14 GMT
Organization: /etc/organization
Lines: 40
Message-ID: <5cv0qm$2e@news.lth.se>
References: <nIuTqBAGvK8yEwVz@highmount.demon.co.uk> <erkyrathE4u105.Jnn@netcom.com> <32F28AF7.2A89@globalserve.net>
NNTP-Posting-Host: marvin.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:21842 rec.games.int-fiction:20641

In article <32F28AF7.2A89@globalserve.net>,
Drone  <foxglove@globalserve.net> wrote:
>Andrew Plotkin wrote:
>> 
>> Well, "In The End" takes place in the future, with rejuvenation
>> treatments and computer-controlled cars; "Tapestry" has angels and other
>> mythologic figures; "Weather" has, mmm, there's a fantastic element in it.
>> 
>> I think this distinction winds up pre-judging a point which the author
>> deliberately left open to question. I know that's true in my case. Were
>> 
>
>If you leave something open to question, you have to expect someone to attempt 
>an answer.

But he doesn't have to like that answer, does he?

Personally, I think that it's the same thing as in non-interactive
literatute: some works are written within a genre, and categorizing
them as such only re-affirms the author's intentions. Saying that, for
example, Eddings' "Belgariad" is epic fanasy takes nothing away from the
books.

Other works aren't easily categorized, and forcibly stuffing them into
a pigeonhole requires either ignoring some qualities of the work or
overemphasizing others. Suppose I label "The Name of The Rose" as a
detective story - what do I gain? Not very much (except that I might
get some hard-core mystery fans to read what they might otherwise
ignore as a stuffy historical novel :-)), but I lose a lot by
deliberately ignoring all the non-mystery aspects of the book. 

This doesn't mean that "Name of the Rose" *isn't* a mystery, just that
it's so much more than a mystery. 

In the case of IF, there are still relatively few games around and most
of them are genre pieces that are easily categorized. Why not let the
rest remain "uncategorized"?

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From john@elvw.demon.co.uk Sat Feb  1 11:05:08 CET 1997
Article: 21843 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!uwm.edu!math.ohio-state.edu!howland.erols.net!rill.news.pipex.net!pipex!dispatch.news.demon.net!demon!mail2news.demon.co.uk!elvw.demon.co.uk!john
From: John Wood <john@elvw.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: how big is a competition game?
Date: Sat, 01 Feb 1997 09:16:51 GMT
Organization: None
Message-ID: <746586388wnr@elvw.demon.co.uk>
References: <5ct80p$u4@nntp5.u.washington.edu>
Reply-To: john@elvw.demon.co.uk
X-Mail2News-User: john@elvw.demon.co.uk
X-Mail2News-Path: relay-11.mail.demon.net!relay-10.mail.demon.net!elvw.demon.co.uk
X-Broken-Date: Friday, Jan 31, 1997 18.52.05
X-Newsreader: Newswin Alpha 0.7
Lines: 18

mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) writes:
> So, from a player's point of view, what's a good size?  Weather-sized?
> Sherbet-sized?  (Obviously both of those must have seemed good enough!)

Well, Sherbet is IMO far too big.  Weather felt about the right size, 
but boy is it tough!  I haven't actually finished either so I can't 
give an informed opinion, but I'd keep it nearer Weather-sized.

The only competition-winner I have finished (*and* I did it in the two 
hours) is the one you didn't mention - Uncle Zebulon's Will.  That 
seemed to me to be perfectly sized.  At least for me, which is of 
course what matters... ;-)

John






From whizzard@uclink.berkeley.edu Sun Feb  2 00:26:41 MET 1997
Article: 21856 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!news-peer.gsl.net!news.gsl.net!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!feed1.news.erols.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: how big is a competition game?
Date: 1 Feb 1997 06:22:00 GMT
Organization: University of California at Berkeley
Lines: 43
Message-ID: <5cune8$bp0@agate.berkeley.edu>
References: <5ct80p$u4@nntp5.u.washington.edu> <32F2638F.6F86@nospam.address> <32F292E4.2781@greenhouse.llnl.gov> <sandifer-3101971949030001@sci-dial-2-mac6.sdsu.edu>
NNTP-Posting-Host: uclink.berkeley.edu

Re: Split the contest into long/short categories.

[My first post, full of urine and vinegar, deleted.]
[My second post, full of hate and vitriol, deleted.]
[Original poster's message deleted, don't want him to think I'm mad at
him.]

Hmm.  I really seem to have a bee in my bonnet tonight.  Ok, I'll just
give the short answer this time.  No.  One category is already hard enough
to organize.  You want another competition, you run it.

There, that's not terribly rude, just a bit foul-tempered.  I can live
with that.

Re: Activision doesn't publish longer works...

[First post deleted.  Sheesh, someone has pushed my buttons tonight.]

Short answer again.  Activision has published what I have shown them.  I
have had my reasons for not showing them particular games, and I do not
accept the job of presenting longer works to them for publication.  It is
the responsibility of each game author to do his/her own PR work.  As for
this year's competition, I have sent them several more games beyond 6th
place, because I felt there were several that really deserved a look.
Before someone points out the tyranny involved in this, let me say that I
will not make excuses for the things I do as organizer of the I-F contest.
If I did that, then I wouldn't have time to get anything useful done, like
getting the best games published, and making their authors some good
money.

[Sigh.  More vitriol deleted.]

Anytime someone else wants this lousy job, let me know.  I'd rather enter
the contest than run it.  I don't know what's gotten me so mad tonight,
really I don't.  Certainly nothing posted on raif was anywhere near bad
enough to justify those rants.  Maybe I just need more sleep.  Maybe it's
this damn writer's block.  A game and a book to finish, and I sit around
all day trying, for the love of god, to write just one word.  Bloody waste
of a day.  Grr.

Apologies to those upset by this post.  I'm just not myself tonight.
-- 
	"Stress?  WHO ME???!!!  Never."


From erkyrath@netcom.com Sun Feb  2 00:26:49 MET 1997
Article: 21855 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: how big is a competition game?
Message-ID: <erkyrathE4xnGs.36I@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ct80p$u4@nntp5.u.washington.edu> <32F2638F.6F86@nospam.address> <32F292E4.2781@greenhouse.llnl.gov> <sandifer-3101971949030001@sci-dial-2-mac6.sdsu.edu> <5cune8$bp0@agate.berkeley.edu>
Date: Sat, 1 Feb 1997 16:36:28 GMT
Lines: 30
Sender: erkyrath@netcom7.netcom.com

Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:
> Re: Activision doesn't publish longer works...

> [First post deleted.  Sheesh, someone has pushed my buttons tonight.]

> Short answer again.  Activision has published what I have shown them.  I
> have had my reasons for not showing them particular games, and I do not
> accept the job of presenting longer works to them for publication. 

Actually, I don't think it's generally known how much personal credit 
Whizzard deserves for getting Activision to publish the competition 
entries at all. As I understand it, the only reason they even *know* 
about the competition is that while Whizzard was helping them get the 
documentation right for Masterpieces, he said, "Hey, how about some *new* 
games...?"

Everything proceeded from there. If it starts a tradition of Activision 
promoting competition winners, that's great. But it's not their 
*responsibility* to get our work out there -- any more than it's 
Wizzard's responsibility to argue them into doing so.

Besides, we're about to have our own CD, really... (pieces are still 
falling into place at a non-zero rate.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Sun Feb  2 00:27:01 MET 1997
Article: 21854 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!ais.net!cdc2.cdc.net!news.texas.net!news-xfer.netaxs.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: how big is a competition game?
Message-ID: <erkyrathE4xn5K.2ox@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ct80p$u4@nntp5.u.washington.edu> <746586388wnr@elvw.demon.co.uk>
Date: Sat, 1 Feb 1997 16:29:44 GMT
Lines: 32
Sender: erkyrath@netcom7.netcom.com

John Wood (john@elvw.demon.co.uk) wrote:
> mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) writes:
> > So, from a player's point of view, what's a good size?  Weather-sized?
> > Sherbet-sized?  (Obviously both of those must have seemed good enough!)

> Well, Sherbet is IMO far too big.  Weather felt about the right size, 
> but boy is it tough!  I haven't actually finished either so I can't 
> give an informed opinion, but I'd keep it nearer Weather-sized.

> The only competition-winner I have finished (*and* I did it in the two 
> hours) is the one you didn't mention - Uncle Zebulon's Will.  That 
> seemed to me to be perfectly sized.  At least for me, which is of 
> course what matters... ;-)

I've spent plenty of time aggressively supporting the right of 
competition entries to be any style, any genre, any lack-of-genre for 
that matter -- without fear, favor, or pre-categorization.

So I'd better stick in that they can be any difficulty as well, and any
size (measured in number of rooms, number of objects, number of dramatic
scenes, or any other measure) It just has to have a playing time which can
plausibly be labelled "two hours or less." 

--Z




-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Sun Feb  2 10:08:32 MET 1997
Article: 21855 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: how big is a competition game?
Message-ID: <erkyrathE4xnGs.36I@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ct80p$u4@nntp5.u.washington.edu> <32F2638F.6F86@nospam.address> <32F292E4.2781@greenhouse.llnl.gov> <sandifer-3101971949030001@sci-dial-2-mac6.sdsu.edu> <5cune8$bp0@agate.berkeley.edu>
Date: Sat, 1 Feb 1997 16:36:28 GMT
Lines: 30
Sender: erkyrath@netcom7.netcom.com

Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:
> Re: Activision doesn't publish longer works...

> [First post deleted.  Sheesh, someone has pushed my buttons tonight.]

> Short answer again.  Activision has published what I have shown them.  I
> have had my reasons for not showing them particular games, and I do not
> accept the job of presenting longer works to them for publication. 

Actually, I don't think it's generally known how much personal credit 
Whizzard deserves for getting Activision to publish the competition 
entries at all. As I understand it, the only reason they even *know* 
about the competition is that while Whizzard was helping them get the 
documentation right for Masterpieces, he said, "Hey, how about some *new* 
games...?"

Everything proceeded from there. If it starts a tradition of Activision 
promoting competition winners, that's great. But it's not their 
*responsibility* to get our work out there -- any more than it's 
Wizzard's responsibility to argue them into doing so.

Besides, we're about to have our own CD, really... (pieces are still 
falling into place at a non-zero rate.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From fxp4258@flourine.cs.rit.edu Sun Feb  2 10:08:59 MET 1997
Article: 21870 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!www.nntp.primenet.com!nntp.primenet.com!newsxfer3.itd.umich.edu!portc01.blue.aol.com!newsstand.cit.cornell.edu!cornellcs!rochester!news.csug.rochester.edu!rit.cs.rit.edu!flourine!fxp4258
From: fxp4258@flourine.cs.rit.edu (Frank X Pape;951;icsg1;)
Newsgroups: rec.arts.int-fiction
Subject: Re: how big is a competition game?
Date: 1 Feb 1997 23:32:54 GMT
Organization: Rochester Institute of Technology
Lines: 9
Message-ID: <5d0jr6$i45@rit.cs.rit.edu>
References: <5ct80p$u4@nntp5.u.washington.edu> <746586388wnr@elvw.demon.co.uk>
NNTP-Posting-Host: flourine.cs.rit.edu
X-Newsreader: TIN [version 1.2 PL2]

: The only competition-winner I have finished (*and* I did it in the two 
: hours) is the one you didn't mention - Uncle Zebulon's Will.  That 
: seemed to me to be perfectly sized.  At least for me, which is of 
: course what matters... ;-)

I would tend to agree with you there.  I thought Zebulon was just right,
at least in terms of size.

Frank.


From gerlach7@nospam.address Sun Feb  2 16:28:35 MET 1997
Article: 21822 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!cdc2.cdc.net!news.texas.net!news-xfer.netaxs.com!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!howland.erols.net!math.ohio-state.edu!newsfeed.acns.nwu.edu!news.acns.nwu.edu!news	
From: Charles Gerlach <gerlach7@nospam.address>
Newsgroups: rec.arts.int-fiction
Subject: Re: how big is a competition game?
Date: Fri, 31 Jan 1997 15:26:39 -0600
Organization: Northwestern University, Evanston, IL, US
Lines: 38
Message-ID: <32F2638F.6F86@nospam.address>
References: <5ct80p$u4@nntp5.u.washington.edu>
NNTP-Posting-Host: tam7.mech.nwu.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (X11; I; HP-UX B.10.10 9000/715)

Mary K. Kuhner wrote:
> 
> Is there any consensus on approximately what size these competition
> games are supposed to be?  "Solvable in two hours" doesn't help me much.
> I can't solve *anything* in two hours.  I've been trying to proceed
> by comparison with previous games, but I'm looking at _Sherbet_ and
> _A Change in the Weather_ and getting rather confused.  Sherbet seems
> easily three times as big as Weather.   I haven't finished enough
> other games to have an idea about the range.
> 
> So, from a player's point of view, what's a good size?  Weather-sized?
> Sherbet-sized?  (Obviously both of those must have seemed good enough!)
> 
> Mary Kuhner mkkuhner@genetics.washington.edu

Well, many people commented that both Sherbet and Delusions were
just too darn big for a two hour game, unless you happened to be
a genius with excellent typing skills, speed reading abilities, and
large amounts of amphetamines in your blood stream.

My preference: the smaller the better. I've seen other people complain
about unrealistic minimalist settings, but I much prefer that to 
wading through hordes of locations with no real relevance to the game,
other than to make it feel bigger.

>From  the POV of an entrant, instead of a player, it struck me that
many games were judged by a bigger = better yardstick. Many people
seemed to give Aayela a low score with the comment "It was nice,
but I wanted more." I rated Aayela highly because it was well crafted
and well written, and was sorry to see others dismiss it based on 
size alone. 

-- 
**********************************************************************
Charles Gerlach does not speak for Northwestern, and can be mailed at: 
cagerlac  a t  merle  d o t  acns  d o t  nwu  d o t  edu
He hopes that placing his e-mail in this format did not seriously 
inconvenience anyone attempting to contact him (except for spam-bots).


From graham@gnelson.demon.co.uk Tue Feb  4 10:30:50 MET 1997
Article: 21911 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!rill.news.pipex.net!pipex!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: simple question on pronouns in TADS [was Re: annoying pronouns]
Date: Mon, 03 Feb 1997 20:14:38 +0000 (GMT)
Organization: none
Message-ID: <ant0320381cbM+4%@gnelson.demon.co.uk>
References: <Pine.SGI.3.95L.970107093713.14934A-100000@tower.york.ac.uk> <32E39EBD.21C210C@alcyone.com> <sandifer-2101972325190001@sci-dial-2-mac1.sdsu.edu> <5d07dv$qne@prometheus.acsu.buffalo.edu> <5d47sc$h6h@bartlet.df.lth.se> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 39

In article <5d47sc$h6h@bartlet.df.lth.se>, Magnus Olsson
<URL:mailto:mol@bartlet.df.lth.se> wrote:
> >Like, in Inform, having a separate location called "the_dark" instead of
> >being able to say that the current location is dark.
> 
> This is actually a major inconvenience in that it leads to a lot of extra
> testing. I find that my code is full of things like
> 
> if (location == thedark)
>    move foo to real_location;
> else
>    move foo to location;
> 
> Perhaps Graham would like to comment on the historical reasons for
> this? I suspect that it has something to do with Infocom's doing it
> this way...

I wouldn't do it this way again, no.  It arises from a Z-machine
issue: in V3 the location name on the status bar is always drawn
>from  the variable Infocom used as "location".  Stupidly, I did too,
rather than making it merely copy either the location or darkness.

And then again... there is an argument for "darkness" as a location
in its own right.  In many games, darkness behaves conceptually
much more like an area with its own characteristics than like
a slight modification to real, physical areas.  Most events in
adventure games are perceived by means of sight, so that being
in darkness cuts the player off from almost every aspect of the
physical place.  Similarly, all dark places tend to behave alike:
monsters lurk and so on.

What really _is_ pointless is the failure of "real_location" to
simply always hold the physical location!  (At present it tends
only to be meaningful when the player is in darkness.)  I will
attend to this in some future library release.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From florian.beck@lrz.uni-muenchen.de Tue Feb  4 10:31:26 MET 1997
Article: 21915 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!news.ecrc.de!blackbush.xlink.net!fu-berlin.de!informatik.tu-muenchen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: Mon, 3 Feb 1997 20:56:23 GMT
Organization: Private GNU Site
Lines: 50
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m3ybd5a9s8.fsf@ue801di.lrz-muenchen.de>
References: <5d3q6c$k6u@news.ccit.arizona.edu>
Reply-To: florian.beck@lrz.uni-muenchen.de
NNTP-Posting-Host: dial136.ppp.lrz-muenchen.de
X-Newsreader: Red Gnus v0.83/Emacs 19.34

jdyer@mustique.u.arizona.edu (Jason B Dyer) writes:

> I certainly don't condone going back to 500 rooms per game, but some IF is
> packed so unrealistically to lose atmosphere. In The End is a case in
> point; there just aren't enough places to go for it to be interesting.

The few rooms was one thing I liked about In The End. It is a short game,
but it had all the places that fit in. Perhaps the whole game should
have been longer - but that's another point. Nothing would have been
gained by adding useless rooms or buildings you could wander
about, as the ITE character is *not* an adventurer.

A common technique is to split the locations into sub locations. That
would have spoiled ITE's ease of navigation. It wouldn't achieve
anything, either. Interactive fiction is not a simulation, it's a
story (or better: a kind of a play).

> Jigsaw has instances of both too compact and just right; the Moon and
> Titanic had wonderful atmosphere, along with a few "useless" rooms, while
> I can't even remember where the Penicillin scene was located.
> 
> I-0 took about five minutes to play, and nothing in the game was
> compelling enough for me to go back and play other variations.
> 
> The granddaddy of them all, Adventure, would have been quite boring if it
> didn't have so much to explore.

That is a good point. But Adventure is *about* exploring a world (or a
cave), that is it's "plot". Exploring the world might be a sub plot in
some games (the fantasy genre comes to mind). Even then, map drawing
and running about in a large world will become tiresome if the world
is not designed and described *really* well.

> For short games, it certainly is possible for every room to have meaning.
> But some games like Maiden in the Moonlight benefit from a few "useless"
> rooms.

Other large games, Christminster for example, have a minimalistic
setting (concerning the rooms). And it works well.

Large worlds which the player has to map with many "useless" rooms is
one of the things IF will have to move away from in the future. While
it works fine for some games, there are just too many stories which
can't be told this way. There's a matter of taste hidden here, of
course, but it's not "Minimalism or not?". It's what kind of story you
like. 

-- 
Flo



From mol@bartlet.df.lth.se Tue Feb  4 18:03:56 MET 1997
Article: 21926 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Darkness in Inform (was: simple question on pronouns in TADS [was Re: annoying pronouns])
Date: 4 Feb 1997 16:59:12 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 39
Message-ID: <5d7mcg$teh@bartlet.df.lth.se>
References: <Pine.SGI.3.95L.970107093713.14934A-100000@tower.york.ac.uk> <5d07dv$qne@prometheus.acsu.buffalo.edu> <5d47sc$h6h@bartlet.df.lth.se> <ant0320381cbM+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

Topic drift is an amazing thing, isn't it: a sub-thread in the
discussion about the semantics of pronouns led to a "simple question
on pronouns in TADS" which mutated into a discussion of the OO-ness of
the Inform library which in turn led to the current question. Usenet
is fantastic...
 
Anyway:

In article <ant0320381cbM+4%@gnelson.demon.co.uk>,
Graham Nelson  <graham@gnelson.demon.co.uk> wrote:
>And then again... there is an argument for "darkness" as a location
>in its own right.  In many games, darkness behaves conceptually
>much more like an area with its own characteristics than like
>a slight modification to real, physical areas.  Most events in
>adventure games are perceived by means of sight, so that being
>in darkness cuts the player off from almost every aspect of the
>physical place.  Similarly, all dark places tend to behave alike:
>monsters lurk and so on.

I must respectfully disagree. In the real world, darkness affects
our perception (and a few properties of material objects), but it
does not move us to a parallel universe.

IMHO, Inform's treatment of darkness looks like a hack that is
convenient as long as you don't want to modify the behaviour of
darkness (such as making everything but sight-related activites work
as usual), in which case it seems more like a liability than an asset.

>What really _is_ pointless is the failure of "real_location" to
>simply always hold the physical location!  (At present it tends
>only to be meaningful when the player is in darkness.)  I will
>attend to this in some future library release.

That would save programmers quite a lot of trouble, I think.



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From erkyrath@netcom.com Tue Feb  4 18:41:31 MET 1997
Article: 21928 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!rill.news.pipex.net!pipex!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Darkness in Inform (was: simple question on pronouns in TADS [was Re: annoying pronouns])
Message-ID: <erkyrathE5388C.7nJ@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <Pine.SGI.3.95L.970107093713.14934A-100000@tower.york.ac.uk> <5d07dv$qne@prometheus.acsu.buffalo.edu> <5d47sc$h6h@bartlet.df.lth.se> <ant0320381cbM+4%@gnelson.demon.co.uk> <5d7mcg$teh@bartlet.df.lth.se>
Date: Tue, 4 Feb 1997 16:53:00 GMT
Lines: 48
Sender: erkyrath@netcom.netcom.com

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> In article <ant0320381cbM+4%@gnelson.demon.co.uk>,
> Graham Nelson  <graham@gnelson.demon.co.uk> wrote:
> >And then again... there is an argument for "darkness" as a location
> >in its own right.  In many games, darkness behaves conceptually
> >much more like an area with its own characteristics than like
> >a slight modification to real, physical areas.  Most events in
> >adventure games are perceived by means of sight, so that being
> >in darkness cuts the player off from almost every aspect of the
> >physical place.  Similarly, all dark places tend to behave alike:
> >monsters lurk and so on.

> I must respectfully disagree. In the real world, darkness affects
> our perception (and a few properties of material objects), but it
> does not move us to a parallel universe.

> IMHO, Inform's treatment of darkness looks like a hack that is
> convenient as long as you don't want to modify the behaviour of
> darkness (such as making everything but sight-related activites work
> as usual), in which case it seems more like a liability than an asset.

It does get one thing right, however: all darkness looks the same to the
player, even to the point of only printing the "room description" the
first time you enter *any* dark room. And things like the "places" 
command don't list places that you've been with no light.

Of course, I'd rather those things were hacked in and everything *else* 
were handled more simply. 

One thing which is very hard under the current system is to make 
different dark areas distinct -- I obviously did a lot of this _So Far_, 
and I really don't want to think about the code I wrote. Not just for the 
sounds, but to get realistic commands like "feel floor" to behave 
differently depending on the area.

> >What really _is_ pointless is the failure of "real_location" to
> >simply always hold the physical location!  (At present it tends
> >only to be meaningful when the player is in darkness.)  I will
> >attend to this in some future library release.

> That would save programmers quite a lot of trouble, I think.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Wed Feb  5 18:46:44 MET 1997
Article: 21964 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!demos!Gamma.RU!srcc!news1.relcom.ru!EU.net!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Funny Bug in Inform Library
Message-ID: <erkyrathE550ns.79v@netcom.com>
Followup-To: rec.arts.int-fiction
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <32F89578.6A84@cogentex.com>
Date: Wed, 5 Feb 1997 16:04:40 GMT
Lines: 50
Sender: erkyrath@netcom4.netcom.com

Daryl McCullough (daryl@cogentex.com) wrote:
> I was playing an Inform game recently (never mind which) 

Quick! Everybody guess!

> and my
> player had a jar full of water. I encounter a creature that 
> I think might be thirsty, so I try:

>    Give water to creature.

> Inform's response was this:

>    (the quantity of water to the crested animal)
>    (first taking the quantity of water)
>    The quantity of water is already in the jar.

> Hmmm. (I'm guessing that the problem is with the Inform
> library rather than with the specific game.)

The message is coming from the library, but it's actually a game bug. 
(Unless you regard the fact that the library doesn't handle liquids as a
library bug -- which I don't.)

If you know the library, it's pretty obvious what's going on. The "give 
X to Y" verb, correctly, tries to "take X" if X is not actually in your 
hands. And the "take water" command is rigged to perform "put water in 
jar", since that's the only way you can carry water.

A more accurate error message for "take water" might be "You can't carry 
water in your bare hands!" (I mean, an error message for the case where 
your jar is already full of water.) But that doesn't actually improve the 
case under discussion.

Unfortunately, there is no really easy fix. There is no way to override 
the auto-take action of "held" verb tokens. (It happens before "before" 
clauses.) That *is* a bug, or at least a lack of important feature. 
(Request! Request!) The only way to deal with it is to change the grammar 
line from
        * held "to" creature -> Give
to
        * noun "to" creature -> Give
and hope nobody complains about the sudden lack of auto-take for that verb.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mol@bartlet.df.lth.se Wed Feb  5 19:12:11 MET 1997
Article: 21970 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Funny Bug in Inform Library
Date: 5 Feb 1997 19:10:11 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 58
Message-ID: <5daie3$uil@bartlet.df.lth.se>
References: <32F89578.6A84@cogentex.com> <erkyrathE550ns.79v@netcom.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <erkyrathE550ns.79v@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>Unfortunately, there is no really easy fix. There is no way to override 
>the auto-take action of "held" verb tokens. (It happens before "before" 
>clauses.) That *is* a bug, or at least a lack of important feature. 
>(Request! Request!)


Yes, please! Me too! Me too! :-)

Actually, I find the auto-take feature to be pretty irritating at times,
especially when the thing the parser tries to take is manifestly untakable.
For example, I recently tried the command "eat me" when playing a game where it
seemed appropriate (don't ask!), and got the reply

> eat me  
(First taking yourself)
You are always self-possessed!

which wasn't quit the answer I had expected.

Perhaps grammar lines containing "held" should work the following way:
If the object is held, OK. If not and it is ~= player and not static or
scenery, then take it. Else do something smart - but what? Perhaps "held"
should be viewed as a suggestion rather than an absolute requirement, so
that it could match even non-held objects (equivalent to adding an
extra grammar line with "held" replaced by "noun")? In the latter case,
all action routines would of course have to check if the object really
was held. But this would make the game behave more naturally in cases
such as this:

| Freezer 
| You are inside a gigantic freezer with ice-covered walls. 
| You can see an ice cream cone here.
|
| > Eat cone
| (First taking the ice cream cone)
| Yum!
|
| > Eat ice
| You lick at the ice-covered wall. Your tongue immediately sticks to it.

which IMHO is much preferable to being told that I can't take the wall.


>The only way to deal with it is to change the grammar 
>line from
>        * held "to" creature -> Give
>to
>        * noun "to" creature -> Give
>and hope nobody complains about the sudden lack of auto-take for that verb.

Personally, I can live without auto-take. I know there are people who
regard it as an essential convenience, though.


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From erkyrath@netcom.com Wed Feb  5 23:05:19 MET 1997
Article: 21984 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: A game in the dark [was pronoun thread]
Message-ID: <erkyrathE53Aoq.Fy5@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <Pine.SGI.3.95L.970107093713.14934A-100000@tower.york.ac.uk> <32E39EBD.21C210C@alcyone.com> <sandifer-2101972325190001@sci-dial-2-mac1.sdsu.edu> <5d07dv$qne@prometheus.acsu.buffalo.edu> <5d47sc$h6h@bartlet.df.lth.se> <ant0320381cbM+4%@gnelson.demon.co.uk> <32F76F17.446B@greenhouse.llnl.gov>
Date: Tue, 4 Feb 1997 17:46:02 GMT
Lines: 29
Sender: erkyrath@netcom.netcom.com

Kathleen Fischer (kfischer@greenhouse.llnl.gov) wrote:
> Graham Nelson wrote:
> > Most events in
> > adventure games are perceived by means of sight, so that being
> > in darkness cuts the player off from almost every aspect of the
> > physical place.

> What an interesting thought... write a game from the point of view of
> somebody who is visually impaired. Everything would be done by touch,
> taste, sound and smell.  Sounds like a nice competition game (not that I
> have time!)

"Aayela" was one angle on this, of course. Although the last time this 
topic came up, I noted that we've had games where you're *temporarily* 
blind or endarkened, but never a game where you've been blind since birth. 
There'd be a difference, I think.

> Of course, given the way Inform handles Darkness, I guess that really
> wouldn't be possible, would it (she says from the point of view of
> complete ignorance)?

Anything's *possible*.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mkkuhner@phylo.genetics.washington.edu Thu Feb  6 09:02:24 MET 1997
Article: 21991 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!www.nntp.primenet.com!nntp.primenet.com!enews.sgi.com!insync!news.maxwell.syr.edu!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: 6 Feb 1997 02:29:04 GMT
Organization: University of Washington, Seattle
Lines: 45
Message-ID: <5dbflg$p5v@nntp5.u.washington.edu>
References: <5cqp51$bih@kodak.rdcs.Kodak.COM> <32f2e4bd.897419@hermes.rdrop.com> <5d55in$a80@kodak.rdcs.Kodak.COM>
NNTP-Posting-Host: phylo.genetics.washington.edu

In article <5d55in$a80@kodak.rdcs.Kodak.COM> daly@PPD.Kodak.COM (Matthew Daly) writes:
>So, if the main character were female instead of neuter, how would
>a well-written game look different?

"Female" is not some kind of trans-universe, trans-genre constant, so
there is no answer to this question.  It depends.  What society, if any,
forms the background to the game?  What role has she held within that
society?  What does it expect of her, and how will that color peoples'
dealings with her?  What does she expect of herself, and how will that
color her actions and perceptions?

In _Christminster_ the main character's gender establishes a set of
limits for her, some internal (when men bluster at her, she backs down)
and some external ("No women allowed").  But these are societal, not
biological; in a different setting they'd be inappropriate.

My own feeling is that the biological differences, with the possible
exception of size, are not worth bothering with outside a porn game.
My sense of the character as female doesn't need bolstering by
reminders of her physical makeup.  (In fact, I found being told
Christabel was physically weak made me think of her as a wimp; I'd
assumed she was about as strong as I am, and being explicitly told
made her seem weaker than that.)

However, NPC reactions should take gender into account, in whatever
ways the society would naturally produce.  This can be done with a
very light touch--I do *not* need a game full of gender putdowns
just to make the point that my character is female.  The best thing is
to listen to men and women talking, if your game has a near-present
setting, or to try to imagine it for other settings.  Try to put 
yourself into your character's shoes, too.  How does she expect
people to treat her?  What are her big concerns?  Whose approval does 
she need or want?

If the character's not seen in a societal context, honestly, there
is not going to be much need to distinguish female from male or neuter.
(Just get the pronouns right....)  And attempts to do so will turn into 
annoying stereotypes *very* easily.  (I shudder to think about what a
"feminine" Zork Adventurer would be like.)  If there is a societal 
context, that's what determines how you have to handle gender.
The character may well not accept her society's views on gender, but
she will, none the less, exist in their context--perhaps as a rebel,
but rebels have definite characteristics of their own.

Mary Kuhner mkkuhner@genetics.washington.edu


From erkyrath@netcom.com Thu Feb  6 09:04:51 MET 1997
Article: 22007 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!news.texoma.net!www.nntp.primenet.com!nntp.primenet.com!enews.sgi.com!news.sgi.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] initial,describe,arg!
Message-ID: <erkyrathE55Bv5.Au1@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <19970205070101.CAA29838@ladder01.news.aol.com> <erkyrathE551yw.9BM@netcom.com> <32F8DC5D.794B@greenhouse.llnl.gov>
Date: Wed, 5 Feb 1997 20:06:40 GMT
Lines: 43
Sender: erkyrath@netcom.netcom.com

Kathleen Fischer (kfischer@greenhouse.llnl.gov) wrote:
> Ok, here's the deal.  It's back to my machine with a slot.  I want to be
> able to put something into the slot and have it still visible (partly
> sticking out). I would also like to able to say "Put x into machine" and
> have that work right too.  The machine is portable.

> Imagine, a tv remote control with a single battery that is always
> visible.  The battery fits into a slot.  Thats the *kind* of thing that
> I want to do (though of course, not really want I want to do!)  So you
> can say

> > put battery in slot
> or
> > put battery in remote

> and both should work

> when you look at the remote there should be a battery visible.  However,
> its not the kind of container that you can open or close and nothing
> else can go in there but the battery. I don't want the slot to just
> another name for the remote because, well, I don't.  It can make stupid
> things like "push button on slot" work.   :(

I've found that players are very forgiving about this -- when they notice 
at all. Everyone is so pleased that sensible things work that they don't 
care about all the stupid things that work.

>   But when the remote wasnt
> a container, then "put battery in remote" didn't work either.  Right
> now, when you put the battery into the remote it relocates it to the
> slot.  That works great.  However, the room descriptions look aweful.

Well, a "describe" property with an "rtrue" at the end should allow you 
to completely control the listing in the room description.

Getting it right in the inventory may be tricky, but it's possible. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From whizzard@uclink.berkeley.edu Thu Feb  6 09:05:34 MET 1997
Article: 21987 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!eru.mt.luth.se!bloom-beacon.mit.edu!newsfeed.internetmci.com!hunter.premier.net!worldnet.att.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: SPAG 10 out.
Date: 5 Feb 1997 17:21:15 GMT
Organization: University of California at Berkeley
Lines: 14
Message-ID: <5dafib$icp@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:21987 rec.games.int-fiction:20762


SPAG 10 is out, and it has hopefully made it to GMD by now, I'm not sure.
Reviews of most of the competition entries, interviews with some of the
winners, that sort of thing.  Not as good as last year's I-F contest
issue, since I could hardly interview everyone, but some interesting
comments from the authors.  No in-depth analysis this time, I was feeling
too rushed to get to it.  Next issue, for sure.  I already have enough
saved up reviews for SPAG 11, just looking at the stack.  Of course, I can
always stuff it with more reviews, no problem.

Anyways, ta ta for now.
-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From erkyrath@netcom.com Thu Feb  6 12:28:42 MET 1997
Article: 22008 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!cdc2.cdc.net!news.texas.net!news-xfer.netaxs.com!news.maxwell.syr.edu!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Funny Bug in Inform Library
Message-ID: <erkyrathE55Cq4.DGE@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <32F89578.6A84@cogentex.com> <erkyrathE550ns.79v@netcom.com> <5daie3$uil@bartlet.df.lth.se>
Date: Wed, 5 Feb 1997 20:25:15 GMT
Lines: 93
Sender: erkyrath@netcom.netcom.com

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> In article <erkyrathE550ns.79v@netcom.com>,
> Andrew Plotkin <erkyrath@netcom.com> wrote:
> >Unfortunately, there is no really easy fix. There is no way to override 
> >the auto-take action of "held" verb tokens. (It happens before "before" 
> >clauses.) That *is* a bug, or at least a lack of important feature. 
> >(Request! Request!)

> Yes, please! Me too! Me too! :-)

> Actually, I find the auto-take feature to be pretty irritating at times,
> especially when the thing the parser tries to take is manifestly untakable.
> For example, I recently tried the command "eat me" when playing a game where it
> seemed appropriate (don't ask!), and got the reply

> > eat me  
> (First taking yourself)
> You are always self-possessed!

> which wasn't quit the answer I had expected.

> Perhaps grammar lines containing "held" should work the following way:
> If the object is held, OK. If not and it is ~= player and not static or
> scenery, then take it. Else do something smart - but what?

I'd rather be able to control it myself, rather than having any automatic 
rule. (Or rather, if there is any automatic rule, I must be able to 
override both "yes, auto-take" decisions and "no, don't auto-take" 
decisions.)

Now that there's no property limit, I guess just another property is the 
best answer. The current system is nearly always right; it's only for 
particular objects that I want to override it, so allowing some kind of 
"autotake" property on objects seems to be the right approach. 

It would return three different possible values: 
 * yes, try to take the object, and proceed with the action if that succeeds
 * no, don't try to take the object, but proceed with the action anyway
 * print a message and fail.

And of course the property could have action cases. (As before, after, 
and life do.)

This is, remember, only done for "held" verb tokens. And if there is no 
autotake property, it assumes "yes", which is the current behavior.

> Perhaps "held"
> should be viewed as a suggestion rather than an absolute requirement, so
> that it could match even non-held objects (equivalent to adding an
> extra grammar line with "held" replaced by "noun")? In the latter case,
> all action routines would of course have to check if the object really
> was held. But this would make the game behave more naturally in cases
> such as this:

> | Freezer 
> | You are inside a gigantic freezer with ice-covered walls. 
> | You can see an ice cream cone here.
> |
> | > Eat cone
> | (First taking the ice cream cone)
> | Yum!
> |
> | > Eat ice
> | You lick at the ice-covered wall. Your tongue immediately sticks to it.

> which IMHO is much preferable to being told that I can't take the wall.

I would then handle this with
Object icewall
with autotake [;
  Eat: return 2; ! value for "no, don't auto-take"
],
before [;
  Eat: "You lick at the ice-covered wall.";
];

Of course in this case you could put the "You lick..." message directly 
in autotake, but extra flexibility never hurt anyone.

There. A complete proposal. Backwards-compatible, even. Graham?

> Personally, I can live without auto-take. I know there are people who
> regard it as an essential convenience, though.

At least as essential as a "sack" object, which is pretty important in 
games with many objects.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mol@bartlet.df.lth.se Thu Feb  6 15:42:02 MET 1997
Article: 22020 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] using `location' and `real_location' [was Re: simple question on pronouns in TADS]
Date: 6 Feb 1997 15:36:36 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 69
Message-ID: <5dcq9k$af0@bartlet.df.lth.se>
References: <Pine.SGI.3.95L.970107093713.14934A-100000@tower.york.ac.uk> <5d07dv$qne@prometheus.acsu.buffalo.edu> <5d47sc$h6h@bartlet.df.lth.se> <yxs3evahvsy.fsf_-_@stint.cl.cam.ac.uk>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <yxs3evahvsy.fsf_-_@stint.cl.cam.ac.uk>,
Gareth Rees  <gdr11@cl.cam.ac.uk> wrote:
>Magnus Olsson <mol@bartlet.df.lth.se> wrote:
>> I find that my code is full of things like
>> 
>> if (location == thedark)
>>    move foo to real_location;
>> else
>>    move foo to location;
>
>For exactly this reason you should try to avoid using `location' or
>`real_location' in your code.  It is almost always better to write
>
>     move foo to parent(player);
>
>in these circumstances.

Of course, this depends on what I'm trying to do. Should a thing I drop,
for example, end up on the floor or on the chair I'm sitting on? 

Using location/real_location is IMHO the best way of actually getting
at the room teh player is in, and not some intervening container.

But, of course, I don't perform the test above all the time; instead
I've given the player a method that returns location or real_location
depending on the lighting:

   move foo to player.real_loc();

>In some cases, one might want to write
>
>     move foo to container(player);
>
>where the `container' function is given by something like
>
>     [ container o;
>         do {
>             o = parent(o);
>         } until (o == NULL || parent(o) == NULL || 
>                  (o hasnt supporter && o hasnt open));
>         return o;
>     ];

Isn't NULL = 0xffff (I suppose you mean "nothing")?

This function, along with

[ contains outer inner;

    o = inner;
    do {
	if (o in outer)
	    rtrue;
        o = parent(o);
    } until (o == 0);
    rfalse;
];

should IMHO be a part of the standard Library; they're simply so useful.
(contains(box, gnat) is true if and only if there is a chain of containers-
within-containers where the outermost is the box and the gnat is inside the
innermost one; contains(player, penny) is true if and only if the player
is carrying the penny or something that contains the penny, and so on).




-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From graham@gnelson.demon.co.uk Thu Feb  6 21:51:30 MET 1997
Article: 22027 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!newsxfer3.itd.umich.edu!su-news-hub1.bbnplanet.com!cpk-news-feed2.bbnplanet.com!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!howland.erols.net!rill.news.pipex.net!pipex!netcom.net.uk!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: a french novel with no letter e?
Date: Thu, 06 Feb 1997 13:01:13 +0000 (GMT)
Organization: none
Message-ID: <ant0613131cbM+4%@gnelson.demon.co.uk>
References: <Pine.WNT.3.95.970205151341.-181677D-100000@scimitar.netdoor.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 30

In article <Pine.WNT.3.95.970205151341.-181677D-100000@scimitar.netdoor.com>,
TK Harris <URL:mailto:thomas@netdoor.com> wrote:
> 
> I heard about a French novel written entirely devoid of the letter e, and
> then there was an English translation of the novel, also entirely deviod
> of the letter e.  Does anyone know the author or title of the original or
> the translation?

La Disparition, by Georges Perec, as translated by Gilbert Adair
(I think the translation's called "A Void").

It's a detective yarn about the disappearance of the 5th item
in a series of items... one of the amusing points is that the
original features six classic French poems rewritten so as to leave
out the letter E (Rimbaud's sonnet about the vowels being one
of these!).  Adair's translation features six classic English
ones (e.g. Milton's "On His Glaucoma" rather than "On His Blindess"),
but there's a nice article in the recent French issue of
Modern Poetry in Translation, by Timothy Ades, translating the six
French poems into English and still without the letter E.

You should try Roubaud's poem "31 Cubed" if you like this kind of
thing -- 31 poems, each consisting of 31 little squares of text,
each with 31 words in.  There are allegedly amazing plots to be
read if you follow paths through the structure when regarded as
three-dimensional.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From graham@gnelson.demon.co.uk Thu Feb  6 21:51:55 MET 1997
Article: 22028 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!cs.utexas.edu!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-dc-9.sprintlink.net!rill.news.pipex.net!pipex!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: What did ZIL look like?
Date: Thu, 06 Feb 1997 18:43:06 +0000 (GMT)
Organization: none
Message-ID: <ant061806b49M+4%@gnelson.demon.co.uk>
References: <5dcbd0$95q@bertrand.ccs.carleton.ca> <yxsiv4653qd.fsf@stint.cl.cam.ac.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 36

In article <yxsiv4653qd.fsf@stint.cl.cam.ac.uk>, Gareth Rees
<URL:mailto:gdr11@cl.cam.ac.uk> wrote:
> Here's an object definition.  There are some obvious similarities with
> Inform.
> 
> <OBJECT ["BILLS" "STACK" "PILE"]
>         ["NEAT" "200" "ZORKM"]
>         "stack of zorkmid bills"
>         < + ,OVISON, READBIT, TAKEBIT, BURNBIT>
>         BILLS-OBJECT
>         (  )
>         [ODESC1 "200 neatly stacked zorkmid bills are here."
>         ODESCO "On the floor sit 200 neatly stacked zorkmid bills."
>         OSIZE 10
>         OTVAL 15
>         OFVAL 10
>         OREAD ,ZORKMID-FACE]>
...
> I don't know if Infocom went on to use MDL for their commercial games.

Essentially yes.  ZIL ("Zork Implementation Language") is close
to MDL -- my spies think that they didn't write a manual specifically
for ZIL, because books on MDL would do, for instance.

The above example object is atypically like Inform -- it contains
little serious code.  But the structure of having properties listed
inside objects is the same, and that's where the joint Z-machine
inheritance shows.

ZIL can be quite elegant, if you like LISP-like languages in the
first place.  But a really hacky bit of ZIL looks hideous.  (Then
again, so does a really hacky bit of Inform, of course.)

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From gdr11@cl.cam.ac.uk Fri Feb  7 09:15:33 MET 1997
Article: 22038 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!rill.news.pipex.net!pipex!netcom.net.uk!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!warwick!lyra.csx.cam.ac.uk!news
From: Gareth Rees <gdr11@cl.cam.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Is file editing by an Inform program possible?
Date: 06 Feb 1997 14:19:47 +0000
Organization: Cambridge University Computer Lab
Lines: 35
Sender: gdr11@stint.cl.cam.ac.uk
Message-ID: <yxszpxiggos.fsf@stint.cl.cam.ac.uk>
References: <robbj95.854855844@octarine>
NNTP-Posting-Host: stint.cl.cam.ac.uk
X-Newsreader: Gnus v5.3/Emacs 19.34

Barbara Robson <robbj95@octarine.cc.adfa.oz.au> wrote:
> I realise that this isn't the kind of thing the language is designed
> for, but is it possible to edit an ascii file from within an Inform
> game without a major hacking effort?

You'll need to learn a bit of Z-code assembler to do this in Inform. The
`save' opcode (in version 5) can be called with a pointer to an area of
memory, a number of bytes to be saved, and a filename to save them
to. For example:

    ! Create an array of bytes to hold the filename, with the number of
    ! characters in the string in the first byte.
    Array filename string "filename.xyz";
  
    ! Create an array in which to encode the necessary data to write to
    ! the file (let's suppose 100 bytes of data may be needed).
    Constant data_size 100;
    Array save_data -> data_size;
  
    ! Save the data to a file
    [ SaveData result;
        ! Encode the data into the `save_data' array somehow.
        ...
  
        ! Save the data.
        @save save_data data_size filename result;
        if (result) "Save succeeded.";
        "Save failed.";
    ];

The `restore' opcode reads data from a file in a similar way.  I don't
know whether this will be enough to do what you want.

-- 
Gareth Rees


From straight@email.unc.edu Fri Feb  7 09:17:03 MET 1997
Article: 22042 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.ececs.uc.edu!news.kei.com!news.texas.net!uunet!in1.uu.net!198.82.160.249!solaris.cc.vt.edu!newsgate.duke.edu!news-relay.ncren.net!newz.oit.unc.edu!login0.isis.unc.edu!straight
From: Michael Straight <straight@email.unc.edu>
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: a french novel with no letter e?
Date: Thu, 6 Feb 1997 19:02:37 -0500
Organization: The University of North Carolina at Chapel Hill
Lines: 75
Message-ID: <Pine.A41.3.95.970206190019.121976B-100000@login0.isis.unc.edu>
References: <Pine.WNT.3.95.970205151341.-181677D-100000@scimitar.netdoor.com> <baf.855262007@max.tiac.net> <erkyrathE5793F.G8A@netcom.com>
NNTP-Posting-Host: login0.isis.unc.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Sender: straight@login0.isis.unc.edu
In-Reply-To: <erkyrathE5793F.G8A@netcom.com>
Xref: news.lth.se rec.arts.int-fiction:22042 rec.games.int-fiction:20817


On Thu, 6 Feb 1997, Adam Cadre wrote:

/ TK Harris wrote:
/ > 
/ > I heard about a French novel written entirely devoid of the letter e,
/ > and then there was an English translation of the novel, also entirely
/ > devoid of the letter e.  Does anyone know the author or title of the
/ > original or the translation?
/ 
/ Original: LA DISPARITION by Georges Perec
/ Translation: A VOID, translated by Gilbert Adair

/ Not that this has anything to do with IF, but oh well...

ATTIC

>look

A solitary hanging bulb dimly lights this drab gray room.  Your boots
crunch old paint chips to dust.  Chill drafts blow through a door ajar
just right of a hallway going south.

Your dad's dusty monitor sits on a short black cart. 

>examine monitor

I don't know any such symbol 'e'.

>x monitor

This dusty old thing has sat upstairs for months.  Two knobs and a switch
stick out from your dad's monitor in front and a cord hangs out in back.
It is off. 

>throw switch

SNAP!

>turn knob

Which knob, top or bottom?

>turn bottom knob

It turns with a click.

>move cart

I told you, I don't know this 'e' thing you talk about.

>push cart

Which way?

>push cart e

I don't know any such symbol 'e'.

>push cart s

It rolls smoothly north.

HALLWAY

This floor is too old to support you, a monitor, and a cart.  With a
crash, you fall two floors, smashing your dad's monitor and your skull. 

  **** YOU JUST BOUGHT IT ***

Michael Straight couldn't put his name on such a game.
FLEOEVDETYHOEUPROEONREWMEILECSOFMOERSGTIRVAENRGEEARDSTVHIESBIITBTLHEEPSRIACYK
Ethical	Mirth Gas/"I'm chaste alright."/Magic Hitler Hats/"Hath	grace limits?"
"Irate Clam Thighs!"/Chili Hamster Tag/The Gilt	Charisma/"I gather this calm."



From whizzard@uclink.berkeley.edu Fri Feb  7 09:17:21 MET 1997
Article: 22033 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!cnn.exu.ericsson.se!uunet!in2.uu.net!199.94.215.18!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 6 Feb 1997 21:18:21 GMT
Organization: University of California at Berkeley
Lines: 14
Message-ID: <5ddhqt$3su@agate.berkeley.edu>
References: <5d3q6c$k6u@news.ccit.arizona.edu> <m3ybd5a9s8.fsf@ue801di.lrz-muenchen.de> <5d8sfp$pla@news.ccit.arizona.edu>
NNTP-Posting-Host: uclink.berkeley.edu

I can't remember if I've shot off my mouth about this or not, but I am a
firm advocate of details.  In fact, when I sent off a Top 10 Items of
Importance in Games list to Interplay as part of my resume, I included
Details as my #1 item of importance.

Details are interesting to me, and they add play time and replayability to
your game.  The problem of overwhelming a player with too much to explore
and look at is more one of structure than excessive detail.  Properly
presented, details and useless rooms are bonuses for players instead of
something to wade through.

Mind you, they are terribly time consuming to add. ;)
-- 
	"Stress?  WHO ME???!!!  Never."


From mol@bartlet.df.lth.se Fri Feb  7 16:24:37 MET 1997
Article: 22066 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 7 Feb 1997 16:23:57 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 30
Message-ID: <5dfhed$8b7@bartlet.df.lth.se>
References: <5d3q6c$k6u@news.ccit.arizona.edu> <5ddhqt$3su@agate.berkeley.edu> <5deot1$75m@bartlet.df.lth.se> <5dfe85$sob@flood.xnet.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol


In article <5dfe85$sob@flood.xnet.com>,
Jason Compton <jcompton@typhoon.xnet.com> wrote:
>Magnus Olsson (mol@bartlet.df.lth.se) wrote:
>: I'm a minimalist in the sense that I don't think IF should contain
>: rooms and objects just "because they would be there in real life". A
>: 500-room hotel doesn't have to implement the 499 rooms where no action
>: takes place.
>
>On the other hand, as a player I often hate hotel-type scenes because my
>hand is constantly being forced.  I step into the elevator from the lobby
>and am immediately deposited at Room 1214 because that's the only place in
>the world I might possibly want to be.  Too much of that, done carelessly,
>and the game loses its charm.

Indeed. And this is exactly the kind of "bad minimalism" that I don't
like.  The hotel has to implement as much rooms, objects, and so on to
make it feel real. Not realistic, perhaps, since that would require a
complete simulation of reality, but sufficiently detailed that it
feels like a hotel and not a prop. On the other hand, the author
should not feel compelled to put in too much detail "Just to make it
realistic". It's a balance between only putting in what is "really"
needed (making for a dry, abstract, and probably dull game) and
putting in *everything* (which is impossible).




-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From whizzard@uclink.berkeley.edu Sat Feb  8 09:20:25 MET 1997
Article: 22082 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 7 Feb 1997 23:26:42 GMT
Organization: University of California at Berkeley
Lines: 57
Message-ID: <5dgdni$fjp@agate.berkeley.edu>
References: <5d3q6c$k6u@news.ccit.arizona.edu> <5dfe85$sob@flood.xnet.com> <5dfhed$8b7@bartlet.df.lth.se> <32fb5f10.1704361@news.u.washington.edu>
NNTP-Posting-Host: uclink.berkeley.edu

In article <32fb5f10.1704361@news.u.washington.edu>,
Matthew Amster-Burton <mamster@u.washington.edu> wrote:
>
>One possible solution is a hotel with plenty of extra *doors*, but the
>player has a key that will only open the proper one.  This is plenty
>realistic and fair, IMHO.  Of course, then some players will try their
>key (or their hammer) on every other door, but I don't think you can
>blame the author for this.

Here's what a multi-level hotel needs to be fully realized in an I-F game,
imho.  This is if I were using it as a central location for the game, and 
the player had to return there several times to sleep and so forth:

Lobby.  Fully furnished.  Preferably with some interesting touches to make
it worthwhile, like pictures of famous people who've stayed there,
brochures of local areas of interest, etc.  I feel that if you aren't
willing to put in at least enough detail to make a room interesting, a)
You should be ashamed of yourself.  and b) Hustle the player through it as
fast as possible, then close it off in the forseeable future.

Elevator or stairs.  I recommend both.  Stairs are an easy addition after
coding up an elevator, and all hotels have them.

A dummy non-interesting floor.  This floor serves as all the floors except
the important one.  It is really easy to use global variables and a little
fancy coding to add differences depending on what floor the player is on.
Trust me.  All rooms should be locked, or occupied.  Knocking on occupied
rooms should get some sort of Go away message, and can get as complicated
as you want.  A foreign maid can be a nice touch here, if rather
stereotypical.  A more interesting maid could snap pictures f you and talk
into a wrist mike when she thought you weren't looking.

The interesting floor.  This should have the player's room on it, with TV,
telephone, bathroom (possibly make it a communal bathroom, one per
floor.), bible in the dresser drawer, and probably some coupons good at
local attractions.

Then, if you were doing a conspiracy game, throw in a missing 13th floor,
some spies, a few mysterious events that the player is guaranteed to see
at some point, and you have a really neat setup.

On the other extreme, you can do a perfectly serviceable Florida motel
with two or three rooms.  Lobby, door facade, and room.


As others have said, and this post attempts to illustrate, there are no
hard and fast rules on how much detail to add.  No matter what your level
of detail, you will probably find people who love it, and people who hate
it.  Write the way you like to write, and let's not worry about what
current market trends show players enjoying the most (Probably Command and
Conquer, which would be less than amusing to write or play as a text
game.)  Write a fun game and let people know about it, and everything will
sort itself out.

-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From svanegmo@undergrad.math.uwaterloo.ca Sat Feb  8 09:22:20 MET 1997
Article: 22085 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!torn!kwon!watserv3.uwaterloo.ca!undergrad.math.uwaterloo.ca!svanegmo
From: svanegmo@undergrad.math.uwaterloo.ca (Stephen van Egmond)
Subject: Re: Another Bug in Inform?
Sender: news@undergrad.math.uwaterloo.ca (news spool owner)
Message-ID: <E599yz.Gw7@undergrad.math.uwaterloo.ca>
Date: Fri, 7 Feb 1997 23:16:11 GMT
References: <32FB384B.6F60@cogentex.com>
Nntp-Posting-Host: cantor.math.uwaterloo.ca
Organization: University of Waterloo
Lines: 19


>Is there some email address for sending bug reports on Inform? 
>Are              
>people encouraged to send mail directly to G. 
>Nelson?                           
 
Absolutely.  Many people post bug reports to raif; back in the days when
Graham maintained his "olympian detachment", he might not even seen them. 

In general, with any piece of software where the author is accessible,
it's nice to send reports directly to them if you -know- it's a bug.  If 
you -suspect- it's a bug but aren't sure, it's probably best to discuss 
it with fellow users first, since many bugs are actually 
misunderstandings of prescribed or documented behaviour.  What you've got 
there is obviously a bug, though.

Graham's address is
	graham@gnelson.demon.co.uk



From kfischer@greenhouse.llnl.gov Sat Feb  8 14:37:53 MET 1997
Article: 22090 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!news.radio.cz!voskovec.radio.cz!news-feed.inet.tele.dk!mr.net!news.maxwell.syr.edu!news.bbnplanet.com!cam-news-hub1.bbnplanet.com!uunet!in1.uu.net!199.170.183.55!brighton.openmarket.com!decwrl!lll-winken.llnl.gov!usenet
From: Kathleen Fischer <kfischer@greenhouse.llnl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: Fri, 07 Feb 1997 09:18:23 -0800
Organization: Lawrence Livermore National Laboratory
Lines: 60
Message-ID: <32FB63DF.2781@greenhouse.llnl.gov>
References: <5d3q6c$k6u@news.ccit.arizona.edu> <m3ybd5a9s8.fsf@ue801di.lrz-muenchen.de> <5d8sfp$pla@news.ccit.arizona.edu> <5ddhqt$3su@agate.berkeley.edu> <5deot1$75m@bartlet.df.lth.se> <5dfe85$sob@flood.xnet.com>
NNTP-Posting-Host: greenhouse.llnl.gov
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (X11; I; IRIX 5.3 IP22)

Jason Compton wrote:
> 
> Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> : I'm a minimalist in the sense that I don't think IF should contain
> : rooms and objects just "because they would be there in real life". A
> : 500-room hotel doesn't have to implement the 499 rooms where no action
> : takes place.
> 
> On the other hand, as a player I often hate hotel-type scenes
> because my hand is constantly being forced.  I step into the 
> elevator from the lobby and am immediately deposited at Room 1214
> because that's the only place in the world I might possibly want
> to be.  Too much of that, done carelessly, and the game loses its 
> charm.

The Grand Hotel Lobby
The sign outside boasts 500 rooms and from the size of the place you
believe it. At the north end of the lobby is a massive mahogany
information desk. There is an elevator here manned by a bell boy and a
side door leading to a staircase.

> enter elevator
"Floor please?" asks the bell boy as you step into the elevator.

> tell bell boy 3
"I'm sorry, that floor is being renovated at this time.  Perhaps you
should recheck your room reservation at the information desk."

> tell bell boy 2
"I believe they are testing for asbestos there today... I'm sure they
could help you at the information desk."

> exit
You step out of the elevetor.

> u
Opening the door you discover the janitor busily mopping the floor.
"Sorry ma'am..." says the old man as he stops for a moment to rest
against his mop and wipe his brow. "Should be done is just a few
minutes, though." He sighs heavily then turns back to his mopping. At
the rate he's going it could easily take him all day.

> enter elevator
"Floor please? Oh, hello again." says the bell boy.

> tell bell boy 4
The bell boy shakes his head.  "There was a fire there last week." He
bends a little closer and whispers "They say it was an accident, but I
don't believe them. Just last week I heard a guy on that floor say he
was going to burn the place to the ground if they didn't give him better
room service in the morning.  He's in room 1214 now, I belive."

> tell bell boy 1
The bell boy nods and push the button for the first floor...

-- 
*******************************************************************
*  Kathleen M. Fischer
*  kfischer@greenhouse.llnl.gov
** "Don't stop to stomp ants while the elephants are stampeding" **


From mol@bartlet.df.lth.se Sat Feb  8 14:38:02 MET 1997
Article: 22097 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 8 Feb 1997 14:34:40 +0100
Organization: The Computer Society at Lund University and Lund Institute of Technology
Lines: 83
Message-ID: <5dhvdg$vtn@bartlet.df.lth.se>
References: <5d3q6c$k6u@news.ccit.arizona.edu> <5deot1$75m@bartlet.df.lth.se> <5dfe85$sob@flood.xnet.com> <32FB63DF.2781@greenhouse.llnl.gov>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol

In article <32FB63DF.2781@greenhouse.llnl.gov>,
Kathleen Fischer  <kfischer@greenhouse.llnl.gov> wrote:
>Jason Compton wrote:
>> On the other hand, as a player I often hate hotel-type scenes
>> because my hand is constantly being forced.  I step into the 
>> elevator from the lobby and am immediately deposited at Room 1214
>> because that's the only place in the world I might possibly want
>> to be.  Too much of that, done carelessly, and the game loses its 
>> charm.

(...)

>> enter elevator
>"Floor please?" asks the bell boy as you step into the elevator.
>
>> tell bell boy 3
>"I'm sorry, that floor is being renovated at this time.  Perhaps you
>should recheck your room reservation at the information desk."
>
>> tell bell boy 2
>"I believe they are testing for asbestos there today... I'm sure they
>could help you at the information desk."
>
>> exit
>You step out of the elevetor.
>
>> u
>Opening the door you discover the janitor busily mopping the floor.
>"Sorry ma'am..." says the old man as he stops for a moment to rest
>against his mop and wipe his brow. "Should be done is just a few
>minutes, though." He sighs heavily then turns back to his mopping. At
>the rate he's going it could easily take him all day.
>
>> enter elevator
>"Floor please? Oh, hello again." says the bell boy.
>
>> tell bell boy 4
>The bell boy shakes his head.  "There was a fire there last week." He
>bends a little closer and whispers "They say it was an accident, but I
>don't believe them. Just last week I heard a guy on that floor say he
>was going to burn the place to the ground if they didn't give him better
>room service in the morning.  He's in room 1214 now, I belive."
>
>> tell bell boy 1
>The bell boy nods and push the button for the first floor...

(Sorry for quotin so much, but I think all of the above transcript is
relevant).

Actually, this is a solution that I don't like very much. It feels
like I'm being led by the hand through the plot. Of course, the effect
can be consciously used (for example, to create a Kafkaesque
nightmare, or in a comedy), but it tends to get on ones nerves if used
only to restrict the complexity of the game. In the words of Espen
Aarseth (I hope, I'm quoting from memory) it gives you the feeling of
being trapped inside somebody else's story.

Actually, if you don't want to give the player the illusion of freedom
to explore the hotel at will, I think it's better just to tell the
player explicitly that he's not supposed to, rather than inventing a lot
of contrived excuses:

"As you enter the hotel lobby, you realize the difficulty of your task.
There must be hundreds of rooms here, and you have no idea in which of them
Mr. Johnson is staying."

Trying to take the elevator or the stairs gives you a message that
it's no use; you have no idea of where to go and it would take far too
long to search the entire hotel. Once you've figured out where Mr. Johnson is
staying, you can go directly to his room. Trying to go to any other room
gives you the message "Your mission was to contact Mr. Johnson, and he's
in room 1234, so what would you want in room 4321?". Until you discover,
of course, that your kidnapped girlfriend is in room 2341, in which case
you have a reason to go there as well.

Of course, many people will actually prefer to have an implementation of
all 500 rooms, so they can bore themselves stiff knocking on all the locked
doors. And other people will prefer being able to barge into room 2233,
disturbing the people in there, and starting an entirely new plot...


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From nkg@vcn.bc.ca Sun Feb  9 09:24:46 MET 1997
Article: 22123 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!worldnet.att.net!arclight.uoregon.edu!news.bc.net!unixg.ubc.ca!freenet.vancouver.bc.ca!not-for-mail
From: nkg@vcn.bc.ca (Neil K. Guy)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 9 Feb 1997 06:43:30 GMT
Organization: Vancouver CommunityNet
Lines: 25
Message-ID: <5djrmi$mc9@milo.vcn.bc.ca>
References: <5dfhed$8b7@bartlet.df.lth.se> <32fb5f10.1704361@news.u.washington.edu> <5dg7cd$e6g@milo.vcn.bc.ca> <5dj0eo$dnk@kodak.rdcs.Kodak.COM>
NNTP-Posting-Host: opus.vcn.bc.ca
X-Newsreader: TIN [UNIX 1.3 BETA-950824-16colors PL0]

Matthew Daly (daly@PPD.Kodak.COM) wrote:

: > Well, this is the tack I've taken with my game in progress. The problem
: >is that I find some players get really annoyed at having a lot of doors
: >they can never open, and consider it unfair.
: 
: Makes you wonder how these people can stand to walk down a city
: street in real life, eh? :-)

 Heh. Well, of course you're right. In real life most doors with locks on
them *are* locked in a modern city. But, whether it's because in adventure
games people want to be omnipotent (perhaps related to the mindset that
says any object not directly used for solving a puzzle is a red herring
and therefore annoying) or because trying doors is boring, reactions to
games seem to be different. I've put in a few labour-saving devices to try
to avoid the latter, but not much one can do about the former. 

 Though to be fair in real life you generally don't need to go around
trying every door you see to check whether or not it's locked unless
you're a professional burglar. In games, however, you do.

 - Neil K. Guy

        the Vancouver CommunityNet   *   http://www.vcn.bc.ca/
              (formerly the Vancouver Regional FreeNet)


From mkkuhner@phylo.genetics.washington.edu Sun Feb  9 09:25:27 MET 1997
Article: 22110 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!eua.ericsson.se!cnn.exu.ericsson.se!uunet!in1.uu.net!140.142.64.3!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 8 Feb 1997 02:36:33 GMT
Organization: University of Washington, Seattle
Lines: 25
Message-ID: <5dgorh$k9p@nntp5.u.washington.edu>
References: <5dfe85$sob@flood.xnet.com> <5dfhed$8b7@bartlet.df.lth.se> <egh-0702971555080001@news.berkeley.edu>
NNTP-Posting-Host: phylo.genetics.washington.edu

egh@uclink4.berkeley.edu (Erik Hetzner) writes:

>Problems might be caused if you were breaking into rooms, instead of
>having the key (ie you could break into any room). Perhaps one could
>create a sort of randomness to the rooms -- ie you could break into them,
>and there would be random scattered objects of no importance? And have
>random characters walk about. All of this just to add realism, not
>interest.

Problem is that the player, noting that she can break into rooms, and
that there are objects in them, may very well worry that there exists
some room and object which she *needs*.  Generally speaking, when I'm
not stuck I'll waltz by boring stuff, but when I'm stuck I'll feel
obliged to go back and carefully look at it *all*.  I am not going to
appreciate having to go through 500 hotel rooms.  And the kinds of
warn-offs you might use to keep me from doing so may hurt verisimilitude
as much or more as omitting the rooms in the first place.

In general, I'm opposed to coding up random locations.  Non-useful
locations, sure, but if you are not interested enough as a designer to
actually design the individual location, I am not interested enough as
a player to explore it.  And if it's there, and I'm stuck, sooner or
later I will have to explore it.

Mary Kuhner mkkuhner@genetics.washington.edu


From mythago@agora.rdrop.com Sun Feb  9 09:28:35 MET 1997
Article: 22118 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!math.ohio-state.edu!uwm.edu!fnnews.fnal.gov!nntp-server.caltech.edu!news.claremont.edu!jolt.pagesat.net!pagesat.net!hermes.rdrop.com!usenet
From: mythago@agora.rdrop.com (Laurel Halbany)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: Fri, 07 Feb 1997 16:35:36 GMT
Organization: RainDrop Laboratories/Agora(sm)
Lines: 20
Message-ID: <32f96a33.28849630@hermes.rdrop.com>
References: <5cqgvp$l7@kjahds.com> <5cqp51$bih@kodak.rdcs.Kodak.COM> <32f2e4bd.897419@hermes.rdrop.com> <5d55in$a80@kodak.rdcs.Kodak.COM>
NNTP-Posting-Host: slip-d2.rdrop.com
X-Newsreader: Forte Free Agent 1.1/16.230

daly@PPD.Kodak.COM (Matthew Daly) wrote:

>So, if the main character were female instead of neuter, how would
>a well-written game look different?

It depends. (You knew I was going to say that.)

For example, "Christminster" would look much different if Malcolm was
rescuing his sister, rather than the other way around. But Christabel
was not a fainting, helpless girl; she was a Determined Young Lady
with a good deal of complexity and resourcefulness (well, for an IF
character, anyway). 

Also, it seems as though an awful lot of games really mean "assumed
male" instead of "neuter."

----------------------------------------------------------
Laurel Halbany
mythago@agora.rdrop.com
http://www.rdrop.com/users/mythago/


From rendell@fangorn.cs.monash.edu.au Sun Feb  9 09:35:32 MET 1997
Article: 22117 of rec.arts.int-fiction
From: rendell@fangorn.cs.monash.edu.au (Robert Paige Rendell)
Newsgroups: rec.arts.int-fiction
Subject: Re: What did ZIL look like?
Date: 9 Feb 1997 03:22:03 GMT
Organization: Monash University
Lines: 129
Message-ID: <5djfsr$v2t$1@harbinger.cc.monash.edu.au>
References: <5dcbd0$95q@bertrand.ccs.carleton.ca>
NNTP-Posting-Host: fangorn.cs.monash.edu.au
X-NNTP-Posting-User: rendell
X-Newsreader: knews 0.9.3
Path: news.lth.se!solace!nntp.uio.no!Norway.EU.net!sn.no!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!spool.mu.edu!munnari.OZ.AU!news.mel.connect.com.au!news.ade.connect.com.au!duster.adelaide.on.net!spasun.tpa.com.au!ns.saard.net!harbinger.cc.monash.edu.au!not-for-mail

In article <5dcbd0$95q@bertrand.ccs.carleton.ca>,
	sfergus2@chat.carleton.ca (S Ferguson) writes:

} ... I've come to
} wonder what exactly ZIL code looked like -- it seems to (unlike Inform
} some of the time :) ) have had a high learning curve, a platform of tools
} to aid construction of games, and have possibly been LISP-like
<snip>
} 	So I wonder if there are any code examples out there, or perhaps
} if someone has any information on what it's original form was.

Here's a post from 1992 that I kept, of which the last part is relevant
(but I'll leave in the whole thing, anyway, out of interest):

Path: bruce.cs.monash.edu.au!munnari.oz.au!uunet!think.com!galley
From: galley@think.com (Stu Galley)
Newsgroups: rec.games.int-fiction
Subject: Re: Odd questions about Infocom (that Stu can hopefully answer)
Date: 27 Oct 1992 00:00:11 GMT
Organization: Thinking Machines Corporation, Cambridge, Mass., USA
Lines: 97
Message-ID: <1ci0qbINNg74@early-bird.think.com>
References: <caw.0q1f@miroc.Chi.IL.US>
NNTP-Posting-Host: django.think.com

In article <caw.0q1f@miroc.Chi.IL.US> caw@miroc.Chi.IL.US (Christopher A. Wichura) writes:
>I'm posting this as a public message as I figured that other people would be
>interested.  I've a couple of questions that only an Implementor might be
>able to answer... :-)
>
>1)  Infidel (and I couple others, as I recall) came with an envelope that
>your letter to home was going to be mailed in.  The actual address on the
>envelope was that of Infocom.  I'm curious to know just how many people
>actually did mail the thing in.  :-)  Other odd trivia tidbits along this
>line would be most welcome, as well.

I don't remember how many Infidel envelopes were mailed back to
Infocom, but I think there were some.  I do remember that Steve
Meretzky and Marc Blank had a bet concerning how many Planetfall post
cards would be mailed to Infocom within a year, and the actual number
was fewer than the optimist (whichever one it was) had hoped for.

The Infidel envelope was addressed to Rose Ellingsworth, and for a
while she appeared on our employee list, with a home address the same
as mine.  The idea was to trap anyone that ever leaked our employee
list to the outside world.  But no mail ever came to my home for her.

>2)  I've always wondered about the programming environment you folks used.
>What machines did you use to write a game on?  Something like a PDP or one of
>the other "big" computers of the day, or did you actually do development on
>machines like the Apple ][ or TRS-80? 

The game diskette that you bought had two parts: the "game file" and
the "interpreter file".  The "game file" was developed on a "big"
computer, at first a DECsystem-20 and later a Sun 3/330.  The
"interpreter file" was developed on the same kind of machine that you
would run it on, for example the TRS-80.

>Also, what did ZIL/ZIP (which is
>correct?) code look like:  For example, if you wanted to code a room such
>that:
>
>	1) the room's name was Gruble
>	2) the description was "this is a description"
>	3) north took you to room "Rumble"
>	4) west took you to room "Tumble"
>	5) if the user had foobared the barfoo then
>		5a)  Add to description "hole in south wall"
>		5b)  south leads to room "Arstol"
>	6) item "nabble" is here
>	7) item "krabble" is here, but can only be picked up if
>	   the player wasn't carrying item "frabble"
>
>how would you do it?

Well, my ZIL skills are a little rusty, but your example would look
something like this:

<OBJECT GRUBLE
	(IN ROOMS)
	(DESC "Gruble")
	(NORTH TO RUMBLE)
	(WEST TO TUMBLE)
	(SOUTH TO ARSTOL IF BARFOO-DONE)
	(ACTION GRUBLE-F)>

<ROUTINE GRUBLE-F ("OPT" ARG)
 <COND (<EQUAL? .ARG ,M-LOOK>
	<TELL "this is a description" CR>
	<COND (,BARFOO-DONE
	       <TELL "hole in south wall" CR>)>
	<RTRUE>)>>

<GLOBAL BARFOO-DONE <>>

<OBJECT BARFOO
	(DESC "barfoo")
	(SYNONYM BARFOO)
	(ACTION BARFOO-F)>

<ROUTINE BARFOO-F ()
 <COND (<VERB? FOOBAR>
	<SETG BARFOO-DONE T>
	<TELL "You have foobared the barfoo." CR>)>>

<OBJECT NABBLE
	(IN GRUBLE)
	(DESC "nabble")
	(SYNONYM NABBLE)>

<OBJECT KRABBLE
	(IN GRUBLE)
	(DESC "krabble")
	(SYNONYM KRABBLE)
	(ACTION KRABBLE-F)>

<ROUTINE KRABBLE-F ()
 <COND (<AND <VERB? TAKE> <IN? ,FRABBLE ,PLAYER>>
	<TELL
"You can't pick up the krabble if you are carrying the frabble." CR>)>>

                                       -- Stu Galley  <Galley@Think.com>


-- 
Robert Rendell                                                    \((/
rendell@molly.cs.monash.edu.au                                    ~oo~
        What do you know about Tweetle beetles?  Well...          /))\



From adamc@acpub.duke.edu Sun Feb  9 16:10:55 MET 1997
Article: 22106 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!su-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!rill.news.pipex.net!pipex!uunet!in1.uu.net!136.142.185.26!newsfeed.pitt.edu!news.duq.edu!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: I-0 Release 2, sort of...
Date: Sat, 08 Feb 1997 07:24:59 -0500
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 64
Message-ID: <32FC709B.23F@acpub.duke.edu>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)
Xref: news.lth.se rec.games.int-fiction:20886 rec.arts.int-fiction:22106

Okay, I've completed Release 2 of I-0... I think.  I've smashed all
the reported bugs without introducing any new ones... I think.  But
then, that's what I thought about the first release, and of course,
I was wrong.

So for the time being, I'm only putting Release 2 on my web site,
not on the archive.  I'm hoping that the people who wrote me such
thoughtful and detailed feedback on the first edition will be
motivated to check it out and see whether their favorite bugs were
in fact killed dead before I send it to the archive as a definitive
final draft.  The place to go is http://www.duke.edu/~adamc/games,
and the file is I-0.z5 (there's only one to choose from.)

Here's what's different:

* All reported bugs (I believe) have been smushed.  Most of these
  involved the various pickup trucks, which are now separate entities
  rather than one truck that moves around a lot and doesn't always
  quite make it.

* Primitive multi-turn waiting has been implemented.  Simply type
  "wait" or "z" followed by a number, and it'll wait that number of
  turns -- letting you know what is happening in the meantime, but
  not interrupting itself to let you do anything about it.  It's
  meant purely as a convenience for people who have played the game,
  know where the waiting spells are, and don't want to have to press
  "z" 30 times.  (New players are encouraged to spend the time
  looking at objects and fishing for fun responses.)

* Scope has been altered so that you can look at objects in your
  line of sight, even if they're far away.  This comes into play
  chiefly in the opening scene and in the drive-thru lane.

* Certain characters are less lackadaisical about what you're wearing
  or not wearing.

* A sardonic warning message has been added to let people know the
  game's got adult content.

* There's more traffic on I-0 itself.

* Wording has been changed here and there.

* Those who play it for the euphemisms will be glad to know that
  there are now thirteen of them, compared to three in Release 1.
  There is also now a place in the game where the euphemisms are
  unnecessary.

* It is by now a well-known fact that if you're more intent on
  winning than exploring, you can solve I-0 in a couple of minutes.
  Release 2 is even easier: simply type "win", and you do.

This is, at heart, a bug-fix release -- there are no new locations
or characters or anything.  I may beef up the game someday, but I'd
prefer to get another game or two finished before I return to this
one; this is why I'm sort of gun-shy about going all the way with
this release, since the version I do finally upload to the archive
is going to be THE version for quite some time.

And thanks to everyone who said such kind things about Release 1.

  -----
 Adam Cadre, Durham, NC
 http://www.duke.edu/~adamc


From ceforman@postoffice.worldnet.att.net Sun Feb  9 20:20:07 MET 1997
Article: 22131 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!news.idt.net!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!newsadm
From: "C.E. Forman" <ceforman@postoffice.worldnet.att.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: "That's not something you need to refer to in the course of this game."
Date: 9 Feb 1997 15:12:29 GMT
Organization: BranMuffin World Conglomerate
Lines: 24
Message-ID: <5dkpgt$5oa@mtinsc02.worldnet.att.net>
References: <32fdd7ad.21728164@news.csc.fi>
NNTP-Posting-Host: 207.146.165.79
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 1.22ATT (Windows; U; 16bit)

er4055@bessel.tutech.fi (Ella Lynoure Rajamaki) wrote:
>Am I the only players annoyed by games telling me "That's not
>something you need to refer to in the course of this game" ?
>I think a good game has a good atmosphere and IMO, that means I must
>be able to forget it's a game (and not dream). That answer tends to
>always break the illusion for me... :I

This is a necessary evil, I'm afraid, because most authors don't want
to go to the trouble of coding objects for each bit of scenery mentioned
in every room, nor should they have to if they don't want to.

I prefer a slightly different response, such as "There's no need to refer
to that."  This avoids pounding the player over the head with the fact
that this is a "game".  "Christminster", "So Far", and my own "Delusions"
make use of this.

--
C.E. Forman                                     ceforman@worldnet.att.net
Author of "Delusions", the 3rd place winner in the 1996 I-F Competition!!
Release 3 is now at: ftp://ftp.gmd.de/if-archive/games/infocom/delusns.z5
Read "XYZZYnews" @ http://www.interport.net/~eileen/design/xyzzynews.html
Ye Olde Infocomme Shoppe http://netnow.micron.net/~jgoemmer/infoshop.html




From mkkuhner@phylo.genetics.washington.edu Sun Feb  9 23:49:38 MET 1997
Article: 22145 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: 9 Feb 1997 21:29:53 GMT
Organization: University of Washington, Seattle
Lines: 24
Message-ID: <5dlfkh$16m@nntp5.u.washington.edu>
References: <32f96a33.28849630@hermes.rdrop.com> <5dk25d$4a6@bartlet.df.lth.se> <5dktur$hia@echo2.echonyc.com>
NNTP-Posting-Host: phylo.genetics.washington.edu

neild@echonyc.com (Neil deMause) writes:

>We've been over this before, but: There's a difference between a *neuter*
>character and one who's *non-gender-specific*. You simply don't have to
>determine a character's gender in order to give them detail, any more
>than you have to determine their race, ethnic origin, hair color or shoe
>size. They're nice details to have, *if you choose to include them*, but 
>they're not *necessary* to imagining a real person.

>Yeah, it's tricky to write, especially if you want to avoid the "assumed 
>male" thing. But it's not impossible.                        

For a lengthy example in fiction, see Melissa Scott's novel _The Kindly
Ones_ (a science-fiction political intrigue story).  The protagonist is
a reasonably well-drawn character with lots of detail, and his/her
gender is never specificed.  Most readers make one assumption or the
other and stick with it, of course, but both assumptions seem to work.

Your readers/players will almost certainly *give* the character a gender
if you don't, but that's okay.  (The assumption seems to be that they'll
give the character their own gender, but I haven't found that to be the
case personally; neither with _The Kindly Ones_, nor with _Jigsaw_.)

Mary Kuhner mkkuhner@genetics.wshington.edu


From erkyrath@netcom.com Mon Feb 10 22:46:26 MET 1997
Article: 22194 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!erinews.ericsson.se!news.seinf.abb.se!inquo!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [INFORM] Get All scenery fix?
Message-ID: <erkyrathE5En6D.6HI@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5dnq5k$am8$1@neko.syix.com>
Date: Mon, 10 Feb 1997 20:49:24 GMT
Lines: 42
Sender: erkyrath@netcom.netcom.com

Patrick Kellum (patrick@lynx.syix.com) wrote:
> Hi,
>    For anyone wanting to fix GET ALL so that it doesn't keep trying to get
>  static and scenery objects, try following these cryptic instructions. 

>          if(l has scenery || l has static) 
>             jump donttake; 
>          print (name) l, ": "; 
>          if (inp1 == 0) 
>          { inp1 = l; self.begin_action(action, l, second, 0); inp1 = 0; 
>          }
>          else
>          { inp2 = l; self.begin_action(action, noun, l, 0); inp2 = 0; 
>          }
>          temp=0; 
>          .donttake; 
>      }
>  if(temp==1) L__M(##Miscellany, 44); 

>    There you go, it's an extreamly ugly hack but it seems to work.  If
>  anyone finds a prob with this code, please tell me. 

I don't see a specific problem but I recommend against it anyway. What 
you're doing, obviously, is to filter objects out of the list of objects 
*at action time*. If you see what I mean. You're leaving scenery and 
static objects in the list, but making the library silently ignore them. 
Will this cause problems? I don't know. That's because I don't know where 
else that list is used. Since I don't know, I don't trust this hack.

The manual has a sample ChooseObjects() function which prevents scenery 
objects from being in the object list at all. (Easily modifiable to be 
scenery/static objects, or any other set.) 

I hack the libraries all the time, but only when they don't allow me to 
do what I want any other way. :)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From baf@max.tiac.net Tue Feb 11 09:31:32 MET 1997
Article: 22215 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news.idt.net!news.stealth.net!uunet!in3.uu.net!199.0.65.182!news-in.tiac.net!posterchild!max.tiac.net!baf
From: baf@max.tiac.net (Carl Muckenhoupt)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 10 Feb 97 18:35:55 GMT
Organization: The Internet Access Company, Inc.
Lines: 29
Message-ID: <baf.855599755@max.tiac.net>
References: <5dfe85$sob@flood.xnet.com> <5dfhed$8b7@bartlet.df.lth.se> <egh-0702971555080001@news.berkeley.edu> <5dgorh$k9p@nntp5.u.washington.edu>
NNTP-Posting-Host: max.tiac.net

mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) writes:

>Problem is that the player, noting that she can break into rooms, and
>that there are objects in them, may very well worry that there exists
>some room and object which she *needs*.  Generally speaking, when I'm
>not stuck I'll waltz by boring stuff, but when I'm stuck I'll feel
>obliged to go back and carefully look at it *all*.  I am not going to
>appreciate having to go through 500 hotel rooms.  And the kinds of
>warn-offs you might use to keep me from doing so may hurt verisimilitude
>as much or more as omitting the rooms in the first place.

Hmm... This makes me think of computer role-playing games.  The larger
ones (especially the later Ultimas) do exactly this - that is, they
provide lots of area for the sake of realism, perhaps with the
occasional secret reward.  Also, what amounts to the same thing, there
will be NPC's with tons of irrelevant dialogue.  The effect?  It depends.
In the better ones, there's enough guidance and enough redundancy that
the player doesn't need to explore everything and talk to everyone.
In the worse ones, you get exactly the syndrome that Ms. Kuhner
describes.  RPG's can probably get away with big worlds more easily than
adventure games, though, because of differing expectations - no one
expects to kill every last orc, especially if they respawn.  (I wonder
if adventurers tend to be more inclined towards perectionism than
RPGers?)

-- 
Carl Muckenhoupt              | Text Adventures are not dead!
baf@tiac.net                  | Read rec.[arts|games].int-fiction to see
http://www.tiac.net/users/baf | what you're missing!


From trischma@nosc.mil Tue Feb 11 09:34:49 MET 1997
Article: 22203 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!swrinde!ihnp4.ucsd.edu!newshub.nosc.mil!news!news
From: James Trischman <trischma@nosc.mil>
Subject: IF "minimalism" and Hotels
Content-Type: text/plain; charset=us-ascii
Message-ID: <32FFC7C8.1113@nosc.mil>
Sender: news@nosc.mil
Reply-To: trischma@nosc.mil
Content-Transfer-Encoding: 7bit
Organization: NCCOSC 
References: <855552928.65113.4@darkside.demon.co.uk>
Mime-Version: 1.0
Date: Tue, 11 Feb 1997 01:13:44 GMT
X-Mailer: Mozilla 3.01 (Win95; I)
Lines: 28

Whenever you write anything you have to consider your audience.
Most of us are going to write something that we would enjoy if
we were playing. Obviously there are different approaches. Some
like to brute force their way though a fairly complete world while
others want subtle hints to stear them back towards the right track.

Maybe a subtle approach is to make the descriptions get terse and
boring when you get away from the main thread of action.
I've always wondered if it's fair to allow the player to pick up
rocks, leaves, empty cola cans, etc. until he's carrying around
about 100 pounds of trash.  It's sort of the same issue.  In a 
world that allows a realistic degree of freedom, there are going
to be 10-100 boring or useless things to do for every one that
moves the story along.  This is always going to annoy the person
who wants to exercise every path in the program.

By the way:
I've had a wonderful time exploring hotels with out ever going into
a guest room. Any of the big Victorian Hotels like the Hotel del
Coronado in San Diego or the Banff Springs Hotel in Alberta are great
examples to go see.  You need a map to find you way around the shops,
restaurants, bars, dining room, pools, spas, baconies... That's without
even exploring the employee only parts. 
If I had started barging into guest rooms I'm sure a security 
type would have bounced me out pretty soon. Anyway I've found that
hotel rooms are pretty much the most boring part.

Jay


From mamster@u.washington.edu Wed Feb 12 09:23:14 MET 1997
Article: 22254 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!www.nntp.primenet.com!nntp.primenet.com!news.maxwell.syr.edu!worldnet.att.net!news.u.washington.edu!root
From: mamster@u.washington.edu (Matthew Amster-Burton)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Xyzzy Awards (film at 11)
Date: Tue, 11 Feb 1997 21:34:37 GMT
Organization: University of Washington
Lines: 28
Message-ID: <3300e4d4.10038214@news.u.washington.edu>
References: <5dntep$k9g@echo2.echonyc.com> <32ff95e9.20080047@news.u.washington.edu> <fake-mail-1002971504160001@van-as-08a04.direct.ca> <Pine.SUN.3.91.970211084703.28917D-100000@nebula.phy.duke.edu> <5dq3h1$pcs$1@europa.frii.com> <fake-mail-ya02408000R1102971108410001@news.direct.ca>
NNTP-Posting-Host: mamster.cdmrc.washington.edu
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:22254 rec.games.int-fiction:21047

fake-mail@anti-spam.address (Neil K.) wrote:

>> *sigh*  I remembered them - but I was halfway into brewing a batch of
>> beer when I remembered & couldn't abort the process.
>
> Now *that* is the coolest excuse so far! :)

% brew &
brew 2.1 initializing
allocating wort....
preparing hops heap....
Brewing
[1] 38290
% telnet xyzzyawards.com
No CPU avail
% kill %1
brew: cannot abort
% kill -9 %1
brew: you are not listening to me, mortal. cannot abort!
% sigh


Disclaimer:  Okay, I know this is r.a.if and that should have been a
phone IF snippet, but when you're aborting processes, that's Unix to
me.  Also, I know nothing about brewing except that it results in beer
and involves "wort".

Matthew


From olorin@world.std.com Wed Feb 12 09:23:54 MET 1997
Article: 22249 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!www.nntp.primenet.com!nntp.primenet.com!mr.net!arclight.uoregon.edu!hammer.uoregon.edu!zephyr.texoma.net!uunet!in1.uu.net!uucp5.uu.net!world!olorin
From: olorin@world.std.com (Mark J Musante)
Subject: Re: Xyzzy Awards (film at 11)
Message-ID: <E5G4z7.CC2@world.std.com>
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Organization: The World @ Software Tool & Die
X-Newsreader: TIN [version 1.2 PL2]
References: <5dntep$k9g@echo2.echonyc.com> <32FFAC57.59E2@greenhouse.llnl.gov>
Date: Tue, 11 Feb 1997 16:11:30 GMT
Lines: 120
Xref: news.lth.se rec.arts.int-fiction:22249 rec.games.int-fiction:21023

Kathleen Fischer (kfischer@greenhouse.llnl.gov) wrote:
> Neil deMause wrote:
> > Speak of the transcript, here it is -- the whole ceremony from start to
> > finish:
> > http://www.edoc.com/zarf/award-transcript.html
> I don't suppose there is a short form somewhere that lists the 8
> catagories and the winners?  Did I miss that memo?

Well, you really should read the transcript -- there's a lot of
amusing stuff in there.

But anyway...















             <zoom!>




















The short form:
  o Best individual NPC
    Nominated:
       Christopher Robin, from Ralph
       Leo the Lemming, from Phlegm
    Won (3-way tie):
       The Devil, from Small World
       Evan, from Kissing the Buddha's Feet
       The burin, from Frobozz Magic Supoort

  o Best individual puzzle
    Nominated:
       Cramped, crawling, from So Far
       The crystals, from Fear
       The elephant from The Meteor, The Stone, and the Long Glass of Sherbet
       Riding the creature, from So Far
    Won:
       Opening the gate, from So Far

  o Best NPCs
    Nominated:
       Lost New York, by Neil deMause
       Small World, by Andrew Pontious
       The Underoos That Ate New York, by Gerry Kevin Wilson
       The Wedding, by Neil J Brown
    Won:
       Kissing the Buddha's Feet, by Leon Lin

  o Best puzzles
    Nominated:
       Frobozz Magic Support, by Nate Cull
       Lost New York, by Neil deMause
       The Meteor, the Stone and a Long Glass of Sherbet, by Graham Nelson
       Time: All Things Come to an End, by Andy Phillips
    Won:
       So Far, by Andrew Plotkin

  o Best setting
    Nominated:
       The Light: Shelby's Addendum, by Colm McCarthy
       Lost New York, by Neil deMause
       A Night at the Computer Center, by Bonni Mierzejewska
       So Far, by Andrew Plotkin
    Won:
       Small World, by Andrew Pontious

  o Best Story
    Nominated:
       Delusions, by C.E. Forman
       Lost New York, by Neil deMause
       So Far, by Andrew Plotkin
       Time: All Things Come To An End, by Andy Phillips
    Won:
       Tapestry, by Daniel Ravipinto

  o Best writing
    Nominated:
       Aayela, by Magnus Olsson
       Lost New York, by Neil deMause
       The Meteor, the Stone and a Long Glass of Sherbet by Graham Nelson
       Tapestry, by Daniel Ravipinto
    Won:
       So Far, by Andrew Plotkin

  o Best Game of 1996
    Nominated:
       The Light, Shelby's Addendum, by Colm McCarthy
       Lost New York, by Neil deMause
       The Meteor, the stone, and a Long Glass of Sherbet, by Graham Nelson
       Time: All Things Come to an End, by Andy Phillips
    Won:
       So Far, by Andrew Plotkin


From straight@email.unc.edu Wed Feb 12 09:24:25 MET 1997
Article: 22257 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in2.uu.net!198.82.160.249!solaris.cc.vt.edu!newsgate.duke.edu!news-relay.ncren.net!newz.oit.unc.edu!login6.isis.unc.edu!straight
From: Michael Straight <straight@email.unc.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: Tue, 11 Feb 1997 14:51:31 -0500
Organization: The University of North Carolina at Chapel Hill
Lines: 31
Message-ID: <Pine.A41.3.95.970211144004.70604A-100000@login6.isis.unc.edu>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dqar9$lsj@bartlet.df.lth.se> <3300B583.41C6@greenhouse.llnl.gov>
NNTP-Posting-Host: login6.isis.unc.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Sender: straight@login6.isis.unc.edu
In-Reply-To: <3300B583.41C6@greenhouse.llnl.gov>



On Tue, 11 Feb 1997, Kathleen Fischer wrote:

> Magnus Olsson wrote:
> > As far as I can see, this is more or less what Linards meant when he
> > proposed an award for "best parser", isn't it? That is, we don't judge
> > the parser as an isolated system, but how well it supports the
> > interaction needed in the game.

> However, nobody like the name "Best Parser" and everybody fussed about
> "Best Mimesis" (sp?) so I thought the title Best PC might be more
> palateable.

I like the idea (I forget who suggested it) of "Best Parsing" for the game
that does the best job of recognizing all the words I want to use, has the
most interesting and original replies to wrong guesses or irrelevant
actions like "jump" or "laugh," and otherwise makes the most of whatever
parser the author chose to use, be it Inform, TADS, or whatever.

"Best PC" I would save for recognizing well-developed or entertaining or
original or otherwise interesting main characters like Ralph from "Ralph"
or the knight in "Wok" or the narrator in "Of Forms Unknown" or the main
character of "I-0" (which I haven't played but seems to be generating a
lot of interest). 

Add Michael Straight to the list of those who rue forgetting the Xyzzys.
FLEOEVDETYHOEUPROEONREWMEILECSOFMOERSGTIRVAENRGEEARDSTVHIESBIITBTLHEEPSRIACYK
Ethical	Mirth Gas/"I'm chaste alright."/Magic Hitler Hats/"Hath	grace limits?"
"Irate Clam Thighs!"/Chili Hamster Tag/The Gilt	Charisma/"I gather this calm."



From mkkuhner@phylo.genetics.washington.edu Wed Feb 12 09:24:52 MET 1997
Article: 22251 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!www.nntp.primenet.com!nntp.primenet.com!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 12 Feb 1997 00:10:58 GMT
Organization: University of Washington, Seattle
Lines: 27
Message-ID: <5dr1qi$s90@nntp5.u.washington.edu>
References: <33009D0D.1CFB@greenhouse.llnl.gov>
NNTP-Posting-Host: phylo.genetics.washington.edu

In article <33009D0D.1CFB@greenhouse.llnl.gov> Kathleen Fischer <kfischer@greenhouse.llnl.gov> writes:

>I decided that we discuss NPC's because they are hard to program
>correctly   :(   and PC's aren't hard because that's the player's job
>with the help of the parser. Hmmmm. 

As someone who is wrestling with her PC right now, I have to partially
disagree.  A game like _Christminster_ certainly stands or falls in
large part on how well the thoughts and feelings (and sometimes words
and actions!) attributed by the game to Christabel click for the player.
If the PC is just a cypher for the player, then you just have to stay
out of the player's way.  Which is not always easy in itself--"You 
don't want to do that" is so useful in closing things off.  But if the
PC has a personality, it's pretty darned important that it works well.
A good parser won't save a game which makes me hate my alter-ego.

_Christminster_ pushed the line for me once or twice, mainly with "You
can't make head or tail of the math" and similar comments.

I seem to be in a minority in thinking that the protagonist of _Jigsaw_
has a very definite character; I really enjoyed that aspect of the game.

One thing the manuals just don't talk about; where do you *put* the PC's
personality?  Mine is getting smeared all over my code, and I'm sure I
shall die if I have to revise it.

Mary Kuhner mkkuhner@genetics.washington.edu


From avrom@Turing.Stanford.EDU Wed Feb 12 13:26:29 MET 1997
Article: 22271 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 12 Feb 1997 00:21:03 -0800
Organization: CSLI, Stanford University
Lines: 102
Message-ID: <5druhf$ks2@Turing.Stanford.EDU>
References: <5dfe85$sob@flood.xnet.com> <5dfhed$8b7@bartlet.df.lth.se> <egh-0702971555080001@news.berkeley.edu> <5dgorh$k9p@nntp5.u.washington.edu>
NNTP-Posting-Host: turing.stanford.edu

In article <5dgorh$k9p@nntp5.u.washington.edu>,
Mary K. Kuhner <mkkuhner@phylo.genetics.washington.edu> wrote:
>egh@uclink4.berkeley.edu (Erik Hetzner) writes:
>
>>Problems might be caused if you were breaking into rooms, instead of
>>having the key (ie you could break into any room). Perhaps one could
>>create a sort of randomness to the rooms -- ie you could break into them,
>>and there would be random scattered objects of no importance? And have
>>random characters walk about. All of this just to add realism, not
>>interest.
>
>Problem is that the player, noting that she can break into rooms, and
>that there are objects in them, may very well worry that there exists
>some room and object which she *needs*.

The way to keep this from happening is just not to let the player
break into all the rooms.  There are some ways to do this that have
been discussed elsewhere in this thread:

For example, one way, as I think Laurel Halbany suggested, is to say
"You shouldn't go snooping about" or "Don't you have to be on the
12th floor?"  This works, although I feel a bit ambivalent about it,
since it sort of reeks of railroading.

Another way is just not to give the player keys or lockpicking tools
to any of the unimportant doors, as has been suggested a couple of times.

Here's a third way, which I'm a bit partial to:  Have one or a few
randomly generated rooms that an individual break-in will lead to.
But have breaking into a random room end the game, and soon, in a
predictable way so that it doesn't seem like sudden death--a maid
notices something is amiss and calls hotel security, for example.
That way the player will never be tempted to go through an exhaustive
search of the hotel, hundreds of rooms needn't be coded, and the
illusion of a full-size hotel can be preserved for those who are
irritatingly persistent at banging down doors.

I'm quite partial to permanently-locked doors, whether the locks are
simple or more extravagant.  They lend a real sense of scope and space
to what can in fact be a fairly small game.

Some (fairly minor, but quite real) spoilers for a couple of games
whose names I won't even mention yet since that alone would give a bit
away...




























I thought _So_Far_ used permanently locked doors to brilliant effect.
It's not, in retrospect, even a particularly large game, but until you
finish it, it seems _huge_.  So many areas to explore!  In the far
half of the dome, inside the castle, beyond the gate, along the
side-streets in the silent city, in the house with the strange hooting
creature...although, of course, these _aren't_ areas to explore.
They're just doorways to nowhere, although none of the failure
messages let you _know_ they're doorways to nowhere.

An isolated example of a brilliant permanently locked door from a game
that generally had some (perhaps intentional, but real) problems with
claustrophobia:  It's from _In_the_End_.  I didn't get around to
voting in the XYZZY awards, but if I had, I would at least have
seriously considered voting for "Getting into Annie's House" as the
best single puzzle of the year.  The solution to this puzzle is,
though surprising and counter to most conventions of I-F, brilliantly
logical and in fact inevitable given the general structure of the
game.

-Avrom












From dmss100@york.ac.uk Wed Feb 12 13:27:22 MET 1997
Article: 22279 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-dc-9.sprintlink.net!rill.news.pipex.net!pipex!uknet!usenet1.news.uk.psi.net!uknet!uknet!yama.mcc.ac.uk!news.york.ac.uk!ebor.york.ac.uk!dmss100
From: Den of Iniquity <dmss100@york.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: Wed, 12 Feb 1997 11:46:57 +0000
Organization: The University of York, UK
Lines: 45
Message-ID: <Pine.SGI.3.95L.970212112418.28566B-100000@ebor.york.ac.uk>
References: <855552928.65113.4@darkside.demon.co.uk>
NNTP-Posting-Host: ebor.york.ac.uk
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <855552928.65113.4@darkside.demon.co.uk>

On Mon, 10 Feb 1997, Adam Dawes wrote:

>In the case of a hotel with lots of locked doors, I personally would not rest
>until I'd tried every single one -- who knows which one might have an easter
>egg hidden behind it. ;)

Has anyone come across a game called Damocles (Mercenary II) by Novagen? 
It may have been out for other systems but I only know it from the Amiga. 
It's one of those first person 3D games which lies as close to adventure
and exploration as any other genre. The aim of the game is to save the
main, populated planet of a solar system from a comet on direct collision
course. There are a few solutions to the game one or two of which are
quite interesting in their own right but are irrelevant here. 

One planet (or planetoid) in the game (I forget) is completely covered
with pyramids.  Millions of them, equally spaced, all identical but for an
eight figure identification number written in huge numbers round its four
corners. If you wanted to explore every single pyramid you could - it
would take thousands of years in real time, and only one of them contained
the magic ancient artefact (one of the (very) alternative solutions -
again, my memory fails me as to what it is and how it works). 

The trick was lying on another nearby planet(oid) with similar Egyptian
architecture - one sphynx (I think) had a bizarre set of eight hieroglyphs
tucked away in it and another building had eight or nine storeys - with a
different hieroglyph on each floor - one for 0, one for 1, one for 2, etc,
etc - finding the ancient magic artefact was then a matter of minutes.
(Finding the pyramid even with nice sequential numbers is still quite time
consuming because you have to be slow down to point your ship to read the
number and then figure out which way the numbers descend and ascend and so
on.)

Of course this kind of excess, quite the opposite of minimalism, is so
much easier to do in the in-yer-face 3D environment, but often this kind
of repetition of empty buidings (as can be found all over the place in the
solar system) seems to make the task of finding the requisite items
(explosives and the like) nearly impossible. There are clues to tell you
which buidings to go to, and named buildings are ten times more useful to
search than unnamed, but all the same it did often make me feel weirdly
agoraphobic. A great game for Easter Eggs though. One solution was to find
'the author's computer...'

--
Den



From daly@PPD.Kodak.COM Thu Feb 13 20:41:01 MET 1997
Article: 22321 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news.idt.net!enews.sgi.com!news.sgi.com!sdd.hp.com!frankensun.altair.com!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 13 Feb 1997 17:55:30 GMT
Organization: Eastman Kodak Company
Lines: 25
Message-ID: <5dvkii$hd8@kodak.rdcs.Kodak.COM>
References: <egh-0702971555080001@news.berkeley.edu> <5dgorh$k9p@nntp5.u.washington.edu> <5druhf$ks2@Turing.Stanford.EDU>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com

In article <5druhf$ks2@Turing.Stanford.EDU> avrom@Turing.Stanford.EDU (Avrom Faderman) writes:
>
>Here's a third way, which I'm a bit partial to:  Have one or a few
>randomly generated rooms that an individual break-in will lead to.
>But have breaking into a random room end the game, and soon, in a
>predictable way so that it doesn't seem like sudden death--a maid
>notices something is amiss and calls hotel security, for example.
>That way the player will never be tempted to go through an exhaustive
>search of the hotel, hundreds of rooms needn't be coded, and the
>illusion of a full-size hotel can be preserved for those who are
>irritatingly persistent at banging down doors.

Are you kidding?  Rather than deter me, this would take up all of
my time.  I would spend all day and half the night trying to figure 
out how to get away with the break-in without alerting the maid.
You've taken "The door is locked, and you don't have the key", which
is very open-and-sh^H^H^H^H^H^H^H^H^H^H^H^H matter-of-fact, and
turned it into something that looks like a puzzle.

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From avrom@Turing.Stanford.EDU Fri Feb 14 09:23:31 MET 1997
Article: 22341 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 13 Feb 1997 23:08:46 -0800
Organization: CSLI, Stanford University
Lines: 64
Message-ID: <5e131u$k8a@Turing.Stanford.EDU>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu>
NNTP-Posting-Host: turing.stanford.edu

In article <5dr1qi$s90@nntp5.u.washington.edu>,
Mary K. Kuhner <mkkuhner@phylo.genetics.washington.edu> wrote:
>In article <33009D0D.1CFB@greenhouse.llnl.gov> Kathleen Fischer <kfischer@greenhouse.llnl.gov> writes:
>
>>I decided that we discuss NPC's because they are hard to program
>>correctly   :(   and PC's aren't hard because that's the player's job
>>with the help of the parser. Hmmmm. 
>
>As someone who is wrestling with her PC right now, I have to partially
>disagree.  A game like _Christminster_ certainly stands or falls in
>large part on how well the thoughts and feelings (and sometimes words
>and actions!) attributed by the game to Christabel click for the player.

I actually have to disagree with both of these claims.

>If the PC is just a cypher for the player, then you just have to stay
>out of the player's way.

But the PC isn't necessarily just a surrogate for the player.

I'm not Christabel, but I thought she was an interesting character;
I'm not the protagonist of "Kissing the Buddha's Feet," but I thought
he was nearly as hilarious as the NPCs;  I certainly hope I'm not
Ralph, but it was fun to pretend for a while.

I'm not even the protagonist from "So Far."  If I remember correctly,
Andrew Plotkin claimed _he_ was, and he should know, after all.

It's not just that these characters face _situations_ I don't;  it's
that they don't have all my motivations or personality quirks either.

The character's motivations have to be well-communicated and
interesting enough for me to be willing and able to assume them for a
while, but they don't have to be _mine_.

>  Which is not always easy in itself--"You 
>don't want to do that" is so useful in closing things off.  But if the
>PC has a personality, it's pretty darned important that it works well.
>A good parser won't save a game which makes me hate my alter-ego.

Hm...now I think I agree with this...but I no longer understand your
comments about "Christminster" above.  I think it's this sort of game,
not the previous sort.

>_Christminster_ pushed the line for me once or twice, mainly with "You
>can't make head or tail of the math" and similar comments.

Hm.  I guess I'm confused here.

>I seem to be in a minority in thinking that the protagonist of _Jigsaw_
>has a very definite character; I really enjoyed that aspect of the game.

I've written about this before...I agree that the protagonist of
_Jigsaw_ had a very definite character, but that was my main trouble
with it.  It made it impossible for me to understand what all the
careful avoidance of gender talk was about. 

If the character was supposed to be a surrogate for the player, I'd
understand--it would be to allow all players (whatever their gender
and preference) to get into the story.  But he/she wasn't a surrogate
for the player;  at least he/she wasn't a surrogate for _me_.
Interesting, maybe.  Me, no.

-Avrom


From neild@echonyc.com Fri Feb 14 13:13:35 MET 1997
Article: 22347 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!news.apfel.de!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in2.uu.net!198.67.15.6!news.echonyc.com!echonyc.com!neild
From: neild@echonyc.com (Neil deMause)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 14 Feb 1997 01:18:30 GMT
Organization: EchoNYC
Lines: 33
Message-ID: <5e0eh6$m1@echo2.echonyc.com>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu>
NNTP-Posting-Host: echonyc.com
X-Newsreader: TIN [version 1.2 PL2]

Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:
: In article <33009D0D.1CFB@greenhouse.llnl.gov> Kathleen Fischer <kfischer@greenhouse.llnl.gov> writes:

: >I decided that we discuss NPC's because they are hard to program
: >correctly   :(   and PC's aren't hard because that's the player's job
: >with the help of the parser. Hmmmm. 

: As someone who is wrestling with her PC right now, I have to partially
: disagree.  A game like _Christminster_ certainly stands or falls in
: large part on how well the thoughts and feelings (and sometimes words
: and actions!) attributed by the game to Christabel click for the player.
: If the PC is just a cypher for the player, then you just have to stay
: out of the player's way.  Which is not always easy in itself--"You 
: don't want to do that" is so useful in closing things off.  But if the
: PC has a personality, it's pretty darned important that it works well.
: A good parser won't save a game which makes me hate my alter-ego.

I agree with your disagreement. Having heretofore written "PC-less" games 
(i.e., bring your own self), it's, um, er, an interesting learning 
experience trying to do PCs with character. The kind of learning 
experience that either kills you or makes you stronger, I think.

(Awestruck paean to what Adam C. has done with Tracy in I-0 omitted, 
because you've heard me say it already.)

: One thing the manuals just don't talk about; where do you *put* the PC's
: personality?  Mine is getting smeared all over my code, and I'm sure I
: shall die if I have to revise it.

For me, a lot of it winds up in room and object descriptions. Who you are 
is reflected in how you see.

Neil


From mas.supplies@easynet.co.uk Fri Feb 14 13:13:51 MET 1997
Article: 22348 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!EU.net!uknet!usenet1.news.uk.psi.net!uknet!dispatch.news.demon.net!demon!easynet-uk!newsfeed.easynet.co.uk!easynet-cherry!usenet
From: mas.supplies@easynet.co.uk (Bill Hoggett)
Newsgroups: rec.arts.int-fiction
Subject: Re: How much of Zork is Copyrighted?
Date: 14 Feb 97 11:09:24 +0500
Organization: [posted via] Easynet Group PLC
Message-ID: <1302.6984T669T1242@easynet.co.uk>
References: <33036F25.67C2@globalserve.net>
NNTP-Posting-Host: mas.supplies.easynet.co.uk
X-Newsreader: THOR 2.3 (Amiga;TCP/IP) *UNREGISTERED*
X-easynet-cherry: 85591882526529.nnrp
Lines: 30

On 14-Feb-97 Drone wrote:

>I want to design a piece of I-F that uses *all* of the Zork 1 locations
>(with different contents). Now, I realise that Zork 1 is still firmly
>under copyright, but isn't its progenitor, Dungeon, in the public
>domain? And if it is, and I base my map on Dungeon's rather than on Zork
>1's, surely the parts of Zork 1 that are identical to Dungeon cannot be
>under copyright, since they are in the public domain as part of Dungeon.
>Am I wrong here?

I think you'll probably find that Dungeon is also under copyright, only
not to any major publisher. Hence, the chances are no one will pop up
to enforce their legal rights. If you plan to use locations that are
identical in Zork, you may find yourself on swampy legal ground. Activision
may claim that the Zork copyright superceeds that of Dungeon since it's
legal and more recent.

>The other alternative is to use all of the Adventure locations, instead,
>since I assume that it has been modified so much it must be in the
>public domain. Am I at least correct in that assumption?

I would seem so. The most recent game to use the Adventure setting is
SpAdventure - Colossal with spells!


---
Bill Hoggett (aka BeeJay)   <mas.supplies@easynet.co.uk>

IF GOD IS LIFE'S SERVICE PROVIDER WHY HAVEN'T I GOT HIS I.P. NUMBER ?



From mkkuhner@phylo.genetics.washington.edu Mon Feb 17 21:38:04 MET 1997
Article: 22364 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 15 Feb 1997 00:42:58 GMT
Organization: University of Washington, Seattle
Lines: 55
Message-ID: <5e30qi$mvr@nntp5.u.washington.edu>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu> <5e131u$k8a@Turing.Stanford.EDU>
NNTP-Posting-Host: phylo.genetics.washington.edu

avrom@Turing.Stanford.EDU (Avrom Faderman) writes:

>Mary Kuhner wrote:
>>A game like _Christminster_ certainly stands or falls in
>>large part on how well the thoughts and feelings (and sometimes words
>>and actions!) attributed by the game to Christabel click for the player.

I was unclear here.  I was trying to say, "Since Christabel is
a distinct person, her actions have to make sense, be in character,
and demonstrate a personality that the player enjoys, or the game will
be spoiled."  I didn't mean that Christabel's reactions need to
match the player's; I meant they have to *work* for the player, and
not seem out of place, contrived, or hopelessly stupid.

>The character's motivations have to be well-communicated and
>interesting enough for me to be willing and able to assume them for a
>while, but they don't have to be _mine_.

Agreed.  Both having the PC be a cypher for the player, and having the
PC be a distinct person, can work well, but they demand rather different
techniques.  (I get exasperated at games which pretend I'm playing
myself and then resort to telling me what I think or feel, for example,
whereas this is perfectly fair play in a game which has a protagonist
distinct from the player.)

>>I seem to be in a minority in thinking that the protagonist of _Jigsaw_
>>has a very definite character; I really enjoyed that aspect of the game.

>I've written about this before...I agree that the protagonist of
>_Jigsaw_ had a very definite character, but that was my main trouble
>with it.  It made it impossible for me to understand what all the
>careful avoidance of gender talk was about. 

I think the fun part of the gender-avoidance is in getting to
compare the way different people perceive the protagonist.  It
certainly didn't cause me to see him/her as a surrogate for myself;
and honestly, I enjoyed the game more by experiencing White as a
separate character than I would if s/he had been a flavorless
mask for me.  But it did make me think a bit about my attitudes
towards gender, which added some richness to the game.

I knew that the characters' gender was indeterminate before I picked up
the game, so I made up my mind initially what genders they ought to
be.  I was surprised that I couldn't stick to my initial assignment;
a sense of both characters' gender developed out of the game events,
willy-nilly.  And, despite the usual assumption that protagonists will
have the gender of their player, it was White/male, Black/female that
finally clicked for me. 

I think it was that bit of vandalism near the beginning of the game
that settled White's gender--stereotypes, hm?  But I'm still not
sure what settled Black's.  It wasn't any of the scenes where there
is actual evidence on the point.

Mary Kuhner mkkuhner@genetics.washington.edu


From foxglove@globalserve.net Mon Feb 17 21:38:19 MET 1997
Article: 22454 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!news.maxwell.syr.edu!news.bc.net!torn!n1tor.istar!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: Mon, 17 Feb 1997 15:01:25 -0500
Organization: Envision This
Lines: 23
Message-ID: <3308B915.1A3A@globalserve.net>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu> <5e131u$k8a@Turing.Stanford.EDU> <5e30qi$mvr@nntp5.u.washington.edu>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin392.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22454

Mary K. Kuhner wrote regarding Jigsaw:
> 
> I knew that the characters' gender was indeterminate before I picked up
> the game, so I made up my mind initially what genders they ought to
> be.  I was surprised that I couldn't stick to my initial assignment;
> a sense of both characters' gender developed out of the game events,
> willy-nilly.  And, despite the usual assumption that protagonists will
> have the gender of their player, it was White/male, Black/female that
> finally clicked for me.
> 

That's interesting. Even though I also knew in advance that they were to be 
gender non-specific, and that there was to be a romantic involvement, I just 
couldn't get the concept out of my head that White and Black were gay males. 
Regardless of what I knew, I didn't "feel" as if their gender were in question 
at all, but rather as if they started as both male, and when their relationship 
developed, then their sexual orientation became clear. Maybe it's a case of 
sexism overwhelming homophobia. Isn't that a happy thought? <g>

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From avrom@Turing.Stanford.EDU Mon Feb 17 21:38:27 MET 1997
Article: 22417 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!newsfeed.uk.ibm.net!arclight.uoregon.edu!hunter.premier.net!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 15 Feb 1997 13:55:55 -0800
Organization: CSLI, Stanford University
Lines: 12
Message-ID: <5e5bdb$icc@Turing.Stanford.EDU>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu> <5e131u$k8a@Turing.Stanford.EDU>
NNTP-Posting-Host: turing.stanford.edu
Xref: news.lth.se rec.arts.int-fiction:22417

In article <5e131u$k8a@Turing.Stanford.EDU>,
Avrom Faderman <avrom@Turing.Stanford.EDU> wrote:
>  I certainly hope I'm not Ralph,

..although on the Internet...

Sorry. Had to say it.

-Avrom





From daly@PPD.Kodak.COM Mon Feb 17 21:38:38 MET 1997
Article: 22400 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!lade.news.pipex.net!pipex!hose.news.pipex.net!pipex!cold.news.pipex.net!pipex!tank.news.pipex.net!pipex!iafrica.com!uct.uni.net.za!csir.uni.net.za!wits.uni.net.za!howland.erols.net!vixen.cso.uiuc.edu!cdc2.cdc.net!newsfeed.concentric.net!newshost.comco.com!frankensun.altair.com!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 16 Feb 1997 00:07:08 GMT
Organization: Eastman Kodak Company
Lines: 20
Message-ID: <5e5j3c$40t@kodak.rdcs.Kodak.COM>
References: <5e131u$k8a@Turing.Stanford.EDU> <5e5bdb$icc@Turing.Stanford.EDU> <jota.856048861@laraby.tiac.net>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com
Xref: news.lth.se rec.arts.int-fiction:22400

In article <jota.856048861@laraby.tiac.net> jota@laraby.tiac.net (Admiral Jota) writes:
>avrom@Turing.Stanford.EDU (Avrom Faderman) writes:
>>Avrom Faderman <avrom@Turing.Stanford.EDU> wrote:
>>>  I certainly hope I'm not Ralph,
>>..although on the Internet...
>>Sorry. Had to say it.
>
>Y'know, I've heard the quote you're alluding to many, many times -- but I
>have no clue where it comes from. Could you enlighten me?

Came from a cartoon in New Yorker magazine, July 5, 1993.  Page 61.

http://www.anonymizer.com/cartoon.html will save you a trip to the library.

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From avrom@Turing.Stanford.EDU Mon Feb 17 21:41:18 MET 1997
Article: 22388 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!Oslo2.Norway.EU.net!Norway.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: IF "minimalism"
Date: 15 Feb 1997 13:46:39 -0800
Organization: CSLI, Stanford University
Lines: 70
Message-ID: <5e5arv$hr8@Turing.Stanford.EDU>
References: <egh-0702971555080001@news.berkeley.edu> <5dgorh$k9p@nntp5.u.washington.edu> <5druhf$ks2@Turing.Stanford.EDU> <5dvkii$hd8@kodak.rdcs.Kodak.COM>
NNTP-Posting-Host: turing.stanford.edu
Xref: news.lth.se rec.arts.int-fiction:22388

In article <5dvkii$hd8@kodak.rdcs.Kodak.COM>,
Matthew Daly <daly@PPD.Kodak.COM> wrote:
>In article <5druhf$ks2@Turing.Stanford.EDU> avrom@Turing.Stanford.EDU (Avrom Faderman) writes:
>>
>>Here's a third way, which I'm a bit partial to:  Have one or a few
>>randomly generated rooms that an individual break-in will lead to.
>>But have breaking into a random room end the game, and soon, in a
>>predictable way so that it doesn't seem like sudden death--a maid
>>notices something is amiss and calls hotel security, for example.
>>That way the player will never be tempted to go through an exhaustive
>>search of the hotel, hundreds of rooms needn't be coded, and the
>>illusion of a full-size hotel can be preserved for those who are
>>irritatingly persistent at banging down doors.
>
>Are you kidding?  Rather than deter me, this would take up all of
>my time.  I would spend all day and half the night trying to figure 
>out how to get away with the break-in without alerting the maid.
>You've taken "The door is locked, and you don't have the key", which
>is very open-and-sh^H^H^H^H^H^H^H^H^H^H^H^H matter-of-fact, and
>turned it into something that looks like a puzzle.

Yes, but at least you'd be spending the day and a half doing something
_interesting_.  I don't think this is _better_ than "the door is
locked, and you don't have the key," necessarily, but it's different
and gives a bit of variety.  And it makes the game seem bigger, which
is an advantage.

Spoiler for _So_Far_.





























I spent several hours, at least, trying to figure out how to leave the
main road in the silent city in any of the places you're not supposed
to.  It was several hours well spent, I thought.  Well, not as well
spent as they would have been working on my thesis, perhaps, but
well-spent given that I had resolved to waste the afternoon anyway.

I wouldn't, by the way, have enjoyed spending that self-same several
hours searching each of 200 rooms of virtually identical description
for the one room with something interesting in it.

-Avrom




From erkyrath@netcom.com Tue Feb 18 09:27:53 MET 1997
Article: 22467 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsfeeds.sol.net!news.maxwell.syr.edu!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Warning messages: good? bad?
Message-ID: <erkyrathE5rtCw.8L0@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <33070068.40E6@acpub.duke.edu> <m3pvy0mexf.fsf@ue801di.lrz-muenchen.de> <5e8lb6$bv0@nntp5.u.washington.edu> <3308BC01.2D83@globalserve.net> <5eam5r$o8@nntp5.u.washington.edu>
Date: Mon, 17 Feb 1997 23:31:43 GMT
Lines: 40
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:22467

Clyde Sloniker (puma@u.washington.edu) wrote:

> (closing eyes, imagining huge flame fest coming)  I knew posting that was
> a mistake.  I knew posting that was a mistake.  I knew posting that was a
> mistake.  I knew posting that was a mistake.  I knew posting that...

Yeah, I could have told you that. :-) You, too, Drone (whose quote I 
deleted in the interest of delaying the flames.)

There *is* sort of a double standard here, which I regret. Novels and 
short stories can have violent or sexual content (or vulgarity, 
obscenity, blasphemy, etc, to refer back to an earlier thread.) Nobody 
expects these things to be absent unless the book says "juvenile" on the 
spine, or some equivalent mark.

Whereas with games, there's this feeling that the primary market is kids. 
Which is not surprising -- for most kinds of games, the primary market 
*is* kids. But this has not been true of IF in recent years. I mean, if 
someone has gone through the larger TADS/Inform games, Jigsaw and Curses 
and Legend and So Far and LNY and so on, they would not get the idea that 
this is a "juvenile" readership that we're aiming at.

As my own little contribution towards a "mature-audience" assumption for 
text IF, I do not put such warnings on my games. Of course I haven't
written a game with sex in it, yet. 

(As my own little contribution towards peace, I don't try to argue other 
people into removing such warnings. :-) It's up to you.)

Sometimes I really wish IF had book covers. All IF, I mean (nothing 
against Neil dM's manual cover for LNY.) Cover art would make so much of 
this information immediately obvious.

--Z


-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From njgreen@panix.com Tue Feb 18 09:36:02 MET 1997
Article: 22449 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!news.maxwell.syr.edu!worldnet.att.net!hunter.premier.net!uunet!in3.uu.net!199.184.165.2!news.interport.net!usenet
From: Noah Green <njgreen@panix.com>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Question about Zork Nemesis
Date: Mon, 17 Feb 1997 00:51:03 -0500
Organization: Panix.com
Lines: 73
Message-ID: <3307F1C7.3C41@panix.com>
References: <33024FF0.5F54@panix.com> <5dv9jo$b23@kodak.rdcs.Kodak.COM>
Reply-To: njgreen@panix.com
NNTP-Posting-Host: ts5port41.port.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
To: Matthew Daly <daly@PPD.Kodak.COM>
Xref: news.lth.se rec.games.int-fiction:21247 rec.arts.int-fiction:22449

Thanks for that info!  I kind of thought about Lucien as the thief, when
listening to the talking discs in the lab: "I found a vast underground
area with untold riches....to protect my belongings I've had to kill
[other adventurers]." or something along those lines. I reviewed the
game last year for a newspaper in NYC and the Activision people told me
there was a character from Zork I involved, but they told me that before
the final version was ready.

Anyway, for your edification here is the passage from the hint book,
coming from the history of Zork section. This is right after they talk
about the "Conqueror of Zork", i.e. you/me/us in Zork I-III:
"However, all was not well in the heart of this second Dungeon Master,
the Conqueror of Zork. Troubled by the murder he had committed in
self-defense [njg: they talk about you/me/us killing the Thief earlier],
he devoted the entirety of his strength and resources to undoing his
deed. Using the most powerful magical spells to summon an outsider to
his assistance, the adventurer who was chosen found himself wandering
deeper and deeper into a tangled web of confusion and altered reality,
at the center of which lurked the truth behind the Forbidden Lands and
the inexplicable disappearance of the alchemists."

Never mind the misplaced subject in that final sentence...the truth is
who here feels guilty about killing the thief? :-)  Seriously, with your
info I now understand what they were getting at.

Other parts of this section of the hint book go more into depth about
Syovar's lust for power, the Kaine vs. Ellron thing, etc., all of which
comes up in the game but doesn't get enough attention in the docs.

Hey did you hear there is new Zork game coming?  Looks like it's related
to the Inquisition in Zork Zero. If you hear any more details, I'd love
to know.

thanks,
noah


Matthew Daly wrote:
> 
> In article <33024FF0.5F54@panix.com> njgreen@panix.com writes:
> >Hi,
> >I'm new to these groups, and it occurs to me that for some, talking
> >about Zork: Nemesis might be considered blasphemy. (Me, I love it.) I
> >apologize in advance for offending anyone...please don't read further if
> >you are.
> 
> This is the Zork: Nemesis newsgroup -- and the Activision has the
> web link to prove it! :-\
> 
> >Well anyway, what I was wondering was, how many manuals are supposed to
> >come with this game. The reason I ask is that mine came with just the
> >"diary" thing...then I looked in this hint book in a store that talked
> >about a whole backplot that wasn't in the diary, and didn't seem to ever
> >get addressed in the story!  Apparently, the Dungeon Master from the old
> >Zorks is somehow involved in this story. Is this true? Is there a
> >missing manual? Should I just go and get a life already?
> 
> I'd love to hear about that backplot.  I know that it got axed due to
> causing more questions than it answered, but my understanding is that
> the Thief that was killed in Zork 1 was actually Lucien.  The adventurer,
> who went on to become the second Dungeon Master, felt guilty about
> doing this, and sends you, the player character, to go and avenge the
> circumstances that caused Lucien to become the Nemesis.  I'm a little
> confused by the timing of all these events, though.  It sounds like it
> could have been an effective tie-in, but I don't think they got all of
> the inconsistencies ironed out.
> 
> -Matthew
> --
> Matthew Daly       I feel that if a person has problems communicating
> mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer
> 
> My opinions are not necessarily those of my employer, of course.


From foxglove@globalserve.net Tue Feb 18 09:53:22 MET 1997
Article: 22452 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!europa.clark.net!newsfeeds.sol.net!uniserve!van-bc!n1van.istar!van.istar!west.istar!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Scramble! Ideas up for grabs. (LONG)
Date: Sun, 16 Feb 1997 14:16:29 -0500
Organization: Envision This
Lines: 85
Message-ID: <33075D0D.2D3D@globalserve.net>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin461.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22452

I can't help it. "Command Line Interface", which is to be the first 
episode of a series called "Mutter & Cry", is going swimmingly. But 
after that I have to start episode two (not to mention my non-IF 
projects), and I'm getting so immersed in this medium I'm having all of 
these great ideas pop into my head that I have no time whatsoever to 
pursue.

So, partly to get into the community spirit, and partly just to banish 
these nagging thoughts and reestablish my focus, I'm offering up to the 
newsgroup the two ideas that nag me the most. Let me know if you would 
be interested in playing the following, and especially if you would be 
interested in producing them.

(1) "Dungeonville". An IF magazine. Concept: the old Dungeon maze has 
been discovered, reclaimed, and refurbished by dimension-hopping IF 
enthusiasts. "Columnists" have established hangouts where they sit and 
eat chips (or whatever) and chew the fat about the state of IF with 
whomever happens by. Instead of writing an article, a contributor would 
design (through a submission form) a little IF version of himself or 
herself (not necessarily true-to-life), complete with habits, travel 
plans, and a large stock of conversational responses regarding the topic 
of the "article". Regular columnists could actually submit code 
(hopefully Inform so people could read on palmtops like a real portable 
magazine -- I love my PSION). Alternatively, information (like reviews, 
notices, etc.) could be presented as virtual bulletin boards, crystal 
balls, libraries, weird puzzles, telephone booths, covert contacts. I 
envision a very eclectic feel, tinged with the nostalgia of the original 
maze, and with the overriding "conceit" that all of these IF-enthusiasts 
have moved into the original Dungeon maze and set up shop, because they 
consider it their home. (Kind of like "The Promised Land" sort of 
thing.)
         One or two people need to code it up. After the first issue, 
coding should be easier, since a lot of code could be reused, with a few 
changes for the passage of time. All contributors must also serve as 
beta-testers, during which period they will see (for the first time) the 
complete work. And they can suggests new reactions and behaviours for 
their "columnists" or "column-objects" relative to the other columnists 
or to other rooms.
         Puzzles would be allowed, I imagine. But it would be annoying 
if a difficult puzzle were to keep me from "conversing" with a columnist 
or reading an article.
         Column ideas: The Game Critic's Corner (several critics 
combined in a "Siskel & Ebert" room?), The Bulletin Board (new 
releases), The Crystal Ball (future releases), The Work-in-Progress (a 
"guest" set of locations previewing somebody's upcoming release), The 
Tutorial Rooms (where examining objects lists their source code), The 
Short IF Feature (just a few rooms, chosen from submissions, like a 
short story in a paper mag). I could go on and on. I sort of am, 
actually.
         If using the Dungeon/Zork maze would be a copyright problem, 
then I imagine "Adventureville" would work just as well. It's more 
catchy, actually. Although I like the Dungeon maze better for this 
purpose.
         If you like this rather detailed concept, you're free to pursue 
it, in whole or in part or in your own retooled format. Hell, maybe 
there are fifty people out there thinking of something similar. Anyway, 
all I ask is that you keep me informed.

(2) "The Annotated Adventure." I would love to take Graham Nelson's port 
of the original Adventure, play it once again, but this time send off a 
transcript of my play to both Willie Crowther and Don Woods, who would 
annotate it with anecdotes, historical facts, musings, opinions, etc. 
Then I would take the source code and add to it two NPCs: Willie 
Crowther and Don Woods, who would follow you around and comment on what 
you're doing (using the annotations). The real Crowther and Woods would 
know about this plan, and would hopefully write their annotations as if 
they were standing there, in the maze, watching the game happen. Play 
the Original Adventure with the creators at your side! I'm dying to do 
it. Others I would love to see in this series, copyright issues aside: 
"The Annotated Dungeon" (with Marc Blank and Dave Lebling), "The 
Annotated Planetfall/Stationfall" (with Meretzky), "The Annotated 
Trinity" (with Moriarty), and probably hardest to arrange but definitely 
intriguing, "The Annotated Hitchhiker's" (with Meretzky and Adams).

Okay, so I'm throwing these out there in the hopes that, although I 
wouldn't be able to put any work toward them for nearly year, maybe I 
could see them happen anyway. Again, all I ask is that you let me know 
if you want to pick up all or part of one of these ideas and work on it.

Whew. That's a relief. Now back to work on "Command Line Interface".

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From foxglove@globalserve.net Tue Feb 18 09:54:10 MET 1997
Article: 22452 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!europa.clark.net!newsfeeds.sol.net!uniserve!van-bc!n1van.istar!van.istar!west.istar!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Scramble! Ideas up for grabs. (LONG)
Date: Sun, 16 Feb 1997 14:16:29 -0500
Organization: Envision This
Lines: 85
Message-ID: <33075D0D.2D3D@globalserve.net>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin461.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22452

I can't help it. "Command Line Interface", which is to be the first 
episode of a series called "Mutter & Cry", is going swimmingly. But 
after that I have to start episode two (not to mention my non-IF 
projects), and I'm getting so immersed in this medium I'm having all of 
these great ideas pop into my head that I have no time whatsoever to 
pursue.

So, partly to get into the community spirit, and partly just to banish 
these nagging thoughts and reestablish my focus, I'm offering up to the 
newsgroup the two ideas that nag me the most. Let me know if you would 
be interested in playing the following, and especially if you would be 
interested in producing them.

(1) "Dungeonville". An IF magazine. Concept: the old Dungeon maze has 
been discovered, reclaimed, and refurbished by dimension-hopping IF 
enthusiasts. "Columnists" have established hangouts where they sit and 
eat chips (or whatever) and chew the fat about the state of IF with 
whomever happens by. Instead of writing an article, a contributor would 
design (through a submission form) a little IF version of himself or 
herself (not necessarily true-to-life), complete with habits, travel 
plans, and a large stock of conversational responses regarding the topic 
of the "article". Regular columnists could actually submit code 
(hopefully Inform so people could read on palmtops like a real portable 
magazine -- I love my PSION). Alternatively, information (like reviews, 
notices, etc.) could be presented as virtual bulletin boards, crystal 
balls, libraries, weird puzzles, telephone booths, covert contacts. I 
envision a very eclectic feel, tinged with the nostalgia of the original 
maze, and with the overriding "conceit" that all of these IF-enthusiasts 
have moved into the original Dungeon maze and set up shop, because they 
consider it their home. (Kind of like "The Promised Land" sort of 
thing.)
         One or two people need to code it up. After the first issue, 
coding should be easier, since a lot of code could be reused, with a few 
changes for the passage of time. All contributors must also serve as 
beta-testers, during which period they will see (for the first time) the 
complete work. And they can suggests new reactions and behaviours for 
their "columnists" or "column-objects" relative to the other columnists 
or to other rooms.
         Puzzles would be allowed, I imagine. But it would be annoying 
if a difficult puzzle were to keep me from "conversing" with a columnist 
or reading an article.
         Column ideas: The Game Critic's Corner (several critics 
combined in a "Siskel & Ebert" room?), The Bulletin Board (new 
releases), The Crystal Ball (future releases), The Work-in-Progress (a 
"guest" set of locations previewing somebody's upcoming release), The 
Tutorial Rooms (where examining objects lists their source code), The 
Short IF Feature (just a few rooms, chosen from submissions, like a 
short story in a paper mag). I could go on and on. I sort of am, 
actually.
         If using the Dungeon/Zork maze would be a copyright problem, 
then I imagine "Adventureville" would work just as well. It's more 
catchy, actually. Although I like the Dungeon maze better for this 
purpose.
         If you like this rather detailed concept, you're free to pursue 
it, in whole or in part or in your own retooled format. Hell, maybe 
there are fifty people out there thinking of something similar. Anyway, 
all I ask is that you keep me informed.

(2) "The Annotated Adventure." I would love to take Graham Nelson's port 
of the original Adventure, play it once again, but this time send off a 
transcript of my play to both Willie Crowther and Don Woods, who would 
annotate it with anecdotes, historical facts, musings, opinions, etc. 
Then I would take the source code and add to it two NPCs: Willie 
Crowther and Don Woods, who would follow you around and comment on what 
you're doing (using the annotations). The real Crowther and Woods would 
know about this plan, and would hopefully write their annotations as if 
they were standing there, in the maze, watching the game happen. Play 
the Original Adventure with the creators at your side! I'm dying to do 
it. Others I would love to see in this series, copyright issues aside: 
"The Annotated Dungeon" (with Marc Blank and Dave Lebling), "The 
Annotated Planetfall/Stationfall" (with Meretzky), "The Annotated 
Trinity" (with Moriarty), and probably hardest to arrange but definitely 
intriguing, "The Annotated Hitchhiker's" (with Meretzky and Adams).

Okay, so I'm throwing these out there in the hopes that, although I 
wouldn't be able to put any work toward them for nearly year, maybe I 
could see them happen anyway. Again, all I ask is that you let me know 
if you want to pick up all or part of one of these ideas and work on it.

Whew. That's a relief. Now back to work on "Command Line Interface".

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From adam@tucson.princeton.edu Tue Feb 18 09:54:13 MET 1997
Article: 22416 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!hunter.premier.net!news.maxwell.syr.edu!worldnet.att.net!cbgw2.lucent.com!cbgw1.lucent.com!cnn.Princeton.EDU!tucson.princeton.edu!adam
From: adam@tucson.princeton.edu (Adam J. Thornton)
Newsgroups: rec.arts.int-fiction
Subject: Re: Scramble! Ideas up for grabs. (LONG)
Date: 16 Feb 1997 23:05:55 GMT
Organization: Princeton University
Lines: 19
Message-ID: <5e83sj$qpc@cnn.Princeton.EDU>
References: <33075D0D.2D3D@globalserve.net> <erkyrathE5ppMt.LAt@netcom.com>
NNTP-Posting-Host: tucson.princeton.edu
Xref: news.lth.se rec.arts.int-fiction:22416

Here's an idea I've been having, and if my dissertation continues to go
nowhere, maybe one I will implement:

A short (25-page?) monograph on Stephen Bishop, Bedquilt Cave, and the
humongous and mostly unrecognized influence of caving and caving language
on the fundamental forms and assumptions of the text adventure.

It'll draw heavily on "The Craft of Adventure" and _The Longest Cave_, of
course, and on some cool Kentucky archival documents I found of
19th-century trips into Colossal Cave.

Whether I write it is of course very much in doubt.

Adam
-- 
"I'd buy me a used car lot, and | adam@princeton.edu | As B/4 | Save the choad!
I'd never sell any of 'em, just | "Skippy, you little fool, you are off on an-
drive me a different car every day | other of your senseless and retrograde
depending on how I feel.":Tom Waits| little journeys.": Thomas Pynchon | 64,928


From adam@yuma.Princeton.EDU Tue Feb 18 09:54:37 MET 1997
Article: 22445 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!Gamma.RU!srcc!sovam!cam-news-feed1.bbnplanet.com!cam-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.pbi.net!cbgw3.lucent.com!cbgw1.lucent.com!cnn.Princeton.EDU!yuma.Princeton.EDU!adam
From: adam@yuma.Princeton.EDU (Adam J. Thornton)
Newsgroups: rec.arts.int-fiction
Subject: Re: Scramble! Ideas up for grabs. (LONG)
Date: 17 Feb 1997 16:05:25 GMT
Organization: Princeton University
Lines: 36
Message-ID: <5e9vk5$2t0@cnn.Princeton.EDU>
References: <33075D0D.2D3D@globalserve.net>
NNTP-Posting-Host: yuma-subnet124.princeton.edu
Xref: news.lth.se rec.arts.int-fiction:22445

In article <33075D0D.2D3D@globalserve.net>,
Drone  <foxglove@globalserve.net> wrote:
>(2) "The Annotated Adventure." I would love to take Graham Nelson's port 
>of the original Adventure, play it once again, but this time send off a 
>transcript of my play to both Willie Crowther and Don Woods, who would 
>annotate it with anecdotes, historical facts, musings, opinions, etc. 
>Then I would take the source code and add to it two NPCs: Willie 
>Crowther and Don Woods, who would follow you around and comment on what 
>you're doing (using the annotations). The real Crowther and Woods would 
>know about this plan, and would hopefully write their annotations as if 
>they were standing there, in the maze, watching the game happen. Play 
>the Original Adventure with the creators at your side! I'm dying to do 
>it. Others I would love to see in this series, copyright issues aside: 
>"The Annotated Dungeon" (with Marc Blank and Dave Lebling), "The 
>Annotated Planetfall/Stationfall" (with Meretzky), "The Annotated 
>Trinity" (with Moriarty), and probably hardest to arrange but definitely 
>intriguing, "The Annotated Hitchhiker's" (with Meretzky and Adams).

The Crowther and Woods would be especially endearing since the parts that
are cave simulation are mostly Crowther and the parts that are mostly Woods
are the Tolkeinesque/fantastic elements.  For instance, in the Dome Room
you can have Crowther happily scrambling around the walls checking for
missed exits while Don Woods tries unsuccessfully to get the muck off his
pants.  On the other hand, at the Grand Vista, you can have Woods beaming
happily and pointing out his magnificent writing as Will Crowther says
"Right.  A *live volcano* in a limestone cave.  Sure, Don.  *Where*,
exactly, did you learn your geology?"  Likewise with the dwarf: Woods
shouts something in Dwarvish and throws the knife back, while Crowther just
looks disgusted.  This would be a scream if done well.

Adam
-- 
"I'd buy me a used car lot, and | adam@princeton.edu | As B/4 | Save the choad!
I'd never sell any of 'em, just | "Skippy, you little fool, you are off on an-
drive me a different car every day | other of your senseless and retrograde
depending on how I feel.":Tom Waits| little journeys.": Thomas Pynchon | 64,928


From erkyrath@netcom.com Tue Feb 18 14:06:19 MET 1997
Article: 22370 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Other forms of interactive fiction
Message-ID: <erkyrathE5MoIq.A57@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5e2hve$4rd@news.wco.com>
Date: Sat, 15 Feb 1997 04:59:13 GMT
Lines: 121
Sender: erkyrath@netcom12.netcom.com

Curt Siffert (siffert@shell.wco.com) wrote:

> I've been spending a lot of time thinking about interactive fiction
> lately, on my own and with my creative writing group.  I just recently
> came across this group and was intrigued.

> However, most of the discussion seem to be in only one area of
> interactive fiction, the infocommish sort. 

Yup. I hear the newsgroup didn't start out this way, but that was before 
my time. 

> Some questions, then, for discussion:

> 1) How are most of these already existing interactive fiction games
>     different from muds, aside from the multi-user aspect?  Or 
>     alternatively, what is it about these games that makes you want 
>     to play them as opposed to playing a mud?  The followup questions
>     would be, what elements of interactive fiction should be concentrated 
>     on to make it distinctive from a mud? (aside from the single-player 
>     nature)  Or, how could multiple players be introduced to 
>     interactive fiction without it turning into a mud?

This is not an uninteresting question. :) My experience with MUDs is 
limited (despite the award ceremony last week). This is precisely 
because the Great MUD Explosion of 1989 (TinyMUD and its descendants) 
was a set of social environments -- as opposed to both puzzles and works 
of fiction. I played around with simple puzzle-story scenarios in 
TinyMUD and Islandia, but I was in a small minority. Most people wanted 
to hang out with each other, not explore.

Do I have a point here? I guess the distinctive characteristic of a MUD 
is a lot of people in an unstructured setting -- they log in when they 
have time, but not in any coordinated way. Whereas IF of the Infocom 
variety demands very structured attention. If you have a multi-character 
story going on, and you want each character played by a different person, 
they must all join in at the same time, with the intent of doing nothing 
else for the entire session. And if they don't finish in one session 
(remember that two hours play-time is a *short* IF work) they have to
all be present the next day, to restore their saved game. That's not 
impossible, but it sure wasn't the TinyMUD crowd.

People do manage to have paper-and-pencil RPG campaigns that go on for 
years at weekly meetings. It's not impossible, like I said. But we 
haven't started doing it yet.

> 2) Have there been many experiments with using first or third 
>     person as opposed to the traditional second person approach?
>     (YOU see a leaflet in the mailbox.)

A few. "Piece of Mind" from this year's competition plays around with
first person; the "I" in "I get out of bed" is actually a separate
character, one who talks to you as well as obeys your commands. 

I don't recall seeing any third-person experiments. ("Fred gets out of 
bed.") I don't see any particularly nifty prospects in that area; it 
seems like it would just distance the player from the action, and I've 
always liked the closeness of second person. But I'm sure it'll be tried 
eventually. Or more likely it has and I'm forgetting something obvious.

> 3) Do you see any alternatives in the interactive stage besides
>     either the choice-making of a cyoa or the brief action-reaction
>     of a text game?  There is this paradigm of "1. print out the 
>     description, 2. wait for limited input" that is begging for 
>     new ideas.

Well, we don't have the technology to understand anything *but* limited 
input. That kind of forces the issue.

> 4) What of switching viewpoints with another character?  Has this
>     been experimented with?  You are Detective Bob trying to solve
>     a crime, and you run into Hooker Harriet.  You then switch - 
>     you are Hooker Harriet living the seedy night life for a few
>     nights.  (And then you could switch to a congressman!) All the 
>     while, Detective Bob is still on the case.

There have been multi-character games, most obviously _Suspended_. I can 
think of more graphical ones than text ones, actually -- _Bad Day on the 
Midway_ and _The Dark Eye_ are recent graphical adventures that allowed 
character jumping. The techniques were perfectly applicable to text IF.

> 5) Cyoa's usually involve choices which create divergent plotlines - 
>     choose one path, and the result of the path you *didn't* choose
>     never happens.  That's like saying that a tree falling in a forest
>     with no one around doesn't make a sound.  I guess it's a question
>     of philosophy, but has anyone experimented in the matter of 
>     outside events happening without being a function of the 
>     character's interaction?  Result of path B *still* happens,
>     you just weren't there to see it.  I guess this does happen
>     sometimes, but it still seems to be the exception rather than
>     the rule.

Well, in a sense this is very common -- most games have some kind of 
"daemon" or "timer" system. If you stay in the room with the time-bomb, 
it goes off and you die; if you run away, there's a distant boom behind 
you as you look around the next scene. _Deadline_ was an early Infocom 
game that had very detailed timed actions going on, involving multiple 
characters, over an entire day.

I think this is less common these days because it can easily lead to a lot
of *boring stories*. The player can easily be in the wrong place at the
right time, and vice versa, and wind up spending hours of playing time
without seeing anything happen. We want to make the main character the
focus of the story -- which is an assumption of static fiction which is so
obvious that it's invisible -- so we rig up events that are triggered when
the player walks in, or force the player to the right place at the right
time. Or else (this is one easy way out) have static situations that can 
plausibly just sit there waiting for the player to show up, and then let 
the *player* kick things off.

> There's a specific kind of interactive fiction I am interested
> in that addresses these particular issues.

By all means spill it. :-) 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From siffert@shell.wco.com Tue Feb 18 14:07:41 MET 1997
Article: 22372 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.pbi.net!samba.rahul.net!rahul.net!a2i!news.walltech.com!hsnx.wco.com!news.wco.com!shell!siffert
From: siffert@shell.wco.com (Curt Siffert)
Newsgroups: rec.arts.int-fiction
Subject: Multi-player interactive fiction (long)
Date: 15 Feb 1997 06:17:05 GMT
Organization: Finger's Pizza
Lines: 200
Message-ID: <5e3kd1$fb3@news.wco.com>
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com>
NNTP-Posting-Host: shell.wco.com

erkyrath@netcom.com (Andrew Plotkin) sayeth:
>Curt Siffert (siffert@shell.wco.com) wrote:
>
>> Some questions, then, for discussion:
>
>> 1) [Muds vs. Int Fiction]
>
> [unstructured vs. structured]

    (excuse me for over-simplifying; I'm going to try to focus this
    toward my idea.)

    Yes, that does seem to be the dilemma - if the goal is to bring
    in multiple users without sacrificing the integrity of the 
    structured environment, one must find a way to keep the game
    going without any user missing out too much if they don't play
    for a while.  A part of the solution, I think, is not to 
    specifically assign any one game character to any one game
    player.

>> 2) [1st, 3rd person vs. default 2nd person]
>
>A few. "Piece of Mind" from this year's competition plays around with
>first person; the "I" in "I get out of bed" is actually a separate
>character, one who talks to you as well as obeys your commands. 

    That one sounds interesting.  I'll have to play with it.

>I don't recall seeing any third-person experiments. ("Fred gets out of 
>bed.") I don't see any particularly nifty prospects in that area; it 
>seems like it would just distance the player from the action, and I've 
>always liked the closeness of second person. But I'm sure it'll be tried 
>eventually. Or more likely it has and I'm forgetting something obvious.

    Yeah, third person is dangerous.  One the one hand, I believe
    third person can bring a reader closer to a character in terms
    of identifying with a *separate character*, but obviously, if
    the character is understood to be the reader/player, then it
    creates distance from an interactive sort.

    The idea I've been struggling with involves the player not 
    controlling a particular player, but actually controlling the 
    plot itself.  Third person might not be so bad in this case.
    I suppose that this sounds an awful lot like regular prose 
    writing, but I'm also trying to keep the elements of multiple 
    users and interactivity, while maintaining a cohesive universe.

>> 3) Do you see any alternatives in the interactive stage besides
>>     either the choice-making of a cyoa or the brief action-reaction
>>     of a text game?  There is this paradigm of "1. print out the 
>>     description, 2. wait for limited input" that is begging for 
>>     new ideas.
>
>Well, we don't have the technology to understand anything *but* limited 
>input. That kind of forces the issue.

    We don't have the technology if we are focusing on the paradigm of
    human interacting with machine, yes, that's true.  (Again, I'm
    focusing on multiple users, I guess - that's one way to solve that
    issue).  But even with single users, another way to interact would
    be to find a particular point in the story and branch off,
    inventing a new plotline of your own.  This could get disorganized
    very quickly and could go against the idea of a "cohesive playing
    universe", but I think controls could be put in place.

>> 4) [Switching viewpoints with other characters]
>
> [Examples]

    I think just the idea of this is a lot of fun.  =)

>> 5) [Divergent plotlines versus alternate perspectives]
>
>Well, in a sense this is very common -- most games have some kind of 
>"daemon" or "timer" system. If you stay in the room with the time-bomb, 
>it goes off and you die; if you run away, there's a distant boom behind 
>you as you look around the next scene. _Deadline_ was an early Infocom 
>game that had very detailed timed actions going on, involving multiple 
>characters, over an entire day.

    You're right, I guess both are common to a degree.  And I agree
    that it could also be boring - if less happens as a result of the
    character being the nexus, the player could feel like he or she
    isn't exerting very much control over the game.  But perhaps this
    wouldn't be as much of a problem in a multi-user game where the
    point is seeing how outside variables (other players) affect the
    game, and how they are affected by your input.  Maybe that wouldn't
    be boring.

    I think the greatest danger to a group-generated story is the 
    divergent plotlines.  A control would need to be implemented 
    that would keep everyone on the same general saga without
    contradicting each other.  The challenge is for everything in
    the story to happen - when you go back to explore alternate
    pathways, you don't have to be thinking "if I hadn't have 
    chosen what I did, then this would have happened", it could
    be "oh wow, this also happened and I wasn't there!"

>> There's a specific kind of interactive fiction I am interested
>> in that addresses these particular issues.
>
>By all means spill it. :-) 

    It's based off of a couple of things that are popping up all over
    the web, and for all I know it's been done.  I'm afraid I'm still
    in the early stages of idea generation, so this may be raw and in
    need of brainstorming, but okay.

    The main distinctive trait of this game is that the "players" would
    either be readers or writers.  Someone could either check back in to 
    see how their favorite plotline is going, or they could participate
    in writing to a thread.  This rules out the more interactive 'tweeners
    that most of us are when we play an infocom game, at least until I 
    figure out a way to let a "reader" participate more without writing
    significant material.

    Yes, that sounds like your basic add-to story.  But the twist is
    that the plotlines wouldn't be divergent.  There would be a master
    timeline that is created as the stories are written, that everyone
    adheres to.  That is what makes it interactive of a sort - every
    plot writer can affect the overall makeup of the game by writing 
    about something that the other plots may have to react to.

    I run a creative writing mailing list that enjoys creating group
    novels.  One person submits one chapter.  It's fun and all, but can
    die easily, and it's very prone to plot contradictions.  I think that
    it can be successful on a larger scale with more moderating control
    and modularity.

    Here's how it could work:

    A plot is started by a group of people, for instance my mailing list.
    Six or eight episodes are written, characters are introduced into
    the narrative.  There are various points that would be eligible for
    spinning off into another plot that happens concurrently.  There
    would be readers that (I assume, I hope) would be interested in 
    joining in and submitting writing for another thread.  For every 
    thread, there would need to be one group of writers and one moderator.
    The moderator would have to agree to make sure the thread they are
    maintaining stays within the scope of the game.

    Here's the trick - every episode has a length of game time associated
    with it, so the entire game would be synchronized to a master 
    calendar.  The moderator of each thread would submit "major events"
    that may have happened in that episode.  These events could be 
    reported to the other threads and incorporated into the plots.
    This would hopefully ensure that plot contradictions between 
    threads would be kept to a minimum.  If Sally dies in thread four,
    Rob wouldn't be calling her on the telephone three days later in 
    thread seven.

    The master calendar, the macroplot, whatever, *does not exist*
    before the game starts - it is created on the fly by all the
    writers.

    Every group of writers may find their threads branching out a 
    bit here and there - they could leave the opportunity for other
    groups to take over diverging threads.  If too much game time
    elapses, the opportunities would expire.  (If the game is at 
    March 1st and there was an opportunity left open on game time
    Jan 15th, it wouldn't do to make a volcano explode on an island
    on 1/21 when another thread had already written about a luau
    on 1/22.)  Conversely, if any one thread gets too far ahead, 
    perhaps it could be frozen until the others catch up in game 
    time (although this doesn't address the possibility of one
    group of writers losing interest and abandoing their thread).

    Readers would be entertained by watching the plot grow, or by
    attempting their hands at writing, or perhaps even some sort of
    plot suggestion voting system could be rigged up at some point.

    

    Anyway, those are along the lines I'm thinking.  It wouldn't really
    even take a lot of programming; it's more of a plot management
    system.  It *could* be more automated, like a database program
    could demand the elapsed time of each episode, the major events,
    and distribute them all automatically.  Or it could be done by a
    master moderator that doesn't actually read all the threads, but 
    just goes by the events and synopses.

    The cool thing about it is that each story potentially ends up as
    a grand sweeping saga - the readers don't necessarily have to read
    all the threads if they don't want to, since the larger events 
    would be referred to in the threads they do read (and linked back
    and forth by hypertext).  Finally, this is pretty much all in 
    the magazine submission paradigm - any chapter of writing is 
    copyrighted and owned by the author, while the collection is
    copyrighted by the hosts of the game.  This opens up the possibility
    of culling for some manner of publication later, with authorship
    credits retained and exposure being given all around.

    That's what I've got for now.  I'd love comments on what you think
    might work, as well as pitfalls to look out for or suggestions for
    improvement.

    Thanks!

    Curt Siffert



From florian.beck@lrz.uni-muenchen.de Tue Feb 18 14:08:55 MET 1997
Article: 22376 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!fu-berlin.de!informatik.tu-muenchen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: Sat, 15 Feb 1997 14:38:33 GMT
Organization: Private GNU Site
Lines: 138
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m33euygmmu.fsf@ue801di.lrz-muenchen.de>
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com>
Reply-To: florian.beck@lrz.uni-muenchen.de
NNTP-Posting-Host: dial164.ppp.lrz-muenchen.de
X-Newsreader: Red Gnus v0.83/Emacs 19.34

erkyrath@netcom.com (Andrew Plotkin) writes:
> Curt Siffert (siffert@shell.wco.com) wrote:
> > Some questions, then, for discussion:
> 
> > 1) How are most of these already existing interactive fiction games
> >     different from muds, aside from the multi-user aspect?  Or 
> >     alternatively, what is it about these games that makes you want 
> >     to play them as opposed to playing a mud?  The followup questions
> >     would be, what elements of interactive fiction should be concentrated 
> >     on to make it distinctive from a mud? (aside from the single-player 
> >     nature)  Or, how could multiple players be introduced to 
> >     interactive fiction without it turning into a mud?

I've never played one (any starters?) so I can't say anything about
MUDs. But I would say that single vs multi-player is not a minor issue
in IF. If the players have control over your world I'm sure the story
will loose some depth: In a good story every single sentence and every
single object has it's purpose; which might not be revealed at first
sight. How do you do this, when the story is created by several
persons? 

On the other hand you might gain something. Perhaps spontaneity,
perhaps new ideas, perhaps creativity. Surely worth experimenting
with. But plot would have a completely different standing in
"infocommish" and multi-player IF. "Infocommish" IF has it's own
difficulties concerning plot.

[...]

> > 2) Have there been many experiments with using first or third 
> >     person as opposed to the traditional second person approach?
[...]

> A few. "Piece of Mind" from this year's competition plays around with
> first person; the "I" in "I get out of bed" is actually a separate
> character, one who talks to you as well as obeys your commands. 
> 
> I don't recall seeing any third-person experiments.

First and third person might help adopting traditional fiction;
writing more traditionally. Though this might not be desirable. 

On the other hand, a growing distance between player and character
may be a good idea (e.g. addressing moral issues, switching characters,
very detailed character personality).

[...]

 
> > 3) Do you see any alternatives in the interactive stage besides
> >     either the choice-making of a cyoa or the brief action-reaction
> >     of a text game?  There is this paradigm of "1. print out the 
> >     description, 2. wait for limited input" that is begging for 
> >     new ideas.
> 
> Well, we don't have the technology to understand anything *but* limited 
> input. That kind of forces the issue.

How about this: The player gets a (finished) story to read. Then he
can change the initial conditions: What he takes with him in the
morning, what bus to take, how much money, whom to visit, etc;
perhaps even more general conditions like weather, season, time of day
or meta conditions like where the character lives, what job he has,
and so on.

But I can think of only one way of implementing this: writing a
separate story for *each* combination (which is - even if possible -
quite beside the point). You could make a simulation, sure, but where
to put the plot?

> > 4) What of switching viewpoints with another character?  Has this
> >     been experimented with?  
[...]
Switching viewpoints is just a special case. You can also switch time
and place (real switch not just walking from one room to
another). Those switches (cf dramatic unities) are to be handled
carefully as they are quite "hard" in IF (unlike in novels but
similar to theatre).

I have been planning a game where you would direct all the
characters. There would be *no* Player. You would type:

>Tim, pick up basket
Tim stoops and picks up the yellow basket.
>Tom, hit Tim
Tom walks over to Tim and smacks him hard. Tim topples over, dropping
the basket and the newspaper he is  carrying.

One idea was to avoid 'You can't do that' answers. The orders really
would only be suggestions:

>Tim, hit Tom
Tim struggles to his feet. He clenches his fists and looks at Tom
furiously. Tom apologises but Tim needs several minutes to calm down.

Or even:

>Tim, jump through window
Tim walks over to the window and opens it. Ah, a fresh evening
breeze. He takes a look over the garden. Justine and Mary are sitting
near the fountain and wave to Tim. He studies the walkway some dozen
feet below, then returns from the window.

Of course, this would get out of hand pretty soon, even for small sets
of characters. Not to speak of other problems.

> 
> > 5) Cyoa's usually involve choices which create divergent plotlines - 
> >     choose one path, and the result of the path you *didn't* choose
> >     never happens.  That's like saying that a tree falling in a forest
> >     with no one around doesn't make a sound.  I guess it's a question
> >     of philosophy, but has anyone experimented in the matter of 
> >     outside events happening without being a function of the 
> >     character's interaction?  Result of path B *still* happens,
> >     you just weren't there to see it.  I guess this does happen
> >     sometimes, but it still seems to be the exception rather than
> >     the rule.
> 
> Well, in a sense this is very common -- most games have some kind of 
> "daemon" or "timer" system. If you stay in the room with the time-bomb, 
> it goes off and you die; if you run away, there's a distant boom behind 
> you as you look around the next scene. _Deadline_ was an early Infocom 
> game that had very detailed timed actions going on, involving multiple 
> characters, over an entire day.
> 
> I think this is less common these days because it can easily lead to a lot
> of *boring stories*. 

Or to no stories at all. Think of it. Take a novel, a short story, a
play. What could have been done different? Well, almost anything. But
then there would have been no story at all (like Macbeth hadn't killed
Duncan, Bilbo hadn't picked up the ring or Bloom had decided to stay
at home). The author might have made a *different* story out of it,
sure. But ceteris paribus, omitting a critical act will destroy the
story.

-- 
Flo


From erkyrath@netcom.com Tue Feb 18 14:09:46 MET 1997
Article: 22404 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Other forms of interactive fiction
Message-ID: <erkyrathE5o59C.37M@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com> <m33euygmmu.fsf@ue801di.lrz-muenchen.de>
Date: Sat, 15 Feb 1997 23:58:24 GMT
Lines: 35
Sender: erkyrath@netcom22.netcom.com
Xref: news.lth.se rec.arts.int-fiction:22404

Florian Beck (fb@ue801di.lrz-muenchen.de) wrote:
> I've never played one (any starters?) so I can't say anything about
> MUDs. But I would say that single vs multi-player is not a minor issue
> in IF. If the players have control over your world I'm sure the story
> will loose some depth: In a good story every single sentence and every
> single object has it's purpose; which might not be revealed at first
> sight. How do you do this, when the story is created by several
> persons? 

> On the other hand you might gain something. Perhaps spontaneity,
> perhaps new ideas, perhaps creativity. Surely worth experimenting
> with. But plot would have a completely different standing in
> "infocommish" and multi-player IF. "Infocommish" IF has it's own
> difficulties concerning plot.

I'd say that this jump, to multi-player shared-authorship stories, is so
large that it's really a switch to an entirely new art form -- one 
closely related to improv theater and RPG campaigns. It's a much larger 
difference than the difference between a written novel and an 
Infocom-style game. There can be many people creating a story, or there 
can be one person creating a story and many people reading it.

If I proposed "interactive theater" (IT) as a term to be contrasted with 
IF, would you all throw tomatoes?

(I'm not at all saying that it doesn't belong on "rec.arts.int-fiction", 
of course. If rec.arts.sf.* can accomodate fantasy, r.a.if can accomodate 
IT. :-)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From foxglove@globalserve.net Tue Feb 18 14:10:05 MET 1997
Article: 22408 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!Oslo2.Norway.EU.net!Norway.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news-xfer.netaxs.com!hammer.uoregon.edu!zephyr.texoma.net!uunet!in1.uu.net!204.191.213.61!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: Sun, 16 Feb 1997 01:06:06 -0500
Organization: Envision This
Lines: 49
Message-ID: <3306A3CE.1780@globalserve.net>
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com> <m33euygmmu.fsf@ue801di.lrz-muenchen.de>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin276.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22408

Florian Beck wrote:
> 
> I have been planning a game where you would direct all the
> characters. There would be *no* Player. You would type:
> 
> >Tim, pick up basket
> Tim stoops and picks up the yellow basket.
> >Tom, hit Tim
> Tom walks over to Tim and smacks him hard. Tim topples over, dropping
> the basket and the newspaper he is  carrying.
> 
> One idea was to avoid 'You can't do that' answers. The orders really
> would only be suggestions:
> 
> >Tim, hit Tom
> Tim struggles to his feet. He clenches his fists and looks at Tom
> furiously. Tom apologises but Tim needs several minutes to calm down.
> 
> Or even:
> 
> >Tim, jump through window
> Tim walks over to the window and opens it. Ah, a fresh evening
> breeze. He takes a look over the garden. Justine and Mary are sitting
> near the fountain and wave to Tim. He studies the walkway some dozen
> feet below, then returns from the window.
> 

This is exactly the way I'm writing my current project. Two suggestions though. 
If no specific character is addressed, default to the last one used. Nobody wants 
to be typing "Tim, nw" six times in a row. And the second suggestion is to list 
the current "default" character in the status line, as in "Tom: Round Room". 
Then, you only have to type names when you switch perspective. Also make sure you 
can set one character to "permanently" follow another so that you can travel as a 
"party", if that is allowed.

The disadvantage I have encountered myself is that it becomes impossible to 
implement the standard accepted way of having one character order another. What 
was once "Floyd, go north" must now become "Tom, tell floyd to go north", or in 
the best case scenario (if Tom is already your default), "Floyd, n" becomes "Tell 
Floyd n". The only way around this is to make *every* character directly 
controllable by the player. Not a pretty prospect. Furthermore "ask about" and 
"tell about" become the only ways to converse.

Nevertheless, I think that on balance it will be a very intriguing style of play.

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From erkyrath@netcom.com Tue Feb 18 14:10:35 MET 1997
Article: 22403 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: TinyMUD (Re: Other forms of interactive fiction)
Message-ID: <erkyrathE5o4t4.2Er@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com>  <ant151632d07c4bn@arnod.demon.co.uk>
Date: Sat, 15 Feb 1997 23:48:40 GMT
Lines: 50
Sender: erkyrath@netcom22.netcom.com
Xref: news.lth.se rec.arts.int-fiction:22403

Julian Arnold (jools@arnod.demon.co.uk) wrote:
> In article <erkyrathE5MoIq.A57@netcom.com>, Andrew Plotkin
> <URL:mailto:erkyrath@netcom.com> wrote:
> > 
> > This is not an uninteresting question. :) My experience with MUDs is 
> > limited (despite the award ceremony last week). This is precisely 
> > because the Great MUD Explosion of 1989 (TinyMUD and its descendants) 
> > was a set of social environments -- as opposed to both puzzles and works 
> > of fiction. I played around with simple puzzle-story scenarios in 
> > TinyMUD and Islandia, but I was in a small minority. Most people wanted 
> > to hang out with each other, not explore.

> Hang on, Andrew.  This is the second time this week you've closely
> associated your name with this TinyMUD (which I had never heard of
> before).  You seem to be implying:
> 	a) You (co-)wrote TinyMUD, and
> 	b) TinyMUD spawned all the others.

> And thus:
> 	c) You are responsible for MUDs.

> Is this what you're saying, or am I mad?

You're mad. :)

I had nothing to do with TinyMUD, but it happened at my school. I got 
back from summer vacation, starting my second year, and found that 
everyone was hypnotized by this *thing* running on Jim Aspnes's 
workstation, down in the bowels of Wean Hall. (Aspnes was a grad student 
at CMU; I think he's now at Yale.)

So I was "just there from the beginning." Give or take several months. I 
think I was slightly notable as a builder, mostly because I was 
interested in building and everyone else was interested in talking, so I 
did more than a lot of other people.

As for (b), TinyMUD was not the first MUD; there was LPMUD earlier, and 
possibly others. But I believe TinyMUD was the first entirely 
Internet-based MUD (telnet as opposed to dial-up.) And all the evolution 
of MUCK, MUSH, and MOO either started with TinyMUD source code or were 
directly inspired by it.

Anyone with a better sense of history is welcome to correct me.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From jools@arnod.demon.co.uk Tue Feb 18 14:29:45 MET 1997
Article: 22389 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!feed1.news.erols.com!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: Sat, 15 Feb 1997 15:53:46 +0000 (GMT)
Organization: Organisation name, location. Telephone/Fax?
Message-ID: <ant151546b49c4bn@arnod.demon.co.uk>
References: <5e2hve$4rd@news.wco.com> 
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 101
Xref: news.lth.se rec.arts.int-fiction:22389

In article <5e2hve$4rd@news.wco.com>, Curt Siffert
<URL:mailto:siffert@shell.wco.com> wrote:
> 
> 
> I've been spending a lot of time thinking about interactive fiction
> lately, on my own and with my creative writing group.  I just recently
> came across this group and was intrigued.
> 
> However, most of the discussion seem to be in only one area of
> interactive fiction, the infocommish sort.  Not to knock it, I loved
> those games, and even feel a bit of goofy pride that I was able to
> solve "Sorcerer" without a hint book.  But with the web and the
> possibilities of networking and community, I'm wondering what other
> kinds of interactive fiction people are working to develop.
> 
> Some questions, then, for discussion:
> 
> 1) How are most of these already existing interactive fiction games
>     different from muds, aside from the multi-user aspect?  Or 
>     alternatively, what is it about these games that makes you want 
>     to play them as opposed to playing a mud?  The followup questions
>     would be, what elements of interactive fiction should be concentrated 
>     on to make it distinctive from a mud? (aside from the single-player 
>     nature)  Or, how could multiple players be introduced to 
>     interactive fiction without it turning into a mud?

I know almost nothing about MUDs.  I guess one reason people write
(single-player) IF rather than (multi-player) MUDs is that as soon as
you allow multiple human players into your game you're relinquishing a
huge chunk of authorial control.  Each player has conflicting intent,
wants to do their thing at the same time as everyone else, etc.  This
problem is discussed, somewhat superficially, in "The Stage as a
Character: Automatic Creation of Acts of God for Dramatic Effect"
(http://rhodes.www.media.mit.edu/people/rhodes/Papers/aaai95.html).  One
reason to play IF and not MUDs is that IF is cheaper (it can be played
off-line). :)

> 2) Have there been many experiments with using first or third 
>     person as opposed to the traditional second person approach?
>     (YOU see a leaflet in the mailbox.)

A few.  But I can't think of any just now.  I'm sure someone else will
post some examples.  Different tense (past, not present) is interesting
too.  No-one ever tries future tense... :)

> 3) Do you see any alternatives in the interactive stage besides
>     either the choice-making of a cyoa or the brief action-reaction
>     of a text game?  There is this paradigm of "1. print out the 
>     description, 2. wait for limited input" that is begging for 
>     new ideas.

Of course, the main problem here is coming up with the new ideas.  A
second problem is that to implement a substantially different paradigm
one would probably need to develop a new authoring system, and not
everyone can do this (I can't).  A third "problem" is that many people
(authors and players alike) are happy with the current format-- IMO
Infocommish IF has not yet been exhausted, not nearly.  This is of
course no reason not to experiment.

> 4) What of switching viewpoints with another character?  Has this
>     been experimented with?  You are Detective Bob trying to solve
>     a crime, and you run into Hooker Harriet.  You then switch - 
>     you are Hooker Harriet living the seedy night life for a few
>     nights.  (And then you could switch to a congressman!) All the 
>     while, Detective Bob is still on the case.

I've experimented with this a bit (unreleased), and I think it is an
extremely useful, powerful, and novel approach.  Infocom's "Suspended"
and "HHGTTG" did this a bit.

> 5) Cyoa's usually involve choices which create divergent plotlines - 
>     choose one path, and the result of the path you *didn't* choose
>     never happens.  That's like saying that a tree falling in a forest
>     with no one around doesn't make a sound.  I guess it's a question
>     of philosophy, but has anyone experimented in the matter of 
>     outside events happening without being a function of the 
>     character's interaction?  Result of path B *still* happens,
>     you just weren't there to see it.  I guess this does happen
>     sometimes, but it still seems to be the exception rather than
>     the rule.

This is rare, I think (again, examples elude me).  The role of the PC as
centre-of-the-universe is a very well-ingrained tradition in IF.  A
couple of recent attempts at multiple, mutually exclusive plotlines are
"Tapestry" and "I-0" (both Inform).

> There's a specific kind of interactive fiction I am interested
> in that addresses these particular issues.  I'm hoping to launch it
> off my web page in the next few months.  I'm still trying to spec it 
> out, because right now it's still kind of gnarled in my mind, but it's
> gradually becoming more cohesive.  I thought that getting your thoughts 
> on the above matters might help my thought process.

Hope so.

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from  ever completing anything." -- Herman Melville, "Moby Dick"



From foxglove@globalserve.net Tue Feb 18 14:40:51 MET 1997
Article: 22406 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!nntp.uio.no!newsfeeds.sol.net!news.ececs.uc.edu!news.kei.com!news.thenet.net!uunet!in3.uu.net!204.191.213.61!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: Sun, 16 Feb 1997 00:49:52 -0500
Organization: Envision This
Lines: 71
Message-ID: <3306A000.39EA@globalserve.net>
References: <5e2hve$4rd@news.wco.com>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin276.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22406

Curt Siffert wrote:
> 
> 1) How are most of these already existing interactive fiction games
>     different from muds, aside from the multi-user aspect?  Or

Infocom-style IF currently suffers from "story shortage", which is probably 
due to the constraints of the medium putting a lot of burden on author to 
manipulate story without seeming to be a puppeteer. However, compared to 
even the best MUD I've seen (and my experience is not that extensive), even 
something like "Planetfall" suddenly looks like a full-length novel. 
Considering your post, which focuses on story, I would think the current MUD 
setup would be a step in the wrong direction. But I read Andrew's post and 
he's right: maybe nobody has really used MUDs to their potential.

> 2) Have there been many experiments with using first or third
>     person as opposed to the traditional second person approach?
>     (YOU see a leaflet in the mailbox.)

Not many, and none very successfully. But then, I haven't seen an example 
that takes advantage of the full range of characterisation that this would 
allow. My current project is third person IF. A debate crops up here 
occasionally which boils down to: less emotional distance (2nd person) vs. 
better characterisation (1st/3rd person). Some argue that second person 
provides an essential feeling of immersion. I don't really think of it as a 
trade-off. I would argue that being able to witness and identify with the 
main character's emotional states provides a different, perhaps more 
effective level of immersion. I think the desire for emotional 
identification is out there, but it's usually displaced into debates about 
the quality of supporting characters, i.e. sidekicks.

> 
> 3) Do you see any alternatives in the interactive stage besides
>     either the choice-making of a cyoa or the brief action-reaction
>     of a text game?  There is this paradigm of "1. print out the
>     description, 2. wait for limited input" that is begging for
>     new ideas.
> 

Here is where you and I would part ways. I *do* think that the short 
action-reaction exchange is a mainstay of a highly interactive work. 
Learning to tell a story in rearrangeable little blocks is just part of the 
craft. Also, there is currently no method of input less limited than the 
Infocom-style parser, including web-style hypertext links. The reason the 
parser has fallen out of general favour has nothing to do with its limits 
and everything to do with the demands it makes on the user.

> 4) What of switching viewpoints with another character?  Has this
>     been experimented with?  You are Detective Bob trying to solve
>     a crime, and you run into Hooker Harriet.  You then switch -
>     you are Hooker Harriet living the seedy night life for a few
>     nights.  (And then you could switch to a congressman!) All the
>     while, Detective Bob is still on the case.
> 

I believe that this goes hand-in-hand with the third-person style: combined, 
these two features should go a long way toward pinpointing IF's strengths 
when compared to an all-graphic game. A "third person" video would have to 
show the main character as part of the action. That entails different video 
for each character. It's useful to think of the amount of work required 
(both from the author and the CPU) roughly as the NUMBER OF LOCATIONS times 
the NUMBER OF PLOT BRANCHES times the NUMBER OF CHARACTERS times the SIZE OF 
THE DATA. Then you can see how much bigger an impact plot complexity and 
multiple perspectives would have in, say, a completely full-motion video 
environment. On the other hand, a hybrid environment could give you the best 
of both worlds. I realise you didn't really mention graphics: I'm just 
wandering in an aimless and long-winded manner.

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From whizzard@uclink.berkeley.edu Tue Feb 18 14:41:41 MET 1997
Article: 22410 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!nntp-oslo.UNINETT.no!nntp-trd.UNINETT.no!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: 16 Feb 1997 07:01:56 GMT
Organization: University of California at Berkeley
Lines: 29
Message-ID: <5e6bd4$i4d@agate.berkeley.edu>
References: <5e2hve$4rd@news.wco.com> <3306A000.39EA@globalserve.net>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:22410


Well, I haven't tooted my own horn for a few days, what the hell.  Avalon,
while written in second person (when I started writing it I was too
inexperienced to really do it any other way,) is not about the ubiquitous
YOU, it's about Frank Leandro.  It asks you to step into his shoes for
awhile, and pretend you're him.  It's not seamless, and not entirely
perfect mimesis-wise, but it's there.

Frank has a past, which is established throughout the story, as necessary
either to the game, or the atmosphere.  He has a personality, which is
established in the way he reacts to your commands and the dialogues
between him and the NPCs.

To me, it simply seems odd to have to write a story in which I can reveal
absolutely nothing about the main character's feelings, thoughts, etc.  I
mean, a good story has the characters grow and change over time, but how
can I do that unless I establish some starting point for change to occur
from.

Simply, whether or not it is well received, it is more satisfying for me
to write if I have an interesting main character to play with.  Just look
at Gabriel Knight.  Despite its many, many flaws, it was one of the most
popular graphic adventures around.  It couldn't have been because of the
wretched, often unfair puzzles.  The story was decent, if slow to start,
but the characters, especially Gabriel himself, are fascinating.

All imho, of course.
-- 
	"Ha.  Made ya look!"


From jota@laraby.tiac.net Tue Feb 18 15:27:31 MET 1997
Article: 22484 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in3.uu.net!199.0.65.182!news-in.tiac.net!posterchild!laraby.tiac.net!jota
From: jota@laraby.tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: 18 Feb 97 11:56:39 GMT
Organization: The Internet Access Company, Inc.
Lines: 41
Message-ID: <jota.856266999@laraby.tiac.net>
References: <5e131u$k8a@Turing.Stanford.EDU> <5e30qi$mvr@nntp5.u.washington.edu> <3308B915.1A3A@globalserve.net> <5eamgu$ru@nntp5.u.washington.edu>
NNTP-Posting-Host: laraby.tiac.net
X-Newsreader: NN version 6.5.0 #1 (NOV)
Xref: news.lth.se rec.arts.int-fiction:22484

mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) writes:
>In article <3308B915.1A3A@globalserve.net> foxglove@globalserve.net writes:

>>That's interesting. Even though I also knew in advance that they were to be 
>>gender non-specific, and that there was to be a romantic involvement, I just 
>>couldn't get the concept out of my head that White and Black were gay males. 
[snip]

>Both male is the assignment I started with, but (maybe because I
>recently became acquainted with a person named Black in another context,
>and she was female) I couldn't get Black to settle down into that
>assumption.  I then tried to persuade White to be female too--I was
>trying hard to avoid stereotypes!--but failed.  Being female myself didn't
>seem to make any difference.

I find it very interesting that you were trying to force the characters
into roles that you didn't find natural, simply because you wanted to
avoid stereotypes. isn't it more important to let the character be who
they are (that is, to read the story, and let the characters develope as
they will) than to set them unnaturally?

>I've heard of players who made your set of assignments, and players who
>made mine; never the other two, though.  I wonder whether that's a
>function of the text or some societal mindset?

Am I that much of a weirdo?

I started out with both Black and White as fairly nebulous, intentionally.
I wanted to play, and let the characters give me whatever impression of
themselves I would get from them. Oddly enough, I leaned strongly towards
White as female and Black as male. I think it has mainly to do with the
personalities the characters exhibited: Black exhibited traits of being a
leader, of being egotistical, and of always message things up. White
appeared to be following behind, staying in the background, and always
fixing everything that Black was doing wrong.

BTW, I'm personally a male. Feel free to psychoanalyze me at will :)
--
                                      /<-= Admiral  Jota =->\
                                    -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  -= -=->/


From flanagan@students.uiuc.edu Tue Feb 18 16:30:26 MET 1997
Article: 22495 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!vixen.cso.uiuc.edu!ux9.cso.uiuc.edu!not-for-mail
From: flanagan@students.uiuc.edu (john thomas flanagan)
Newsgroups: rec.games.roguelike.misc,rec.arts.int-fiction
Subject: Re: Old "Roguelike-like" games (was Re: Graphics and ADOM)
Followup-To: rec.games.roguelike.misc,rec.arts.int-fiction
Date: 18 Feb 1997 14:17:53 GMT
Organization: University of Illinois at Urbana
Lines: 23
Message-ID: <5ecdmh$cqr@vixen.cso.uiuc.edu>
References: <5dcer8$mg4@oban.cc.ic.ac.uk> <19970209054300.AAA26533@ladder01.news.aol.com> <3300950F.27092660@alcyone.com> <3301431a.9943260@news.internetland.net> <sheldon-1202970338520001@lpm2-19.atlcom.net> <5dt78i$7fj$1@mark.ucdavis.edu> <sheldon-1202971631030001@lpm2-27.atlcom.net> <5ebo3d$c68@bolivia.earthlink.net>
NNTP-Posting-Host: ux9.cso.uiuc.edu
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.games.roguelike.misc:8041 rec.arts.int-fiction:22495

grundman (Allspammers@mustdie!.com) wrote:
: Wow.
: Okay guys, if you want to go WAAY back (whats the average age here
: anyway?), does anyone remember some of the truely 'first' computer rpgs?

The first one I ever played was called Oldorf's Castle.  It was written 
in basic (and reading through the source taught me a lot about 
programming- I was in 4th grade at the time).  It used Apple's HIRES 
graphics mode, and you could watch as the lines and dots get plotted on 
the screen, since it was so slow.  You wandered around a maze collecting 
treasure and solving puzzles, by using the ability to change between 
different classes that could do different things.  As a Strongman you 
could move things, as a Cleric you could read, as a Swordsman you could 
kill things (once you found the sword), and so on.

After that, I got Wizardry: Proving Grounds for the Mad Overlord, which I 
thought was absolutely awesome.  I played through it again using an Apple 
emulator just a few months ago, and was stunned at how primitive it seems 
now.

-- 
John Flanagan
flanagan@uiuc.edu


From jota@laraby.tiac.net Tue Feb 18 16:31:21 MET 1997
Article: 22494 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!news.zeitgeist.net!wizard.pn.com!news.gte.com!news-in.tiac.net!posterchild!laraby.tiac.net!jota
From: jota@laraby.tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction
Subject: Re: Warning messages: good? bad?
Date: 16 Feb 97 21:08:50 GMT
Organization: The Internet Access Company, Inc.
Lines: 47
Message-ID: <jota.856127330@laraby.tiac.net>
References: <33070068.40E6@acpub.duke.edu> <5e7eld$435@lyra.csx.cam.ac.uk>
NNTP-Posting-Host: laraby.tiac.net
X-Newsreader: NN version 6.5.0 #1 (NOV)
Xref: news.lth.se rec.arts.int-fiction:22494

rgs20@cam.ac.uk (Richard Stamp) writes:
>In article <33070068.40E6@acpub.duke.edu>,

[Adam Cadre asked if people thought I-0 should have a warning at the
start.]

>Well, you asked for opinions, so here's mine:

[Richard thinks there should be some warning, but notes that too specific
a warning course affect players' perceptions of the game, or could give
away spoilers.]

>With all this in mind, my preference would be for a bland general
>warning along the lines of

>  Certain paths through I-0 have adult content and may not be
>  suitable for children.

>I don't think this spoils any of the surprises -- I'd guess that most
>people would come quite quickly on the hitchhiking scene and think
>"Ah, so that's what he means".  But I think it's an adequate warning.
>If you felt the need to be more explicit you could add something like

>  If you would like to know more about this, type PARENTS
>  to see a longer explanation (which contains some spoilers).

>...with the command PARENTS bringing up the full warning you
>had before.

I agree with what you're saying, but I think I'd make one small
modification to your warning:

  Certain paths through I-0 have adult or violent content and may 
  not be suitable for children.

I tihnk that if the warning is phrased this way, it won't be quite so
obvious that the objectionable material is sexual, and so the player won't
be as likely to be spoiled about the 'fun' sexual content of the game.
Another useful aspect of this version of the disclaimer is that it's more
informative to a parent, because there are some parents who wouldn't mind
their kids playing LGoP on lewd mode, but wouldn't want their kids to play
through a rape scene.

--
                                      /<-= Admiral  Jota =->\
                                    -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  -= -=->/


From meta@pobox.com Tue Feb 18 16:31:45 MET 1997
Article: 22498 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!uunet!in1.uu.net!198.3.232.58!epcot.harlequin.com!win7-dhcp.harlequin.com!user
From: meta@pobox.com (mathew)
Newsgroups: rec.arts.int-fiction
Subject: Re: Warning messages: good? bad?
Date: Tue, 18 Feb 1997 09:45:26 -0500
Organization: Otter Obsessives Anonymous
Lines: 19
Message-ID: <meta-1802970945270001@win7-dhcp.harlequin.com>
References: <33070068.40E6@acpub.duke.edu>
NNTP-Posting-Host: win7-dhcp.harlequin.com
X-newsreader: MT-NewsWatcher 2.2.2
X-Attribution: ><(([@
X-Files: The Truth Is Out There
Xref: news.lth.se rec.arts.int-fiction:22498

In article <33070068.40E6@acpub.duke.edu>, adamc@acpub.duke.edu wrote:
> This also made a lot of sense.  So now I'm of two minds about whether
> to leave the warning in for Release 3.  What do you think?

How about:

NOTE: This game may display textual descriptions of violent or sexual acts.

I like it because
1. it's purely factual, with no value judgements,
2. it draws a clear distinction between sex and violence,
3. it gives minimal spoilers to the reader, and
4. it won't lead nave parents to think that the game's suddenly going to
display images.


mathew
-- 
http://www.pobox.com/~meta/


From foxglove@globalserve.net Tue Feb 18 17:47:47 MET 1997
Article: 22503 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!news.stealth.net!zephyr.texoma.net!www.nntp.primenet.com!nntp.primenet.com!winternet.com!n1ott.istar!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: Tue, 18 Feb 1997 01:12:47 -0500
Organization: Envision This
Lines: 47
Message-ID: <3309485F.2DD3@globalserve.net>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dqar9$lsj@bartlet.df.lth.se> <3300B583.41C6@greenhouse.llnl.gov> <3308deb1.777158@news.netspace.net.au>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin672.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22503

James Cole wrote:
> 
> Kathleen Fischer <kfischer@greenhouse.llnl.gov> wrote:
> 
> >However, nobody like the name "Best Parser" and everybody fussed about
> >"Best Mimesis" (sp?) so I thought the title Best PC might be more
> >palateable.
> >
> >What do you think?
> 
> I like it.

Just as a follow-up to my other post, I thought it would be more responsible to 
offer constructive suggestions instead of simply criticisms. But first, more 
criticisms. <g>

"Best Parser": As has been stated, confuses the game with the design environment.

"Best Use of Parser": Kludgy. But accurate.

"Best Parsing": Obscure. Sounds like splitting hairs.

"Best Mimesis": Don't get me started. I really dislike this word as an evaluation 
tool. A good game does not have to be transparent, unless it wants to be 
transparent. An example of "good bad mimesis" is Hitchiker's: putting an item 
called "no tea" in your inventory, and then admonishing the player for referring 
to it is lousy mimesis. And yet, it is a very inventive use of the parser. It 
just "wanted" to be opaque.

Anyway, for the constructive part, I think the way to avoid the "duelling 
platforms" when rating "Best Parser" is to specify exactly what makes a parser of 
any style good, without imposing "transparency" as a goal. I would think that a 
good parser of any flavour just anticipates well. And this has little to do with 
the type of parser, i.e. TADS or Inform, but rather to do with how well the 
author thinks through what might be tried and how.

So a few suggestions along this vein...
"Best Anticipator"
"Best Lexicon"
"Most Responsive"

Also, as a separate category on its own, I think "Best PC" is just dandy.

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From graham@gnelson.demon.co.uk Tue Feb 18 20:49:05 MET 1997
Article: 22517 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!rill.news.pipex.net!pipex!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Crowther v. Woods
Date: Mon, 17 Feb 1997 23:15:07 +0000 (GMT)
Organization: none
Message-ID: <ant1723071cbM+4%@gnelson.demon.co.uk>
References: <33075D0D.2D3D@globalserve.net> <5e9vk5$2t0@cnn.Princeton.EDU> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 32
Xref: news.lth.se rec.arts.int-fiction:22517

In article <5e9vk5$2t0@cnn.Princeton.EDU>, Adam J. Thornton
<URL:mailto:adam@yuma.Princeton.EDU> wrote:
[Speculation on introducing Crowther and Woods as NPCs in their
own game.]

> The Crowther and Woods would be especially endearing since the parts that
> are cave simulation are mostly Crowther and the parts that are mostly Woods
> are the Tolkeinesque/fantastic elements.  For instance, in the Dome Room
> you can have Crowther happily scrambling around the walls checking for
> missed exits while Don Woods tries unsuccessfully to get the muck off his
> pants.  On the other hand, at the Grand Vista, you can have Woods beaming
> happily and pointing out his magnificent writing as Will Crowther says
> "Right.  A *live volcano* in a limestone cave.  Sure, Don.  *Where*,
> exactly, did you learn your geology?"  Likewise with the dwarf: Woods
> shouts something in Dwarvish and throws the knife back, while Crowther just
> looks disgusted.  This would be a scream if done well.

All true enough, but Crowther's original wasn't totally geology --
the snake and bird puzzle was Crowther's, I think, and there
were "about five treasures", mostly just tokens to reward exploring
in depth.

Oddly, I think the literary merit of Advent is mainly caused by
the tension between Crowther's text and Woods's.  A game written
by either alone would not have the same appeal, just as the
weakest sections of Advent are those predominantly by one author
(e.g. across the chasm, by Woods, or some of the messy geography,
by Crowther).  That said -- Crowther was the more original author.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From ldaly@bu.edu Tue Feb 18 21:34:30 MET 1997
Article: 22519 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.pbi.net!cbgw3.lucent.com!cbgw2.lucent.com!news.bu.edu!cgl!ldaly
From: ldaly@bu.edu (Liza Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: 18 Feb 1997 19:24:27 GMT
Organization: Boston University
Lines: 50
Message-ID: <5ecvlb$32v@news.bu.edu>
References: <5e2hve$4rd@news.wco.com> <erkyrathE5MoIq.A57@netcom.com>
NNTP-Posting-Host: cgl.bu.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:22519

Andrew Plotkin (erkyrath@netcom.com) wrote:
: Curt Siffert (siffert@shell.wco.com) wrote:

: > 1) How are most of these already existing interactive fiction games
: >     different from muds, aside from the multi-user aspect? 

: This is not an uninteresting question. :) My experience with MUDs is 
: limited (despite the award ceremony last week). This is precisely 
: because the Great MUD Explosion of 1989 (TinyMUD and its descendants) 
: was a set of social environments -- as opposed to both puzzles and works 
: of fiction. 

There have been some other attempts.  The only MUD I've ever played
at length was Infinity (I don't have a current address -- it's always
moving.)  It's a traditional sword-and-sorcery MUD (rather than
a more social MUSH/MOO environment), in which your goal is to advance
your character in strength, experience, etc.  However, to advance
each "level" you're required to solve mini-quests, which resemble
very short I-F games.

Most people on the MUD spent time chatting or fighting (another way
to gain experience) - I was most interested in the quests.  I eventually
got too frustrated to continue - each quest was by a different author,
the parser was limited relative to TADS or Inform (and extremely variable
depending on the experience of the author), and too many relied on
burying important objects in layers of room description.

The multi-user aspect made it somewhat interesting - there was no 
technical reason why users couldn't solve the puzzles simultaneously,
but there was a strict ethical code about "quest cheating."  Sometimes
finding a quest half-completed was helpful, but more often it would
be annoying to find important objects missing.  In that case, you'd
have to wait (in real-time, of course) for the quest to "reset", which
would happen periodically during the day.

Unfortunately, the quest-cheating rule eliminated the possibility of
exploring the relationship between the quests and the multi-user
aspect of the MUD.  Traditional I-F is, by nature, artificial - we
generally _don't_ go through life solving complex problems on our
own in a perfectly linear fashion.  

I'd be very interested in developing a multi-user I-F system that requires
the users to think in an additional dimension (time), but I 
doubt based on my experience so far that any existing MUD language
would be advanced enough to suit our discriminating tastes. :)

--Liza

--
http://fovea.retina.net/~gecko/


From mythago@agora.rdrop.com Wed Feb 19 09:25:49 MET 1997
Article: 22552 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!news.maxwell.syr.edu!news.bc.net!info.ucla.edu!psgrain!hermes.rdrop.com!not-for-mail
From: mythago@agora.rdrop.com (Laurel Halbany)
Newsgroups: rec.arts.int-fiction
Subject: Re: Award for Best PC
Date: Wed, 19 Feb 1997 05:37:43 GMT
Organization: RainDrop Laboratories/Agora(sm)
Lines: 25
Message-ID: <3309468c.6206250@hermes.rdrop.com>
References: <33009D0D.1CFB@greenhouse.llnl.gov> <5dr1qi$s90@nntp5.u.washington.edu> <5e131u$k8a@Turing.Stanford.EDU> <5e30qi$mvr@nntp5.u.washington.edu> <5e80sc$cjf@Turing.Stanford.EDU>
NNTP-Posting-Host: slip-dc.rdrop.com
X-Newsreader: Forte Free Agent 1.1/16.230
Xref: news.lth.se rec.arts.int-fiction:22552

avrom@Turing.Stanford.EDU (Avrom Faderman) wrote:


>This is an interesting point, and one that (so far as I could tell)
>was basically absent from the original flurry of discussion about
>"Jigsaw," which centered largely around a division between those who
>liked this aspect of the game and thought it was to allow players to
>get into the PC and those who didn't like it and thought it was to
>avoid giving offense.  And I took the position that it was to allow
>players to get into the PC but that I didn't like it anyway.  But I
>hadn't heard this idea before, and I think I mind that bit of the game
>less when it's put in this light.

I don't know; this is precisely one of the reasons I really liked that
aspect of _Jigsaw_. It was interesting to see people trying to guess
what gender Black "really" was (comments about "acting definitely
male/female" even appear in the official walkthrough!), and grumbling
about the unrealism of a female character doing thus-and-such at
points in history (though nary a word of how Russian soldiers
understand and respond to the PC in English).

----------------------------------------------------------
Laurel Halbany
mythago@agora.rdrop.com
http://www.rdrop.com/users/mythago/


From whizzard@uclink.berkeley.edu Wed Feb 19 09:27:47 MET 1997
Article: 22540 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!newsxfer3.itd.umich.edu!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Other forms of interactive fiction
Date: 19 Feb 1997 00:54:10 GMT
Organization: University of California at Berkeley
Lines: 42
Message-ID: <5edivi$ouc@agate.berkeley.edu>
References: <5e2hve$4rd@news.wco.com> <5e6bd4$i4d@agate.berkeley.edu> <3308C25A.1A44@globalserve.net> <jota.856266070@laraby.tiac.net>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:22540


Hmm, just for that, I'm going to post something I've been saving for
awhile:

			The Author's Bill of Rights

1.  The author has a right to be wrong.  (c.f. ridiculous deadlines.)

2.  The author has a right to be late. (c.f. ridiculous deadlines.)

3.  The author has a right not to be held accountable for posts over one
year old (c.f. Admiral Jota.)

4.  The author has a right to try and make money, even if evryone DOES
laugh at him. (c.f. Can IF make money?)

5.  The author has a right to be wrong about being wrong about being
right. (c.f. How to keep a disgruntled audience busy.)

6.  The author has a right have his/her game betatested before releasing
it. (c.f. possible delays in release.)

7.  The author has a right to not join in the laughter when it's his/her
game you're ridiculing. (c.f. What a sorehead.)

8.  The author has a right to ignore non-constructive criticism and not
feel guilty.  (c.f.  Wow, that game truly sucked.)

9.  The author has a right to get indignant over a mean review (c.f.  In
conclusion, the world would be a better place without this game.)

10.  The author has a right to be wrong.  (c.f. Things that bear
repeating.)


	Smilies all around.  New authors should be warned that, much like
the US's Bill of Rights, most of these go ignored.  And of course, Jota
should watch out for Men in Black knocking on his door...

Anyways, :) for now.  Later.
-- 
	"Ha.  Made ya look!"


From erkyrath@netcom.com Wed Feb 19 09:29:30 MET 1997
Article: 22527 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Other forms of interactive fiction (more questions)
Message-ID: <erkyrathE5tL6M.6K2@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5e2hve$4rd@news.wco.com> <5ea5of$u3@remus.rutgers.edu> <3309186A.71E9@tricon.net> <5eblbs$78v$1@news.wco.com>
Date: Tue, 18 Feb 1997 22:30:22 GMT
Lines: 46
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:22527

Curt Siffert (siffert@shell.wco.com) wrote:
> Just wanted to thank you all for a fascinating thread.

> So, what of the idea of allowing more than one player in these games?
> Does this appeal to anyone?

Playing with someone hanging over your shoulder is always fun. (Not that 
I've done it recently.) Sure, it should be possibly electronically, 
kibitzer-style. Anyone feel like writing it? Sigh.

> 1)  Have there been many experiments with the "unreliable narrator"?
>     The only example I can think of offhand is in Hitchhiker's, where
>     the narrator repeatedly tries to convince you that you don't want
>     to go into a certain room.  Giving the parser an actual personality
>     that the player has to contend with could be quite entertaining.

Again, _Piece of Mind_. 

I've done some subtle stuff with an unreliable narrator -- trying to 
simulate the main character's subconscious and automatic assumptions, 
rather than a separate personality.

(Now, a character with actual Multiple Personality Disorder would present 
some interesting possibilities. Heh.)

> 2)  What about generating the output of an actual narrative based off
>     of the character's actions?

Go ahread and write it. :-)

> 3)  What of the possibility of making an IF game a Java application;
>     a Marimba channel, so multiple players could attach at once, but
>     unlike a mud, would not be visible to each other - the game would
>     keep its integrity, but it would open up new entertaining 
>     possibilities, such as races, or perhaps events one player would
>     trigger that would be reported to others, etc...

Wait, can they see each other's effect on the game-state, or not? If they 
can, it's silly to make them invisible to each other.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From gerlach7@nospam.address Wed Feb 19 18:25:43 MET 1997
Article: 11074 of rec.arts.int-fiction
Path: news.demon.nl!fido.news.demon.net!demon!dispatch.news.demon.net!demon!news.sprintlink.net!news-peer.sprintlink.net!news.maxwell.syr.edu!worldnet.att.net!howland.erols.net!math.ohio-state.edu!newsfeed.acns.nwu.edu!news.acns.nwu.edu!news	
From: Charles Gerlach <gerlach7@nospam.address>
Newsgroups: rec.arts.int-fiction
Subject: Re: Warning messages: good? bad?
Date: Wed, 19 Feb 1997 08:59:42 -0600
Organization: Northwestern University, Evanston, IL, US
Message-ID: <330B155E.3604@nospam.address>
References: <33070068.40E6@acpub.duke.edu> <5ec992$es4@bartlet.df.lth.se> <3309e26b.2467063@news.u.washington.edu> <slrn5gld2b.37s.spatula@underground.error.net>
NNTP-Posting-Host: tam7.mech.nwu.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (X11; I; HP-UX B.10.10 9000/715)
Lines: 44
Xref: demon rec.arts.int-fiction:11074

they got purple; purple's a fruit wrote:
> 
> And behold, Matthew Amster-Burton <mamster@u.washington.edu> did spake, speaking:
> > mol@bartlet.df.lth.se (Magnus Olsson) wrote:
> >
> > >To summarize, if you don't put a warning on a game, people will assume
> > >it's aimed at children (games are for kids, right?) and there's a risk
> > >that they'll be mightily pissed when they realize that it isn't. I
> > >wouldn't take that risk if I were you.
> >
> > Isn't "I-0" subtitled "The Jailbait on the Interstate Game" or
> > similar?  Exactly who among the literate is going to mistake this for
> > a children's game?
> >
> 
> The same type of people who rent "Porky's" for their kids and assume it to
> be a cartoon.  (I saw it happen.)
> 
> Oh, you said "literate" above there, I'm sorry, I take this back.
> 

Also, there are the parents that don't seem to care. I was in a
bookstore shopping for X-mas presents when a guy brought a toddler
over to the aisle next to me and said "Ok, get the one you want." 

The toddler picked up one of those books with electronic sound 
effects. I was thinking: "Oh, how cute." 

Then the child pressed one of the buttons, and was rewarded 
with: "Huh-huh, huh-huh-huh. Shut up, ass-munch." Which the child
gleefully repeated in his little high-pitched, barely-literate 
voice. The father(?) showed no recognition, concern, or even 
surprise; he simply continued shopping.

So, what with all the stupid parents and apathetic parents, are there
actually any out there that would get offended at their child playing
a somewhat off-color text-adventure? 

-- 
**********************************************************************
Charles Gerlach does not speak for Northwestern, and can be mailed at: 
cagerlac  a t  merle  d o t  acns  d o t  nwu  d o t  edu
He hopes that placing his e-mail in this format did not seriously 
inconvenience anyone attempting to contact him (except for spam-bots).


From fake-mail@anti-spam.address Wed Feb 19 18:25:59 MET 1997
Article: 11056 of rec.arts.int-fiction
Path: news.demon.nl!fido.news.demon.net!demon!dispatch.news.demon.net!demon!news.sprintlink.net!news-peer.sprintlink.net!visi.com!news.maxwell.syr.edu!arclight.uoregon.edu!newsfeed.direct.ca!fake-mail
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: Warning messages: good? bad?
Date: Tue, 18 Feb 1997 21:30:49 -0800
Organization: tela design
Message-ID: <fake-mail-ya02408000R1802972130490001@news.direct.ca>
References: <33070068.40E6@acpub.duke.edu> <5ec992$es4@bartlet.df.lth.se>
NNTP-Posting-Host: van-as-06a07.direct.ca
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
X-Newsreader: Yet Another NewsWatcher 2.4.0
Lines: 33
Xref: demon rec.arts.int-fiction:11056


 Of course, the extent of the warning question goes beyond the ol' sax and
violins question, I think. Dave Baggett's "Legend" contains the warning
"Recommended for mature readers only" at startup. I was never quite sure
why he put that in... was he trying to stress that it wasn't an easy game
playable by kids? Was it because of the Watchmaker and Timon Sketch's use
of the word "fuck"?

 Like Magnus and Matthew, I'm rather concerned about the way warning
messages equate sex and violence as "bad" things. And I'd have to say I
think of language much the same way - particularly with regards to textual
fiction. Kids old enough to read IF and not find it incredibly boring (no
pictures!) are going to have heard a hell of a lot more naughty words in
the playground than on their computer screen.

 My game in progress (here we go again) contains such language, because
that's how people speak in real life. It also contains references to
same-sex relationships, which is guaranteed to offend some people. However
it has no sexual content and relatively little violence.

 I've considered the issue of whether I should include something by way of
a notice. I'm leaning towards putting nothing, since I take the view that
it should be viewed as a short story or novel or somesuch. And as far as
I'm concerned if someone is offended by the idea of a same-sex relationship
that's their damned problem, not mine. Putting in a label warning
essentially succumbs to the view that same-sex relationships are bad and
thus people should be warned about them.

 - Neil K.

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From mamster@u.washington.edu Wed Feb 19 18:26:21 MET 1997
Article: 11081 of rec.arts.int-fiction
Path: news.demon.nl!fido.news.demon.net!demon!dispatch.news.demon.net!demon!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!rill.news.pipex.net!pipex!uunet!in2.uu.net!140.142.64.3!news.u.washington.edu!root
From: mamster@u.washington.edu (Matthew Amster-Burton)
Newsgroups: rec.arts.int-fiction
Subject: Re: Warning messages: good? bad?
Date: Wed, 19 Feb 1997 17:03:31 GMT
Organization: University of Washington
Message-ID: <330b2e9b.2340401@news.u.washington.edu>
References: <33070068.40E6@acpub.duke.edu> <5ec992$es4@bartlet.df.lth.se> <fake-mail-ya02408000R1802972130490001@news.direct.ca>
NNTP-Posting-Host: mamster.cdmrc.washington.edu
X-Newsreader: Forte Free Agent 1.1/32.230
Lines: 60
Xref: demon rec.arts.int-fiction:11081

fake-mail@anti-spam.address (Neil K.) wrote:

>Like Magnus and Matthew, I'm rather concerned about the way warning
>messages equate sex and violence as "bad" things. And I'd have to say I
>think of language much the same way - particularly with regards to textual
>fiction. Kids old enough to read IF and not find it incredibly boring (no
>pictures!) are going to have heard a hell of a lot more naughty words in
>the playground than on their computer screen.

No shit! :)  I certainly have a less dirty mouth now than I did in
second grade, and I think I was a pretty average second-grader.  I
don't think I played any IF until fourth grade.  Any kid who does know
all your basic four-letter words by then has led an extraordinarily
sheltered life.

But I don't think it's the kids we're talking about here.  It's
paranoid parents who think their kids will be harmed by playing a game
with bad words or sex in it.  Many of these same parents think there's
nothing of physically assaulting their children by spanking them or
worse (after all, the second leading cause of death among children is
being killed by their parent or guardian and 40 percent of parents
spank;  the research on spanking could not possibly be clearer or more
complete).  There's a real problem for you.

Beyond that, there is the issue of the disclaimer affecting my
enjoyment of the game.  I want to be pleasantly or unpleasantly
surprised that there's sex or a gruesome murder or a character that
says "fuck" in the game.  I wouldn't want to read a novel with the
disclaimer:  "Warning: this novel may contain graphic language,
violence, nudity :), or sexual content."  Almost every novel has at
least one of those everyday things and almost no one complains.  While
I'm harping on parents, let me postulate that some of the same parents
who would be horrified that their child was playing "I-0" are probably
reading romance novels--turgid members, heaving bosoms, not to mention
plenty of "she says no but means yes" bullshit--while their kid is on
the computer.

Perhaps I'm going after a straw man here, but the fact is that there
are people who will go to great lengths to protect children from
things they don't need to be protected from while ignoring actual
dangers.  Take Bill Bennett and Jack Kemp, who rail against smutty and
violent lyrics but never mention the sexual and physical violence
suffered by thousands of children in their own homes.  Putting
warnings on games invites censorship, excuses parental negligence, and
detracts from my enjoyment of the game.  Let's just don't, okay?

</tirade>

> I've considered the issue of whether I should include something by way of
>a notice. I'm leaning towards putting nothing, since I take the view that
>it should be viewed as a short story or novel or somesuch. And as far as
>I'm concerned if someone is offended by the idea of a same-sex relationship
>that's their damned problem, not mine. Putting in a label warning
>essentially succumbs to the view that same-sex relationships are bad and
>thus people should be warned about them.

I agree.  I don't remember having played a text game with a gay
character, and it would be a welcome addition to the pantheon.

Matthew


From gleemoth@aol.com Thu Feb 20 09:45:55 MET 1997
Article: 22603 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!news.stealth.net!cdc2.cdc.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer3.itd.umich.edu!rill.news.pipex.net!pipex!uunet!in2.uu.net!204.238.120.21!jump.net!grunt.dejanews.com!not-for-mail
Date: Wed, 19 Feb 1997 19:21:03 -0600
From: gleemoth@aol.com
Subject: Re: [TADS] Referring to a rooms
Newsgroups: rec.arts.int-fiction
Message-ID: <856401048.8282@dejanews.com>
Organization: Deja News Usenet Posting Service
References: <3308df27.895147@news.netspace.net.au>

X-Article-Creation-Date: Thu Feb 20 01:10:48 1997 GMT
X-Originating-IP-Addr: 152.172.171.24 (172-171-24.ipt.aol.com)
X-Http-User-Agent: Mozilla/2.0 (compatible; MSIE 3.0B; Win32)
X-Authenticated-Sender: gleemoth@aol.com
Lines: 21
Xref: news.lth.se rec.arts.int-fiction:22603

In article <3308df27.895147@news.netspace.net.au>,
  jrcole@ozemail.com.au (James Cole) wrote:
>
> Hi,
>
> [2 paragraphs describing how he couldn't use rooms with verbs]
>
> 	What am I missing?

Well, let me flip through my print-out of WORLD.T for a moment... let's
see... nothing wrong in the "Room" class... I think I read about this in
Paul Gilbert's WorldClass manual... AHA! Here it is! Check out
"Verb.checkCommon" in WORLD.T; the first thing it does is exclude any
objects with a class of Room, if they do not have a class of Nestedroom
and if the Verb isn't a Systemverb. Just comment that block of text out
and your problem is solved! No more messing around with dummy objects.
For your rooms, at least. :-) Hope this helps!	Gleemoth the Wise
(gleemoth@aol.com)

-------------------==== Posted via Deja News ====-----------------------
      http://www.dejanews.com/     Search, Read, Post to Usenet


From d91frera@ida.liu.se Fri Feb 21 12:30:33 MET 1997
Article: 22648 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Stop prompt & Delay parse
Date: 20 Feb 1997 18:17:42 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 90
Message-ID: <5ei4g6$6ra@curofix.ida.liu.se>
References: <5egglv$jeq@curofix.ida.liu.se> <m34tf7bhar.fsf@ue801di.lrz-muenchen.de>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)
Xref: news.lth.se rec.arts.int-fiction:22648

Florian Beck <fb@ue801di.lrz-muenchen.de> writes:

>d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD)) writes:

>> Hi all,
>> 
>> I'm writing a little routine to allow the player to type things like:
>> 
>> >GO TO THE KITCHEN

>Sorry, can't help. But sounds interesting. Could you elaborate a bit
>on how you do this. I've tried something like this myself. But soon I
>drowned in tons of shortest-way-algorithms for every NPC, handling
>obstacles that weren't there the last time the character passed a
>location (and avoiding the game going around that obstacle: if the
>player doesn't know about it he should walk right into it), handling
>exit routines in the shortest-way-algorithm (esp those killing the
>player and stuff), has_visited room attributes for every character,
>keeping track what places and objects the characters know about, and
>so on. Nothing impossible, but lots of things to keeps track of.



I think the secret is to start out with something less complicated, get it
to work, and learn while doing it. That knowledge will make it easier to
see how to solve future problems, when extending the algorithm.

I have now, as far as I can tell, solved my first prolem, getting the player
to walk around with time passing as usual, so both GO TO THE KITCHEN and
JOHN, GO TO THE KITCHEN work fine.

I ended up modifying a piece of code from timewait.h by Andrew Clover (thanks
Andrew!) to let time pass while the player walks around.



Here's what my routines do:

First, a routine called FindPath, that takes three arguments; startlocation,
destination and actor. It uses breadth-first searching, utilizes knowledge
about the state of doors on the way that the the actors maybe shouldn't
possess. For this particular game, it doesn't matter. If you think it does, you
can store an array of knowledge in every actor, that the routine will look
for when making decisions about what paths are possible. Furthermore, the
routine will only try to pass through doors of a certain class, and will only
try to pass through rooms of a certain second class. That way, I can
restrict the search to the meaningful areas, and no one will go to
sudden-death-locations, if they are coded as a routine in an exit. 

All actors are of the class Walker. That way, they are guaranteed to have all
the properties that the various routines are trying to read and write. That
class sets up a daemon, calling self.walk(), which does the actual walking.
If the actor needs a daemon that does more, he can set up his own, just
making sure he calls self.walk() from it. self.walk() calls self.move(), which
is the same for all actors except the player, as he needs to call PlayerTo();

If a movement proves impossible, due to a door that has been locked _after_
the path was established, the walk-routine calls FindPath to find another
way to get to the target.

The player is not moved using a daemon, because I want to make sure his
walking is done before everybody else's, just as if he typed every command
himself. He still uses the same walk-routine, though.




These routines are a bit more complicated than this, to speed up search and
handle other things than just walking around for instance, but more detail
would make it less comprehensible. They are still under development, but
I'm pretty close to what I need for this game, so I won't refine them much
more at the moment.

Something I think a lot of people (including myself) tend to forget, is that
we're trying to create an illusion for the player. If the player never
realizes that your actors are purposefully avoiding the use of information
they should not have aquired, why spend effort building it that way?

I would find it interesting to hear peoples opinions on how NPC:s can be
made more realistic. Anyone in for a discussion? (I know the topic has been
dealt with before, but still very few games display credible NPC:s)

Regards,

/Fredrik
--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
I want to make it perfectly clear that I can't say I don't think people who
aren't avoiding using too many negations aren't putting things clearly enough.


From erkyrath@netcom.com Fri Feb 21 15:19:25 MET 1997
Article: 22687 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: English Language Parsing
Message-ID: <erkyrathE5v1Fw.MrE@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3308B528.47BE@usdiamond.com> <slrn5glbei.37s.spatula@underground.error.net>
Date: Wed, 19 Feb 1997 17:19:08 GMT
Lines: 49
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:22687

they got purple; purple's a fruit (spatula@underground.error.net) wrote:
> And behold, William M. McCarroll <neosaint@usdiamond.com> did spake, speaking:
> > With MUDS it is very difficult to create a "storyline" as the 
> > mud has no beginning or end, it exists to allow interaction. And
> > "puzzles", once solved are spread amongst the other players, and 
> > rendered basically useless.  I want to create a more hybrid system
> > that allows plots and subplots to form from seeming chaos, Hack & 
> > Slash gets pretty boring if you ask me ;).

> MUD is a terrible system to create puzzles with.  You'd be far better off
> using a MUSH or MUCK or one of those hybrids,  hell, even a MOO.  They exist
> more for the programming than the interaction, (well, perhaps, programming
> over interaction, but both are 'equal') and can be programmed as such to
> handle complicated sentences - however even then it's a bit of a code
> kludge. 

It's not the programming difficulty we're talking about, but the whole 
MUD paradigm.

(Huh huh huh -- "paradigm". Huh huh.)

TinyMUD was certainly a pain to program for, since it didn't have any 
programming language except for boolean combinations of objects, used to 
lock doors and object-picking-up. (In other words, you could mark a door 
as "can't go through unless you are holding ((X or Y) and Z and W)". And 
you could mark an object as "can't pick up unless you are holding..." 
etc. That was about it as far as programming constructs, although I am 
leaving out a few things less useful to puzzle construction.) 

> It's also hard, object-wise, to handle multiple puzzle objects to
> be held and used by many different players - cloned objects for every player
> would work, but are hell on system resources, while a single object must be
> 'returned' to its spot once a player is finished with it, and with many
> objects, restricts gameplay to one person at a time, in which case you'd be
> better off just writing for non-multiplayer use.

But this is exactly the problem, and it applies equally to all MUDs that 
I've seen. You can "lock" a quest/puzzle once a player is inside it; that 
means you're just writing a single-player scenario. You can clone the 
scenario and all contents for each player that enters; ditto. Or you can 
allow multiple people inside, with the near-certainty that some will drop 
out early, or come in late, and break your scenario.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From MKST21C@prodigy.com Fri Feb 21 15:20:23 MET 1997
Article: 22710 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!news1.relcom.ru!EU.net!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!newsxfer.itd.umich.edu!uunet!in1.uu.net!192.207.105.50!prodigy.com!usenet
From: MKST21C@prodigy.com (Chris Lang)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: 21 Feb 1997 05:51:31 GMT
Organization: Prodigy Services Company  1-800-PRODIGY
Lines: 28
Distribution: world
Message-ID: <5ejd53$vq0@usenetz1.news.prodigy.com>
References: <5dqeir$5m2@koala.scott.net> <5dr19m$1t4@vixen.cso.uiuc.edu> <5e0dgq$m1@echo2.echonyc.com> <5e21gh$2n8@kodak.rdcs.kodak.com> <slrn5glav4.37s.spatula@underground.error.net>
NNTP-Posting-Host: innugap4-int.news.prodigy.com
X-Newsreader: Version 1.2
Xref: news.lth.se rec.arts.int-fiction:22710

 Given all that, I would claim that the adventurer in Zork is
>> non-gender-specific, unless there were some pronouns like "he" used
>> in Enchanter.  OTOH, the adventurer in Zork Zero is known to be male
>> in a couple of places, although that fact is never really factored
>> into the plot.
>
>I can't remember any gender-specific pronouns used towards the player 
in
>Zork, though I'm wondering if it's assumed that the "Adventurer" rank 
is
>masculine.  I would hope not, for "Adventuress" is rather unwieldy.

   There is no hint of the Zork trilogy adventurer's gender in Zorks 1 
and 2. The only female NPC in any of the Zork trilogy games is Zork II's 
princess, who treats the player's character (PC) in a gender-neutral way 
(and completely ignores any attempt at romance). 
  Zork III, however, does imply that the player character is in fact a 
male. Try time-travelling to certain places in the Royal Museum in 777 
and see what gender pronoun is used by a certain ruler when referring to 
your character.
  The twist at the ending also implies that the PC is a male, though I 
won't give it away for those who haven't finished the game. Suffice to 
say, if certain lines are to be taken literally, said twist depends on 
the PC being the same sex as the dungeon master, which is, in this case, 
male.
  
                                            Chris Lang



From graham@gnelson.demon.co.uk Sat Feb 22 08:19:35 MET 1997
Article: 22716 of rec.arts.int-fiction
Path: news.lth.se!solace!news.stealth.net!news.ibm.net.il!arclight.uoregon.edu!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Sex in I-F
Date: Fri, 21 Feb 1997 00:41:26 +0000 (GMT)
Organization: none
Message-ID: <ant2100261cbM+4%@gnelson.demon.co.uk>
References: <meta-1802970945270001@win7-dhcp.harlequin.com> <19970219153800.KAA15709@ladder01.news.aol.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 81
Xref: news.lth.se rec.arts.int-fiction:22716

In article <19970219153800.KAA15709@ladder01.news.aol.com>, Deidre Ng
<URL:mailto:deidreng@aol.com> wrote:
> 
> It happens that the erotica writers list has just started a thread on the
> subject of interactive sex stories. Are there any works of I-F that
> actually revolve around sexual activity? As was pointed out on that list,
> porn if often an early adopter of technology. Was that true of I-F as
> well, or has the combination of sex and computers always been image
> oriented? Perhaps the scripts of phone sex operators are examples of crude
> interactive sex fiction.

A salutary tale, if possibly one that I'm mis-remembering: I read
a piece in a computer magazine once, interviewing a programmer
who'd worked on one of the early PC pretend-you're-having-sex games.
(Hats off to any players of such -- suspension of disbelief
doesn't get any more heroic than this.)  Anyway, the programmer
said that the team had spent about 75% of their time perfecting the
scene in which Ms X takes off her blouse.  They became fascinated
with the folds of the fabric, the way it ought to catch the virtual
light, the cantilevering of the elbows, and so on.  By the time
any horizontal jogging was called for, the programmers were
already out of time and resources.

To give a serious answer.  I see no reason why there couldn't be
an erotic IF game (except perhaps good taste).  One obstacle is
that the interface would need thought.  What combination of
verb and noun would we like the player to type in, as simulated
passion grows?  I don't really think most naturally of these
kind of actions in verbal terms, only in terms of a sort of
understood semaphore with one's partner.

But it's not purely a matter of niceties or the rudeness of
"rude words".  Most commands in adventure games refer to completed
actions: FILL BASKET, TAKE INGOT, etc., or to actions which could
be continued but which are understood to be interrupted: GO SOUTH.
I don't think a parser interface for intercourse could deal only
in such actions.  Wouldn't it have to keep saying something like
"(taking your hand off ****** first)", and having to assume that
all activities are continuing unless explicitly stopped?

Besides this, sex is certainly about communication, but not much
of it's about decision processes, and a lot of the negotiation
that takes place is tactile.  In an IF game, the player would be
spending all of the time pondering what to ask to do next, or
tapping it out (a lengthy process left-handed), with only brief
intermissions to watch text rush by describing the allegedly
ecstatic result.

As a final negative point, IF is partly about puzzles. Admittedly,
in a few games, at least some of the puzzles are about discerning
the characters of other people.  Nevertheless the majority are
brain-teasers of one kind or another.  Are we to postulate a
coy mistress who behaves in matters of the bedroom rather as
the lady shopkeeper does in "The Magic Toyshop", insisting that
we win games of noughts-and-crosses and so on?

Thus, I reckon simulated IF sex is infeasible.  What _might_ be
feasible?  I could imagine a detective thriller in which some
erotic milieu would be explored -- hero as voyeur, I suppose,
mirroring the player.  And/or I could imagine a game in which
a couple, no more, of sparely interactive sex scenes lead to
important discoveries (Great Scott! Lola has a Chinese tong
marking tattooed on her inner thigh! So Mr Li was working for
El Gangstero after all!).

I can't help wondering what phone sex scripts read like...
"51. Briefly impersonate Shirley Temple.  Press the button marked
 "bedsprings noise".  Go back to line 40."

(Don't you love these inappropriate couplings of words?  "Phone
sex", hmm.  I saw a reference today to a saint having been
"brutally dismembered" in AD 650.  As opposed to "humanely",
no doubt.)

Enough rambling.  What I'd prefer would be a good, honest,
strike at romantic IF, not as a piece of kitsch genre fiction
but as a gutsy work in its own right.  Any volunteers?

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From MKST21C@prodigy.com Sun Feb 23 09:52:53 MET 1997
Article: 22760 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-dc-9.sprintlink.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer.itd.umich.edu!news.ececs.uc.edu!news.kei.com!news.texas.net!uunet!in2.uu.net!192.207.105.50!prodigy.com!usenet
From: MKST21C@prodigy.com (Chris Lang)
Newsgroups: rec.arts.int-fiction
Subject: Re: A Question of Gender
Date: 20 Feb 1997 07:46:10 GMT
Organization: Prodigy Services Company  1-800-PRODIGY
Lines: 17
Distribution: world
Message-ID: <5egvg2$17vq@usenetz1.news.prodigy.com>
References: <5dqeir$5m2@koala.scott.net> <5dr19m$1t4@vixen.cso.uiuc.edu> <5e0dgq$m1@echo2.echonyc.com> <5e21gh$2n8@kodak.rdcs.kodak.com>
NNTP-Posting-Host: innugap4-int.news.prodigy.com
X-Newsreader: Version 1.2
Xref: news.lth.se rec.arts.int-fiction:22760

Given all that, I would claim that the adventurer in Zork is
>non-gender-specific, unless there were some pronouns like "he" used
>in Enchanter.  
   Actually, Zork 3 does sort of 'break radio silence' on this point. Try 
time-travelling to 777's Royal Museum or Jewel Room and see what gender 
pronoun is used when referring to your character.
  The ending twist of the game also hints that your character is a male, 
but I won't go into specifics to avoid spoiling it for those who (for 
some reason) haven't played it yet. Suffice to say, it has to do with the 
fact that the dungeon master is also a male (though in truth, it would 
make little difference if the dungeon master were a female just as it 
would make little difference if Zork I's thief were female; read back 
issues of XYZZY News and the 'Gender in Interactive Fiction' articles for 
further analysises).

                                       Chris Lang



From jota@laraby.tiac.net Sun Feb 23 10:00:02 MET 1997
Article: 22740 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-dc-5.sprintlink.net!news-in.tiac.net!posterchild!laraby.tiac.net!jota
From: jota@laraby.tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction
Subject: Re: Scramble! Ideas up for grabs. (LONG)
Date: 22 Feb 97 13:50:41 GMT
Organization: The Internet Access Company, Inc.
Lines: 18
Message-ID: <jota.856619441@laraby.tiac.net>
References: <33075D0D.2D3D@globalserve.net> <zCQQ6MD4F2Daez11@trib0029.tribal.line.org> <330BB4EF.9A6@globalserve.net> <jota.856427068@laraby.tiac.net> <330EF61D.6BEB@globalserve.net>
NNTP-Posting-Host: laraby.tiac.net
X-Newsreader: NN version 6.5.0 #1 (NOV)
Xref: news.lth.se rec.arts.int-fiction:22740

Drone <foxglove@globalserve.net> writes:
>Admiral Jota wrote:

>> I would say that this would be a pretty fair arrangement then, wouldn't
>> you?

>No. In order to make a proposition like this palatable, I would need ... 
>Function keys. In small unmarked increments. One through ten ... No, make that 
>one through *twelve*. Left in an unmarked briefcase on the corner of Bloor & 
>Bathurst...

Da Boss says dat you been askin' too much. Da Boss dudn't like people who
ask foh too much. Da Boss sez dat if you eveh wanna see youse li'l rodent
again, you gunna take the ALT key an' be happy. Kapish?
--
                                      /<-= Admiral  Jota =->\
                                    -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  -= -=->/


From daleys@ihug.co.nz Sun Feb 23 12:05:18 MET 1997
Article: 22275 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!EU.net!newsfeed.internetmci.com!newsfeed.direct.ca!news.wildstar.net!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.access.net.au!news.netspace.net.au!news.mira.net.au!vic.news.telstra.net!sa.news.telstra.net!nsw1.news.telstra.net!ihug.co.nz!news
From: - <daleys@ihug.co.nz>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Library 6/4 Bug in English.h
Date: Tue, 11 Feb 1997 16:17:27 +1300
Organization: -
Lines: 39
Message-ID: <32FFD505.7E49@ihug.co.nz>
References: <32F8DADC.7EB@soundcraft.co.uk.trim.these.last.five.words>
Reply-To: daleys@ihug.co.nz
NNTP-Posting-Host: 203.29.165.40
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)

DaveK wrote:
> 
> Hello, debuggers!
> 
> <groans all round at the thought of yet another release being needed..>
> 
>  Nahh, don't worry; it's only a little one. In the CompassDirection
> objects in English.h 6/4 we have
> 
> CompassDirection -> out_obj "outside"
>                     with                               door_dir out_to;
> CompassDirection -> in_obj "inside"
>                     with                               door_dir in_to;
> 
>  Erm. No name properties for out_obj and in_obj; hence no way to refer
> to them. Anyone who's been wondering why they're getting the response
> 'But you aren't in anything' when they try to type 'out', here's your
> answer: it's because out gets interpreted as <<Exit>> rather than
> <<go out_obj>>
> 
>  Solution: simple. I reccommend:
> 
> CompassDirection -> out_obj "outside"
>                     with name 'o//' 'out'              door_dir out_to;
> CompassDirection -> in_obj "inside"
>                     with name 'i//' 'in'               door_dir in_to;

small problem Dave 'i' is used for inventory and 'o' is used for oops
:-).
Does It still do exit when you want to do so?
-- 
Nicholas Daley
<mailto:daleys@ihug.co.nz>

Everyone agreed it was a splendid funeral, but no one enjoyed it more
than the deceased himself.
--Pt1 C11 Red Dwarf  Grant Naylor




From andreas.hoppler@logon.ch Sun Feb 23 12:05:34 MET 1997
Article: 22354 of rec.arts.int-fiction
From: andreas.hoppler@logon.ch (Andreas Hoppler)
Newsgroups: rec.arts.int-fiction
Subject: One more library bug
Date: Thu, 13 Feb 1997 22:52:44 +0100
Message-ID: <MPG.d6dab9743e3e2809896b6@news.logon.ch>
Organization: NOT!
X-Newsreader: Anawave Gravity v1.10.556
NNTP-Posting-Host: modem104.logon.ch
Lines: 21
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!news.sprintlink.net!news-peer.sprintlink.net!newsfeed.internetmci.com!masternews.telia.net!newssrv.ita.tip.net!ubnsrv.unisource.ch!scsing.switch.ch!news.logon.ch!

If you return 'true' from a door_to routine, it won't 
stop as described in the manual, rather it moves the player to
a dark neverwhere.

To fix the bug, replace the following fragment of
routine "GoSub" in "Verblibm.h"

-------------- original
      if (ZRegion(j.door_to)==2) j=RunRoutines(j,door_to);
      else
      {   if (j.door_to == 0) return L__M(##Go,6,j);
          j=j.door_to;
          if (j==1) rtrue;
      }
-------------- correct version
      if (ZRegion(j.door_to)==2) j=RunRoutines(j,door_to);
      else
      {   if (j.door_to == 0) return L__M(##Go,6,j);
          j=j.door_to;
      }
      if (j==1) rtrue;
--------------

Andreas


From foxglove@globalserve.net Mon Feb 24 13:39:13 MET 1997
Article: 22787 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!newsxfer3.itd.umich.edu!howland.erols.net!ais.net!ameritech.net!uunet!in2.uu.net!204.191.213.61!ott.istar!istar.net!tor.istar!east.istar!news.globalserve.net!usenet
From: Drone <foxglove@globalserve.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Alien or invented languages in IF
Date: Sun, 23 Feb 1997 20:04:07 -0500
Organization: Envision This
Lines: 51
Message-ID: <3310E907.1CA0@globalserve.net>
References: <5elpp6$dh9@eve.enteract.com>
Reply-To: foxglove@globalserve.net
NNTP-Posting-Host: dialin490.globalserve.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (Macintosh; I; 68K)
Xref: news.lth.se rec.arts.int-fiction:22787

sharvey wrote:
> 
> - Create a small ficticious language to be used sparingly in the game,
> leaving the player to do the translation.  This would entail implementing
> some sort of lexicon for the player to find, which can easily look more
> like artifice than art.
> 

Darmok at Tanagra?

Seriously, though, I thought of a type of alien language a while back for a 
roleplaying session. You're welcome to use it as inspiration if you like. This 
alien culture ("Clutchlings") developed a "maze" language. If a single square 
is a "thought or sentences", the twists and turns of the labyrinth within it 
represented twists and turns of thought.

So this...

---------
!       !
! !---  !
! !     !
---------

Might say "give me the paper"

While this...

---------
!    !  !
! !  !  !
! !     !
---------

Could mean "give me the pen"

Except the labyrinths were much bigger. I'm just too lazy to give a proper 
example in ascii.

I didn't really know what any of it meant. I just based something on chinese 
characters and let the players believe I knew what it meant.

Oh, when they discovered "ancient alien writings" they were in triangles 
instead of squares. The extent of the decoding they had to do was try to find a 
triangle symbol that was similar enough to a square symbol that it could be an 
archaic form of the same thing.

Drone.
-- 
"Esse est percipi."
foxglove@globalserve.net


From wosam@iastate.edu Mon Feb 24 16:56:29 MET 1997
Article: 22819 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!newsxfer.itd.umich.edu!newsrelay.iastate.edu!news.iastate.edu!du206-10.cc.iastate.edu!user
From: wosam@iastate.edu (Wesley Osam)
Newsgroups: rec.arts.int-fiction
Subject: Re: New game in beta: Nimble
Date: Sun, 23 Feb 1997 09:00:03 -0600
Organization: (Insert mildly humorous organization name here)
Lines: 32
Message-ID: <wosam-2302970900030001@du206-10.cc.iastate.edu>
References: <5e79jl$db4@beast.connix.com> <5efm7v$dcs@fido.asd.sgi.com> <jota.856427963@laraby.tiac.net>
NNTP-Posting-Host: du206-10.cc.iastate.edu
Xref: news.lth.se rec.arts.int-fiction:22819

In article <jota.856427963@laraby.tiac.net>, jota@laraby.tiac.net (Admiral
Jota) wrote:

> jfrancis@dungeon.engr.sgi.com (John Francis) writes:
> >Rybread Celsius <rybread@cshore.com> wrote:
> 
> >>From the msispellar of Liquid and Rippled Flesh comes a
> >>new nitemare... Nimble.
> >>Actualyl it's only in beta and I programmed it in under 
> >>8 hours and though winable, its still slightly barren.
> 
> >Imagine that - a whole eight hours!
> >I wonder if anyone will be masochistic enough to actually try this.
> 
> If anyone does, could he or she report back to the rest of us? I don't
> dare try it out myself.
> 
I've tried it.  The spelling is much better than the contest entries, and
the game itself is just as enjoyably bizarre as "Rippled Flesh."  (I
should note here that I probably have different tastes than most IF fans
-- I really liked "Pick Up the Phone Booth and Die," I thought "Phlegm"
was one of the best competition games, and I ported "Space Aliens Laughed
at my Cardigan to Inform purely for my own amusement, preserving most of
the bugs in the process.)  It involves a mime and a glowing thing that
explodes at random for no readily apparent reason.  I couldn't figure out
how to get anywhere without using the debugging verbs, though.

-- 
M. Wesley Osam
wosam@iastate.edu
"Iowa state college -- the high school *after* high school!"
                              --Mystery Science Theater 3000


From max@alcyone.com Mon Feb 24 22:19:29 MET 1997
Article: 22832 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!newsxfer3.itd.umich.edu!howland.erols.net!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news.idt.net!enews.sgi.com!news.sgi.com!news.spies.com!nixon.area.com!usenet
From: Erik Max Francis <max@alcyone.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: HAL=IBM (was Re: Ah the wonders of learning a new language (inform)..)
Date: Mon, 24 Feb 1997 10:22:57 -0800
Organization: Alcyone Systems
Lines: 28
Message-ID: <3311DC81.4F3C9D81@alcyone.com>
References: <5e25cj$81a@uni00nw.unity.ncsu.edu><Pine.SOL.3.91.970214194746.23933A-100000@mcmail.CIS.McMaster.CA><5e4mlo$249@uni00nw. <Pine.LNX.3.95.970223193310.272A-100000@seraphim> <fake-mail-ya02408000R2402970007390001@news.direct.ca> <5esjoq$ko5@echo2.echonyc.com>
NNTP-Posting-Host: newton.alcyone.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (X11; I; Linux 2.0.29 i686)
Xref: news.lth.se rec.arts.int-fiction:22832

Neil deMause wrote:

> Neil K. (fake-mail@anti-spam.address) wrote:
> 
> :  You can do little author profiles of everyone, and find out that most
> : of
> : the people who frequent this group are geeks who also post to sf and
> : computer programming newsgroups. :)

Yes, I noticed that too.  I used to read rec.arts.int-fiction a long, long
time ago (you can find some of my old articles on a few Usenet archival
sites on the web).  I recently rejoined, because I recently found these
archival sites and remembered how I enjoyed the group.

When I arrive, I see many of the same people I've been talking to on
rec.arts.sf.science, comp.os.msdos.djgpp, and others.  Very, very strange.

> Hmm. Maybe XYZZYNews needs to start a gossip column...

Don't look at me, man, I didn't do it.

-- 
       Erik Max Francis, &tSftDotIotE / email:  max@alcyone.com
                     Alcyone Systems /    web:  http://www.alcyone.com/max/
San Jose, California, United States /    icbm:  37 20 07 N  121 53 38 W
                                   \
              "I am become death, / destroyer of worlds."
                                 / J. Robert Oppenheimer (quoting legend)


From puma@u.washington.edu Tue Feb 25 11:05:23 MET 1997
Article: 22857 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer.itd.umich.edu!uunet!in1.uu.net!192.220.251.22!netnews.nwnet.net!news.u.washington.edu!puma
From: puma@u.washington.edu (Clyde Sloniker)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform6] Need more flexible pronouns
Date: 25 Feb 1997 07:20:49 GMT
Organization: University of Washington, Seattle
Lines: 58
Message-ID: <5eu3sh$g53@nntp5.u.washington.edu>
References: <madsenhgj22aa0.fsf@yfn.ysu.edu> <5esan3$p2c@nntp5.u.washington.edu> <madsenwwrx4i8n.fsf@yfn.ysu.edu>
NNTP-Posting-Host: saul6.u.washington.edu
NNTP-Posting-User: puma
Xref: news.lth.se rec.arts.int-fiction:22857

Christopher J. Madsen <ac608@yfn.ysu.edu> wrote:

>I don't think ambiguous-gender characters like Black work very well.
>I think it's better either to make the player specify his/her gender
>at the beginning of the game, or for the author to just decide what
>genders his characters are.  (Except for games where the player's
>gender is irrelevant, like Zork.)

> SEARCH UNDERWEAR

Gender is irrelevant.

> RESIST

Futile.  You will be assimilated.

> SHOOT BORG WITH PLASMA RIFLE

The Borg disappears in a flash of ionized particles.

> AGAIN

The Borg have adapted to your weapon.  It is ineffective.

> BLACK, SHOOT BORG WITH GRENADE LAUNCHER

Black turns slowly towards you, the left half of the time-traveller's face
covered with mechanical bits and bobs.  Your nemesis drops the grenade
launcher, lurching towards you in a fashion that reminds you of one of the
characters from "The Bride of Frankenstein".  "Your cultural and
technological distinction will be added to our own," the new Borg
declares.

> BLACK, ASSIMILATE GMD ARCHIVE

The Borg have never been *asked* to assimilate anything.  You almost think
you see Black shrug; a data jack attackes to a nearby T1 junction, and the
data is transferred.  Almost immediately, Black begins to move sluggishly,
as the puzzles of the archive occupy the Collective into which your
counterpart has been assimilated.

> BLACK, SOLVE 'A CHANGE IN THE WEATHER'

Black begins to mutter, sounding mentally constipated.  "Score is
irrelevant.  Fairness is irrelevant.  Saving is futile.  You will... you
will..."

> KILL BLACK WITH SWORD

The ancient elven blade easily penetrates Black's chest, shorting out
various vital components and disabling the Borg.  Unfortunately for you,
the handle of the sword is not insulated.

*** You have died ***

---
(The sigless one mutters about forgetting to wear the rubber gloves first.) 



From trischma@nosc.mil Thu Feb 27 09:50:26 MET 1997
Article: 22918 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!uninett.no!hermod.uio.no!nntp.uio.no!news.radio.cz!CESspool!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!howland.erols.net!cs.utexas.edu!news.cs.utah.edu!dog.ee.lbl.gov!newshub.nosc.mil!news!news
From: James Trischman <trischma@nosc.mil>
Subject: Re: Sex in I-F
Content-Type: text/plain; charset=us-ascii
Message-ID: <331483AC.2EE7@nosc.mil>
Sender: news@nosc.mil
Reply-To: trischma@nosc.mil
Content-Transfer-Encoding: 7bit
Organization: NCCOSC 
References: <meta-1802970945270001@win7-dhcp.harlequin.com> <19970219153800.KAA15709@ladder01.news.aol.com> <ant2100261cbM+4%@gnelson.demon.co.uk> <331189DB.6CF@fred.aurora.edu> <ant252210d07M+4%@gnelson.demon.co.uk>
Mime-Version: 1.0
Date: Wed, 26 Feb 1997 18:40:44 GMT
X-Mailer: Mozilla 3.01 (Win95; I)
Lines: 44
Xref: news.lth.se rec.arts.int-fiction:22918

What does the F in I-F stand for?

I think the discussion is getting a little silly.
I tend to agree with Graham that the actual act of intercourse is
not going to be very interesting. This is pretty much true in most
fiction.  The pulp romance novel and the porno flick are hardly held
up as paragons of their respective mediums.

I contend that when sex is used effectively in fiction it is used to
symbolize something or reflect an inner state of a character that the 
author doesn't want to explicitly relate. ( Sometimes in film I think
sex is used as "shortcut" to evoke a sense of intimacy since we only
get about 90 minutes to get to know the characters. )

Certainly most of the readers here are clever enough to think of ways
to convert just about anything into an I-F puzzle.  Several examples
have been posted. I imagine that given an evening and a 6-pack of beer
we could concoct a whole adventure full of sexual puzzles.  It would
ultimately reduce to the experience of Bill Murray's character in the
film "Groundhog's Day" where he has infinite attempts to seduce the
girl just by trying every possible combinations of actions, but the
process renders the end result meaningless.

I don't think that it is impossible to integrate a sexual encounter 
into an I-F story, I just think the puzzle angle is ultimately a 
dead end.  I'm not interested in an I-F game that reads like a letter
to the Playboy Forum, and there's no appeal to a game of "guess that
verb," where the verb happens to be f**k.  I assume that most reader
in this forum are interested in advancing the "fiction" aspect of I-F.

I think an interesting discussion would be about how romance, 
intimacy, love, hate, AND sex (and the moral consequences), fit into 
the unique requirements of interactive fiction. Can we really get
the player to feel emotionally involved with the other characters?
Can we even get the player involved in his own character? 

Another issue involves the technical limitations of computer 
controlled characters, and still another involves interaction 
with characters who might be real humans somewhere over the network. 
( Star Trek has put an interesting spin on the first with
the use of the holodeck as a plot device, but of course it
presupposes a more advanced state-of-the-art.)

Jay Trischman


From florian.beck@lrz.uni-muenchen.de Thu Feb 27 09:51:45 MET 1997
Article: 22931 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!uninett.no!nntp.uio.no!news.radio.cz!CESspool!news.maxwell.syr.edu!newsfeed.nacamar.de!news.nacamar.de!news.nacamar.de!fu-berlin.de!informatik.tu-muenchen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Crime IF (was: Sex in I-F)
Date: Wed, 26 Feb 1997 22:49:07 GMT
Organization: Private GNU Site
Lines: 35
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m320a389p8.fsf@ue801di.lrz-muenchen.de>
References: <meta-1802970945270001@win7-dhcp.harlequin.com> <19970219153800.KAA15709@ladder01.news.aol.com>  <ant2100261cbM+4%@gnelson.demon.co.uk> <5et0cb$bmb@eve.enteract.com>
Reply-To: florian.beck@lrz.uni-muenchen.de
NNTP-Posting-Host: dial069.ppp.lrz-muenchen.de
X-Newsreader: Gnus v5.4.13/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:22931

sharvey@enteract.com (sharvey) writes:

> What I'd like to see is not romantic IF, but modern crime noir IF (my
> reasons _against_ the romance format are personal, ugly, and not suitable
> for family viewing).

I have been to the pictures this evening and saw 'Last Supper'. Now,
wouldn't this be something for IF :-) Quite simple, too, as it would
be perfectly clear what you have to do (otoh the player shouldn't be
*too* sure either).
 
> Anyone who's familiar with the work of James Ellroy will know what I have
> in mind.  A main character who's not the "save the world and be a hero"
> type so common in IF.  I think it would be a real kick in the genre to
> play an amoral character, like a mafia hitman, a loanshark, a bookie,
> something in that category.  Naturally, the player would still need to be
> a hero and achieve goals, but those goals would be somewhat less than
> honorable.  

This actually isn't to different from older games where you're running
around slaughtering trolls, dwarves and thieves.

Things like Pulp Fiction or 'From Dusk Till Dawn' (sorry, just in a
film mood today) are a bit different, as they focus a lot on
atmosphere. 

The old 'perfect crime' motive could work well. Or setting the scene
*after* the first crime has been committed. The player then had to try
to get away with it. (And forced to commit further crimes.) Care
should be taken to avoid the mindless "mercenary/hit squat/elite
soldier" plot where the enemy is bad, killing good, the own side right,
the morality stinks, and whole thing gets dead boring.

-- 
Flo


From Linards.Ticmanis@post.rwth-aachen.de Fri Feb 28 17:46:29 MET 1997
Article: 22974 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news-fra1.dfn.de!news-koe1.dfn.de!news.rwth-aachen.de!not-for-mail
From: Linards Ticmanis <Linards.Ticmanis@post.rwth-aachen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Adventure Game Writing Help?
Date: Fri, 28 Feb 1997 16:47:15 +0100
Organization: RWTH Aachen, Germany
Lines: 62
Message-ID: <3316FE03.1DF142B5@post.rwth-aachen.de>
References: <5eqkjh$inu@ruby.ucc.nau.edu> <5et5kq$e02@wanda.vf.pond.com> <5evk71$erk$2@neko.syix.com> <5evtel$cti@agate.berkeley.edu> <5f0n87$s4g@joker.rz.hu-berlin.de> <egh-2602971836460001@news.berkeley.edu>
NNTP-Posting-Host: s2m131.dialup.rwth-aachen.de
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (X11; I; Linux 2.0.28 i486)
Xref: news.lth.se rec.arts.int-fiction:22974

Erik Hetzner wrote:

> 
> Well, after reading a later post, he responds that he was only saying 
> that
> it didn't extract the interpreter as well as the game file. As well it
> shouldn't -- that's not what it's for, right? Would be a neat trick to
> extract the interpreter and use it for other games, though -- just to 
> see
> if it'd work.

the interpreter (at least the 'last V3' one) is contained in the reverse
utility, inftod64, also by PDD, which creates disk images from V3 story
files (except Lurking w/ Sound, which doesn't work obviously). 

> 
> To another post: yes, the .z5 game used both sides of the disk. I 
> haven't
> delved too deeply into the C64, so I don't know how hard things would > be
> to extract, except that it seems to me that it would make sense for 
> the
> interpreter to fit on part of one side, and to fill up the rest of the
> disk with the game, so it doesn't seem like too much of a problem.

The Z Machine has one intrinsic problem when considering older machines,
while it can well handle a game that's too big for the comp's main
memory, there's a problem with games larger than one disk (or disk side
for single side drives like the 1541).

Just consider this scenario: some really smart guy writes an Assembler
V5 parser that fits into 10KB, including Video RAM and Data (I doubt
that would be possible). Now we have two problems:

1.) Dynamic memory is limited to 54 KB (if you get sick and employ the
RAM inside the 1541, a tiny bit more.)

2.) The whole game size is limited to 54KB (RAM left) + 170 KB (second
disk side, again a bit more if you use 40 tracks) , making a whole of no
more than 220 KB possible. I guess there's a reason only the
Help-endowed "Solid gold" versions of V3 games and "Nord & Bert" as a
shorter V4 game were sold for the C64, but not the other V4-6 games. I
doubt the "solid gold" V5 machine was fully featured anyway, probably
some things like timed input were left out. 

Anybody like to give the V4 (N&B) and V5 (SG editions) parsers a try and
add them to "inftod64" ?

Also, I wonder when we will finally see a C128 mode in any of the
popular C64 EMUs other than "VICE".

Is there a ".d128" format in existence for storing (not necessarily
using) 1571 double sided disks on a PC ? Does a transfer program for the
C128 exist? Does anybody want to write a parser with REU1750 Support ? I
Guess a bunch of "no"s are the answers.


-- 

Linards Ticmanis

 The Master said, "The business of laying on the colors follows the
preparation of the plain ground."


From fake-mail@anti-spam.address Sat Mar  1 20:21:27 MET 1997
Article: 23007 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!uunet!in3.uu.net!207.22.81.9!europa.clark.net!mr.net!newsfeed.direct.ca!newsgate.direct.ca!fake-mail
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: TADS rope implementation, cont.
Date: Sat, 01 Mar 1997 01:01:17 -0800
Organization: tela design
Lines: 29
Message-ID: <fake-mail-ya02408000R0103970101170001@news.direct.ca>
References: <wheeler.1207590616A@newshost.cc.utexas.edu>
NNTP-Posting-Host: van-52-0428.direct.ca
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
x-no-archive: yes
X-Newsreader: Yet Another NewsWatcher 2.4.0
Xref: news.lth.se rec.arts.int-fiction:23007

In article <wheeler.1207590616A@newshost.cc.utexas.edu>,
wheeler@moontower.com (J. Robinson Wheeler) wrote:

> I think I recall in some game or other (Curses?) that the rope is 
> automatically untied from whatever as the player exits, to avoid this
> confusion, but that still leaves me not sure where to trap the exiting-
> a-room code, or the delicate, proper way to do so.

 Check out adv.t and look for the addLeaveList() function. That function
and each location's leaveRoom( actor ) method is probably what you want to
look at.

 The idea is you register each problematic object with the room it's in.
Then, when the player leaves the room, the leaveRoom code goes through and
triggers the .leaving method for each object that's a problem. You then
have to write a chunk of code that does the dirty work - figuring out if
the player is carrying the rope, if anything's tied to it, etc.

>                                          --- COMING SOON --
> Rob Wheeler                       An exciting TADS adventure with a 
> wheeler@moontower.com                 rope item in it somewhere!

 Woo hoo! :)

 - Neil K.

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From spatula@underground.error.net Sun Mar  2 10:40:48 MET 1997
Article: 23016 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsxfer.itd.umich.edu!newsxfer3.itd.umich.edu!newsfeed.internetmci.com!avalon.net!spatula
From: spatula@underground.error.net (they got purple; purple's a fruit)
Newsgroups: rec.arts.int-fiction
Subject: Re: Kylie Minogue
Date: 2 Mar 1997 06:58:29 GMT
Organization: Pulling Mussels From The Shell
Lines: 56
Message-ID: <slrn5hi95a.pf1.spatula@underground.error.net>
References: <33132E32.3BBC@aha.ru>  <ant2523570b0c4bn@arnod.demon.co.uk> <5faqvo$d5l@chile.earthlink.net>
NNTP-Posting-Host: underground.error.net
X-Newsreader: slrn (0.8.8.4 (BETA) UNIX)
Xref: news.lth.se rec.arts.int-fiction:23016

And behold, Cardinal Teulbachs <cardinalt@earthlink.net> did spake, speaking:
> Julian Arnold <jools@arnod.demon.co.uk> made so bold as to state:
> >The other part recoils in fear and says, "Jools, just move on, forget
> >you ever read this."
> 
> You think you've got problems? I didn't even know what a Kylie Minogue
> was. I thought it was some kind of D&D monster or something.

Your foot bumps into a compact disc jewel case, sending it clattering down
the stairs.  Far below, you hear a startled snort, and then an angered
bellow.  You have awakened the Kylie Minogue!

Now what? RUN LIKE HELL

That's not a valid direction.

A horrible scraping - as horrible as nails on a chalkboard - emanates from
below, as yellowed claws scrape at the granite stairs in an attempt to
reach you.

Now what? SHUT THE DOOR

There is no door, only stairs below.

A horrid visage slowly comes into view from the blackness below as the
creature shambles up the stairs, a face of true evil, a horrible spectral
mask that could only be of the creature known as the Kylie Minogue.

Now what? KILL KYLIE MINOGUE

With what do you want to kill the Kylie Minogue?

Now what? WITH MY SWORD, YOU DAMN PRIMITIVE PARSER

Hey, this is a Z5 story file, pal, I'm hardly primitive.

You have wasted enough time.  In the precious seconds it took you to argue
semantics with the parser, the Kylie-beast has completed its demonic
ascent, reaching with slime-encrusted tentacles out for your head, and
before you can gasp "Australian pop", your entire front torso is rent from
your lower half and devoured messily in a horrid orgy of teeth and blood
and choruses of The Locomotion.  Kylie Minogue shambles back down the
stairs to continue its fearsome sleep, snoring underneath the stone steps
until the next fool ventures down and fails his saving roll...

			*** You have died. ***


- spatch, i wouldn't even know how to solve this puzzle -

-- 
derSpatchel resides at http://error.net/~spatula, among other places.
"But Basketball is a peaceful planet!  We have no weapons!"
          PUTPBAD 2: 94%     IQ DROPPED: 12%
                                                                  mstie#43790



From erkyrath@netcom.com Mon Mar  3 17:45:58 MET 1997
Article: 23045 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!news.stealth.net!ais.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: The tedium of annoyingly similar items
Message-ID: <erkyrathE6Ft2D.9MK@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5fcr59$r3h@eve.enteract.com>
Date: Sun, 2 Mar 1997 22:27:49 GMT
Lines: 72
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23045

sharvey (sharvey@enteract.com) wrote:
> Allow me to preface this /rant/ by confessing that my gripe comes of a
> graphic adventure, not "pure IF", but I've seen it parsed as well as
> rendered, so...

The difference is not totally transparent. Many graphic games use 
inventory-management schemes which are a pain in the butt; it can take 
significant time to scroll through all the items you have, and sometimes 
you have to do this every time you want to use an object. In text IF the 
"inventory" command is almost always very quick. And you *don't* have to 
use it every time you need a different crystal rod.

> Why do designers insist upon heaping players' inventories with dozens of
> items that are annoyingly similar? 

I have seven keys, two dozen coins, a wallet containing several dozen 
cards, and a billfold containing eight bills and fifteen business cards 
in my pockets. That's life.

> In the game, I've found maybe only 5 "classes" of items: symbol plaques,
> design plaques, crystals, tuning forks, and lenses.  The problem, however,
> is that I've lugged around literally DOZENS of items, many of which are
> virtually identical to each other.  The problem is that the symbol plaques
> function mainly as keys to doors, fitting the appropriate one according to
> a pattern you must decipher.  However, since you're carrying 17 different
> plaques, it's more a case of scrolling through an inventory than solving
> the puzzle.

Not my interface. 

> Infocom's contribution to this truly annoying phenomenon were the rods in
> Starcross.  A black rod, a white rod, a chartruce rod, a silver rod, a
> burnt umber rod, and so on.

And so what? It made sense, in context. A computer room is going to have 
dozens of differently-labelled floppy disks. The Starcross technology 
used lots of colored rods. 

If I have a building with locked doors, I'm going to have to strain 
awfully hard to explain why the first one is opened by a key, the second 
by a pencil, the third by a frog, the fourth by a brass lantaern... keys 
open doors. 

> For example, if you wanted to implement picking a lock, would you make the
> player go through ten or twelve different picks to find the one that
> opened the door?

That entirely depends on what I wanted the effect to be. If the 
protagonist is picking this lock for the first time in his life, or if 
it's a sudden, strange, unexpected experience, I'll make the player try 
several picks. Ditto if the lockpicks are unfamiliar to him. *Definitely* 
if any of these are true *and* there are guards closing in, so that the 
player is under time pressure.

But if the protagonist picks locks every day, and is using his own set of 
picks, or if it's near the end of the game and he's done it a dozen 
times, I'd make it a one-command thing.

> I know that one method is difficult, challenging, and maybe even more
> realistic.  However, we can never forget that these are games, meant to be
> fun.  

Sometimes I want a scene where the player does something difficult. 
Sometimes I don't. The decision is not made at random, and it's certainly 
not determined by what I feel like programming.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Mon Mar  3 23:50:10 MET 1997
Article: 23057 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!www.nntp.primenet.com!nntp.primenet.com!europa.clark.net!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: The tedium of annoyingly similar items
Message-ID: <erkyrathE6HF7E.GA6@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5fcr59$r3h@eve.enteract.com> <erkyrathE6Ft2D.9MK@netcom.com> <5ff5t7$k4d@curofix.ida.liu.se>
Date: Mon, 3 Mar 1997 19:23:37 GMT
Lines: 47
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23057

FReDRiK RaMSBeRG (WILdcARD) (d91frera@ida.liu.se) wrote:
> erkyrath@netcom.com (Andrew Plotkin) writes:

> >sharvey (sharvey@enteract.com) wrote:
> >> Why do designers insist upon heaping players' inventories with dozens of
> >> items that are annoyingly similar? 

> >> Infocom's contribution to this truly annoying phenomenon were the rods in
> >> Starcross.  A black rod, a white rod, a chartruce rod, a silver rod, a
> >> burnt umber rod, and so on.

> >And so what? It made sense, in context. A computer room is going to have 
> >dozens of differently-labelled floppy disks. The Starcross technology 
> >used lots of colored rods. 

> Can anyone who played Starcross say that the rods scattered about made sense.

To a certain extent. It was supposed to be an intelligence test, and 
furthermore one which a lot of beings had failed already, so all the toys 
had been picked up and played with and thrown away and gnawed on by 
rat-ants. 

> How often do you need 10 or so different keys to open all doors in a building?

Sometimes this is silly. But it's often a *high-security* building, or
lab, or control center, or whatever. Just because genre writing tends to
such places. The complex in Planetfall was very plausible to me, for
example; lots of different keycards and keys for various areas, most of
which had valuable or dangerous equipment in them. 

> Leaving that aside, it's true that you have many similar objects in real life.
> IF is a way to get away from real life for a while, so it doesn't have to
> model boring things unless it's necessary for the credibility of the plot or
> the environment.

Anyway, were the rods in Starcross really boring? I mean, you didn't just
sit around and juggle them; their manner of use was pretty obvious once
you figured it out, so there was no need to try every rod in every
possible usage. The interesting part of the game was the situations you
found them in. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mol@bartlet.df.lth.se Tue Mar  4 19:52:18 MET 1997
Article: 23079 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Supersedes: <5fhmrg$89d@bartlet.df.lth.se>
Date: 4 Mar 1997 18:41:51 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 79
Message-ID: <5fhmsv$8jo@bartlet.df.lth.se>
References: <5egglv$jeq@curofix.ida.liu.se> <m34tf7bhar.fsf@ue801di.lrz-muenchen.de> <5ei4g6$6ra@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23079

In article <5erfa4$8dp@kjahds.com>,
Kenneth Albanowski <kjahds@kjahds.com> wrote:
>In article <5ei4g6$6ra@curofix.ida.liu.se>,
>FReDRiK RaMSBeRG (WILdcARD) <d91frera@ida.liu.se> wrote:
>>
>>Something I think a lot of people (including myself) tend to forget, is that
>>we're trying to create an illusion for the player. If the player never
>>realizes that your actors are purposefully avoiding the use of information
>>they should not have aquired, why spend effort building it that way?
>
>I think because it's generalized, and lets you build NPC by knowledge rules
>instead of action scripts.
>
>Also think of it from the perspective of a player trying unusual commands.

I think Fredrik's advice is excellent, and something that should be
kept in mind at all times. To draw the argument to its extreme, when
people argue that NPC's need AI to be convinving, I like to remind
them that writers of static fiction have been creating convincing
characters for millenia, and a character in a book doesn't have a
shred of intelligence, being entirely non-interactive.

So interactivity obviously has something to do with it. It seems as if
the more the player is going to interact with some entity in our game,
the more detailed must the way it's modelled be. But the model doesn't
have to exhibit more detail than is needed to maintain the illusion.

An example with NPC's:

Suppose we have a game where you (the player) and your rival Nevada
Smith (an NPC) are searching the labyrinthine tomb of king
Quezcoatleclatl for treasure. All the treasure is hidden in the
innermost chamber. 

Now, if all the author wants is a final confrontation with Smith, then
it's perfectly OK to "cheat" and just move him to the innermost
chamber; no need to have the NPC walk through the maze if the player
will never see any difference (in terms borrowed from quantum
physics, Smith's trek through the maze, while implied by the logic of
the story, is unobservable). 

The same applies if you want the player to meet Smith halfway through
the maze - just move him there, and then when the encounter is
over, move him to the final chamber in time for the final
confrontation.

But what if the player's encounter with Smith can have consequences
for the final encounter? For example, if the player tells Smith
something that deludes him about the shortest way through the maze, or
if the player gets into a fight with him and hurts him so he moves
more slowly? Or what if the player removes clues on the way, hoping
that Smith will be delayed (if he isn't ahead of the player and has
already seen them)?

Up to a point, we can "cheat" by modelling this in an ad-hoc way: if
the player leaves all the clues in place, Smith will appear in the
final chamber one move after the player; for each clue tampered with,
Smith arrives one move later.

But we'll reach a point of complexity where it's actually simpler to
make a "realistic" model: an NPC that really *does* find its own way
through the maze, dealing with clues, doors and traps as it encounters
them. For example, suppose the maze has movable walls, and the player
moves them around to confuse Smith? That would be a nightmare to model
in any other way than actually giving Smith a maze-solving algorithm
and let him traverse the (dynamically changing) maze together with the
player.

But before attempting such a feat, the author must consider exactly
what he's trying to achieve. Let's not swat flies with sledgehammers!




-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From mol@bartlet.df.lth.se Tue Mar  4 19:53:38 MET 1997
Article: 23080 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Recursion and IF
Date: 4 Mar 1997 19:51:54 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 128
Message-ID: <5fhr0a$ndr@bartlet.df.lth.se>
References: <erkyrathE6ELyG.M9E@netcom.com> <5fff0j$f5l@wanda.vf.pond.com> <wheeler.1207825374A@newshost.cc.utexas.edu> <5fg2c8$j1i@nntp5.u.washington.edu>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23080

In article <5fg2c8$j1i@nntp5.u.washington.edu>,
Dan Shiovitz <scythe@u.washington.edu> wrote:
>In article <wheeler.1207825374A@newshost.cc.utexas.edu>,
>J. Robinson Wheeler <wheeler@moontower.com> wrote:
>>
>>>>To which I can only add: Do not do deep recursion in TADS programs. It
>>>>breaks Mac interpreters.
>>>
>>>For loops are your friend.
>>>
>>
>>This sounds like good advice -- only I'm a little taken aback because,
>>although I am currently finishing up a rather large TADS game, I have 
>>yet to conceive any use for recursion (slight or deep).  I barely had
>>2 uses for a tiny For loop.
>>
>>Maybe I'm doing it wrong.... <shrug>
>
>Nah. 90% of i-f coding is composed of printing text, setting
>variables, testing if variables are set, and setting daemons that set
>variables and print text and test if variables are set. 

Indeed. And most of the coding-intensive stuff consists of lots of
special cases where you have to check what happens under different
circumstances.

However, there are some problems that appear in IF coding that are
more like the classic problems of CS, and where recursion can be
useful. One such problem that has been discussed a lot on this
newsgroup is finding a path between two rooms; another, much simpler
one, is finding the outermost container containing a given object (if
the radioactive sample is in the envelope in the pocket of my jacket,
which I'm carrying in a bag, I still want the Geiger counter to detect
that there's radiation coming from my bag), and a more complicated
relative of this problem is the tracing of "sense paths" a la
WorldClass.

Not to speak of the parsing problem, of course, but few Inform, TADS
or HUGO programmers have to worry about that.

But the fact that recursion is useful in thinking about these problems
doesn't mean that they have to be coded using recursion. In fact, all
recursive algorithms can be re-formulated iteratively, and vice versa.

Since both the TADS runtime and the Z machine don't have very much
stack space, it's probably best to avoid recursion in those languages,
as long as we're not certain that the recursion will bottom out
quickly (such as in the Geiger counter example; my example has five or
six levels of recursion depending on how you count, and it's already
quite contrived).


About recursion in general:

To begin with, there's the fact that there are often two ways of
thinking about a problem, the recursive way and the iterative way, and
sometimes the recursive way of thinking is much simpler and yields as
clearer understaning of the problem. For example, consider sorting a
list of numbers. This can be done by dividing the list in two lists,
sorting each of them, and then merging the sorted lists so the merged
list is sorted. Merging is simple, and as for sorting the smaller
lists - well, we just keep applying the same tactic recursively until
the lists are of size 1 (and sorting a list of size 1 is not very
difficult). And lo and behold: we've just re-invented quicksort.

Recursion can also be very economic in cases where an iterative
algorithm would have to build up some data structure as it goes. A
cleverly written recursive algorithm builds such a structure on the
call stack. 

But uncritical application of recursion can lead to terribly
inefficient algorithms, such as this one (to compute Fibonacci
numbers):

double fib(unsigned n)
{
  if (n < 3)
    return 1;
  else
    return fib(n - 1) + fib(n - 2);
}

which is simple and looks elegant, but performs terribly compared to the
iterative

double fib(unsigned n)
{
   double a = 1;
   double b = 1;
   unsigned i;

   for (i = 3; i <= n; ++i) {
     double temp;
     temp = a + b;
     a = b;
     b = temp
   }
   return b;
}

The reason is that the recursive algorithm makes _two_ recursive
calls, each of which does essentially the same thing, leading to an
exponentially exploding duplication of work. A much better recursive
algorithm does the same thing as the iterative one, but uses the stack
for temporary storage:

double fib(unsigned n)
{
  return fibsub(n, 1, 1);
}

double fibsub(unsigned n, double a, double b)
{ 
  if (n < 3)
    return b;
  else
    return fibsub(n - 1, b, a + b);
}

The last function fibsub may look opaque, but if you think about it
a little it very nicely exhibits the way the Fibonacci series is
generated - "shift and apply the same operation again".




-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From wheeler@moontower.com Wed Mar  5 09:21:07 MET 1997
Article: 23087 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsxfer.itd.umich.edu!newsxfer3.itd.umich.edu!howland.erols.net!cs.utexas.edu!geraldo.cc.utexas.edu!newshost!wheeler
From: wheeler@moontower.com (J. Robinson Wheeler)
Newsgroups: rec.arts.int-fiction
Subject: Re: Recursion and IF
Date: Tue, 4 Mar 97 23:38:39 GMT
Organization: The University of Texas at Austin, Austin, Texas
Lines: 60
Message-ID: <wheeler.1207906359B@newshost.cc.utexas.edu>
References: <erkyrathE6ELyG.M9E@netcom.com> <5fff0j$f5l@wanda.vf.pond.com> <wheeler.1207825374A@newshost.cc.utexas.edu> <5fg2c8$j1i@nntp5.u.washington.edu> <5fhr0a$ndr@bartlet.df.lth.se>
NNTP-Posting-Host: slip-39-6.ots.utexas.edu
X-Newsreader: VersaTerm Link v1.1
Xref: news.lth.se rec.arts.int-fiction:23087

mol@bartlet.df.lth.se (Magnus Olsson) wrote:
>Dan Shiovitz <scythe@u.washington.edu> wrote:
>>J. Robinson Wheeler <wheeler@moontower.com> wrote:
>>>Maybe I'm doing it wrong.... <shrug>
>>
>>Nah. 
>
>Indeed. And most of the coding-intensive stuff consists of lots of
>special cases where you have to check what happens under different
>circumstances.
>
>However, there are some problems that appear in IF coding that are
>more like the classic problems of CS, and where recursion can be
>useful. One such problem that has been discussed a lot on this
>newsgroup is finding a path between two rooms; another, much simpler
>one, is finding the outermost container containing a given object (if
>the radioactive sample is in the envelope in the pocket of my jacket,
>which I'm carrying in a bag, I still want the Geiger counter to detect
>that there's radiation coming from my bag), and a more complicated
>relative of this problem is the tracing of "sense paths" a la
>WorldClass.

Oh, good.  This is exactly the info I was hoping to elicit with my
"maybe I'm doing it wrong" post.  I just wanted to make sure I'd know
how to approach certain IF coding problems in case they come up in 
some other game.

>About recursion in general:
>
>To begin with, there's the fact that there are often two ways of
>thinking about a problem, the recursive way and the iterative way, and
>sometimes the recursive way of thinking is much simpler and yields as
>clearer understaning of the problem. 
>
>Recursion can also be very economic in cases where an iterative
>algorithm would have to build up some data structure as it goes. A
>cleverly written recursive algorithm builds such a structure on the
>call stack. 


Thanks also for the overview of recursion vs. iteration, with examples.
It's always been a little baffling to me to learn to "think recursively,"
as they say in CS classes.  After a long childhood of playing with 
computers on my own, I was completely stymied when this concept was
introduced, because I'd never come across it before.  (There were other
guys in the class who had apparently been doing some work with recursion
on their C-64s, and they quickly sped ahead in the class while I lagged
behind.)  Although I now for the most part "Get it," finally, I still
tend to think iteratively unless beaten over the head to do otherwise.

That's why I was a little afraid, perhaps, that there was some more
general IF coding application, for which recursion was well-suited,
that I was failing to recognize.





Rob Wheeler                                     - COMING SOON -
wheeler@moontower.com


From gerlach7@nospam.address Wed Mar  5 09:22:02 MET 1997
Article: 23089 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!vixen.cso.uiuc.edu!uchinews!news.luc.edu!newsfeed.acns.nwu.edu!news.acns.nwu.edu!news	
From: Charles Gerlach <gerlach7@nospam.address>
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (Very Mild Hijinx spoiler)
Date: Tue, 04 Mar 1997 17:07:22 -0600
Organization: Northwestern University, Evanston, IL, US
Lines: 48
Message-ID: <331CAB2A.5DF@nospam.address>
References: <5egglv$jeq@curofix.ida.liu.se> <m34tf7bhar.fsf@ue801di.lrz-muenchen.de> <5ei4g6$6ra@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se>
NNTP-Posting-Host: tam1.mech.nwu.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (X11; I; HP-UX B.10.10 9000/720)
Xref: news.lth.se rec.arts.int-fiction:23089

Magnus Olsson wrote:

>But the model doesn't
> have to exhibit more detail than is needed to maintain the illusion.
> 
(Maze example snipped)

It was precisely in the maze of Hollywood Hijinx that my illusions
were shattered. If I remember right, I was in a spot like this:

|---|    |
|        |
|        |
|   |    |
|   |    |_____
|   |     
|   | ME 
----------------
South side of maze

when I got the message about hearing a noise on the other side 
of the hedge. Since I could see to the north and east, the noise 
had to be either to the south or west (if you take them literally 
that the noise was on the other side of the hedge). Since south 
was outside the maze entirely, I figured the noise-maker was 
in the dead-end with no escape.

Of course, he's not there at all; HH just puts in random messages 
like that to freak you out and make you think there is someone 
else lurking around. I know that this has been pointed out 
before. Other people have heard the noise coming from a dead-end 
in the house and been similarly disappointed at their inability 
to catch the jerk. 

I probably would have been much more frustrated if the NPC had 
been written like the thief, and moved my stuff around from where 
I had left it, and used the elevator in the house so that I 
couldn't-- but you need to be careful with things that are 
just meant to give the "feel" of something happening without 
the relevant framework underneath, especially when that framework
can be tested from within the game. 

-- 
**********************************************************************
Charles Gerlach does not speak for Northwestern, and can be mailed at: 
cagerlac  a t  merle  d o t  acns  d o t  nwu  d o t  edu
He hopes that placing his e-mail in this format did not seriously 
inconvenience anyone attempting to contact him (except for spam-bots).


From gerlach7@nospam.address Wed Mar  5 12:30:22 MET 1997
Article: 23089 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!vixen.cso.uiuc.edu!uchinews!news.luc.edu!newsfeed.acns.nwu.edu!news.acns.nwu.edu!news	
From: Charles Gerlach <gerlach7@nospam.address>
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (Very Mild Hijinx spoiler)
Date: Tue, 04 Mar 1997 17:07:22 -0600
Organization: Northwestern University, Evanston, IL, US
Lines: 48
Message-ID: <331CAB2A.5DF@nospam.address>
References: <5egglv$jeq@curofix.ida.liu.se> <m34tf7bhar.fsf@ue801di.lrz-muenchen.de> <5ei4g6$6ra@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se>
NNTP-Posting-Host: tam1.mech.nwu.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (X11; I; HP-UX B.10.10 9000/720)
Xref: news.lth.se rec.arts.int-fiction:23089

Magnus Olsson wrote:

>But the model doesn't
> have to exhibit more detail than is needed to maintain the illusion.
> 
(Maze example snipped)

It was precisely in the maze of Hollywood Hijinx that my illusions
were shattered. If I remember right, I was in a spot like this:

|---|    |
|        |
|        |
|   |    |
|   |    |_____
|   |     
|   | ME 
----------------
South side of maze

when I got the message about hearing a noise on the other side 
of the hedge. Since I could see to the north and east, the noise 
had to be either to the south or west (if you take them literally 
that the noise was on the other side of the hedge). Since south 
was outside the maze entirely, I figured the noise-maker was 
in the dead-end with no escape.

Of course, he's not there at all; HH just puts in random messages 
like that to freak you out and make you think there is someone 
else lurking around. I know that this has been pointed out 
before. Other people have heard the noise coming from a dead-end 
in the house and been similarly disappointed at their inability 
to catch the jerk. 

I probably would have been much more frustrated if the NPC had 
been written like the thief, and moved my stuff around from where 
I had left it, and used the elevator in the house so that I 
couldn't-- but you need to be careful with things that are 
just meant to give the "feel" of something happening without 
the relevant framework underneath, especially when that framework
can be tested from within the game. 

-- 
**********************************************************************
Charles Gerlach does not speak for Northwestern, and can be mailed at: 
cagerlac  a t  merle  d o t  acns  d o t  nwu  d o t  edu
He hopes that placing his e-mail in this format did not seriously 
inconvenience anyone attempting to contact him (except for spam-bots).


From mol@bartlet.df.lth.se Wed Mar  5 12:30:46 MET 1997
Article: 23097 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Recursion and IF
Date: 5 Mar 1997 10:38:33 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 33
Message-ID: <5fjeup$7hc@bartlet.df.lth.se>
References: <erkyrathE6ELyG.M9E@netcom.com> <5fg2c8$j1i@nntp5.u.washington.edu> <5fhr0a$ndr@bartlet.df.lth.se> <5fhv27$i4r@curofix.ida.liu.se>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23097

In article <5fhv27$i4r@curofix.ida.liu.se>,
FReDRiK RaMSBeRG (WILdcARD) <d91frera@ida.liu.se> wrote:
>mol@bartlet.df.lth.se (Magnus Olsson) writes:
>>For example, consider sorting a
>>list of numbers. This can be done by dividing the list in two lists,
>>sorting each of them, and then merging the sorted lists so the merged
>>list is sorted. Merging is simple, and as for sorting the smaller
>>lists - well, we just keep applying the same tactic recursively until
>>the lists are of size 1 (and sorting a list of size 1 is not very
>>difficult). And lo and behold: we've just re-invented quicksort.
>
>Mergesort, that is. 

Oops. Sorry. You're of course correct.

Just in case any of the IF people without a CS background are
interested, quicksort is built on the same basic idea as mergesort
(divide-and-conquer), but in quicksort you don't merge the lists
afterwards. Instead you start by dividing the initial list into a "left"
and a "right" part (not necessarily of equal size), shuffle the elements
so that all elements in the left list are smaller than those of the
right list, and then sort each of the lists.

Legend has it that recursive programming (not recursion, of course,
that's always been around :-) ) was invented by the guy who invented
quicksort: he started out coding the routine iteratively, and then
found out that the nicest way of implementing it would be to have it
call itself, pushing intermediate values on a stack.

End of digression. Back to Interactive Fiction.

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From fake-mail@anti-spam.address Wed Mar  5 12:31:02 MET 1997
Article: 23091 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!news.stealth.net!cdc2.cdc.net!vixen.cso.uiuc.edu!howland.erols.net!feed1.news.erols.com!news.ecn.uoknor.edu!news.wildstar.net!newsfeed.direct.ca!newsgate.direct.ca!fake-mail
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Date: Tue, 04 Mar 1997 14:09:15 -0800
Organization: tela design
Lines: 28
Message-ID: <fake-mail-ya02408000R0403971409150001@news.direct.ca>
References: <5egglv$jeq@curofix.ida.liu.se> <m34tf7bhar.fsf@ue801di.lrz-muenchen.de> <5ei4g6$6ra@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se>
NNTP-Posting-Host: van-52-0209.direct.ca
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
x-no-archive: yes
X-Newsreader: Yet Another NewsWatcher 2.4.0
Xref: news.lth.se rec.arts.int-fiction:23091

In article <5fhmsv$8jo@bartlet.df.lth.se>, mol@bartlet.df.lth.se (Magnus
Olsson) wrote:

> I think Fredrik's advice is excellent, and something that should be
> kept in mind at all times. To draw the argument to its extreme, when
> people argue that NPC's need AI to be convinving, I like to remind
> them that writers of static fiction have been creating convincing
> characters for millenia, and a character in a book doesn't have a
> shred of intelligence, being entirely non-interactive.

 Well, I'm afraid I'd argue that the success of static fiction in creating
believable NPCs derives in large part *because* of the total lack of
interactivity. The author creates the entity like the beautifully realistic
facades built for movie sets. If you look at the set from the right camera
angle then it looks real - it's when you walk around it to the back that
you see the "structural truth" of plywood and plaster.

 Same with fiction. The author writes down the words; you can't change
them. So you can't go poking around, asking the character questions,
because everything's there and presented before you. IF, with its carefully
constructed illusion of choice, allows you to step behind the sets. And
therein lies a problem.

 - Neil K.

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From mol@bartlet.df.lth.se Wed Mar  5 12:31:06 MET 1997
Article: 23098 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Date: 5 Mar 1997 12:28:32 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 53
Message-ID: <5fjld0$trp@bartlet.df.lth.se>
References: <5egglv$jeq@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se> <fake-mail-ya02408000R0403971409150001@news.direct.ca>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23098

In article <fake-mail-ya02408000R0403971409150001@news.direct.ca>,
Neil K. <fake-mail@anti-spam.address> wrote:
>In article <5fhmsv$8jo@bartlet.df.lth.se>, mol@bartlet.df.lth.se (Magnus
>Olsson) wrote:
>
>> I think Fredrik's advice is excellent, and something that should be
>> kept in mind at all times. To draw the argument to its extreme, when
>> people argue that NPC's need AI to be convinving, I like to remind
>> them that writers of static fiction have been creating convincing
>> characters for millenia, and a character in a book doesn't have a
>> shred of intelligence, being entirely non-interactive.
>
> Well, I'm afraid I'd argue that the success of static fiction in creating
>believable NPCs derives in large part *because* of the total lack of
>interactivity. 

That's true, of course. And it's just that point that I made (albeit
less forcefully) in the next sentence (which you snipped).

> Same with fiction. The author writes down the words; you can't change
>them. So you can't go poking around, asking the character questions,
>because everything's there and presented before you. IF, with its carefully
>constructed illusion of choice, allows you to step behind the sets. And
>therein lies a problem.

My point is that IF has an *illusion* of choice. Unless you want to
solve an AI complete simulation problem, at some point or another you
have to stop the player from peeking behind the sets. 

A tendency I've seen in some posts from beginning IF authors is that
they assume that (to continue your metaphor) if they want the town in
the movie to look real, they'll have to build real houses with
backsides, rooms inside them, gardens, and so on. That can of course
be required: if the camera will follow the hero into the saloon,
you'll have to build the inside of it. But if your script only calls
for exterior shots, a simple, two-dimensional set would be just as
effective and much cheaper.

For it's all a matter of economy. Don't get me wrong: I love detail, I
love interactivity, I love to be able to go behind the sets and see
that everything really *works*, even though it's not needed for the
story. But if the extra realism means that the game will never be
finished, because it will need five man-years of programming rather
than five man-months, then I'd prefer the cardbord illusion.

(An example in point is "Undertow" from the 1995 competition, where
the author had obviously spent a lot of time ensuring that the taps
and sinks in the bathroom worked; time that IMHO had been better spent
correcting bugs).


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From mkkuhner@phylo.genetics.washington.edu Thu Mar  6 10:17:54 MET 1997
Article: 23110 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!CESspool!www.nntp.primenet.com!nntp.primenet.com!news.sgi.com!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: When is enough enough?
Date: 5 Mar 1997 22:34:22 GMT
Organization: University of Washington, Seattle
Lines: 65
Message-ID: <5fksde$cd8@nntp5.u.washington.edu>
References: <wheeler.1207908142C@newshost.cc.utexas.edu>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:23110

wheeler@moontower.com (J. Robinson Wheeler) writes:
>As an IF author, do I really have to make sure every last "scrape parrot"
>example is handled?  When do I get to quit and say "Okay, I've trapped
>enough peculiarities -- enough's enough," and move on to the next bit?
>Or, better yet, call the game done?

You have to balance the need to finish the game against that nasty lurch
the player will feel when s/he has a brilliant and apparently sensible
idea, and the game totally fails to cope with it.  (I crashed one of the
competition games with "tie rope to me", a command that seemed quite
reasonable at the time.)  Playtesters are probably the ones to tell
you if you're there yet.

>It is occurring to me that there are a lot of players who will find the rope
>and then carry it around all over the place, tying it to everything in 
>sight and perhaps getting weird responses.  

A rope is such a damnably useful object that it is natural for the
player to apply it willy-nilly, and it's really hard to see why "tie
rope to bedpost" should fail.  I'd be inclined to try to part the player
>from the rope ASAP, or else give the rope a second use.  Objects which
seem really useful but only do one thing exasperate me as a player.

The classical answer to ropes is to use them to climb down and then be
unable to untie them, like the one in Sherbet.  Or you could break them, 
though even a bit of rope might be a pest.

>My other hangup, and this has made my code swell to probably twice the size
>it need be, is that I feel compelled to put in decorative objects all over
>the place just so that the parser recognizes the significant words of a
>room's long description.  I probably feel like this because I like to find
>the game to be relatively "smart" about what it's describing when I'm playing.

I'm fairly happy with "You don't need to refer to that" which in Inform
is programmatically easy and doesn't need separate objects for each bit of
scenery.  I really dislike a room full of scenery none of which is even
known to the parser; getting "I don't see any X here" repeatedly as I
try to find the one real object spoils the game illusion.

On the other hand, to my tastes movable bits of useless stuff stop being
desirable quite quickly.  I don't want dishes, ashtrays, etc. as real
objects just because they'd be in the house.  A couple of red herrings
is plenty.  (I'm an implacable foe of inventory-management issues in
IF.)

>I guess what I'm going for is that one at least has to keep up whatever
>pattern that one establishes early on in the game, even if it's a pain
>in the neck to code.  Or -- is there a real point of diminishing returns,
>and consistency can get stuffed after that point?

Most games I've played sluff a bit towards the end.  Perhaps for related
reasons, most IF games are anticlimatic--the best material is near
the beginning.  (Look at the XYXXY awards for "Best single puzzle.")
I think if one part has to be weak, the end is not the best choice, 
though it's better than the beginning.  (On the other hand, a lovely 
first two rooms followed by an average game is likely to really 
frustrate players, whose expectations by that point are impossibly 
high; so lavishing everything on the beginning isn't a good answer either.)

>From the player's point of view, of course, the answer is "Lavish detail
on everything."  It's possible to have too many rooms or objects, but
I've never seen a game with too much detail work in programming
responses to actions.  But then the game never gets finished.  Sigh....

Mary Kuhner mkkuhner@genetics.washington.edu


From mol@bartlet.df.lth.se Thu Mar  6 10:18:27 MET 1997
Article: 23118 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Missing during-routines
Date: 6 Mar 1997 10:16:37 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 46
Message-ID: <5fm21l$f59@bartlet.df.lth.se>
References: <5flo2q$njq@curofix.ida.liu.se>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23118

In article <5flo2q$njq@curofix.ida.liu.se>,
FReDRiK RaMSBeRG (WILdcARD) <d91frera@ida.liu.se> wrote:
>While getting in to a (sort of) large project in Inform, I've felt for quite
>a while that something important is wrong with the way actions are processed.
>Until now, I couldn't put my finger on it. Now I think I can.
>
>A group 2 action consist of 3 steps, before during and after. Group 3 actions
>never even get to the after step. While claiming to have full object
>orientation, Inform will not let the objects interfere with the most
>critical step, during. 

To be slightly pedantic: Inform the language is (more or less) fully OO,
the Inform library certainly isn't, and doesn't claim to either.

>This has one severe drawback, implying several others;
>You can not, in an object definition, write your own code to deal with the
>action _and_ signal that it is a success. If you write your own code in the
>before-rule, you must return true to stop the normal effects from happening.

[...]

>The natural place for the code to insert liquids is in the non-existant
>during-rule. Then, all before-rules will have their chance to interact, and
>if none of them choose to do so, the actual action can take place, followed
>by the after rules, if it succeeded.
>
>Am I overlooking something here, or am I just plain wrong?

I certainly don't think you're wrong. In fact, your criticism of the
Inform library is very similar to mine (see the "Inform library
criticism" thread from a few months ago): that while "before" and
"after" rules are OO, the main action routines are as un-OO as you can
get. In fact, for those who haven't studied the library source, the
"during" stage is handled by action routines, one for each action, and
the action routines contain lots of test for all special cases Graham
could think of when he wrote the Library. The problem is that it's
quite hard to add one more special case in the middle of an action
routine, without replacing the entire routine, and then we run into
problems when the library is updated. It violates encapsulation and
all that.

Your proposed "during" rules would solve at least part of the problem.


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From mgraham@cega.demon.co.uk Thu Mar  6 16:56:32 MET 1997
Article: 23120 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!newsfeed.uk.ibm.net!ibm.net!arclight.uoregon.edu!dispatch.news.demon.net!demon!cega.demon.co.uk!cega.demon.co.uk!cega
From: Michael Graham <cega@cega.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: The tedium of annoyingly similar items
Date: Thu, 6 Mar 1997 01:57:29 +0000
Organization: Cega Ltd., Web Design Consultants
Distribution: world
Message-ID: <FOSazAAISiHzEwsy@cega.demon.co.uk>
References: <5fcr59$r3h@eve.enteract.com> <erkyrathE6Ft2D.9MK@netcom.com>
 <5ff5t7$k4d@curofix.ida.liu.se> <5ffanl$4fb@eve.enteract.com>
Reply-To: Michael Graham <mgraham@cega.demon.co.uk>
NNTP-Posting-Host: cega.demon.co.uk
X-NNTP-Posting-Host: cega.demon.co.uk
MIME-Version: 1.0
X-Newsreader: Turnpike Version 3.02 <8GdB6y3FvPYnxRxdS7oWRviWR2>
Lines: 184
Xref: news.lth.se rec.arts.int-fiction:23120

In article <5ffanl$4fb@eve.enteract.com>, sharvey <sharvey@enteract.com>
writes
>I did, however, toy with the idea of a player who was a hardcore
smoker,
>and contiunally fought the urge for a smoke.  I eventually gave it up
as
>gimmicky and "no fun", which is in my mind the downfall of all of these
>relentlessly realistic games.
>

At one point I was toying with "QUIT!" which would be a short little
experiment game.  In it, most of your time would be spent hiding your
cigarettes from yourself, finding things to distract yourself with, and
arguing with the parser:

        ======
The velvet bag is still tantalizingly out of reach of your outstretched
fingers. You feel the ladder rock dangerously under the ball of your
right foot, but your left knee is pretty firmly wedged in the crook of
the heating duct, so you figure you're safe for the moment.  You feel
your spine pop as you stretch another half-inch.  Sweat streaming into
your eyes, blood pounding in your ears, you hardly feel the ladder
slipping out from beneath you or hear it clatter down on the floor below
a moment later.  Desperately, you tease the loop of the bag with the tip
of your middle finger, until -- success! You hook your finger around the
string, and the bag is yours! A moment later you feel the duct groan and
give way. Twisting and grappling vainly, you fall...


QUIT!
An Interactive Tale of Will and Desperation
by Michael Graham


You land on the remains of your comfortable couch, in a slowly settling
cloud of plaster and dust. The velvet bag lies at your feet.

Living room (on the remains of the couch)
Light streams in from the south windows, revealing the sad extent of
your earlier frenzy. The room is a disaster area: magazines and
paperbacks are strewn all over the floor, the bookshelves and racks long
toppled and dismantled. A trail of dirty laundry leads east into your
bedroom, and a trail of broken dishes leads northwest into the kitchen.
The small bathroom ignores you silently to the north, and the the front
door stands bolted and insufferable to the west.

Luckily your earlier "search" of the couch resulted in this soft
pile of stuffing and cushions that broke your fall.

> get bag
Taken, taken, taken!  (Oh, how it is taken!)

> north
You'll have to extricate yourself from the couch first.

> get up
Your body screams in protest, but it has been doing that all day, and
you try not to notice. Pain shoots up your leg as you stand, muttering
something about a twisted ankle. You figure that it's doing it
deliberately, and so ignore it.

> north
You limp into the bathroom, pulling open the velvet bag as you go.
There's a carton of cigarettes inside!

[Your score has just gone down by one point]

Bathroom
It's not surprising that the bathroom is ignoring you, considering how
long you have neglected it. In fact the only attention you have paid it
in the last three weeks was to rifle its cabinets and drawers this
afternoon, searching for hidden cigarettes.

You pull out the carton of cigarettes, tossing aside the velvet
bag. A whole carton! What a find!

> put cigarettes in toilet
(first opening the toilet)
You lift up the seat. It's times like this that you're thankful for your
dulled sense of smell.

(first opening the carton of cigarettes)
Gingerly, you tug on the tab, salivating at the crisp sound the plastic
strip makes as it rends the foil-backed paper. You draw out the first
packet and with a fluid motion, strip it of celophane, thumb open the
top, and pull out the foil paper.

With trembling fingers, you draw out a cigarette, and place it between
your lips.

> again

Diligently, you let fall one packet, and watch as it floats lazily on
the surface of the murky water. Absently, you root around in your
pockets for a light. Now where are those matches?

> flush toilet

The water swirls hungrily around the cardboard packet, but fails to get
a grip. Good thing those cigarettes are packed in celophane.  You might
need those later.  Ah! There's that lighter!

> drop cigarette
Which cigarette do you mean?  The cigarette in your mouth, the
cigarettes in the open pack, the packet of cigarettes floating in the
toilet bowl, or the packets of cigarettes in the open carton?

> all
I'm sorry, but you can't use multiple direct objects when referring to
cigarettes.

> drop the cigarette in my mouth.

You the cigarette fall from your mouth. It bounces off the rim of 
the toilet and rolls across the floor, wedging itself into a crack 
beneath the bathtub.

> step on it
You can't reach it while it's wedged into the crack.

> score
It's been 3 hours, 53 minutes since your last smoke. Statistically, you
still have a greater chance of heart-disease than getting run over by a
bus.

> wait
You tried that all afternoon. It didn't work.

> diagnose
You're absolutely dying for a smoke. What else is new?

> imperial
Imperial mode.

> diagnose
You're absolutely dying for a fag. What else is new?

> south
You stagger out into the living room, pulling out another cigarette on
the way.

Living Room

> examine window
The windows are vintage 1930's workmanship, and are likely to remain so
for the duration of your tenancy. Something to do with the National
Trust, apparently. You make a mental note to write another angry letter.

You light the fag quickly, and take a long, satisfying pull on it.

[Your score has just gone down by one point]

> open window
The window creaks open, admitting a stale gust of wind from the
street. Exhaling with a sigh, you watch as the smoke curls lazily
around, in exuberent defience of the breeze.

> quit
Putting out that cigarette would be a good start.

> throw cigarette out window
(the lit cigarette)
What a waste! You've only taken one drag!

> throw cigarette out window
(the lit cigarette)
After taking one final drag, you flick the lit cigarette out the
window. A moment later, you hear a curse from down below.

> destroy cigarettes
You'll have to be more specific than that...

        ======

And so on. Quite aside from being annoying to play, it would be an
absolute nightmare to code. So it remains on the cutting room floor with
all my other bright ideas.


-- 
Michael Graham                             mailto:mgraham@cega.demon.co.uk
Cega Ltd. Web Design Consultants           http://www.cega.co.uk
London (Stratford), UK
Tel/Fax: +44-(0)181-221-2417


From whizzard@uclink.berkeley.edu Fri Mar  7 09:19:20 MET 1997
Article: 23135 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: When is enough enough?
Date: 6 Mar 1997 21:18:42 GMT
Organization: University of California at Berkeley
Lines: 28
Message-ID: <5fncbi$cg5@agate.berkeley.edu>
References: <wheeler.1207908142C@newshost.cc.utexas.edu> <5finf8$85m@vixen.cso.uiuc.edu> <wheeler.1207958690A@newshost.cc.utexas.edu> <5fkl6q$f70@wanda.vf.pond.com>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23135

Someone wrote this, and I'm jiggered if I know who:

}The rope problem turns out to be a real test of an IF author's mettle, 
}moreso than I realized.  Someone kindly pointed me to a web page full of
}IF posts, and one of them was about the difficulty of rope problems, and
}how one is generally better off not writing a rope into one's game.

I know I've written something like that in the past.  Don't remember if I
ever posted it up anywhere.  If I recall, it was more a caution against
multi-purpose items than rope specifically.  ("Oh look, a can of kerosene.
I wonder if I can burn that white house down...")  Exponential growth
being a hassle and all that.

Of course, you could try to implement everything in your game and join me
in the land of vaporware.  Yes, that's it Luke, feel the pull of the dark
side.  Yes, Luke, I am your cousin's accountant's brother's bookie.
<Sounds of someone breathing through a coffee filter.>

Lots of detail makes for a long development time.  If you find youself
wondering just how to program tying different knots into a piece of yarn,
it's probably time to finish the game and push it out the door.

"This brief bout of silliness brought to you by a man who has no idea what
he's talking about."

-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From thoni@softlab.se Fri Mar  7 14:52:05 MET 1997
Article: 23150 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!hammer.uoregon.edu!arclight.uoregon.edu!news.algonet.se!uab.ericsson.se!erinews.ericsson.se!news
From: Thomas Nilsson <thoni@softlab.se>
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Date: Fri, 07 Mar 1997 10:13:37 +0100
Organization: SoftLab
Lines: 23
Message-ID: <331FDC40.3A0D@softlab.se>
References: <5egglv$jeq@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se> <fake-mail-ya02408000R0403971409150001@news.direct.ca> <5fjld0$trp@bartlet.df.lth.se> <5fkdlb$gpu@echo2.echonyc.com>
NNTP-Posting-Host: rabbit.softlab.se
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-Mailer: Mozilla 3.01Gold (X11; I; SunOS 5.5 sun4m)
Xref: news.lth.se rec.arts.int-fiction:23150

Neil deMause wrote:

> 
> The trick to interactive fiction, really, is making the lack of
> interaction feel natural.
> 
> Neil


One of the most elegant and compact 'says it all's that I have ever
seen! It will be copied into my quote book.

	Thomas

-- 
"Little languages go a long way..."
(ThoNi of ThoNi&GorFo Adventure Factories in 1985)
-------------------------------------------------------------------------------
Thomas Nilsson				Phone Int.: (+46) 13 651 12
Junovgen 12				Phone Nat.: 013 - 651 12
S-590 74  LJUNGSBRO 			Email: thoni@softlab.se
SWEDEN					alan-request@softlab.se for info
-------------------------------------------------------------------------------


From mol@bartlet.df.lth.se Fri Mar  7 14:52:49 MET 1997
Article: 23098 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Date: 5 Mar 1997 12:28:32 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 53
Message-ID: <5fjld0$trp@bartlet.df.lth.se>
References: <5egglv$jeq@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se> <fake-mail-ya02408000R0403971409150001@news.direct.ca>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23098

In article <fake-mail-ya02408000R0403971409150001@news.direct.ca>,
Neil K. <fake-mail@anti-spam.address> wrote:
>In article <5fhmsv$8jo@bartlet.df.lth.se>, mol@bartlet.df.lth.se (Magnus
>Olsson) wrote:
>
>> I think Fredrik's advice is excellent, and something that should be
>> kept in mind at all times. To draw the argument to its extreme, when
>> people argue that NPC's need AI to be convinving, I like to remind
>> them that writers of static fiction have been creating convincing
>> characters for millenia, and a character in a book doesn't have a
>> shred of intelligence, being entirely non-interactive.
>
> Well, I'm afraid I'd argue that the success of static fiction in creating
>believable NPCs derives in large part *because* of the total lack of
>interactivity. 

That's true, of course. And it's just that point that I made (albeit
less forcefully) in the next sentence (which you snipped).

> Same with fiction. The author writes down the words; you can't change
>them. So you can't go poking around, asking the character questions,
>because everything's there and presented before you. IF, with its carefully
>constructed illusion of choice, allows you to step behind the sets. And
>therein lies a problem.

My point is that IF has an *illusion* of choice. Unless you want to
solve an AI complete simulation problem, at some point or another you
have to stop the player from peeking behind the sets. 

A tendency I've seen in some posts from beginning IF authors is that
they assume that (to continue your metaphor) if they want the town in
the movie to look real, they'll have to build real houses with
backsides, rooms inside them, gardens, and so on. That can of course
be required: if the camera will follow the hero into the saloon,
you'll have to build the inside of it. But if your script only calls
for exterior shots, a simple, two-dimensional set would be just as
effective and much cheaper.

For it's all a matter of economy. Don't get me wrong: I love detail, I
love interactivity, I love to be able to go behind the sets and see
that everything really *works*, even though it's not needed for the
story. But if the extra realism means that the game will never be
finished, because it will need five man-years of programming rather
than five man-months, then I'd prefer the cardbord illusion.

(An example in point is "Undertow" from the 1995 competition, where
the author had obviously spent a lot of time ensuring that the taps
and sinks in the bathroom worked; time that IMHO had been better spent
correcting bugs).


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)


From neild@echonyc.com Sat Mar  8 18:14:50 MET 1997
Article: 23177 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news.uni-c.dk!news-inn.uni-c.dk!news.planetc.com!cpk-news-feed1.bbnplanet.com!inri.com!news-out.internetmci.com!newsfeed.internetmci.com!su-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news.maxwell.syr.edu!metro.atlanta.com!uunet!in2.uu.net!198.67.15.6!news.echonyc.com!echonyc.com!neild
From: neild@echonyc.com (Neil deMause)
Newsgroups: rec.arts.int-fiction
Subject: Re: Maintaining the illusion (was [Inform] Stop prompt & Delay parse)
Date: 5 Mar 1997 18:22:35 GMT
Organization: EchoNYC
Lines: 36
Message-ID: <5fkdlb$gpu@echo2.echonyc.com>
References: <5egglv$jeq@curofix.ida.liu.se> <5erfa4$8dp@kjahds.com> <5fhmsv$8jo@bartlet.df.lth.se> <fake-mail-ya02408000R0403971409150001@news.direct.ca> <5fjld0$trp@bartlet.df.lth.se>
NNTP-Posting-Host: echonyc.com
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:23177

Magnus Olsson (mol@bartlet.df.lth.se) wrote:

: A tendency I've seen in some posts from beginning IF authors is that
: they assume that (to continue your metaphor) if they want the town in
: the movie to look real, they'll have to build real houses with
: backsides, rooms inside them, gardens, and so on. That can of course
: be required: if the camera will follow the hero into the saloon,
: you'll have to build the inside of it. But if your script only calls
: for exterior shots, a simple, two-dimensional set would be just as
: effective and much cheaper.

: For it's all a matter of economy. Don't get me wrong: I love detail, I
: love interactivity, I love to be able to go behind the sets and see
: that everything really *works*, even though it's not needed for the
: story. But if the extra realism means that the game will never be
: finished, because it will need five man-years of programming rather
: than five man-months, then I'd prefer the cardbord illusion.

To carry the point still further: Trying to create a more "complete" 
reality can work against creating a fuller-seeming reality. Which seems 
more real, a hotel with 500 rooms, all identical, or one with a 
lushly-detailed lobby and a counterperson who won't let you in the 
elevator? Which seems more real, an NPC who has detailed responses to 20 
items you can ask him/her about but "looks confused" the rest of the 
time, or one who nods vacantly and stares off into space no matter you ask?

I was terrified of writing NPCs for almost two years because I thought it 
would require massive amounts of tricky coding. Now I'm convinced that 
all it takes is somewhat-massive amounts of good writing -- characters in 
I-F, as in static fiction, come to life because of what they say and do, 
not (necessarily) how they respond to your every whim.

The trick to interactive fiction, really, is making the lack of 
interaction feel natural.

Neil


From d91frera@ida.liu.se Sun Mar  9 01:06:52 MET 1997
Article: 23185 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: [TADS] Recursion
Date: 7 Mar 1997 13:54:23 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 26
Message-ID: <5fp6mf$sr1@curofix.ida.liu.se>
References: <erkyrathE6ELyG.M9E@netcom.com> <19970303043801.XAA11742@ladder02.news.aol.com> <5fdlte$f8n@vixen.cso.uiuc.edu> <331afc34.2181969@news.u.washington.edu> <5ff51n$qq0@vixen.cso.uiuc.edu> <331f1efb.11350376@news.peinet.pe.ca>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)
Xref: news.lth.se rec.arts.int-fiction:23185

>grzanich@uiuc.edu (Will Grzanich) wrote:

>>I think you may be right, there...you even *try* suggesting to a Schemer 
>>that Scheme might not be quite as useful as C or even Basic, and you've 
>>got a holy war on your hands... *shudder*

And why doesn't Basic ever turn into a religion the same way? Try a Lisp
language open-minded, and perhaps you'll see the light. Basic is only more
useful when built into a more powerful environment, and the success of the
system is hardly due to the usefulness of the language. Prototyping or
development of small programs can be very fast in Basic, but not as fast as
in Lisp. C is fast and rather easily portable, if you take care when writing,
but both writing and debugging is timeconsuming.

Sorry for staying off topic. And yes, I love Lisp, but we're not engaged and
not planning to get married. Mainly because she can't stand Inform, which I
can't live without. (Seriously though, some guys _would_ marry a Lisp
language if it was possible... (Would they wear a circular list for a wedding
ring? Stop it!))

/Fredrik
--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
I want to make it perfectly clear that I can't say I don't think people who
aren't avoiding using too many negations aren't putting things clearly enough.


From NoJunkmail_sharvey@enteract.com Sun Mar  9 18:56:26 MET 1997
Article: 23208 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!news.enteract.com!enteract.com!not-for-mail
From: sharvey@enteract.com (sharvey)
Newsgroups: rec.arts.int-fiction
Subject: Re: Types of Puzzles
Date: 9 Mar 1997 17:51:47 GMT
Organization: Burpleson AFB
Lines: 42
Message-ID: <5futbj$jbj@eve.enteract.com>
References: <331F3C45.794B@x_greenhouse.llnl.gov> <5fnhkf$c0t@nntp5.u.washington.edu> <331F56FE.15FB@x_greenhouse.llnl.gov> <5fq1od$veg@koala.scott.net> <5fqdoc$btn@eve.enteract.com>  <ant081519b49c4bn@arnod.demon.co.uk>
Reply-To: NoJunkmail_sharvey@enteract.com
NNTP-Posting-Host: adam.enteract.com
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.arts.int-fiction:23208

Julian Arnold (jools@arnod.demon.co.uk) wrote:
: > - same goes for the angry-dragon-sees-his-reflection puzzle.  True, a
: > "locked door" in the sense that you're prevented from travelling until the
: > puzzle is completed, but so much more elegant than finding a key
: > somewhere.
: 
: Elegance is not a qualitative difference.

What makes it a good puzzle is that the solution is in more than one step.
There are numerous things the player has to "learn" in order to solve this
puzzle.

1) you can HIT DRAGON WITH SWORD (once) without getting yourself cooked
2) if you run, the dragon will follow you. 
3) if you don't keep hitting him, he'll get bored and go back.
4) if you lead the dragon to the Ice Cavern, he'll melt the ice and solve
   your problem.

As for dissecting the lizard door problem, the player has to learn things,
in several stages:

1) the clay brick is really a plastic explosive
2) the black cord (wire?) is really a fuse
3) you can put them together and make a big bang
4) the lizard will happily eat things, even lit bombs

Each of these is a a "door and key" puzzle, but what makes them good
puzzles is the quality of the disguises of the door and the key.  In order
to keep from annoying the player, I feel that locked doors have to not
seem like locked doors.  

The elegance comes in being able to design puzzles that are more creative
than "the key is up on a shelf and you can't reach it from here".

Scott

-- 
+--------------------------------------------------------------------+
| reply-to header hacked      | war and slavery, explotation         | 
| to prevent spam             | the common basis of a western nation |
| sharvey at enteract dot com |                       -KMFDM, Glory  |
+--------------------------------------------------------------------+


From avrom@Turing.Stanford.EDU Mon Mar 10 11:21:42 MET 1997
Article: 23215 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Types of Puzzles
Date: 9 Mar 1997 12:49:41 -0800
Organization: CSLI, Stanford University
Lines: 57
Message-ID: <5fv7p5$e90@Turing.Stanford.EDU>
References: <331F3C45.794B@x_greenhouse.llnl.gov> <ant0715440b0c4bn@arnod.demon.co.uk> <erkyrathE6p0qF.JyM@netcom.com> <ant0815470b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: turing.stanford.edu
Xref: news.lth.se rec.arts.int-fiction:23215

In article <ant0815470b0c4bn@arnod.demon.co.uk>,
Julian Arnold  <jools@arnod.demon.co.uk> wrote:
>In article <erkyrathE6p0qF.JyM@netcom.com>, Andrew Plotkin
><URL:mailto:erkyrath@netcom.com> wrote:
>> At the highest level, there is only one puzzle type: the mechanical
>> puzzle. You have to figure out how the mechanism works. The mechanism is
>> the Z-machine or TADS-machine. 

It doesn't seem right to think of this as a description of a _puzzle_
any more.

Puzzles, in IF, are aspects of stories.  The Z-machine or TADS-machine
can't be the object of a puzzle because it's not an entity within the
story.

The relationship between a gate and its components (pulleys,
counterweights, the physical door itself) can be thought of as a
relationship between levels, one of implementation.  So, in a
different sense, can the relationship between the gate and the code
for it.

But this is a different sense--the gate,counterweights, and pulleys
are all bits of the game;  the code is not.
 
>I've said before that ultimately all puzzles reduce to locked doors. 
>However, on some level there must be some qualitative distinction
>between many of the puzzle "types" on Kathleen's list, and it may be
>useful to isolate the level on which such a distinction occurs, and then
>consider particular puzzles on that level[1].

On the level of the story (as opposed to the level of the code, where
I don't think things should be described as "puzzles" at all), I think
one must make some distinction like this.  While all puzzles may in
some deep way be programmed the way locked doors are (don't jump to
these bits of the code unless the player has managed to set these
states), they're not _written_ the way locked doors are.  A locked
door doesn't talk back to you, you can't feel sympathy for it, and
while you can engage its creator in a battle of wits, you can't engage
_it_ in a battle of wits.  An NPC you must manipulate in a certain way
has all these features.

A locked door is a fictional inanimate object.  An NPC is fictional,
but not inanimate--although he/she is implemented in an inanimate
medium, of course.

The only time when a player's task should be thought of as
manipulating the Z-machine is when the programming stops being
transparent, when it starts intruding into the story, i.e., when the
puzzle is "guess the verb."

And I don't recommend increasing the diversity of your puzzles by
adding a few of these.

-Avrom





From erkyrath@netcom.com Mon Mar 10 11:22:11 MET 1997
Article: 23224 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!rill.news.pipex.net!pipex!netcom.net.uk!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Types of Puzzles
Message-ID: <erkyrathE6t1DA.7o2@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <331F3C45.794B@x_greenhouse.llnl.gov> <ant0715440b0c4bn@arnod.demon.co.uk> <erkyrathE6p0qF.JyM@netcom.com> <ant0815470b0c4bn@arnod.demon.co.uk> <5fv7p5$e90@Turing.Stanford.EDU>
Date: Mon, 10 Mar 1997 01:55:58 GMT
Lines: 42
Sender: erkyrath@netcom9.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23224

Avrom Faderman (avrom@Turing.Stanford.EDU) wrote:
> >> At the highest level, there is only one puzzle type: the mechanical
> >> puzzle. You have to figure out how the mechanism works. The mechanism is
> >> the Z-machine or TADS-machine. 

> It doesn't seem right to think of this as a description of a _puzzle_
> any more.

> Puzzles, in IF, are aspects of stories.  The Z-machine or TADS-machine
> can't be the object of a puzzle because it's not an entity within the
> story.

I was being slightly facile. I should have said "the mechanism is the 
entire world", since of course the world behaves in a mechanical fashion. 

(Figuring out how the Z-machine behaves is in fact a different sort of
puzzle, and those of us on the Z-machine mailing list are currently
solving yet another part of it.  A new Z-spec should be released fairly
soon. :)

> On the level of the story (as opposed to the level of the code, where
> I don't think things should be described as "puzzles" at all)

On the level of the *story*, these things are not puzzles either; they 
are things which happen to the protagonist. They are only puzzles to the 
*player*, on a level which the protagonist knows nothing about.

This in-between status is fairly unsatisfying to me, and to many people, 
I think. That thought has spawned several variations on the theme of IF, 
including "well-integrated puzzle" IF and (of course) "puzzle-free" IF. 

I find that categorizing puzzle types is about the least interesting 
thing a student of IF can do. :) But the original poster (Kathleen?) 
said, I think, that it had some particular relevance to something she was 
doing, so I anticipate something sneaky is being cooked up. Heh.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From rglasser@penning.lanl.gov Mon Mar 10 12:54:44 MET 1997
Article: 23232 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Types of Puzzles
Date: Sun, 09 Mar 1997 21:11:36 -0800
Organization: UCSD
Lines: 47
Message-ID: <33239808.5BE@penning.lanl.gov>
References: <331F3C45.794B@x_greenhouse.llnl.gov> <5fnhkf$c0t@nntp5.u.washington.edu> <331F56FE.15FB@x_greenhouse.llnl.gov> <5fq1od$veg@koala.scott.net> <5fqdoc$btn@eve.enteract.com>  <ant081519b49c4bn@arnod.demon.co.uk> <5futbj$jbj@eve.enteract.com>
NNTP-Posting-Host: sdx-ca9-22.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Sun Mar 09 11:11:36 PM CST 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23232

[WARNING!!!!  CONTINUED POSTING OF MESSAGES WITH OBVIOUS SPOILERS FOR ZORK 
II!!]











sharvey wrote:
> 
> As for dissecting the lizard door problem, the player has to learn things,
> in several stages:
> 
> 1) the clay brick is really a plastic explosive
> 2) the black cord (wire?) is really a fuse
> 3) you can put them together and make a big bang
> 4) the lizard will happily eat things, even lit bombs
> 
> Each of these is a a "door and key" puzzle, but what makes them good
> puzzles is the quality of the disguises of the door and the key.  In order
> to keep from annoying the player, I feel that locked doors have to not
> seem like locked doors.
> 

	Scott, you may not be aware of this, but there is an alternative to 
what you have just described.  Feed the lizard the candy from the Alice room. 
Hold on to the brick.  Go to the top of the volcano in the hot air balloon.  
Put the brick with string into the hole in the rusty box.  Light it up, leave, 
then come back.  This will give you a crown, the eleventh treasure to replace 
the candy that you lost.
	To be honest, I never even realized that feeding the bomb to the 
lizard was an option!  I was about to tell you "that can't possibly be right, 
because then you can't ever get ahold of the crown"... but then I remembered 
for the first time that THE CANDY is a treasure.
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From dancer@oxford.com.au Tue Mar 11 09:42:51 MET 1997
Article: 23249 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!bunyip.cc.uq.edu.au!news.design.net.au!news
From: Dancer <dancer@oxford.com.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: Alien or invented languages in IF
Date: Tue, 11 Mar 1997 13:44:02 +1000
Organization: Oxford Media PTY LTD
Lines: 41
Message-ID: <3324D502.21B6@oxford.com.au>
References: <5elpp6$dh9@eve.enteract.com> <erkyrathE60LpM.3oz@netcom.com> <5eur9u$j4f@inxs.ncren.net> <3319464b.8540398@news.dungeon.com>
NNTP-Posting-Host: 192.168.1.152
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 4.0b2 (X11; I; SunOS 5.5.1 sun4m)
X-Priority: 3 (Normal)
Xref: news.lth.se rec.arts.int-fiction:23249

Snaps wrote:

  echerry@warren-wilson.edu (Erskin Cherry) wrote an interesting
  piece,
  here's my twopennyworth:

  >Ultima Underground, the Stygian Abyss used this sort of idea.
  >(Limited vocabulary, and the translator was mute and had to gesture

  >the ideas to you when you had access to him)
  >
  >It may be a littel gimmicky, but it worked really well for me,
  >and I think if used judiciously (and, like spells, each word is
  used
  >much more than once,) you could make for a nice texture.

  Reading this, does anyone remember a /really/ old (ie 8-bit) game
  called Captain Blood, where you communicated with the aliens using a

  small set of icons. I actuaaly found the translations rather
  impenerable IIRC, but that was probably just a failing on my part.

Absolutely.I loved the communications system, and forgot about the rest
of the game, just chatting to creatures. Some of them had quite a
sophisticated 'sense of humour', which is to say they could joke or kid
around, if you could see the nuances through the icon-system...Which is
quite possible,

TWO-RELIGION-SMALL-PERSON-GROUP-GO-IN-FOOD-PLACE
MALE-AUTHORITY-PERSON-SAY->>-ME-GROUP-NO-GIVE-YOU-GROUP-HERE
ONE-RELIGION-SMALL-PERSON-SAY->>-OK-ME-NO-ASK-ME-GROUP

ME-SMALL-FRIEND-NO-SMELL-PART
HOW-SMALL-FRIEND-SMELL-?
BAD

Admittedly they lose a little, but a lot can be communicated with only
90 or so symbols.

D



From kjahds@kjahds.com Wed Mar 12 09:48:25 MET 1997
Article: 23282 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsxfer.itd.umich.edu!newsxfer3.itd.umich.edu!howland.erols.net!newsserver.jvnc.net!newsreader.jvnc.net!kjahds.com!not-for-mail
From: kjahds@kjahds.com (Kenneth Albanowski)
Newsgroups: rec.arts.int-fiction
Subject: Re: Alien or invented languages in IF
Date: 12 Mar 1997 01:52:11 -0500
Organization: None
Lines: 31
Message-ID: <5g5jqr$7aa@kjahds.com>
References: <5elpp6$dh9@eve.enteract.com> <3319464b.8540398@news.dungeon.com> <3324D502.21B6@oxford.com.au> <mreddy-ya02408000R1103971700310001@news.fu-berlin.de>
NNTP-Posting-Host: prn-ts1-12.jvnc.net
Xref: news.lth.se rec.arts.int-fiction:23282

In article <mreddy-ya02408000R1103971700310001@news.fu-berlin.de>,
Mike Reddy <mreddy@glam.ac.uk> wrote:
>In article <3324D502.21B6@oxford.com.au>, Dancer <dancer@oxford.com.au> wrote:
>>TWO-RELIGION-SMALL-PERSON-GROUP-GO-IN-FOOD-PLACE
>>MALE-AUTHORITY-PERSON-SAY->>-ME-GROUP-NO-GIVE-YOU-GROUP-HERE
>>ONE-RELIGION-SMALL-PERSON-SAY->>-OK-ME-NO-ASK-ME-GROUP
>
>Firstly, can you explain this one to me?

For a value of X where X indicates a member of a minority religion:

	Two X went into a restaurant. The maitre d' says "We don't serve X
	here". One of the X said "OK, we won't order X, then".

(Or at least, that is the sense I get out of it, which isn't too bad
considering I've never heard it before, oddly enough.) It's essentially
identical to the second joke, a pun on words (er, icons), but "serve"
instead of "smell".

Hmm. _Big Hmm_. I wonder if you could build a modern game around an "alien
language" like this, except make the language ASL (American Sign Language).
It'd have to be a graphical game, obviously (text descriptions of ASL would
get annonying real quick, I expect) and if you made the foriengers aliens
(with tentancles, natch) instead of humans, the player might not even
realize what they are learning. I think you should be able to learn it in
exactly the same fashion Dancer learned those icons -- painlessly, or at
least with fun.

-- 
Kenneth Albanowski (kjahds@kjahds.com)



From d91frera@ida.liu.se Wed Mar 12 15:21:03 MET 1997
Article: 23186 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Missing during-routines
Date: 7 Mar 1997 14:21:47 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 45
Message-ID: <5fp89r$t78@curofix.ida.liu.se>
References: <5flo2q$njq@curofix.ida.liu.se> <erkyrathE6Msr7.5tw@netcom.com>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)
Xref: news.lth.se rec.arts.int-fiction:23186

erkyrath@netcom.com (Andrew Plotkin) writes:

>Stopping other before-rules, in contrast, is an unavoidable problem. If 
>you used a "during" system, you'd have the same problem with it. 
>*Something* has to do the actual work; it can't be done in two places, so 
>there has to be a way to control which one wins. In Inform, you have 
>several avenues of control, which have a particular order of precedence 
>(room.before, player.before, object-parent-class.before... I forget the 
>sequence.) Which rule runs will prevent all the other rules from running.

If before-rules were only used to prevent actions, you would not have a
problem with them any more. It doesn't matter much if you are killed by
the grue guarding the chest, or by the posinous nails on the chest, you get
_one_ message from _one_ of the before-rules, and you die. I think this is
what you meant, but still felt the urge to clarify.

The during-step, though, should be used to perform the work. There, the
programmer decides through the writing of his rules, and through the order
of inheritance, which object or class should do the work. The list of objects
considered, and in what order, must be well-known to the programmer for the
during-step as well. Of course, a during-rule must have the right to decline
doing the work as well, by returning a certain value.

>I think the standard library should remain largely as it is. If you want to 
>write a new library, though, I'd be very interested in using it.

I haven't looked into it yet, but perhaps it's possible to just replace a
routine in the library, basically to make it go through another before-step
called "during" before applying the default action, with the difference that
it can still execute the after-step? If it's that simple, I'll make a
library extension that does it.

It's certainly not up to me to decide if it should be in the library, but I
can't see how it would do harm. Games that don't supply a during-property
wouldn't be affected at all, just like objects that don't have before-rules
aren't affected by that system. If you think people may have a property called
'during' for other purposes, you could require the game to define the constant
USE_DURING_RULES to invoke the system.

/Fredrik
--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
I want to make it perfectly clear that I can't say I don't think people who
aren't avoiding using too many negations aren't putting things clearly enough.


From mol@bartlet.df.lth.se Wed Mar 12 17:10:52 MET 1997
Article: 23292 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: What is a meta-command?
Date: 12 Mar 1997 15:49:52 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 54
Message-ID: <5g6fqg$5t5@bartlet.df.lth.se>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23292


In the current debate about the "look" command, the term
"meta-command" is used liberally; people say that they think "look"
should be a meta-command, and so on. 

As far as I can see, what most of the posters mean by this is that
"look" should be a "free action", i.e. the turn counter shouldn't be
incremented and daemons and timers shouldn't run after it.

But does this really make it a meta-command? To me, a meta-command is
one which is outside of the game world. To me, the action of looking,
whether it consumes a turn or not, is very much a part of the game,
unlike commands such as "save" or "verbose" which are commands to the
game-as-a-program.  

I think we should distinguish meta-command from free actions, in the
following way:

A free action is an ordinary game command, having to do with the
player's interaction with the game world, that just doesn't happen to
take any time. The candidates I can think of right now are "look",
"inventory" and "what is a grue", though it can be argued that these
*should* take up time (see below). Free actions are affected by the
game state just as any other command, trapped by react_before (in
Inform) and so on.

Meta-commands are commands that are caught by the game's parser
*before* they affect (or are affected by) the game state. For example,
they are not trapped by react_before; the player can still save even
when in total darkness, and so on.

A role-playing analogy may help: a free action is something a player
does inside his role, that doesn't advance the clock. The role-playing
equivalent of a meta-command would be something like a player asking
the game master to clarify a rule.


Finally, I think it's a difficult question whether commands such as
'look' or 'inventory' should be free actions or not. Depending on the
context, the command 'look' may mean that the player examines his
surroundings in detail - which of course should take some time - or
just that he keeps looking around while doing other things.

In one case I can actually consider 'look' to be a meta-command in the
sense I've used the word above: viz. if the player is merely asking
the game to re-display the room description that just scrolled off the
screen, or which would have been displayed automatically if the player
hadn't typed 'brief' 10 turns ago. 



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From erkyrath@netcom.com Wed Mar 12 22:13:55 MET 1997
Article: 23300 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: What is a meta-command?
Message-ID: <erkyrathE6xxH1.Hxs@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5g6fqg$5t5@bartlet.df.lth.se>
Date: Wed, 12 Mar 1997 17:19:49 GMT
Lines: 51
Sender: erkyrath@netcom4.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23300

Magnus Olsson (mol@bartlet.df.lth.se) wrote:

> In the current debate about the "look" command, the term
> "meta-command" is used liberally; people say that they think "look"
> should be a meta-command, and so on. 

> As far as I can see, what most of the posters mean by this is that
> "look" should be a "free action", i.e. the turn counter shouldn't be
> incremented and daemons and timers shouldn't run after it.

There's a reason for this assumption: In Inform, you turn off daemons and 
timers (and each_turns) by putting the keyword "meta" in the grammar 
line. Or setting the "meta" variable. 

"meta" in Inform also prevents before/after actions from being run (which 
is reasonable for "save" and "restore", and maybe less so for "look" as a 
free action.) 

I know you're just nitpicking the terminology, but I don't think it's a 
huge deal. :)


> Finally, I think it's a difficult question whether commands such as
> 'look' or 'inventory' should be free actions or not. Depending on the
> context, the command 'look' may mean that the player examines his
> surroundings in detail - which of course should take some time - or
> just that he keeps looking around while doing other things.

> In one case I can actually consider 'look' to be a meta-command in the
> sense I've used the word above: viz. if the player is merely asking
> the game to re-display the room description that just scrolled off the
> screen, or which would have been displayed automatically if the player
> hadn't typed 'brief' 10 turns ago. 

Contrariwise, I've seen (and written) scenes where "look" *was* supposed 
to take a turn. This most often happens when something changes in the 
room *without* a warning message, or with a warning message which just 
says "Something seems different." (This can be very eerie when done 
correctly. The player has to type "look" and read the text carefully -- 
because the protagonist is looking carefully around himself for whatever 
it was that moved in his peripheral vision.) You can easily think of 
scenes where stuff continues to happen as he looks.

--Z



-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mol@bartlet.df.lth.se Wed Mar 12 22:19:00 MET 1997
Article: 23303 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: [TADS] Help me with delword!
Date: 12 Mar 1997 22:18:41 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 42
Message-ID: <5g76jh$4c5@bartlet.df.lth.se>
References: <19970312090301.EAA21325@ladder01.news.aol.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23303

Neil deMause (nulldogma@aol.com) writes:
>Neil K. Guy wrote:
>> Frankly, though, my own game in progress is pretty well
>> unaffected by the
>> remaining few hardcoded runtime bugs in TADS, so I suppose I'm
>> a little blas. Generally speaking, I find it's a pretty stable
>> system with only a handful of features added towards the end
>> (such as the ones that Andrew (Pontious) identifies) that have
>> glitches.
>
>I'll second that. At this point, after two+ years of TADS
>programming, I've yet to run into a major problem (I wanted to
>use delword() once, but it wasn't important), and am still
>discovering things that I never knew existed, or at least never
>understood the first time I read the manual.

And I'll third [:-)] that. TADS is a mature, stable system, and I've
never had any problem with compiler or interpreter bugs. Library bugs,
yes, but the library is much easier to fix. 

The delword bug is irritating, but so far I've never seen a game where
delword is essential (addword, on the other hand, often is). There are
reports about a serious bug in the 32-bit DOS version of tadsr, but
since that port isn't done by Mike himself it probably wouldn't help
if he was working actively with TADS (and I suppose that when Dave or
someone else finally fixes that bug, Mike will not need much
persuading to include it in the official distribution).

But it's sad that Mike isn't actively supporting TADS anymore. Inform
is more exciting, perhaps, since it's a "living" system that's still
growing. That also means that a bug-free Inform is a moving target, and
that Inform *needs* Graham's constant attention right now.

Right now, I feel comfortable using both TADS, knowing that it's stable
and can do what I want it to, as well as Inform 6.11, knowing that
there are quite a few bugs but that Graham will fix them in the next
release :-).


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From mol@bartlet.df.lth.se Wed Mar 12 23:47:55 MET 1997
Article: 23301 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: 12 Mar 1997 22:16:47 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 80
Message-ID: <5g76fv$412@bartlet.df.lth.se>
References: <5g6fqg$5t5@bartlet.df.lth.se> <erkyrathE6xxH1.Hxs@netcom.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23301

In article <erkyrathE6xxH1.Hxs@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>Magnus Olsson (mol@bartlet.df.lth.se) wrote:
>
>> In the current debate about the "look" command, the term
>> "meta-command" is used liberally; people say that they think "look"
>> should be a meta-command, and so on. 
>
>> As far as I can see, what most of the posters mean by this is that
>> "look" should be a "free action", i.e. the turn counter shouldn't be
>> incremented and daemons and timers shouldn't run after it.
>
>There's a reason for this assumption: In Inform, you turn off daemons and 
>timers (and each_turns) by putting the keyword "meta" in the grammar 
>line. Or setting the "meta" variable. 
>
>"meta" in Inform also prevents before/after actions from being run (which 
>is reasonable for "save" and "restore", and maybe less so for "look" as a 
>free action.) 

Yes, and that's exactly why I think the distinction is important.

>I know you're just nitpicking the terminology, but I don't think it's a 
>huge deal. :)

Actually, it's more than nitpicking. I think this scenario illustrates
my point:

| Medusa's Cave
| This cave is full of very life-like statues of adventurers in various
| poses. Medusa isn't here in person, though.
|
| > z
| Medusa enters the room behind your back.
| 
| > look
| As your gaze falls upon Medusa's face, you turn to stone.
|
| *** You have died ***

In this example, "look" can be a free action, but it can't be a
meta-command, since in that case it wouldn't be caught by Medusa's
react_before. 

To clarify my position, I'd like to propose that we have three types
of commands:

1) Ordinary commands.  

2) Free action commands. Just like ordinary commands (so other objects
can react to it), except that the time counter doesn't advance, and
daemons and timers don't run after it.

3) Meta-commands. These are commands directed at the game-as-a-program
and affect only the way the player interacts with the program, not the
way the player _character_ interacts with the game world. In
particular, a meta-command (with the exception of "undo", "restore"
and "restart") does not change anything in the game world. You should
be able to insert a meta-command (except "undo", "restore" or
"restart") in the user-program-interaction without changing the
resulting game state.

>> Finally, I think it's a difficult question whether commands such as
>> 'look' or 'inventory' should be free actions or not. Depending on the
>> context, the command 'look' may mean that the player examines his
>> surroundings in detail - which of course should take some time - or
>> just that he keeps looking around while doing other things.

>Contrariwise, I've seen (and written) scenes where "look" *was* supposed 
>to take a turn. This most often happens when something changes in the 
>room *without* a warning message, or with a warning message which just 
>says "Something seems different."

Thanks for providing an example - I was going to write this, but changed
my mind, thinking that it would seem to contrived and that nobody
would want to write such scenes anyway.

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From mol@bartlet.df.lth.se Wed Mar 12 23:48:32 MET 1997
Article: 23302 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Puzzle classification - some random thoughts
Date: 12 Mar 1997 22:17:47 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 72
Message-ID: <5g76hr$47c@bartlet.df.lth.se>
References: <858021665.31854@dejanews.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23302

kfischer@greenhouse.llnl.gov writes:
(quoting Andrew Plotkin)
>> I find that categorizing puzzle types is about the least
>> interesting thing a student of IF can do. :)
>>
>Gee, thanks.  So far my effort has been called unoriginal, "not
>the worst" someone had seen, and now boring. Lovely.

Well, let me add that I find your effort interesting. Interpret that
as a compliment or a put-down, whatever you like :-). 

I'm not sure whether I agree with Andrew or not (and yes, I've noted
his smiley). On one hand, I think it's fun to categorize things. On
the other, I don't think it's very relevant to my own IF writing, and
I play IF more for the stories than for the puzzles. But I also think
this varies a lot from individual to individual. It's a bit like
studying prosody may increase you enjoyment of poetry - or it may bore
you to death, it's a personal thing. (There is a difference, though,
in that I do think that a knowledge of prosody increases your ability
to _write_ poetry. Analogies shouldn't be carried to far.)

Puzzles and problem-solving are interesting fields of study. I think
that theoretical studies of IF is a worthy occupation (some things I
wrote in my past debates with Espen Aarseth may have made a different
impression, but I suppose I was carried away by my own polemics).


Another thought: one thing that strikes me when I see the incomplete
classificiations posted here is that the descriptions are on totally
different levels. It's a bit like a taxonomy of animals that grouped
all animals with four legs in one group, all black animals in another,
but put different breeds of dogs into separate groups. But I suppose
the current lists are in a tentative state.

A difficulty here is that classifying puzzles is much more difficult
than classifying animals. With animals, there is a natural,
hierarchical, exclusive classification in terms of evolutionary
descent (or, rather, the empirical fact is the classification, which
can nowadays be more or less rigourously supported by DNA comparisons;
evolutionary descent is the theoretical framework that explains it).
That is what makes my example with categories such as "black animals"
intentionally absurd. 

But puzzles can't be categorized in that fashion: a puzzle may belong
to many disparate categories at once, the categories are overlapping,
and you may combine elements from categories to create new puzzles. 


Finally, my two cents on the hyperbolic statement that "all puzzles
are locked doors". There is of course no logical refutation of this.
Similarly, I could make a logically unassailable argument that all
animals are birds: birds lay eggs and humans bear live children - OK,
then humans are birds where the eggs don't have shells and hatch inside
the uterus; fish are flightless, legless, aquatic birds that breathe
with gills, and so on. You can't refute that argument with logic,
since all I've done is to widen the category of birds until it
encompasses all animals. But such sophistry is of course worse than
useless, because by doing so we lose the power to distinguish between
birds and other creatures.

My definition of a "locked door puzzle" in a general sense would be a
puzzle where something (or someone) is an obstacle to your progress,
and you solve the puzzle by applying a certain object (or piece of
information) to remove the obstacle, while the obstacle remains
passive and doesn't interact with you. Admittedly, this fits a lot of
puzzles (for example, both ways of getting past the troll in Colossal
Cave), but not all. Puzzles that require you to observe the behaviour
of the obstacle and manipulate it are IMHO in a different category.

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From tbarrie@UPEI.CA Thu Mar 13 09:19:35 MET 1997
Article: 23314 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!torn!news.unb.ca!coranto.ucs.mun.ca!upei.ca!UPEI.CA!tbarrie
From: tbarrie@UPEI.CA (TREVOR FRANCIS BARRIE)
Newsgroups: rec.arts.int-fiction
Subject: Re: [TADS] Recursion
Date: Wed, 12 Mar 1997 17:18:51 GMT
Organization: University of Prince Edward Island, CANADA
Lines: 16
Message-ID: <tbarrie.89.858187131@UPEI.CA>
References: <331f1ef0.11339569@news.peinet.pe.ca> <19970307080701.DAA03467@ladder01.news.aol.com>
NNTP-Posting-Host: pc041.stu-net.upei.ca
Xref: news.lth.se rec.arts.int-fiction:23314

In article <19970307080701.DAA03467@ladder01.news.aol.com> nulldogma@aol.com (Nulldogma) writes:
>Path: upei.ca!news.unb.ca!news.uoregon.edu!arclight.uoregon.edu!news.maxwell.syr.edu!worldnet.att.net!howland.erols.net!newsxfer3.itd.umich.edu!portc01.blue.aol.com!newstf02.news.aol.com!audrey01.news.aol.com!not-for-mail
>> Well, he's right... iteration may be an ugly necessity at times due to
>> performance factors, but recursion is certainly more elegant. (Why do
>> you suppose Neil used recursion the first time?)
>
>Elegant, schmelegant -- I used recursion the first time because I didn't
>really know what I was doing. Either that or it was 3 am and the entire
>notion of for loops had dropped out my accessible memory.

Excuse me, but I'm trying to use you as a rhetorical point here, and I don't 
need you showing up and interjecting the actual facts into the discussion.:)






From rglasser@penning.lanl.gov Thu Mar 13 10:48:56 MET 1997
Article: 23317 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!gsl-stkh-ns.gsl.net!news.gsl.net!sn.no!nntp.uio.no!newsfeeds.sol.net!news-xfer.netaxs.com!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Types of Puzzles
Date: Wed, 12 Mar 1997 23:16:47 -0800
Organization: UCSD
Lines: 62
Message-ID: <3327A9DF.49A2@penning.lanl.gov>
References: <331F3C45.794B@x_greenhouse.llnl.gov> <33243B3F.2790@cogentex.com>
NNTP-Posting-Host: sdx-ca27-06.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Thu Mar 13  1:16:51 AM CST 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23317

Daryl McCullough wrote:
> 
> I don't really care about distinguishing the type of puzzle so much
> as distinguishing the type of *effect* of the puzzle. Some puzzles
> are such that, after they are solved, you say to yourself "In
> retrospect, it all seems so perfectly *obvious*!"; all that
> was necessary was a fresh way of looking at things. Other puzzles
> leave you no more enlightened than you started, and seem mostly to
> be a matter of trying all possible combinations of actions. The
> latter type of puzzle is much easier to create, but the first type
> is much more satisfying for the player (in my opinion).
> 
> Daryl McCullough
> CoGenTex, Inc.
> Ithaca, NY

	Excellent point.  Perhaps we should come up with a new way of 
categorizing puzzles, something like this:

	* Puzzles which leave you smacking your head because they're so 
obvious that you should have gotten it in five minutes.
	* Puzzles which make you feel astoundingly clever, because they 
required a whole lot of observation and contemplation before the logic 
was clear to you and now it all makes sense.  (My favorite examples: 
Andrew's gate opening puzzle in Curses, escaping from the pit with the 
magnets in Gateway II.)
	* Puzzles that make you kick yourself for forgetting to take 
notes.  (i.e., half the puzzles in Myst)
	* Puzzles that make you twiddle little objects around until 
you fall asleep.  (i.e., the other half of puzzles in Myst, the wizard's 
test in Path To Fortune, everything in Magic Toyshop)
	* Puzzles that are just as tedious to solve the second time as 
the first.  (Many of the ones in the previous category also fall in this 
group.)
	* Puzzles which assume you know things that the game hasn't told 
you.  (Like the old man in Hugo 1.  Also, guessing stupid verbs like 
"yank" and "crank" in House of the Stalker.)
	* Puzzles that are included only as a ridiculous form of copy 
protection.
	* "The Sierra Method": puzzles that require you to use every 
object in your inventory on every other object in your inventory and/or 
every object/person in the game, until you get a result.
	* (Graphical games only)  Puzzles which require you to notice a 
single oddly colored pixel and click there.
	* Puzzles where you forget to go back to a place in the game 
where something has inexplicably changed because of something totally 
unrelated that you did elsewhere.
	* Puzzles where you stumble on the answer by trial and error, 
and years later somebody explains the logic behind the solution, and you 
figure nobody could get the answer EXCEPT by chance.  (Like figuring out 
which wife is cheating in TimeQuest.)
	* Puzzles requiring you to decipher bad puns.

	That's about all I can think of right now... how am I doing?
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From d91frera@ida.liu.se Thu Mar 13 14:18:01 MET 1997
Article: 23290 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] During-rules
Date: 12 Mar 1997 12:22:54 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 93
Message-ID: <5g676u$717@curofix.ida.liu.se>
References: <5fv7a0$po2@curofix.ida.liu.se> <5CM$QDA5RIJzEwbN@cega.demon.co.uk>
NNTP-Posting-Host: astmatix.ida.liu.se
Cc: mgraham@cega.demon.co.uk
X-Newsreader: NN version 6.5.0 #7 (NOV)
Xref: news.lth.se rec.arts.int-fiction:23290

Michael Graham <cega@cega.demon.co.uk> writes:

>In article <5fv7a0$po2@curofix.ida.liu.se>, "FReDRiK RaMSBeRG
>(WILdcARD)" <d91frera@ida.liu.se> writes
>>I've now put together a kit to add the functionality of the
>>during-rules I proposed to the library. Now I wonder which objects should
>>be allowed to interfere with the action. Right now, I can't think of any
>>situation where I would like anything but the objects directly referred to
>>in the sentence to define the action. So, I call the property during for
>>noun and during_second for second. I'm also calling during for the current
>>location, but am thinking about removing that. Does anyone have opinions on
>>this matter?
>>

>I'm assuming that the during routines are there to do the actual work of
>moving objects around and so forth, and not primarily to override the
>mechanics.  I can't see how the location would be involved at this
>stage, except to override these mechanics, and in this case, can't that
>be handled by "before"? 

The reason for having during-rules is that if you handle it in before, you must
return true to stop the default action from happening. Then, other before-
rules will not get the chance to stop the action, and the after-step is
skipped entirely. So, yes, during-rules are there to replace a normal verb-sub.
If you just want to do something additional when a certain action is performed,
that can be placed in an after-rule. With this system, the after-rules are
always executed if the action succeeded.

>Similarly, how do nouns and seconds work?  How do you divide up the
>mechanics?  Imagine a Put_On action:

>        noun.during hears about the action and releases noun to be put
>        somewhere (say by removing it from the player's inventory).  

>        second.during_second hears about the action and accepts the 
>        noun, moving noun to second.

>What happens if second refuses?  Is noun in limbo?  Do the two routines
>bicker back and forth before moving any objects?

First noun.during gets the chance to do something. If it doesn't want to
do the work of the verb-sub, it should return false. Then,
second.second_during gets the same chance. If this routine also returns
false, the action is handled by the normal verb routine.

>One other problem.  I looked at the library source the other day, and
>realized that the biggest hurdle in the during rules extension is in
>taking care of the after-routines and library messages, since these are
>always called by the VerbSub for the action in question.  Is the onus on
>each during routine to call Afterroutines() and print out the correct
>Library Message?  Or will this be handled by your extension in some
>generalized way? 

You could write a generalized way of handling this by calling the during_rule
several times with during_step set to different values, or by calling more
than one routine, but then the object has to store some data about what it
was about to print out, which would probably call for more code than simply
accepting the work of calling AfterRoutines directly from during_rule. Anyway,
it's not very complicated and you can copy and modify code from the library
when writing a new verb definition.

I'll supply an example of a fully working, useful during-rule. It changes a
button's state every time you press it, running the AfterRoutines and
printing a message.

Object Button "button"
  with
    name "button",
    during [;
      Push:
        if(self has general)
          give self ~general;
        else
          give self general;
        if(AfterRoutines() || keep_silent) rtrue;
        print (The) self " emitts a loud ";
        if(self has general)
          "BEEP and stays down.^";
        "PLOPP and pops up.^";
    ],
  has static;

>I rather like the during-rules idea.  I'll help with proof reading, but
>I'm not an expert.

Congratulations, you got the job! Thanks.

/Fredrik
--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
I want to make it perfectly clear that I can't say I don't think people who
aren't avoiding using too many negations aren't putting things clearly enough.


From aultman@koala.scott.net Fri Mar 14 09:09:20 MET 1997
Article: 23336 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-ana-24.sprintlink.net!news.scott.net!koala.scott.net!not-for-mail
From: aultman@koala.scott.net (Joe and Bonnie Aultman)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: 12 Mar 1997 17:01:17 -0600
Organization: Scott Network Services, Inc.
Lines: 28
Sender: the login is aultman, the domain is scott.net -- you do the math
Message-ID: <5g7cjt$d9f@koala.scott.net>
References: <5g6fqg$5t5@bartlet.df.lth.se> <erkyrathE6xxH1.Hxs@netcom.com> <5g76fv$412@bartlet.df.lth.se>
NNTP-Posting-Host: koala.scott.net
Xref: news.lth.se rec.arts.int-fiction:23336

In article <5g76fv$412@bartlet.df.lth.se>,
Magnus Olsson <mol@bartlet.df.lth.se> wrote:

>2) Free action commands. Just like ordinary commands (so other objects
>can react to it), except that the time counter doesn't advance, and
>daemons and timers don't run after it.

I've read this thread with interest and taken the opportunity to revisit
this issue in my head.  I still retain, however, the possibly unpopular
opinion that there should be no free action commands.

I understand the reasons that people want them, but I think it's the
wrong approach. If the player does not remember the map well in her
head, and she has to type "LOOK" a lot, then she is playing an unobservant
character. It's an element that she herself has brought to the game.
If she wants to play an observant character, she should map the game
thoroughly.

A similar argument applies to the forgetful character and "INVENTORY."

Of course, the existence of "UNDO" and "RESTORE" muddies up the whole
situation, but I consider it the burden of the player to simulate an
observant character, if necessary, by applying them in the appropriate
circumstances.

That is all,

Joe 


From florian.beck@stud.uni-muenchen.de Fri Mar 14 09:12:56 MET 1997
Article: 23338 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!newsfeed.nacamar.de!news-kar1.dfn.de!news-stu1.dfn.de!news-mue1.dfn.de!news-nue1.dfn.de!uni-erlangen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Fri, 14 Mar 1997 02:58:22 GMT
Organization: Private GNU Site
Lines: 65
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m3vi6vfacx.fsf@ue801di.lrz-muenchen.de>
References: <5g6fqg$5t5@bartlet.df.lth.se> <erkyrathE6xxH1.Hxs@netcom.com> <5g76fv$412@bartlet.df.lth.se>
Reply-To: florian.beck@stud.uni-muenchen.de
NNTP-Posting-Host: dial090.ppp.lrz-muenchen.de
X-Newsreader: Gnus v5.4.25/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:23338

mol@bartlet.df.lth.se (Magnus Olsson) writes:
> Actually, it's more than nitpicking. I think this scenario illustrates
> my point:
> 
> | Medusa's Cave
> | This cave is full of very life-like statues of adventurers in various
> | poses. Medusa isn't here in person, though.
> |
> | > z
> | Medusa enters the room behind your back.
> | 
> | > look
> | As your gaze falls upon Medusa's face, you turn to stone.
> |
> | *** You have died ***
> 
> In this example, "look" can be a free action, but it can't be a
> meta-command, since in that case it wouldn't be caught by Medusa's
> react_before. 

Hm, my point of view is quite different :-) I think *no* game-world command
can ever be a free action. But look *can* be a meta command.

In most games, every action takes one turn, no matter whether the
player looks or reads a book. Thats not realistic of course, but the
author has to decide if its worth the effort to distinguish short
actions from long ones. Looking around may take a few seconds. Even
glancing through a book will take half an hour. Only, in many games
that does not matter.

Strictly speaking, there is no free action in the game world.

What "look" really is, is an ambiguous command. It can *either* be a
(little) time consuming action of the *character* *or* it can be
command the *player* types to get, perhaps repeatedly, information on
the state of the game.  
[In graphical games, BTW, this is not a problem. Perhaps, I-text-F
could simulate this by displaying the room description continuously,
e.g. in the status "line"?]

It's not clear if the room descriptions are objective (as in theatre)
or subjective and thus depending on character (as in a first person
novel). It can be either, though hardly both ways. I'd say, the 
author decides. 


> 
> To clarify my position, I'd like to propose that we have three types
> of commands:
> 
> 1) Ordinary commands.  
> 
> 2) Free action commands. Just like ordinary commands (so other objects
> can react to it), except that the time counter doesn't advance, and
> daemons and timers don't run after it.

This could work, in practice, if you just want to distinguish between
action that take very little time from those who take substantial
time. But where's the border? Look? Inventory? (will take some time,
think of containers) What's with e.g. look at <enemy>? Smell <enemy>?
A glance at your watch? How much time does it take to try to go into a
direction without door?
 
-- 
Flo


From erkyrath@netcom.com Fri Mar 14 10:41:23 MET 1997
Article: 23342 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Gratis Glancing (was Re: Night of the Vampire Bunnies Release 2 soon!)
Message-ID: <erkyrathE70r1r.DAA@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <858008187.24325@dejanews.com> <5g22id$ns7@nntp5.u.washington.edu> <CT6h0KAsoJKzEw0g@cega.demon.co.uk>
Date: Fri, 14 Mar 1997 05:53:51 GMT
Lines: 51
Sender: erkyrath@netcom13.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23342

Michael Graham (cega@cega.demon.co.uk) wrote:
> In article <erkyrathE6yusv.6FM@netcom.com>, Andrew Plotkin
> <erkyrath@netcom.com> writes
> >Michael Graham (cega@cega.demon.co.uk) wrote:
> >> In article <erkyrathE6wMG3.7MJ@netcom.com>, Andrew Plotkin
> >> <erkyrath@netcom.com> writes
> >> >Well, just to throw a note of dissonance into this exits-fest, I always 
> >> >hated it. It stomps all over my suspension of disbelief. 

> >> Or "x" or "i" or "z" 
> >
> >This I don't understand at all. It's not the player's job to type 
> >coherent prose; it's the player's job to get commands into the machine. 
> >It's the author's job to write prose, and I don't find that "W <-*-> E" 
> >gives anything like the effect I want in a room description.

> The thing is, text adventures have their own idiom.  What you're used to
> seems natural and transparent, and novelty seems to intrude.

I am not unaware of the novelty factor.

> What's so inherently natural about typing "i" and getting an itemized
> list of what you're carrying?

Text IF cannot emulate any other form in its player->computer interface. 
It has its own idiom for that, which is now well-established and 
difficult to change.

In its computer->player interface, it does have something it can emulate, 
which is prose fiction. As a player and as an author, I prefer that it do 
that as much as possible. It is possible to describe a room in prose 
rather than as a list presented out-of-band. Therefore, that is the way I 
like it.

For that matter, I like inventory lists presented as English sentences 
rather than vertical lists.

>   So the
> "inventory. x key. get key. look in satchel. get paper clip" shorthand
> is convenient.  But it's not "realistic".

I think I'm not talking about realism, but fictionalism. I'm not trying 
to make games like real life; if I was, I'd be investing heavily in 
virtual-reality goggles. I'm trying to make games like books.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From fake-mail@anti-spam.address Fri Mar 14 13:42:07 MET 1997
Article: 23332 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.cis.okstate.edu!nntp.ksu.edu!newsfeeder.gi.net!news.mid.net!news.sdsmt.edu!news.wildstar.net!newsfeed.direct.ca!newsgate.direct.ca!fake-mail
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Thu, 13 Mar 1997 15:11:22 -0800
Organization: tela design
Lines: 43
Message-ID: <fake-mail-ya02408000R1303971511220001@news.direct.ca>
References: <fake-mail-ya02408000R1203971525390001@news.direct.ca> <19970313150101.KAA04073@ladder01.news.aol.com>
NNTP-Posting-Host: van-52-0427.direct.ca
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
x-no-archive: yes
X-Newsreader: Yet Another NewsWatcher 2.4.0
Xref: news.lth.se rec.arts.int-fiction:23332

In article <19970313150101.KAA04073@ladder01.news.aol.com>,
nulldogma@aol.com (Nulldogma) wrote:

> I added an "exits" command (even though I would never use one myself, and
> think it's awkward and intrusive) in version something-or-other of Lost
> New York specifically because I knew my SO would never play it otherwise
> -- she has no sense of compass directions, and kept getting lost and
> frustrated in the opening scenes. I figured if she was frustrated, other
> novices probably would be as well, so it was worth adding as an option.

 Right. Same here. Well. I don't have an SO, lamentably, and certainly not
one with the patience to play I-F. However, I do have friends who expressed
a similar frustration when it came to navigating. They all found it vastly
easier to move around once they'd seen a map. But of course that entails
spoilers.

> (This is a "which way can I go?" exits command, BTW, not a "which way can
> I go and where does it lead?" one.)

 Last night I worked for a bit on a revised latter command. And gave up.
Again. It's a lot more fiddly and complicated than one might think.

 Writing one of the former commands is fairly easy, and I wrote one that
works nicely enough. But showing where exits lead is complex if you want to
take into account whether or not the player has already traversed that
direction. (ie: you don't simply want to say if the player has been to that
destination or not) For one thing, indoors such direction traversals are
not symmetrical. You don't always know you can get from x to y, even if
you've already been in y, if you've gone around some alternative route.
Outside, of course, it should be symmetrical because you can generally see
>from one arbitrary location to the next.

 Thing is, in TADS anyway, you've got different code depending on whether
you go through a door or just walk to the next location that's specified
with a compass rose direction in the code. (ie: whether there's an obstacle
or not) And in my game I wrote a couple other kinds of custom obstacle
items that present even more problems. Argh.

 - Neil K. Guy

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From mol@bartlet.df.lth.se Fri Mar 14 14:37:12 MET 1997
Article: 23345 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: 14 Mar 1997 13:52:23 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 45
Message-ID: <5gbhm7$c05@bartlet.df.lth.se>
References: <5g6fqg$5t5@bartlet.df.lth.se> <erkyrathE6xxH1.Hxs@netcom.com> <5g76fv$412@bartlet.df.lth.se> <ant131235b49c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23345

In article <ant131235b49c4bn@arnod.demon.co.uk>,
Julian Arnold  <jools@arnod.demon.co.uk> wrote:
>In article <5g76fv$412@bartlet.df.lth.se>, Magnus Olsson
><URL:mailto:mol@bartlet.df.lth.se> wrote:
>> 
>> In article <erkyrathE6xxH1.Hxs@netcom.com>,
>> Andrew Plotkin <erkyrath@netcom.com> wrote:
>> >Magnus Olsson (mol@bartlet.df.lth.se) wrote:
>> >
>> >"meta" in Inform also prevents before/after actions from being run (which 
>> >is reasonable for "save" and "restore", and maybe less so for "look" as a 
>> >free action.) 
>> 
>> Yes, and that's exactly why I think the distinction is important.
>
>I've already replied to Magnus' first comment, so I'll keep this short.
>
>The distinction may be important from an Inform-centric point of view. 

This is certainly the first time anybody's called me "Inform-centric" :-).

>However, Inform ~= IF.  

Of course. I think my distinction ordinary actions / free actions / metaactions
holds for all IF, and should be kept separate from implementation issues.

In fact, the reason I brought this issue up at all was that I sensed a risk for
confusion between terminologies: there's in itself nothing wrong in calling
a "free action" a "metacommand"; but when people start assuming that they
should use Inform's "meta-verb" construct to implement them there's risk
for confusion. 

>Hugo meta commands (xverbs) can be trapped by
>before/after rules.

IIRC, TADS has a "meta-verb" construct taht is used for "real" meta-verbs
such as "save" and "undo", but which should not be used for free actions
- such verbs should simply call abort or something like that to prevent
daemons and fuses from running (since the turn counter in TADS is a daemon,
that will also mean that the command doesn't take any game time).


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From im@dcs.st-and.ac.uk Sun Mar 16 20:26:52 MET 1997
Article: 23377 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!plug.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!uknet!usenet1.news.uk.psi.net!uknet!uknet!strath-cs!st-and!ransom!im
From: Iain Merrick <im@dcs.st-and.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command? [mild Jigsaw spoiler]
Date: Sat, 15 Mar 1997 18:27:00 +0000
Organization: St. Andrews University
Lines: 27
Message-ID: <Pine.OSF.3.93.970315180931.17722A-100000@ransom>
References: <5g6fqg$5t5@bartlet.df.lth.se> <3326CB64.45B6@cogentex.com>
NNTP-Posting-Host: ransom.dcs.st-and.ac.uk
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Sender: im@ransom
In-Reply-To: <3326CB64.45B6@cogentex.com>
Xref: news.lth.se rec.arts.int-fiction:23377

On Wed, 12 Mar 1997, Daryl McCullough wrote:
[snip]
> "Inventory" can similarly be given two interpretations: do you mean
> for the character to rummage through her sack and see what treasures
> she has collected, or do you only mean for the computer screen to tell
> you, the player, what is in your character's possession?
> 
> Daryl McCullough
> CoGenTex, Inc.
> Ithaca, NY

This issue was brought forcibly to my attention in the endgame to
Jigsaw... (not, not _that_ endgame, the other one :)

Basically, there's a bunch of apes who like to mimic your actions: if
you push them, they push you back, and so on. I was quite amused to find
that when I did an inventory, the apes did a comical impression of
someone searching through their possessions; and, of course, when you
"look", the apes scan the horizon keenly.

Up until then I'd never thought of these commands as actual actions: I
guess I implicitly thought of them as "meta-commands". Still do, in
fact, but that's beside the point...

Iain Merrick
im@dcs.st-and.ac.uk



From jools@arnod.demon.co.uk Sun Mar 16 20:29:27 MET 1997
Article: 23361 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!uw.edu.pl!news.icm.edu.pl!newsfeed.nacamar.de!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Thu, 13 Mar 1997 01:54:42 +0000 (GMT)
Organization: Organisation name, location. Telephone/Fax?
Message-ID: <ant1301420b0c4bn@arnod.demon.co.uk>
References: <5g6fqg$5t5@bartlet.df.lth.se> 
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 71
Xref: news.lth.se rec.arts.int-fiction:23361

In article <5g6fqg$5t5@bartlet.df.lth.se>, Magnus Olsson
<URL:mailto:mol@bartlet.df.lth.se> wrote:
> 
> 
> In the current debate about the "look" command, the term
> "meta-command" is used liberally; people say that they think "look"
> should be a meta-command, and so on. 
> 
> As far as I can see, what most of the posters mean by this is that
> "look" should be a "free action", i.e. the turn counter shouldn't be
> incremented and daemons and timers shouldn't run after it.
> 
> But does this really make it a meta-command? To me, a meta-command is
> one which is outside of the game world. To me, the action of looking,
> whether it consumes a turn or not, is very much a part of the game,
> unlike commands such as "save" or "verbose" which are commands to the
> game-as-a-program.

Yes, fair enough.  My initial use of the phrase "meta command" was
because Inform uses meta to differentiate normal actions (GET, etc.)
>from what I call "system" commands (SAVE, etc.).  Perhaps foolishly I
thought that using Inform terminology would prevent this debate. :)

The thing is that Hugo/Inform have but two classes of command-- action
commands and meta commands in Inform, and verbs and xverbs in Hugo-- and
I was trying to stay within the boundaries of the two systems.

That said, I'm not convinced there is a need to differentiate between
"free actions" and "system commands."  In fact, I have argued that LOOK
and INV should be "system commands," as they are to do with the player
and not the character (but I see your point that this is a matter of
context).

Excuse me for being hazy on Inform, but in Hugo at least xverbs (meta
commands) can be trapped by before/after rules, so if LOOK and INV were
xverbs they would have the same functionality as your free actions.

> Finally, I think it's a difficult question whether commands such as
> 'look' or 'inventory' should be free actions or not. Depending on the
> context, the command 'look' may mean that the player examines his
> surroundings in detail - which of course should take some time - or
> just that he keeps looking around while doing other things.
> 
> In one case I can actually consider 'look' to be a meta-command in the
> sense I've used the word above: viz. if the player is merely asking
> the game to re-display the room description that just scrolled off the
> screen, or which would have been displayed automatically if the player
> hadn't typed 'brief' 10 turns ago. 

OK, different contexts call for different interpretations.  It's just
that ATM the default interpretation is that LOOK/INV are verbs, I think
the default should be that they are xverbs.  And someone is bound to
soon say that this is nitpicking, and does it *really* matter. :)

I've had a similar problem in a game I work on sometimes, which
implements REMEBER/THINK ABOUT <object>.  Do I say that this command
means "tell the player what the character knows about <object>" (in
which case it is an xverb) or that it means "the character pauses to
ponder/reminisce about <object>" (in which case it is a verb).  Most
realistically, sometimes it should be the one, sometimes the other,
depending on context, but this is undesirable from the point of view of
the player (what do you mean I get run over while thinking about the
oncominmg traffic?  THINK was an xverb just now!).  As you might have
guessed, I eventually went the xverb route.

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"



From cardinalt@earthlink.net Sun Mar 16 20:30:00 MET 1997
Article: 23363 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!europa.clark.net!mr.net!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Sat, 15 Mar 1997 05:42:44 GMT
Organization: Earthlink Network, Inc.
Lines: 44
Message-ID: <5gdcsd$3ak@chile.earthlink.net>
References: <5g6fqg$5t5@bartlet.df.lth.se>  <ant1301420b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: max1-sc-ca-05.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23363

Julian Arnold <jools@arnod.demon.co.uk> made so bold as to state:

>OK, different contexts call for different interpretations.  It's just
>that ATM the default interpretation is that LOOK/INV are verbs, I think
>the default should be that they are xverbs.  And someone is bound to
>soon say that this is nitpicking, and does it *really* matter. :)

This is nitpicking. Does it *really* matter?

But for what it's worth, I think LOOKing and INVing should always cost
the player. The player should, ideally and as a rule, be expected to
absorb the game text to the point of having it form a fairly clear and
precise imaginary picture in his mind. Granting that the literary
skills of authors can often make this difficult, still it seems to me
to be the IF *ideal* that both author and player should strive for in
their respective capacities. Free LOOKs and INVs just make for lazy
players, who begin to act a bit like speed-readers in that they start
to "scan" instead of really reading, and only seek out the little
tidbit of information they think they need at any given time, while
effectively ignoring the rest. It can be argued, of course, that the
penalty of using up a game-turn isn't generally all that punitive, but
the alternative--making such actions freebies--absolutely tells the
player that superficial attention to the game is not only permissible
but actively encouraged. That's the wrong message to send, in my view.


--Cardinal T

          I mean, what the hell kind of villain thwarts the hero's
	  progress with soup cans in the kitchen pantry?
	                                         --Russ Bryan
	
         Are there any text games prominently featuring dinosaurs?  
         If not, does anyone besides me think it would be cool? 
                                                 --Matthew Amster-Burton

         "The axe bounces off Geoffrey's neck. Doh!"
                                                 --Graham Manson
         
         "Bathroom?  Yeah.  Go through that door, on the end
         of the hall, on your left."  "Pardon?"  "South twice,
         than east."  "Ah."
                                                  --Clyde "Fred" Sloniker



From mgraham@cega.demon.co.uk Sun Mar 16 21:45:05 MET 1997
Article: 23359 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!cancer.vividnet.com!hunter.premier.net!news.maxwell.syr.edu!dispatch.news.demon.net!demon!cega.demon.co.uk!cega.demon.co.uk!cega
From: Michael Graham <cega@cega.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Gratis Glancing (was Re: Night of the Vampire Bunnies Release 2 soon!)
Date: Fri, 14 Mar 1997 23:18:04 +0000
Organization: Cega Ltd., Web Design Consultants
Distribution: world
Message-ID: <kxGi8FAsydKzEwzk@cega.demon.co.uk>
References: <858008187.24325@dejanews.com> <5g22id$ns7@nntp5.u.washington.edu>
 <CT6h0KAsoJKzEw0g@cega.demon.co.uk> <erkyrathE70r1r.DAA@netcom.com>
Reply-To: Michael Graham <mgraham@cega.demon.co.uk>
NNTP-Posting-Host: cega.demon.co.uk
X-NNTP-Posting-Host: cega.demon.co.uk
MIME-Version: 1.0
X-Newsreader: Turnpike Version 3.02 <8GdB6y3FvPYnxRxdS7oWRviWR2>
Lines: 51
Xref: news.lth.se rec.arts.int-fiction:23359

In article <erkyrathE70r1r.DAA@netcom.com>, Andrew Plotkin
<erkyrath@netcom.com> writes

[SNIP]

>In its computer->player interface, it does have something it can emulate, 
>which is prose fiction. As a player and as an author, I prefer that it do 
>that as much as possible. It is possible to describe a room in prose 
>rather than as a list presented out-of-band. Therefore, that is the way I 
>like it.
>
>For that matter, I like inventory lists presented as English sentences 
>rather than vertical lists.

Yes, I'm not advocating "de-fictionalizing" the computer->player
interface any further by having exit tables automatically generated at
the end of each "look" command.  But I don't see anything wrong with the
player typing 'exits' and the computer generating a response (the less
list-like, the better, of course).  I don't see this as any worse than
an inventory list.     

[SNIP]

>I think I'm not talking about realism, but fictionalism. I'm not trying 
>to make games like real life; if I was, I'd be investing heavily in 
>virtual-reality goggles. I'm trying to make games like books.

No argument there (although I also like to simulate a parser with a mind
of its own).

Have you ever been reading a book, and built up a pretty clear spatial
understanding of the landscape, only to have the author casually mention
some detail later that forced you to completely reorganize your mental
map?  

It's very difficult to write good succinct prose and still mention all
the exits and their associated compass directions.  I find that the more
an i-f game approaches good fiction, the more likely it is to bury the
map connections deep within it's wonderful descriptions.  

And speaking of which, I'm not particularly fond of mapping the games I
play (or the books I read, for that matter).  And what justice am I
doing your finely-crafted descriptions if I'm just scanning them for the
magic exit keywords?  And anyway, I'm lazy, so there you have it.


-- 
Michael Graham                             mailto:mgraham@cega.demon.co.uk
Cega Ltd. Web Design Consultants           http://www.cega.co.uk
London (Stratford), UK
Tel/Fax: +44-(0)181-221-2417


From d91frera@ida.liu.se Sun Mar 16 21:47:05 MET 1997
Article: 23385 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ifm.liu.se!liuida!d91frera
From: d91frera@ida.liu.se (FReDRiK RaMSBeRG (WILdcARD))
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: 16 Mar 1997 16:12:42 GMT
Organization: CIS Dept, Linkoping University, Sweden
Lines: 41
Message-ID: <5gh65q$npj@curofix.ida.liu.se>
References: <5gf4r2$fqh@ecuador.earthlink.net>
NNTP-Posting-Host: astmatix.ida.liu.se
X-Newsreader: NN version 6.5.0 #7 (NOV)
Xref: news.lth.se rec.arts.int-fiction:23385

cardinalt@earthlink.net (Cardinal Teulbachs) writes:

>Hi! I was wondering if someone could tell me what Interactive Fiction
>is. It sounds fun.

Sure, I'll take my responsibility as a good citizen, and explain it. 

It's a kind of "violence games". The people who gather at this newsgroup are
people who have problems learning a "real" language, like C or C++,
and make some real 3D-action, like Duke Nukem or Doom. So, they have made up
some simple easy-to-use systems that will at least allow them to write games,
albeit with a text-only interface.

The games are generally about walking around big mazes, killing all the evil
creatures you meet on the way. Sometimes you need to find keys to access
other parts of the maze and, eventually, finish the level. You get points
every time you pick up a key or enter a new area or level, as well as for
killing people and creatures. 

Due to the obvious lack of skill involved, only a few of the games include
automatic mapping facilities, so you have to make a map of the maze on a
piece of paper on the side. It feels a bit like going back to the 13:th
century at first, but you get used to it.

The game writers are an assorted bunch of oddballs, interesting in that they
take their task so seriously. That's probably why this group is mentioned in
the rec.humor FAQ as a nice place to hang out.

>Thanks!

You're welcome. Join in the crowd here, I think you'll feel right at home.

>--Satan

Can one be baptised to that name, or is it taken?

/Fredrik
--
Fredrik Ramsberg, d91frera@und.ida.liu.se, http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
Macintosh - 0.4% Actual Users!


From egh@uclink4.berkeley.edu Mon Mar 17 09:35:49 MET 1997
Article: 23396 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!agate!egh
From: egh@uclink4.berkeley.edu (Erik Hetzner)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Sun, 16 Mar 1997 18:45:41 -0800
Organization: Lies, Inc.
Lines: 52
Message-ID: <egh-1603971845410001@news.berkeley.edu>
References: <5g6fqg$5t5@bartlet.df.lth.se> <erkyrathE6xxH1.Hxs@netcom.com> <5g76fv$412@bartlet.df.lth.se> <ant131235b49c4bn@arnod.demon.co.uk> <erkyrathE700pG.A8y@netcom.com>  <ant1417340b0c4bn@arnod.demon.co.uk> <erkyrathE71yMI.FIn@netcom.com>
NNTP-Posting-Host: ckc18.reshall.berkeley.edu
X-Newsreader: Yet Another NewsWatcher 2.2.0b7
Xref: news.lth.se rec.arts.int-fiction:23396

In article <erkyrathE71yMI.FIn@netcom.com>, erkyrath@netcom.com (Andrew
Plotkin) wrote:

> If you want to have *three* classes of verbs (meta, free-action, 
> normal-action) things get a little more complicated. You'd have to add 
> another global variable, "freeaction", and set it by some test early in 
> the parsing process. Then go through the library and for each usage of 
> "meta", decide whether it should be "meta", "freeaction", or "meta || 
> freeaction." I haven't done the work, here, but it wouldn't be a big 
> deal. 

I don't think three classes of verbs are exactly what we want. What we're
dealing with here is a number of things (IMHO):
 1. Time of action.
 2. The player's v. the character's memory.
Text is harder to remember than sights. So the character would have an
easier time spotting slight changes in the landscape than the player has
noticing slight changes in the prose. So a game /ought/ to inform the
player for things along the lines of: `You notice something has changed.'
This is only fair. Which brings me to:

Perhaps the player's first `look' out to take a turn. Subsequent looks
within, say, 30 turns or three different rooms would be free. After that,
a look would take a turn again.

Of course, a player generally gets a `free' look when she enters a room.
Perhaps this ought to take time according to the same rules as above. If
the player has brief on, of course, they don't have to `pay' for looks
when the enter a room.

Even better would be to have a system where different commands took
different times -- so the first look might take 10-30 sec., depending on
the size of the room. Looks after might take less, or no time at all (as
it is just as if the player is recalling what the character had seen).

On the other hand, this is all rather complicated and bureaucratic.
 
> Note that the Inform library also makes another distinction for
> "meta"-verbs: you can't order another character to do them. (No fair
> typing "Floyd, save" or "Wizard, undo.") This restriction shouldn't apply
> to free-action verbs. 

Of course, a command to another character should really take /two/ turns
-- one to tell the character what to do, and another for the character to
do it. But then the player should be free for that second turn to do what
they'd like, except to command the other character again, who would have
to be `busy'.
 
> --Z
-- 
Erik Hetzner             | `I'm celebrating my love for you;
egh@uclink4.berkeley.edu |  with a pint of beer and a new tattoo.'


From john@elvw.demon.co.uk Mon Mar 17 14:00:46 MET 1997
Article: 23399 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!news-m01.ny.us.ibm.net!ibm.net!arclight.uoregon.edu!dispatch.news.demon.net!demon!mail2news.demon.co.uk!elvw.demon.co.uk!john
From: John Wood <john@elvw.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: Sun, 16 Mar 1997 17:12:34 GMT
Organization: None
Message-ID: <674708336wnr@elvw.demon.co.uk>
References: <5gf4r2$fqh@ecuador.earthlink.net>
Reply-To: john@elvw.demon.co.uk
X-Mail2News-User: john@elvw.demon.co.uk
X-Mail2News-Path: relay-11.mail.demon.net!elvw.demon.co.uk
X-Broken-Date: Sunday, Mar 16, 1997 13.09.42
X-Newsreader: Newswin Alpha 0.7
Lines: 42
Xref: news.lth.se rec.arts.int-fiction:23399

In article: <5gf4r2$fqh@ecuador.earthlink.net>
  cardinalt@earthlink.net (Cardinal Teulbachs) writes:
> 
> Hi! I was wondering if someone could tell me what Interactive Fiction
> is. It sounds fun.
> 
> Thanks!
> 
> --Satan

Your Infernalness,

Yes, it is fun.  It's also got a good range of material for us to work
on - particularly from the authors:

* Sloth, when they should be working on their game but can't be
  bothered;
* Envy of other, more successful authors;
* Pride in their work (though this is often temporary);
* Gluttony, common to all programmers on long sessions;
* Anger, when they get frustrated that they can't get the game to do
  what they want.

I'm afraid Avarice quickly get's quashed when they find out it's
impossible to make any money doing it.  And they're all nerds, so Lust
is not doing well (note to self: work on the isolationist pent-up
feelings angle).

Oh, one more observation - as the Father of Lies I think you should be
particularly proud of our work with the authors on their release date
estimates.  I've had one agent working full-time on something we've
codenamed Project Avalon - the subject is responding very well...

I haven't answered your original question, my Lord, because it is
impossible to define.  Fortunately this is irrelevant to the task at
hand - IF can be whatever we make of it.

Your obedient servant,

Wormwood.




From cardinalt@earthlink.net Mon Mar 17 14:01:15 MET 1997
Article: 23395 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!enews.sgi.com!news.sgi.com!howland.erols.net!newsxfer.itd.umich.edu!news.ececs.uc.edu!news.kei.com!news.thenet.net!uunet!in3.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: Mon, 17 Mar 1997 01:50:10 GMT
Organization: Earthlink Network, Inc.
Lines: 43
Message-ID: <5gi7vk$63n@ecuador.earthlink.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <674708336wnr@elvw.demon.co.uk>
NNTP-Posting-Host: max1-sc-ca-03.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23395

John Wood <john@elvw.demon.co.uk> made so bold as to state:

>Your Infernalness,

>Yes, it is fun.  It's also got a good range of material for us to work
>on - particularly from the authors:

>* Sloth, when they should be working on their game but can't be
>  bothered;
>* Envy of other, more successful authors;
>* Pride in their work (though this is often temporary);
>* Gluttony, common to all programmers on long sessions;
>* Anger, when they get frustrated that they can't get the game to do
>  what they want.

Hmm. These seem familiar, somehow.

>I'm afraid Avarice quickly get's quashed when they find out it's
>impossible to make any money doing it.  And they're all nerds, so Lust
>is not doing well (note to self: work on the isolationist pent-up
>feelings angle).

Personally, I find the Vampire Bunny rather attractive. And Black, too
(Oh, my Self! A dahlia by any other name...). 

>Oh, one more observation - as the Father of Lies I think you should be
>particularly proud of our work with the authors on their release date
>estimates.  I've had one agent working full-time on something we've
>codenamed Project Avalon - the subject is responding very well...

So you're acquainted with my spawn, then? He's one of my better
creations, I must say. 

>I haven't answered your original question, my Lord, because it is
>impossible to define.  Fortunately this is irrelevant to the task at
>hand - IF can be whatever we make of it.

Ah! Splendid! A blank check. Perhaps I'll cash it one day (right--when
home freezes over, maybe. I've got more unfinished "whatever we make
of it"s than you can shake a pitchfork at).

--Sate



From jools@arnod.demon.co.uk Tue Mar 18 10:14:14 MET 1997
Article: 23436 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!news.algonet.se!hammer.uoregon.edu!arclight.uoregon.edu!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Mon, 17 Mar 1997 21:17:16 +0000 (GMT)
Organization: Organisation name, location. Telephone/Fax?
Message-ID: <ant172116d07c4bn@arnod.demon.co.uk>
References: <5g6fqg$5t5@bartlet.df.lth.se> <ant1301420b0c4bn@arnod.demon.co.uk> <5gavqn$2m8@oravannahka.Helsinki.FI> <ant170123b49c4bn@arnod.demon.co.uk> <E76xCL.MEq@world.std.com> 
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 32
Xref: news.lth.se rec.arts.int-fiction:23436

In article <E76xCL.MEq@world.std.com>, Mark J Musante
<URL:mailto:olorin@world.std.com> wrote:
> 
> Julian Arnold (jools@arnod.demon.co.uk) wrote:
> > Well, a similar system to LOOK/XLOOK has been used before.  In Infocom's
> > "Suspect" for example (I think), you could LOOK (took 1 minute), SEARCH
> > (took, say, 5 minutes), or SEARCH CAREFULLY (took, say, 15 minutes).
> 
> Is this the only instance of an adverb in an IF game?  I believe most games
> just use nouns, verbs, adjectives and prepositions.  Would adding adverbs
> to the player's syntax help or hurt the gameplay?
> 
> >PUT VASE CAREFULLY ON THE CUSHION
> >OPEN DOOR SLOWLY
> >GO QUICKLY NORTH
> >TURN DIAL GENTLY

I've seen them in other (non-Infocom) games.  ISTR "The Hobbit" used
them?  Maybe.

In general though, I think they'd be unuseful at best, a downright
hindrance at worst.  Imagine all those horrible "guess the adverb"
puzzles: "But I went east cautiously!" "No, you go east surreptitiously,
then north cautiously, and finally take a sneaky inventory and slyly
throw the gooblet at Kenneth."

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"



From fake-mail@anti-spam.address Tue Mar 18 10:16:05 MET 1997
Article: 23435 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!hammer.uoregon.edu!arclight.uoregon.edu!newsfeed.direct.ca!newsgate.direct.ca!fake-mail
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is a meta-command?
Date: Mon, 17 Mar 1997 15:02:34 -0800
Organization: tela design
Lines: 27
Message-ID: <fake-mail-ya02408000R1703971502340001@news.direct.ca>
References: <5g6fqg$5t5@bartlet.df.lth.se> <ant1301420b0c4bn@arnod.demon.co.uk> <5gavqn$2m8@oravannahka.Helsinki.FI>  <ant170123b49c4bn@arnod.demon.co.uk> <E76xCL.MEq@world.std.com>
NNTP-Posting-Host: van-as-12c04.direct.ca
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
x-no-archive: yes
X-Newsreader: Yet Another NewsWatcher 2.4.0
Xref: news.lth.se rec.arts.int-fiction:23435

In article <E76xCL.MEq@world.std.com>, olorin@world.std.com (Mark J
Musante) wrote:

> Is this the only instance of an adverb in an IF game?  I believe most games
> just use nouns, verbs, adjectives and prepositions.  Would adding adverbs
> to the player's syntax help or hurt the gameplay?

 Oh-oh. The great adverb discussion rears its ugly head again. :) For what
it's worth, I think the general consensus as to why hardly any games
implement adverbs is two-fold.

 First, it means it becomes a nightmare to code. There are enough verbs as
it is to have to write in, let alone to worry about coding in zillions of
permutations of each verb. Second, it becomes a nightmare for the player to
guess the correct adverb for each action, and the whole thing becomes even
worse than the usual "guess the verb" game.

 Of course, you could specify to the player in the game instructions that
there is a certain number of adverbs that can be applied in the game. eg:
slowly, carefully, quickly. And that's it. This is workable, but what it
adds to the game I don't know.

 - Neil K. Guy

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From mol@bartlet.df.lth.se Tue Mar 18 17:16:21 MET 1997
Article: 23462 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: 18 Mar 1997 16:16:48 +0100
Organization: Societas Datori Universitatis Lundensis
Lines: 56
Message-ID: <5gmbl0$u9b@bartlet.df.lth.se>
References: <Ed-1803970204530001@207.103.118.124>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23462

In article <Ed-1803970204530001@207.103.118.124>, Ed! <Ed@eSquare.com> wrote:
>Ok, I understand the nostalgic factor in IF, I certainly  don't expect to
>come across 3D worlds and surround sound - that would be like expecting TV
>to replace books. However I did expect the parsers to advance a little in
>the past 10 years. That was the last time I played a game (HitchHiker's
>Guide). The parsers are just as inflexible and can only understand things
>in a certain format.

That's more or less true. IF parsers haven't advanced much beyond Infocom's
parsers.

The reason for that is certainly not that IF authors *can't* write better
parsers. In fact, it would be fairly eas (if non-trivial) to extend the
Inform parser to handle the cases you list.

No, the problem is much deeper than that, and has nothing to do with the
parser _per se_. 

Take the case where the problem is most noticeable, viz. NPC's: In most IF,
you can give the NPC's simple commands ("troll, give me the bottle"), ask
them about or tell them about simple concepts ("ask the troll about the
bottle"), and that's about all.

But suppose I wanted to ask the troll something more complicated, like
"Troll, what happens if I press the button?", or "Ask the troll about
what was in the bottle before he broke it".

Now writing a parser that can parse such sentences is not the big
problem. What the parser does is basically to identify the grammatic
structure of the input. The difficult thing is not grammar, but
*understanding* the sentence, having the knowledge to act on it, and
acting on it. All these are *hard* problems; research problems in AI,
in fact. Some AI researchers are even using IF-like scenarios to explore
these problems.

Of course, we'd all dearly like to see games that really possessed the
intelligence necessary to deal with more compliated input. But writing
such games is hard. Very hard. The entire games industry hasn't come
up with anything like it yet, so maybe it's a bit ambitious to expect
us amateurs to do so in a mere 10 years.

Finally, an example that shows that the parser is the small problem; a
simple command that almost all existing IF parsers can parse, but where
it would be very hard to have the game come up with a sensible answer
(unless, of course, the programmer anticipates it and puts in a canned
response):

"Troll, prove Pythagoras' theorem."





-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From erkyrath@netcom.com Tue Mar 18 19:09:47 MET 1997
Article: 23465 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!fu-berlin.de!news.nacamar.de!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Disappointed with IF parsing
Message-ID: <erkyrathE79275.3xu@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <Ed-1803970204530001@207.103.118.124> <5gmbl0$u9b@bartlet.df.lth.se>
Date: Tue, 18 Mar 1997 17:35:29 GMT
Lines: 89
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23465

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> In article <Ed-1803970204530001@207.103.118.124>, Ed! <Ed@eSquare.com> wrote:
> >Ok, I understand the nostalgic factor in IF, I certainly  don't expect to
> >come across 3D worlds and surround sound - that would be like expecting TV
> >to replace books. However I did expect the parsers to advance a little in
> >the past 10 years. That was the last time I played a game (HitchHiker's
> >Guide). The parsers are just as inflexible and can only understand things
> >in a certain format.

> That's more or less true. IF parsers haven't advanced much beyond Infocom's
> parsers.

> The reason for that is certainly not that IF authors *can't* write better
> parsers. In fact, it would be fairly eas (if non-trivial) to extend the
> Inform parser to handle the cases you list.

If I may add to what Magnus said (and I only snipped his reply for space 
and because I agree with it):

The current parsing scheme has one huge advantage, which is that it's 
inflexible and can only accept things in a certain format.

A given action can pretty much only be phrased one way. This means that 
(1) if a player wants to do something, he only has to try a single 
phrasing before he knows whether it worked, and (2) if an author wants 
his game to react to a command, he only has to anticipate and handle a 
single phrasing. 

When this breaks down -- when an action can be phrased in several 
differnt ways within the Infocom syntax -- the author *must* anticipate 
and handle all of them. If the syntax was more flexible, the author would 
have to do that much more work *in order to give the player the same 
range of possible actions.* Is this worthwhile? We agree that it's 
worthwhile up to a point -- we don't use two-word parsers -- but a line 
must be drawn somewhere, and it was drawn ten years ago, and nobody has 
seen advantage in moving it.

Anyway, the existing syntax seems to be good enough for action and
movement commands. How would you expand it for the realm of manipulating
physical objects? You could toss in adverbs -- well, we just were
discussing why this is a bad idea. 

The other sort of commands is talking to people. Here, the existing 
command set is pretty limited: "tell y about x", "ask y about x", "say 
yes", and so on. I note that your list of sample commands is mostly of 
this type (either they would appear after a character's name: "fred, who 
created you?" or they are being asked of the viewpoint character: "what 
is a grue?")

I wouldn't mind an expansion of the accepted talking-to-people syntax. If 
it appeared in a game which had a lot of conversation, and had an intro 
file detailing the new syntax. But I'm *not* talking about "try to 
understand everything the player might type." I mean a few extra 
phrasings like "Fred, x is y" and "Fred, is y x?" -- those, for example, 
to support a very simple knowledge-model in which each NPC can associate 
properties with objects.

Put it this way (which is pretty much what Magnus said:) *First*, you 
complexify the model behind the game, such that it can handle new 
commands in a consistent way. *Second*, you explain this new model to the 
player, so that he's not totally lost trying to deal with it. *Then* it's 
time to improve the parser so that it can deal with the new model features.

Example: you suggested "HOW FAR IS BOSTON FROM NEW YORK". Well, that's 
easy enough to parse -- in Inform, it's

Verb "How" * "far" "is" noun "from" noun;

Well, spiff that up with "distant" as a synonym for "far", and use a 
location-token routine for the nouns (to match all the locations known to 
the game, plus "here".) Maybe also "how far is it from x to y". This is 
half an hour's work at worst.

Now, what on Earth (so to speak) will inspire the player to type that? It 
would have to be a situation where asking that question is practically 
the only sensible thing to do. Or else give a blatant hint, or just tell 
the player to type something like that. I *might* do that if distance 
were a key factor in the game, such that the player is using that command 
over and over again, in different situations. But more likely I'd give 
him a distance chart and forget the parsing.

Ok, enough ranting.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From avrom@Turing.Stanford.EDU Wed Mar 19 10:15:22 MET 1997
Article: 23478 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.Stanford.EDU!not-for-mail
From: avrom@Turing.Stanford.EDU (Avrom Faderman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: 18 Mar 1997 12:44:20 -0800
Organization: CSLI, Stanford University
Lines: 54
Message-ID: <5gmur4$fm9@Turing.Stanford.EDU>
References: <Ed-1803970204530001@207.103.118.124> <fake-mail-ya02408000R1703972332030001@news.direct.ca>
NNTP-Posting-Host: turing.stanford.edu
Xref: news.lth.se rec.arts.int-fiction:23478

In article <fake-mail-ya02408000R1703972332030001@news.direct.ca>,
Neil K. <fake-mail@anti-spam.address> wrote:
>In article <Ed-1803970204530001@207.103.118.124>, Ed@eSquare.com (Ed!) wrote:
>
>
> [ various examples deleted]
>
>> -------------------- ---- ---- --- -- -  -   -    -        -
>> Can your parser do that?
>
> Nope. My parser is based on software written by a couple guys as a fun
>hobby, and it fits on a floppy disk.
>
> It's not based on software running on high-powered iron in an AI lab
>funded by zillions of dollars of government, military and corporate funding
>with lots of full-time employees and tons of grad students who can
>hard-code up a massive knowledge base library with (at least)
>multi-megabytes of responses.

Besides, I, at least, wasn't all that impressed by START, particularly
considering the expensiveness of its hardware.  It's pretty easy to
stump with pretty natural locutions--and I don't mean stump the
database, which is of course limited to certain topics;  I mean stump
the parser.  I take it START's response (in the original post) to "Can
I have your source code?" for example, clearly counts as a miss.  So
does its response to:

How much longer can we expect sun in San Francisco? (although "what is
the whether is San Francisco?" produces relevant information, START
can't figure out that it would be relevant)

Are you the state of the art?  ("I don't know" would be fine;  "I
don't know if I'm the art's state" is reminiscent of Eliza)

Don't get me wrong--I'm not claiming that START is shoddily built, or
even that it's not the state of the art (although its refusal to
answer might be construed as incriminating, were it not for the fifth
amendment).  But if START is the state of the art, the art's state
(why does this sound better to me than START's reply?  I'm not sure,
but it does) just isn't that advanced.  I-F parsers don't seem all
that primitive by comparison.

And START doesn't even have to deal with cross-sentence pronoun
binding.  Unlike IF parsers.

-Avrom










From ldaly@bu.edu Wed Mar 19 10:15:39 MET 1997
Article: 23495 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!super.zippo.com!zdc!enews.sgi.com!decwrl!purdue!news.bu.edu!cgl!ldaly
From: ldaly@bu.edu (Liza Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: 19 Mar 1997 01:28:55 GMT
Organization: Boston University
Lines: 33
Message-ID: <5gnfgn$8m1@news.bu.edu>
References: <Ed-1803970204530001@207.103.118.124> <ant1813500b0c4bn@arnod.demon.co.uk> <332F0EF8.41C6@x_greenhouse.llnl.gov>
NNTP-Posting-Host: cgl.bu.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:23495

Kathleen Fischer (kfischer@x_greenhouse.llnl.gov) wrote:

: > > http://sakharov.ai.mit.edu/start

: Well, as nice as the parser might be, I don't see it being of much use
: for *my* game  :)

: Kathleen (just kidding, really... I'm sure its a very nice system.)

	==> TELL ME SOMETHING NOT ABOUT BOSTON WEATHER 
	
	To obtain the information you requested, click on the 
	*weather in Boston*.

...or maybe not.  Jeez, even most i-f parsers understands negation (PUT ALL
BUT THE AI SYSTEM IN KNAPSACK.)

Okay, let's try with the word "but."

	==> TELL ME ANYTHING BUT SOMETHING ABOUT BOSTON WEATHER 

	The distance between Detroit Michigan and Chicago Illinois is
	235 miles.   

*ahem*

--Liza

--
"Why should we endeavour to make the web exciting, interesting,
 interactive and aesthetically pleasing?" - The House of Erotic Massage
                                            March edition
 gecko@retina.net                           http://fovea.retina.net/~gecko/


From blore@ibm.net Wed Mar 19 10:38:13 MET 1997
Article: 23484 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news-xfer.netaxs.com!hammer.uoregon.edu!arclight.uoregon.edu!newsfeed.uk.ibm.net!ibm.net!news-m01.ny.us.ibm.net!news.ibm.net!news-s01.ca.us.ibm.net!not-for-mail
From: blore@ibm.net    (Steven Howard)
Newsgroups: rec.arts.int-fiction
Subject: Disappointed with START (was Re: Disappointed with IF parsing)
Date: 19 Mar 1997 05:58:25 GMT
Lines: 69
Message-ID: <5gnva1$mj4$2@news-s01.ca.us.ibm.net>
References: <Ed-1803970204530001@207.103.118.124>
Reply-To: blore@ibm.net
NNTP-Posting-Host: slip129-37-242-71.ca.us.ibm.net
X-Newsreader: IBM NewsReader/2 v1.2.5
Xref: news.lth.se rec.arts.int-fiction:23484

In <Ed-1803970204530001@207.103.118.124>, Ed@eSquare.com (Ed!) writes:
>Interestingly enough, one was created years ago and has been on the web
>for over 3 years to demonstrate its abilities - which it can tell you
>about if you ask. It's called START & I'm sure it's only one example of
>what today's parsing technology is capable of doing. Is anyone else
>interested in seeing this technology used in IF games? (Personally, I'm
>looking into the technology for PBeM games which could benefit greatly
>from an excellent parser).
>
>
I already replied to this once, but I decided to check out "START" for myself. 


>Here's START's Web address and a few questions and answers I grabbed from
>my conversation with the MIT creation. Enjoy!
>
>http://sakharov.ai.mit.edu/start
>================================

[I've been reading American authors from the 1920s.  I wonder if START knows 
anything about them . . .]


==>  WHO WAS DOROTHY PARKER

The word PARKER is unknown.  Please choose one of the following: 
PARKED
PARSER
MARKER
Abort

[Oooh.  Not off to a good start.  Mrs. Parker may be a bit obscure.  Let's try 
Fitzgerald . . .]

==>  WHO WAS F

I did not understand the word "f".  Please try using a different word.

==>  SCOTT FITZGERALD

I did not understand the word "fitzgerald".  Please try using a different word.

[Huh.  Well, they never said it knew anything about literature.  Try science.]

==>  WHO WAS ALBERT EINSTEIN

I don't know anything concerning Albert Einstein.

[Getting better.  At least it recognizes that "Albert Einstein" is what I'm 
asking about.  This is the first of my questions that START has been able to 
parse.]

==> WHO WAS TURING

I don't know anything at all about Turing.

[I guess not.]

>Can your parser do that?

Ed, honey, if my parser can't do better than that, I'll eat it.

========
Steven Howard
blore@ibm.net

What's a nice word like "euphemism" doing in a sentence like this?




From d91frera@und.ida.liu.se Wed Mar 19 10:39:03 MET 1997
Article: 23491 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!howland.erols.net!math.ohio-state.edu!jussieu.fr!uvsq.fr!not-for-mail
From: Fredrik RAMSBERG <d91frera@und.ida.liu.se>
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: Wed, 19 Mar 1997 07:56:22 +0100
Organization: University of Linkoeping
Lines: 86
Message-ID: <332F8E16.2F1CF0FB@und.ida.liu.se>
References: <Ed-1803970204530001@207.103.118.124>
NNTP-Posting-Host: venus.prism.uvsq.fr
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (X11; I; SunOS 4.1.3C sun4m)
Xref: news.lth.se rec.arts.int-fiction:23491

Ed! wrote:

> Can your parser do that?

Here are a few examples from Start that make me think that the parser
pretty much
sucks. It's the knowledge base that can add something.



==> IS IRAQ A PART OF THE USA 

Sorry - I don't know if Iraq is the USA's part.

==> WHAT IS IRAQ 

Iraq is Iran's neighbor.

Iraq is potential nuclear power.

Iraq is a country.

Sorry, I don't know what you are asking about.

==> CAN YOU MAKE TEA 

Sorry, no one has told me whether I can make the tea.

==> WHY WOULD ANYONE LIKE TO LIVE IN CLEVELAND (Okay, this one doesn't
prove much...)

Unfortunately, I don't know why anyone would like living in Cleveland
Ohio.

==> IS OHIO IN CLEVELAND 

Unfortunately, I wasn't told whether Ohio is in Cleveland Ohio.

==> ARE THERE ANY IRAQI PORTS IN SOUTH KOREA 

The following seems to be relevant: 

Iraq's major ports are: Umm Qasr, which has reopened in November 1993;
Khawr az Zubayr and Al Basrah, both of which have been closed since
1980. 

South Korea's major ports are: Pusan, Inch'on, Kunsan, Mokp'o, and
Ulsan. 

==> ARE INTERACTIVE FICTION PARSERS BETTER THAN YOURS 

Sorry - I don't know.

==> ARE YOU INTELLIGENT 

Yes 

==> WHAT IS INTELLIGENCE 

I don't know the answer to your question.

==> WHAT IS THE DISTANCE BETWEEN IRAQ 

Sorry - I don't know.

==> WHAT IS THE DISTANCE BETWEEN IRAQ AND IRAQ 

The distance between Baghdad, the capital of Iraq, and Baghdad, the
capital
of Iraq, is 0 miles.

==> TELL ME ABOUT ALL PORTS 

Sorry - I don't know whether or not I can tell you about all ports.

==> WILL YOU TAKE CONTROL OF EARTH 

I am sorry to say I don't know whether or not I will take the control of
the
Earth.

I think this last reply indicates that we should sign a petition that
the project
is stopped immediately.

/Fredrik


From egh@uclink4.berkeley.edu Wed Mar 19 10:39:46 MET 1997
Article: 23486 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!howland.erols.net!newsxfer3.itd.umich.edu!agate!egh
From: egh@uclink4.berkeley.edu (Erik Hetzner)
Newsgroups: rec.arts.int-fiction
Subject: Re: [inform] What the hell is wrong with this?
Date: Tue, 18 Mar 1997 21:14:46 -0800
Organization: Lies, Inc.
Lines: 32
Message-ID: <egh-1803972114460001@news.berkeley.edu>
References: <5gkv44$52f@uni00nw.unity.ncsu.edu> <5glmrk$3og@bartlet.df.lth.se> <fake-mail-ya02408000R1803970200580001@news.direct.ca> <5gm4e8$fom@uni00nw.unity.ncsu.edu>
NNTP-Posting-Host: ckc16.reshall.berkeley.edu
X-Newsreader: Yet Another NewsWatcher 2.2.0b7
Xref: news.lth.se rec.arts.int-fiction:23486

In article <5gm4e8$fom@uni00nw.unity.ncsu.edu>, camangin@unity.ncsu.edu
(Charles Albert Mangin) wrote:

> Oddly enough, i already have done that.. I first had troubles with the 
> quotes "" that i had typed in bbedit, but not in the inform editor, so i 
> turned off the 'smart quotes' and that problem solved itself. However, 
> this did nothing to change the fact that the single quote still messed 
> up. I just decided to try and write my descriptions without using 
> conjunctions or possessives with apostrophes.. not easy.

That's no solution! :) Okay, let's examine the problem: The Macintosh has
too many quote symbols. Consider:
 ` -- on your keyboard, upper-left hand corner.
 ' -- on your keyboard, between return and colon.
  -- typed shift-option-e
  -- option-[
  -- shift-option-[
  -- option-]
  -- shift-option-]

My apologies for peoples who's consoles are now screwed up -- this uses
Mac spefific `ASCII'.

Apparenty, you used the "" symbol, though I don't know how you found it
-- I've never heard or seen of it before, but it appears to be ASCII
character number 96. What you need to do is use the "'" symbol like the
rest of the world. :)

Hope this solves some problems. Email me if you have any more questions. :)
-- 
Erik Hetzner             | `I'm celebrating my love for you;
egh@uclink4.berkeley.edu |  with a pint of beer and a new tattoo.'


From cardinalt@earthlink.net Wed Mar 19 10:40:57 MET 1997
Article: 23485 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!news.maxwell.syr.edu!metro.atlanta.com!uunet!in1.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: Wed, 19 Mar 1997 05:35:38 GMT
Organization: Earthlink Network, Inc.
Lines: 28
Message-ID: <5gntvd$hj8@bolivia.earthlink.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <5gm0aj$bj6@bartlet.df.lth.se>
NNTP-Posting-Host: max3-sc-ca-21.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23485

mol@bartlet.df.lth.se (Magnus Olsson) made so bold as to state:

>Ahem - excuse me, Your Eminence, but just what church did you say you
>represented?

Oh, my. I *am* sorry for confusing you, Magnus. Satan is just my night
job...

:)

--Cardinal T

          I mean, what the hell kind of villain thwarts the hero's
	  progress with soup cans in the kitchen pantry?
	                                         --Russ Bryan
	
         Are there any text games prominently featuring dinosaurs?  
         If not, does anyone besides me think it would be cool? 
                                                 --Matthew Amster-Burton

         "The axe bounces off Geoffrey's neck. Doh!"
                                                 --Graham Manson
         
         "Bathroom?  Yeah.  Go through that door, on the end
         of the hall, on your left."  "Pardon?"  "South twice,
         than east."  "Ah."
                                                  --Clyde "Fred" Sloniker



From lpsmith@rice.edu Wed Mar 19 13:27:07 MET 1997
Article: 23468 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!europa.clark.net!news.msfc.nasa.gov!bcm.tmc.edu!newsfeed.rice.edu!rice!ural.owlnet.rice.edu!lpsmith
From: lpsmith@rice.edu (Lucian Paul Smith)
Newsgroups: rec.arts.int-fiction
Subject: Re: Announcing the 3rd Annual I-F Competition
Date: 18 Mar 1997 18:57:26 GMT
Organization: Rice University, Houston, Texas
Lines: 55
Message-ID: <5gmoim$8h9$1@joe.rice.edu>
NNTP-Posting-Host: ural.owlnet.rice.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:23468

Well, I had to go to DejaNews to find the original announcement--oddly 
enough, the newsreader here received GKW's reply to someone else's reply 
to GKW's original posting, and it hasn't received (yet?) the original 
reply or the original posting.

Anyway.

I have both a question and a proposal.

As stated in the post, the judging rules are undefined as of yet.  The 
last time this came up, I thought that the best idea was to have everyone 
play through the games in a random order, as many as they could in the 
time alloted.  That way, each game would have an even spread of people 
voting for it.

I also have a proposal as to how to make that go smoothly.  I am planning 
on writing a "game" in Inform (something like Comp97.z5) which would 
function as a 'front end' for the contest.  People would play Comp97 
first, where they would answer questions about what kind of platforms 
they had available on which to play games, and what games (if any) they 
had authored or betatested (on the theory that they would be disqualified 
>from judging those games--this is a rule question, however, and could 
easily be modified.)  The game would then produce a randomized list of 
entries, which the player would then follow as they judged the games.

As an added convenience, Comp97 would also provide 'scratch space' for 
the player to record their votes, as well as, possibly, a place to write 
down some of their thoughts on the games.  Another possible convenience 
would be to provide a method of voting on different aspects of the games 
(characters, setting, puzzles, etc.), and would use those results to 
compute a given game's rating.  Again, this would be purely a 
convenience, and a game could just be rated straight up, or modified in 
any way at any step.

As an added added bonus, if I could figure out how to do the @save thing 
in Inform, it could spit out a list of games and their scores, in a 
simple form, stamped and ready to send to whomever is collecting the votes.

Does this sound interesting?  I really would have preferred to write the 
game before talking about it, and let people decide that way, but with 
Whizzard's post, I felt I should bring this up before things progressed 
to a stage where I couldn't do it any more.



Okay, now to my question:

How will betatesting work?  Can I find my own betatesters?  Will you 
provide some for me?  Will betatesters be prohibited from voting on games 
they betatested, but not from others?  Will authors be prohibited from 
voting on their own games, but not on others?

Cheers to Whizzard for doing this again!  Hip Hip...

-Lucian "Lucian" Smith


From robbj95@octarine.cc.adfa.oz.au Thu Mar 20 10:27:28 MET 1997
Article: 23514 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!harbinger.cc.monash.edu.au!newshost.carno.net.au!euryale.cc.adfa.oz.au!octarine!robbj95
From: Barbara Robson <robbj95@octarine.cc.adfa.oz.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: 19 Mar 97 23:20:58 GMT
Organization: ADFA News Service
Lines: 40
Message-ID: <robbj95.858813658@octarine>
References: <Ed-1803970204530001@207.103.118.124> <5gmbl0$u9b@bartlet.df.lth.se> <egh-1803972139180001@news.berkeley.edu>
NNTP-Posting-Host: 131.236.1.1
X-No-Archive: yes
Originator: robbj95@octarine
Xref: news.lth.se rec.arts.int-fiction:23514

egh@uclink4.berkeley.edu (Erik Hetzner) writes:

|I think a problem is that most people who use IF begin to understand what
|the computer wants her to type, how to type it. 

I wouldn't necessarily say that's a problem.  It's perfectly adequate to
the purposes of IF in general.  Yes, a really good parser would be
lovely, but (for IF, which seems largely to be written as a hobby anyway)
the time could probably be better spent writing a good plot with nice
prose than in trying to create a sentient life-form to act as the
interface.

|But true beginners often sit down, and if they haven't read the
|documentation, the first sentence they type most likely won't be
|understood.

I don't know what your background is, but the same is true of START.
After reading the original post, I visited the site, hoping to see
something impressive.  My first four questions (not chosen to be
difficult) were answered with variations on "Sorry, I don't know if
I know about that."  My next question was "Don't you know anything
about anything?", which got a canned response which helped me to
tailor my questions so that they'd be easier for it, but even then,
it was sometimes difficult to get a reasonable response.  START's 
strength seems to be in working out which of the information it has
might be relevant, once it understands a question.  From that point
of view, it is quite impressive.  I'm not sure that its parser is 
really any better than Inform's, though (it is better at understanding
questions, but it was written for that purpose, while Inform's 
parser was designed mainly for understanding actions).

On a related topic, I remember once finding (through a web page) a
telnet site which allowed one to play with a couple of ai attempts.
One was a kind of game during which one talked to a dragon, another
was a conversation with a student before a lecture.  The latter was
actually quite impressive, imo.  I've forgotten the address, though
and haven't been able to find it with Yahoo.  Can anyone point me
in the right direction?

Barbara


From whizzard@uclink.berkeley.edu Thu Mar 20 10:45:01 MET 1997
Article: 23518 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!erinews.ericsson.se!cnn.exu.ericsson.se!uunet!in1.uu.net!128.230.129.106!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer3.itd.umich.edu!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Avalon's Lateness.  A Clarification.
Date: 19 Mar 1997 23:07:05 GMT
Organization: University of California at Berkeley
Lines: 134
Message-ID: <5gprip$b2i@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23518 rec.games.int-fiction:21970


Okay, okay.  Now while I don't mind the jokes and all, it does get
tiresome after a year or two.  This post is to be both an explanation of
why I'm so late and what the hell I've been writing for 3 years.  I've
been trying to sort of diminish its net.presence, but all that seems to do
is make the long-time waiters nervous, while neglecting to advertise to
the newbies this great game I'm writing, which is bad for sales.  So, this
is it.  One long-winded post is all you guys are getting until this thing
goes into final testing, when I'll be sure to throw all sorts of BS at you
in an effort to entice you to buy the wretched thing.

Why I'm Late:

	Obviously the initial estimate, 2 months, made three years ago,
was ridiculous.  You simply cannot write a game of any real length in that
time and pay the kind of attention to detail that I wanted to.  So, things
got stretched out.
	Then, college got hectic.  Less work got done.  Periods of a month
or more would pass in which I had no time to sleep, much less write
Avalon.  As much as my friends at college would deny it, I put in a
helluva lot of work for my degree.
	Over the summers, I wound up taking summer classes to avoid
particularly onerous degree requirements, like foreign language and psych
1.  Only because of these classes was I able to graduate a semester early.
	Then, about a year and a half into the game, I suffered what can
only be described as a bout of depression.  My grades were low, I didn't
want to touch the blasted game, and I moped around for rather a long time.
	So finally, I'm done with college.  Of course, if I had been
hoping for lots of time to finish Avalon, I was again to be disappointed.
Looking for a job is a pain.  Resumes are a pain.  Living at home is a
pain.  Plus, I have other interests.  I like to write normal fiction.
I've written fan fiction in the past for both Magic:the Gathering, and Red
Dwarf.  I run AD&D for some friends, which takes up time.  I have
submitted an article to Dragon magazine recently (rejected) and to Citadel
Journal (accepted.)  I work on other stuff to keep my sanity as I inch
towards the end of this monstrous, loathsome game (you work on something
for three years and see how you feel about it.)  I've written rules for a
miniature wargame (well, mostly), and I'm writing an 88 page book for a
company who published fantasy supplements for role-playing games.  In my
copious amounts of free time (AHAHAHAHA) I run the contest and
occasionally try and throw together an issue of SPAG.
	When I want to truly try and just relax I paint fantasy miniatures
and watch old movies (Hitchcock's Saboteur was on today.  Good flick.)
Occasionally, I leave the house and go to the mall where I buy video games
and books when I can afford it (recent purcahses: Interesting Times by
Terry Pratchett, a wonderfully funny book with a great quote about sumo
wrestlers, and Koala Lumpur, a hysterical video game that is unfortunately
attempting to use the public as its betatesters.  I'm taking it back
tomorrow.)
	There.  That oughtta buy me a week or two of peace.

What I'm Writing:

	Okay, yada yada, if you haven't heard the story yet: Boy goes to
war, boy meets grenade, boy dies, boy gets charged by King Arthur to
retrieve the holy artifacts lost in Avalon and use them to return to the
real world where a grievous wrong must be averted.  Standard stuff here.
Let's see, I like to hype the size a lot, so I'll get that out of the way.
The .gam file is 756k long right now.  The source code is over 30,000
lines long (granted, a number of them consist of just an })  If you
average that over 3 years that's 30 lines a day.  Of course, it was more
like spurts of 500+ lines and long periods of inactivity.  Much of this is
dialogue and scenery.

	Dialogue: There are around 40-50 NPCs planned, of which at least
35 are already done.  I'm probably including NPCs that appear more than
once as different NPCs, but that's because I had to write them twice
anyways.  The NPCs like to talk to each other.  In fact, they are hard to
shut up if you let them get started.  Besides that, the interface is
pretty standard stuff, except in scale.  One NPC has over 50 things to be
asked about.  Most have over 20.  Frank's side of the dialogue is supplied
in each conversation.  (Frank is the character you play.)

	Scenery: There are in the area of 250-300 rooms.  All the
items in every room are described, with few exceptions.  I fully expect to
make those of you who hate red herrings explode.  The current object count
in TADS is 1193 objects.

	Puzzles: Plenty of good old fashioned scavenger hunting going on.
I believe that I can count three seperate hunts.  Some puzzles based on
NPC interaction with the player.  A few clever ones, and one puzzle
guaranteed to heat your scalp, if not incite anger.  Every puzzle has a
fair number of hints scattered around, except for one or two which simply
involve clear real-world thinking and planning ahead.  Two verge on
unfair, but I enforce a strict 'undo anywhere' policy, removing some of
the sting there.  There is a warning mode to let you know if you have left
behind an item in a place no longer accessible to you that you will need.
If you have the mode on and no warnings go off, everything is groovy.
Of course, you can leave behind items needed for an optimum ending but not
for just a winning ending and not be told.  That's just tough nuggets.

	Interface: Avalon knows 1483 words.  I have added every synonym
that even vaguely crossed my mind.  I have tried to implement every single
way to phrase commands (well, not really silly ones, like you might try on
START.)  Inventory is handled by simply letting the character haul around
an infinite number of small objects.  Man's got a lot of pockets, okay?

	Overall: What I have written could fill a book.  I've had no
complaints on the writing other than my flagrant, use, of, commas.  The
plot has been finished for almost 3 years, and the story is solid in my
opinion, even after looking at it for three years, I can still stand to
put my name on it.

	Progress: There are 4 major sections to Avalon.  The first two are
done, barring bug reports.  The third has its map and some of the puzzles
programmed in.  There is still some NPC work needed there and a major
plotpoint before it can go into testing.  The last area is not yet
started.  I have reference materials all set for when I finish the third
area.  The fourth area, of the 270-300 rooms, occupies about 30 rooms, if
that.  However, make no mistake.  There are timing and programming
difficulties that need to be overcome in this segment.  Everything has to
finally come together, and I have to write the endings, of which there are
more than 3.  Beyond that I'm making no promises.

	Other Points of Note: The second area has a lot of stuff in it
that is just there to help build atmosphere.  You can play around in it
for quite awhile without finding everything.  I doubt even the betatesters
have seen everything yet.  In addition, there is a dice game built into
Avalon.  Not terribly interactive other than the betting system, but then,
what dice game is?  A pamphlet with rules is included with the game, and
it is a good party game.  I have played it with friends before.  Avalon
also includes an accurate recreation of two famous sites.  A lot of
research was done to ensure that even though I've never visited either
site, the reproduction would still be as accurate as possible, barring
artistic license.

---

	Anyways, that's why you're still waiting, and what you're waiting
for.  Now, since I've sworn to myself that I'm going to do 30 minutes a
day of work at least on Avalon (and have been for awhile now), I'd better
go put in my 30 minutes.  You betatesters, cover me while I run for it.
-- 
	"Ha.  Made ya look!"


From erkyrath@netcom.com Thu Mar 20 15:04:30 MET 1997
Article: 23537 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!liuida!news.ifm.liu.se!news.lejonet.se!mcevans.tip.net.!newsfeed.tip.net!news.seinf.abb.se!inquo!nntp.uio.no!news-feed.inet.tele.dk!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [TADS] Help me with delword!
Message-ID: <erkyrathE6x1L6.1IG@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <dsglasser-0703971636090001@207.41.27.196> <fake-mail-ya02408000R0803971605170001@news.direct.ca> <5fvjfv$7ev1@news.thorn.net>
Date: Wed, 12 Mar 1997 05:51:05 GMT
Lines: 58
Sender: erkyrath@netcom14.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23537

Andrew D. Pontious (byzantium@tuna.net) wrote:
> In article <Pine.SUN.3.91.970308204501.3642A-100000@nebula.phy.duke.edu>
> Stephen Granade, sgranade@phy.duke.edu writes:
> >Let me second what Neil has said.  I've made a lot of delword() tests, 
> >and it fails only under the original Mac runtime.

> You mean I wrote that whole workaround for nothin'! ;-)

I don't think you should entirely dismiss the Mac runtime. It's still the 
only option for Mac System 6 users.

> I've got to tell you, it was frustrating when writing Small World to
> repeatedly encounter these problems. Here was a language that many had
> touted as more advanced than Inform, certainly based on a more modern
> system (instead of being tied to a decade-old, quirky system), but when I
> tried to really take it through its paces, use its most advanced features
> to round out a game, it failed me more often than not.

Mmm, I hope I can now speak as the author of MaxZip and MaxTADS instead 
of as a biased Inform programmer...

Inform may be tied to the Z-machine, but TADS is tied to the TADS 
runtime, and believe me, the TADS runtime is *far* more complex than the 
Z-machine. That translates to "quirky" in my book. The source code, 
certainly, is somewhere beyond "quirky" and into "stick an eggbeater into 
my bleeding eyesockets, please." The Z-machine is very simple, and this 
means that if it does something strange, it's a lot easier to track down 
what happened. 

Case in point: I tried looking for the TADS delword bug. I gave up. There
was a lot of code for sticking words in, and taking words out, and the
chain of undo information, and so on. This is in the TADS runtime code,
you understand. I got lost. (It's in voc.c, if you care to try.)

In the ZIP source, there is no such thing as adding or deleting words from
an object. Objects don't have words; they have properties, which are
arrays of numbers. In a game that wants to add or delete words, the game
file uses the memory-write opcode to change the contents of a property.
That's it. The memory-write opcode is well-tested, and if it didn't work,
we would have heard about it by now. 

The complexity of Inform lies entirely in the Inform *compiler*, and the 
Inform compiler has been upgraded much more recently (and much more, 
recently) than the TADS compiler. Ok, now I'm talking as an Inform 
programmer again. I'll shut up now.

(As an ironic note, there is currently some discussion about nesting
output-diverting operations in the Z-machine -- Graham wants to allow it
to help support a feature in Inform 6. So things aren't *all* sweetness
and stability, and it's rather amusing that it's the exact same problem as
you had with TADS.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From whizzard@uclink.berkeley.edu Thu Mar 20 15:04:48 MET 1997
Article: 23402 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!news-m01.ny.us.ibm.net!ibm.net!arclight.uoregon.edu!su-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Announcing the 3rd Annual I-F Competition
Date: 16 Mar 1997 18:19:04 GMT
Organization: University of California at Berkeley
Lines: 161
Message-ID: <5ghdio$gll@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23402

Folks, please crosspost this message to relevant newsgroups, websites, and
your local computer club.  The more the merrier.

      Announcing the Third Annual Text Adventure Authorship Competition
				Administered by whizzard@uclink.berkeley.edu

	"Third time's the charm."
	    -Most Common Programmer Saying, right after "&$%&^@%!!"

	Text adventures still exist and thrive on the Internet.  If you
enjoyed Zork, Trinity, Corruption, or any of the many other text based
games put out in the 70's and 80's, then I'm sure you'll be pleased to hear
that.  You'll be even happier when you find out that there is an annual
competition on the Internet to see who can write the best text adventure,
and that you can enter it, or judge the entries, for free.

                                -=The Rules=-

	This year's competition is a bit different in that the rules are
stricter and better defined.  Violaters of any rule will be given a warning
the first time, and disqualified if a second transgression is made.  Sorry
for the harsh crackdown, but it seems to be neccessary to ensure a tranquil
and pleasant competition for all.

  1.  Any text adventure you enter must be winnable in under two hours.
The judges are only allowed to play it that long before quitting and rating
it.  This is to ensure small games, and encourage authors to enter who
might feel intimidated going up against a huge game.

  2.  All games must be entirely your own creations.  You may parody
established works, but you may not, for example, write a game based on
Sherlock Holmes.  This avoids the entire issue of copyright and the ethics
involved.

  3.  All entries MUST be freeware or public domain.  So don't enter a game
you've worked on for 2 years if you don't want to give it away.  No
shareware, no donorware, no commercial products, etc.  Only clear and free
games.

  4. All entries must be previously unreleased at the opening of voting. 
If an entry has previously been circulated, it will be disqualified.  If
you are unsure whether your game fails to meet this rule, please ask me.

  5.  Your game must not have your name listed anywhere in, or associated
with it.  Entries will have pseudonyms in the form of author numbers 
assigned to them, and everyone will be sent a legalese boilerplate to put
into the start of their game to protect their copyrights.  Copyrights will
be retained by the authors, whose names will be on registry with the
Annual I-F competition organizer (i.e. Me.)

  6.  Authors of a competition entry may not discuss the entries in a
public Internet forum while the voting is open.  This means don't post
about your entry (or anyone else's) on a newsgroup until the deadline for
voting has passed.

		    -= Procedures and Recommendations =-

  1. It is recommended that you enclose a complete text walkthrough with
your game.  With a walkthrough, I can doublecheck your entry to ensure
that it is winnable, and judges can get by hard puzzles to see the rest of
your game.

  2.  The entry may be written in any programming language, including any
of the text adventure creation utilities available (such as TADS, Inform,
AGT, or Alan, to name a few.)  If your game is unplayable, then it won't
receive enough votes to be eligable for prizes.  (See Judging.)

  3.  Multiple entries by the same author are fine, so long as all entries
meet all the rules above.  Let me just close this with a caveat emptor. 
You will likely be better off investing more time in a single entry rather
than trying to finish two.

  4.  To enter this year, you must e-mail me by September 1, 1997, with
your intent to enter.  I will assign you an author number, and a
telnet-accessed e-mail address that you can receive feedback on your game
at until the voting period has ended.

  5.  You will need to e-mail me your entry privately, either through
e-mail (as a uuencoded file) or some other arrangement that you will have
to work out with me.  The entries must be received by September 30th,
1997.  No entries will be accepted after this date.

			      -=Judging=-

	The Judging system this year is still in debate.  With the large
number of entries last year, it is unsure whether the old system will
continue to work.  I want to continue the people's choice award method, but
I think it suffers if people are only grading a partial set of the entries.
I am very reluctant to do the judging in stages, with semi-finals and all
that garbage.  It's too much work, quite frankly.  A small number of
registered judges may be the only way to go, if not the most distasteful to
me.  I will attempt to resolve this situation by April, or May at the
latest.

			  -=Awarding of Prizes=-

  1.  The winner will be the game with the highest average score.  Each
winner will have a draft pick to choose a prize of his/her choice until
there are no longer any prizes left.  Tied entrants who both select the
same prize will be decided between by a flip of the coin, the loser
receiving his second choice.

The Prizes So Far Include:

	None so far.  If you would like to donate a prize for this year's
competition, please contact me as soon as possible with your prize.  The
competition is dependent on prize donations from interested parties to
boost interest and the number of entrants.
	However, this year I will be attempting to have trophies made for
the first three places.  This is likely to be a fairly expensive prospect,
so donations of money (or trophy-making talents) are needed this year as
well.

			   -=Online Resources=-

	Lastly, for those of you unfamiliar with the online resources
available to text adventure authors, here are some interesting sources.

ftp://ftp.gmd.de/if-archive/
	Main directory for the interactive fiction (text adventure) archive.
	It is mirrored at several sites, but the info escapes me for the
	moment.

ftp://ftp.gmd.de/if-archive/programming/
	The location of several programs designed to help authors write
	text adventures.  I recommend TADS, Inform, Hugo, Alan, or AGT,
	particularly the first two: TADS and Inform.  Please see the
	relevant directories for further info.

ftp://ftp.gmd.de/if-archive/info/authorship-guide.base
	The main document for Whizzard's Guide to Text Adventure Authorship.
	This is something I wrote to give ideas to prospective authors,
	mostly dealing with the non-technical aspects of writing text
	adventures.

ftp://ftp.gmd.de/if-archive/info/Craft.Of.Adventure.txt
	A file by Graham Nelson also discussing the less technical aspects
	of how to write text adventures.  Included is a Player's Bill of
	Rights that is very useful.

ftp://ftp.gmd.de/if-archive/info/Index
	A filelist that lists numerous other helpful files for new text
	adventure authors to peruse.

Newsgroups:

  REC.ARTS.INT-FICTION
	For the use of text adventure authors in discussing the mechanics and
	other important topics of text adventure creation.  Important contest
	announcements will be posted here.

  REC.GAMES.INT-FICTION
	For the players of text adventures to discuss games and hints, and to
	buy/sell used text adventures.


-- 
=  SPAG Magazine  = Issues 1-9 at ftp.gmd.de:/if-archive/magazines/SPAG =
=       All       =  Ratings =     Issue 10 coming soon.  It's the      =
=      About      =  Reviews =        1996 I-F Competition Issue.       =
= Text Adventures =   News!  =        Editor: whizzard@pobox.com        =


From erkyrath@netcom.com Fri Mar 21 13:06:26 MET 1997
Article: 23563 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Disappointed with IF parsing
Message-ID: <erkyrathE7CtLM.My4@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <Ed-1803970204530001@207.103.118.124> <5gmbl0$u9b@bartlet.df.lth.se> <Ed-2003970306010001@207.103.118.73>
Date: Thu, 20 Mar 1997 18:20:10 GMT
Lines: 81
Sender: erkyrath@netcom4.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23563

Ed! (Ed@eSquare.com) wrote:
> Instead of canned response, the program should be able to tell the player
> of simple facts and relations within the game.

> :Can the can fit inside the box?
> :Did the troll see me yet?
> :Troll, where did you come from? (which area/direction was it in last)
> :Is the machine plugged in?

> These are things which the program would know & would not need a script
> written by the author to convey the answers.

I think this comes to the important point: you're not talking about a 
parser, you're talking about the knowledge system behind the parser. This 
is not an additional capacity for a game; it's a new form of game. At 
least, it is if the knowledge system is fully-used enough to be important 
to the player. (If it's not, it's just a creeping feature in the game 
and should be ignored.)

> Here's an interesting question: If IF software starts recognizing such
> commands and questions, would IF writers turn off the 'advanced parser'
> feature?

I don't think the question addresses the real situation. It's new 
software. It wouldn't be either written or used for the same things that 
(say) Inform is written and used for.

> > I wouldn't mind an expansion of the accepted talking-to-people syntax.

> This is probably the biggie, especially since it wouldn't need a ton of
> writing. Each NPC can have a knowledge base & will reveal certain things
> if certain conditions are met. Simple yes/no questions would add a great
> deal to the games without any additional script writing.

> :Do you own the club?
> :Is your dog in the barn?
> :Would you want to live in Cleveland?
> :Do you know what this red thing is?

> No current IF game can do a thing with these questions.

I still disagree. Parser-speak for these yes/no questions, on top of a
knowledge base, could be implemented in the existing languages. (By 
"parser-speak" I mean the limited-form syntax we have now.) 

> Would they add
> something to the games? I couldn't imagine anyone thinking that they
> wouldn't.

I can. Is the troll in Zork improved if he can agree that yes, he owns the 
axe? The game isn't about that; it would just be a gimmick. 

The idea -- of a knowledge system, not a better parser -- could work in a 
new game. (I generally think that anything can work in a new game.) The 
parsing seems to me to me a chimera. If I'm wrong, it can be demonstrated 
by trying a knowledge-base game in parser-speak, and discovering that the 
players want more out of the parser. (It doesn't have to be demonstrated 
that way, but that's what I'd try.)

[I accidentally snipped your reply to my earlier post, and have no easy 
way to get it back. Basically you said that parser-speak doesn't work 
because players have to try several variations of a command. Well, I know 
it breaks down sometimes. As an author, I try to make that happen as 
rarely as possibly -- by not casting situations where the player needs to 
think up an obscure command. As long as I'm in the realm of physical 
actions, not dialogue, this is not restrictive. And improving the parser 
makes that job *harder* -- that's the point -- for a given range of 
possible protagonist actions.]
 
> The point is that a little AI and some more advanced parsing would open up
> a whole new world in the IF realm - yet no one seems to be pursuing any
> such goal. That surprised me.

Does that mean you're going to start pursuing?

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From cardinalt@earthlink.net Sat Mar 22 14:31:18 MET 1997
Article: 23582 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!news-m01.ny.us.ibm.net!news.ibm.net!newsjunkie.ans.net!newsfeeds.ans.net!sonybc!sonysjc!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.nacamar.de!news.nacamar.de!uunet!in2.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: Fri, 21 Mar 1997 19:27:35 GMT
Organization: Earthlink Network, Inc.
Lines: 39
Message-ID: <5gundu$35l@ecuador.earthlink.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz>
NNTP-Posting-Host: max1-sc-ca-08.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23582

"Giles Boutel" <boutel1g@wcc.govt.nz> made so bold as to state:

>Now there's a potential thread - what do people do when they write IF? As
>in sit down and program the stuff. Personally I couldn't force myself to go
>through the process without copious quantities of white wine and dak (if
>you don't know what dak is, I plead the fifth). Loud music is pumping
>through the CD-Rom, only exceeded by my frequent screams of frustration
>("What do you mean it didn't f-ing compile?"), occasional yells of victory,
>and the odd time when I lose all restraint, laugh at one of my own jokes,
>and fall off my chair  which is constantly balanced precariously upon its
>hind legs so I can keep mine outstreched). Thankfully my bed is behind me.

This is frighteningly close to my own practice. I eschew the loud
music, however, and--being a true American--go more for beer than
white wine. The rest is pretty accurate, though. Especially the
"laughing at my own jokes" part.

Especially the lau...?! Ha ha ha ha ha! Whoo eeeh hee hee hee hee!

Um...ahem. Sorry.

--Cardinal T

          I mean, what the hell kind of villain thwarts the hero's
	  progress with soup cans in the kitchen pantry?
	                                         --Russ Bryan
	
         Are there any text games prominently featuring dinosaurs?  
         If not, does anyone besides me think it would be cool? 
                                                 --Matthew Amster-Burton

         "Hey! *I* wanted to be Envy!"
                                                 --joe dot mason
         
         "Bathroom?  Yeah.  Go through that door, on the end
         of the hall, on your left."  "Pardon?"  "South twice,
         than east."  "Ah."
                                                  --Clyde "Fred" Sloniker



From cardinalt@earthlink.net Sat Mar 22 14:51:25 MET 1997
Article: 23577 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news1.best.com!bdt.com!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: Fri, 21 Mar 1997 02:27:13 GMT
Organization: Earthlink Network, Inc.
Lines: 34
Message-ID: <5gsrlf$q3h@chile.earthlink.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <5gmdet$g6$1@europa.frii.com>
NNTP-Posting-Host: max2-sc-ca-29.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23577

jholder@deimos.frii.com (John Holder) made so bold as to state:

>: --Satan

>Cardinal Satan?  What _are_ you trying to pull, in heck's name?

Just for the record, the idea was that only a truly cruel and devious
entity would ask this particular question once again. IOW, it was a
joke. I assure you that I remain wonderful and perfect in every way.

>Just don't send Phil, the Prince of Insufficient Light after me, ok?

Phil's not available. He's down in Rio for a vacation. However, Steve,
the Prince of Rapidly Waning Luminosity, is right here at his desk and
I could send him if you guys get too far out of line...

--Cardinal T

          I mean, what the hell kind of villain thwarts the hero's
	  progress with soup cans in the kitchen pantry?
	                                         --Russ Bryan
	
         Are there any text games prominently featuring dinosaurs?  
         If not, does anyone besides me think it would be cool? 
                                                 --Matthew Amster-Burton

         "Hey! *I* wanted to be Envy!"
                                                 --joe dot mason
         
         "Bathroom?  Yeah.  Go through that door, on the end
         of the hall, on your left."  "Pardon?"  "South twice,
         than east."  "Ah."
                                                  --Clyde "Fred" Sloniker



From jholder@deimos.frii.com Sat Mar 22 18:37:51 MET 1997
Article: 23579 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!uab.ericsson.se!news.algonet.se!news.maxwell.syr.edu!frii.com!deimos.frii.com!jholder
From: jholder@deimos.frii.com (John Holder)
Newsgroups: rec.arts.int-fiction
Subject: Re: Abusing 'sophisticated' AI parsers for fun and profit (was Re: Disappointed with IF parsing)
Date: 21 Mar 1997 18:07:49 GMT
Organization: Front Range Internet, Inc.
Lines: 79
Message-ID: <5guipl$13a$1@europa.frii.com>
References: <Ed-1803970204530001@207.103.118.124> <ant1813500b0c4bn@arnod.demon.co.uk> <332F0EF8.41C6@x_greenhouse.llnl.gov> <5gnfgn$8m1@news.bu.edu> <slrn5j0la5.of8.spatula@underground.error.net>
NNTP-Posting-Host: deimos.frii.com
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:23579

My conversation with START
(http://www.ai.mit.edu/projects/infolab/ailab):

==> WHY ?
Here is a map of Kuwait: 
{map deleted}
{Wow.  Wacky stuff!}

==> WHERE IS MIT?
The MIT Artificial Intelligence Laboratory is located in Cambridge. 
The Laboratory's mailing address is -- MIT AI Laboratory, 545 
Technology Square, Cambridge, MA 02139.

==> WHAT IS A PARSER?
Professor Berwick and his colleagues have finished constructing the 
next generation of natural language parsers and translators, based 
on modular, universal linguistic theories. During the past year, a 
completely...
{a full page exposition snipped}

==> WHO DID YOUR PROGRAM?
I have the following information which may help: 
{page of "topics I know about" snipped.}

==> WHEN?
I am sorry to say I don't know when who did my program.
{interesting.  A little Eliza?  Explains why I was told about Kuwait.}

==> WHY DO BIRDS SUDDENLY APPEAR?
Unfortunately, I don't know why the birds suddenly appear.
{Nice canned response.}

==> WHAT IS YOUR FAVORITE COLOUR?
{after it makes me correct "colour" to "color":}
Sorry, I just don't know.

==> WHERE BE THE CAPITOL OF IRAN?
Tehran is the capital of Iran.
{Okay, passes a screwy verb tense.}

==> TELL ME ABOUT STALLMAN.
Here is what I know about Stallman: 
Richard Stallman's email address is rms@ai.mit.edu. Richard's 
telephone number is (617) 253-8830 and his MIT address is NE43-430.
{Just curious... ;) }

==> THE SQUARE ROOT OF TWO IS WHAT?
The result is 1.4142135623730952.
{golly.  Accurate to 1E-16!  ;) }

==> IF I ASK YOU WHAT THE SQUARE ROOT OF TWO IS, WOULD YOU BE ABLE TO
    TELL ME THE ANSWER?
I hope, this is what you want -- 
My experimental database contains information about....{snip}
{meta questions may be out, eh?}

==> WERE YOU CREATED?
Yes -
Boris Katz wrote the Start System in Lisp.
It took 11 years in order for Boris Katz to develop START.

==> WHERE DOES THE LABORATORY GET MONEY FROM?
Well, I am not quite sure. Does this answer your question? -- 
The research activities at the Artificial Intelligence Laboratory are
funded by....
{answers the question pretty well.}

---------------
All in all, the parser isn't bad at all - but I believe the parser
doesn't seem out of our league.  There are some odd cases that it 
handled nicely, and others that I got a canned "I don't know what
you mean."

Anyway, Play with it!

--
John Holder (jholder@frii.com) /\            http://www.frii.com/~jholder/
UNIX Specialist, Paranet Inc. <--> Raytracing|Fractals|Interactive Fiction
http://www.paranet.com/        \/           Homebrewing|Strange Attractors


From baf@max.tiac.net Sun Mar 23 21:01:03 MET 1997
Article: 23427 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!rill.news.pipex.net!pipex!uunet!in3.uu.net!199.0.65.182!news-in.tiac.net!posterchild!max.tiac.net!baf
From: baf@max.tiac.net (Carl Muckenhoupt)
Newsgroups: rec.arts.int-fiction
Subject: Re: Types of Puzzles
Date: 17 Mar 97 15:32:12 GMT
Organization: The Internet Access Company, Inc.
Lines: 97
Message-ID: <baf.858612732@max.tiac.net>
References: <331F3C45.794B@x_greenhouse.llnl.gov> <33243B3F.2790@cogentex.com> <3327A9DF.49A2@penning.lanl.gov>
NNTP-Posting-Host: max.tiac.net
Xref: news.lth.se rec.arts.int-fiction:23427

Russell Glasser <rglasser@penning.lanl.gov> writes:

>Daryl McCullough wrote:
>> 
>> I don't really care about distinguishing the type of puzzle so much
>> as distinguishing the type of *effect* of the puzzle. Some puzzles
>> are such that, after they are solved, you say to yourself "In
>> retrospect, it all seems so perfectly *obvious*!"; all that
>> was necessary was a fresh way of looking at things. Other puzzles
>> leave you no more enlightened than you started, and seem mostly to
>> be a matter of trying all possible combinations of actions. The
>> latter type of puzzle is much easier to create, but the first type
>> is much more satisfying for the player (in my opinion).
>> 

Some time ago, I wrote up a broad classification of puzzles based on the
kind of thought processes that lead up to the solution.  The original
is long lost, but I'll try to reproduce it:

Before we can classify puzzles, we must have a clear idea of what a
puzzle is.  I would define a puzzle as anything in a game where it is
possible to get stuck.  This applies to games in general, not just
text adventures.

What makes a puzzle satisfying?  Two things, really.  First, there is
the process of solving it - and some puzzles are definitely more satisfying
to solve than others.  Then there is the reward, which typically involves
opening up more of the game or providing the ability to solve more puzzles.
Both of these aspects are important, but they are completely orthogonal.
I will treat the first aspect first, and possibly follow up with the second.

Now, how do people solve puzzles?

a) Not.  The player ultimately gets a hint, reads the source code, or gives
up.  This is the worst type of puzzle, and the only type that actually
decreases from the enjoyment of the game.

b) By accident.  You're wandering around, randomly examining objects, when
you suddenly and unexpectedly notice something (say, a treasure or a secret
passage).  This is a distinctly unsatisfying sort of puzzle,  because it's
over before you realize it's there.  Any satisfaction it brings must come
entirely from the reward.

c) By trial-and-error.  Differs from type b only in that one is aware of
what one is trying to accomplish.  GAGS monsters are a good example:  only
one weapon will affect any particular monster, and frequently the only way
to tell which is to try them all.  (If there's feedback, the puzzle becomes
type f.  If the solution makes sense, it might be type g.)  Graphic
adventures are notoriously full of these; frequently the UI makes it possible
to approach all puzzles as trial-and-error, even when type g is intended.

d) By following explicit instructions.  This doesn't sound like a puzzle, but
it qualifies because one can encounter the puzzle before getting the
instructions.  Like type b, the satisfaction is small, but at least it
involves the player.  Often used as copy protection.

e) By applying a known set of rules.  Puzzles of this type tend to be
mini-games, like sliding-block puzzles or board games, embedded in a larger
context but largely unaffected by it.  I'd put the classical maze under this
heading, although this is arguable.  This is the first type of puzzle
that rewards the solver for being clever.  Can be non-interactive (for
example, a cryptogram that the player must solve offline).

f) By experiment.  Here, you must figure out how things work by observing
the results of your actions.  This is the most involving type of puzzle, as
it is completely integrated into the game environment.  Often combined with
type e: once you've figured out the rules, you still have to apply them
cleverly.

g) By insight.  Once you think about it the right way, it becomes obvious.
In its extreme form, this is the puzzle that you figure out while waiting for
the bus.  Some of the most satisfying puzzles are of this type.  So are some
of the worst; pretty much all riddles fall under this heading.

Notice that the content of the puzzle is left open.  Consider, for example,
a puzzle where you must give an item to someone in exchange for another
item.  This can be any of the above types, as follows:
a) There's no indication that he wants anything or has anything to give
in return.  The item he wants is completely arbitrary.
b) Same as a, except the game mechanics encourage giving things to people
at random and you don't have much inventory.
c) You know that he's willing to trade you something useful, but there is no
indication of what he wants.  (Like the salesman in LGOP.)
d) He tells you exactly what he wants when you ask him.
e) He gives you a set of criteria that only one item in a particular group
fits.  You must isolate that one.  (If anyone's played Toonstruck, think of the
scarecrow.)
f) You can offer him things and deduce from his reactions what kind of things
he likes.  (There's a scene like this in "Indiana Jones and the Fate of
Atlantis".)
g) There's one item that's particularly appropriate to the situation.  (Say,
he's sitting in a rowboat and you have an oar.)

-- 
Carl Muckenhoupt              | Text Adventures are not dead!
baf@tiac.net                  | Read rec.[arts|games].int-fiction to see
http://www.tiac.net/users/baf | what you're missing!


From aultman@koala.scott.net Sun Mar 23 21:02:18 MET 1997
Article: 23595 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!hole.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!newsfeed.internetmci.com!HiWAAY.net!acara.snsnet.net!news.scott.net!koala.scott.net!not-for-mail
From: aultman@koala.scott.net (Joe and Bonnie Aultman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disappointed with IF parsing
Date: 20 Mar 1997 15:38:17 -0600
Organization: Scott Network Services, Inc.
Lines: 56
Sender: login name: aultman, domain: scott.net... you do the math
Message-ID: <5gsao9$30v@koala.scott.net>
References: <Ed-1803970204530001@207.103.118.124> <5gmbl0$u9b@bartlet.df.lth.se> <Ed-2003970306010001@207.103.118.73>
NNTP-Posting-Host: koala.scott.net
Xref: news.lth.se rec.arts.int-fiction:23595

>
>:Do you own the club?
>:Is your dog in the barn?
>:Would you want to live in Cleveland?
>:Do you know what this red thing is?
>
>No current IF game can do a thing with these questions. Would they add
>something to the games? I couldn't imagine anyone thinking that they
>wouldn't. Would it make the programming & writing more difficult? Yep. But
>I'm sure programming Castle Wolfenstein was a lot simpler than coding
>Wolfenstein 3D.

Not only can no IF game do a thing with them, no _anything_ can do a thing
with them -- or if something can, there are equally simple questions that
will stump it.  I can not contest that this would add something to the
gaming environment, but I think the there is a wider gulf in the programming
involved -- more like that between EDLIN and Word 97. (Note: this is a bow
to the complexity of AI and not a slap at modern IF systems.)

>The point is that a little AI and some more advanced parsing would open up
>a whole new world in the IF realm - yet no one seems to be pursuing any
>such goal. That surprised me. If there was such a push in the IF community
>(and had been for the last ten years), we would now have a parser so
>incredible that Dear Abby would be out of a job.

What you are suggesting would take more than a _little_ AI.  It would take
more AI than has been developed to date. Furthermore, to suggest that IF
authors and system developers should be out-performing MIT et al in AI and
advanced parsing technology is more than a little unfair.  It's like asking
an amateur astronomers club to out-observe the Hubble telescope.

Despite what you say, there is a constant pressure to improve the parser.
It took years simply to catch up to what Infocom developed in the 70s.
Right now what we get out of parser discussion is in depth analysis of
the word "it." Significant parser advancement will not precede useful
advancements outside the field of IF, which can then be bent to our
purposes.  What you have here are hobbyists.  There is not a single person
on the face of this planet who writes IF for a living.  Let the grad
students and professors develop AI, parsers, and knowledge representation.
I'll guarantee you that as soon as they reach a point where they can be
used for good interactive storytelling, someone will do it.

There are, by the way, current projects in the works to marry AI to IF.
Look up "rec.arts.int-fiction" along with "Prolog" at dejanews.

Don't think the IF community is not interested in pushing frontiers.  That
is not at all what I am saying.  It's just that the frontiers being pushed
may sometimes seem silly when viewed from the outside.  Some other sets
of words you can look up could be "z-machine spec" "Freefall" "Life doesn't
work that way" "Black White" "Avalon NPC" "In The End" "Robots" "Lists"
"I-0" "Tapestry" "Baggett Scheme" "pickle" "gender" and (wink) "air
fresheners."  Happy hunting.

That is all,

Joe


From russotto@wanda.vf.pond.com Mon Mar 24 00:31:04 MET 1997
Article: 23598 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!iag.net!news.magicnet.net!news.sprintlink.net!news-atl-21.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-ana-7.sprintlink.net!news.pond.com!wanda.vf.pond.com!not-for-mail
From: russotto@wanda.vf.pond.com (Matthew T. Russotto)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Changing dir
Date: 23 Mar 1997 14:54:09 -0500
Organization: Ghotinet
Lines: 37
Message-ID: <5h41p1$24n@wanda.vf.pond.com>
References: <egh-1303971942260001@news.berkeley.edu> <66.7897.1727@tabb.com>
NNTP-Posting-Host: 198.69.82.2
Xref: news.lth.se rec.arts.int-fiction:23598

In article <66.7897.1727@tabb.com>, Joe Mason <joe.mason@tabb.com> wrote:

}The laws of motion throughout the Smoke Ring were: "East takes you out, 
}out takes you west, west takes you in, in takes you east; north and 
}south bring you back."
}
}        - Larry Niven, "The Kiteman" (a short story set in the world of 
}_The Integral Trees_)
}
}These directions are not only as confusing to keep track of as they 
}sound, its vital to remember them when navigating the Smoke Ring.  And 
}they make perfect sense once you understand the explanation, which I 
}can't remember now - getting the hang of it is the tricky part.
}
}I would LOVE to see some IF set in the smoke ring - but coding 
}directions would be a nightmare!

The Smoke Ring is a matter cloud orbiting a binary system.  The direction
it orbits is east.  Hence if you go "east", you are increasing your
energy and thus increasing the semimajor axis of your orbit, taking
you out.  Similarly, going west brings you into a lower orbit,
bringing you "in".  If you go "out", you are moving into a higher and
thus slower orbit, which brings you "west" relative to the other
objects in the smoke ring.  Similarly with "in" taking you "east".
North and south are a bit trickier -- if I've got it right, if you
start out in an equatorial orbit, going north or south will put you
into a complex orbit that crosses the equator.  So going some distance
north will eventually bring you an equal distance south, and
vice-versa

BTW, where does "The Kiteman" appear?  I've read _The Integral Trees_
and _The Smoke Ring_, but not that.

-- 
Matthew T. Russotto                                russotto@pond.com
"Extremism in defense of liberty is no vice, and moderation in pursuit
of justice is no virtue." 


From erkyrath@netcom.com Tue Mar 25 00:13:41 MET 1997
Article: 23609 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!news.maxwell.syr.edu!worldnet.att.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Announcing the 3rd Annual I-F Competition
Message-ID: <erkyrathE7K5DL.G9B@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ghdio$gll@agate.berkeley.edu> <5gq7ft$ie9$1@neko.syix.com> <3336AD9E.25B63403@alcyone.com>
Date: Mon, 24 Mar 1997 17:17:45 GMT
Lines: 29
Sender: erkyrath@netcom3.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23609

Erik Max Francis (max@alcyone.com) wrote:
> Patrick Kellum wrote:

> > Freeware meaning that the author still retains all copyrights to the
> > entry, PD meaning that the author gives up all copyright to the entry,
> > is that correct?

> Correct.

> > What if the entry is based on characters/setting/etc of another game by
> > the same author?

> That is copyright infringement.

*Same* author! *Same* author!

For example, _Aayela_ in the '96 competition mentions Cyr-Dhool, which 
was mentioned in _Uncle Zebulon's Will_ from the '95 competition. If the 
author (Magnus Olsson) wants to create a third game in the same universe 
for '97, he'll have to either change the name or effectively break the 
anonymity rule. Is this a restriction we're willing to live with? No 
sequels to existing works, even by the same author?

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From spatula@underground.error.neXt Tue Mar 25 09:47:08 MET 1997
Article: 23620 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!Oslo2.Norway.EU.net!Norway.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!dciteleport.com!usenet.logical.net!node2.frontiernet.net!news.eznet.net!news-out.internetmci.com!newsfeed.internetmci.com!avalon.net!spatula
From: spatula@underground.error.neXt (they got purple; purple's a fruit)
Newsgroups: rec.arts.int-fiction
Subject: Re: What is Interactive Fiction?
Date: 25 Mar 1997 03:30:55 GMT
Organization: Pulling Mussels From The Shell
Lines: 64
Message-ID: <slrn5jehj5.n3i.spatula@underground.error.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz> <33371367.51A4@oxford.com.au>
NNTP-Posting-Host: underground.error.net
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-Newsreader: slrn (0.8.8.4 (BETA) UNIX)
Xref: news.lth.se rec.arts.int-fiction:23620

Blah blah blah, Dancer, <dancer@oxford.com.au>, blah:
> 
> I always sat (sit) quietly at the computer, usually without music, and
> tap away at it, while holding a half-zillion online conversations at
> once, writing C++, C and C-- code, and sipping Coca Cola.
> 
> Bizarre?You be the judge. Abowl of curried peanuts usually figures
> strongly into the creative equation somewhere.

The only time inspiration truly strikes for me is during bouts of
insomnia, and insomnia usually strikes only when I really NEED to get a
good night's sleep for some event taking place the next day.  So, I'm
jolted out of bed with "So -that's- how I can work around this puzzle!",
fire up the Geiger counter that is the Compaq Presario, and eventually do
figure out how to implement a puzzle, whereupon I come across another
puzzle I can't figure out how to implement, and I sit around for 20
minutes staring at the screen and checking my Sim City 2000 game to see
how Potzrebie is doing, and then I finally give up, look at the time, and
shudder when I think how short a period of time there is before I'm
supposed to be Officially Awake.  Then it's downstairs to watch some
quality early-morning television before the day begins anew.

As far as comestibles go during game creation, I drink fine brown cola
products and eat whatever I can find in the cabinets.  I stay away from
alcohol or other mind-altering substances, because at that hour of the
night, a drunken code might invariably turn out like this, in the days
where I worked at a supermarket and drank vodka galore:

object oldman "grumpy old man"
 with description "An invariably grumpy-looking old coot, slouching \
 forward in a wrinkled old cardigan, suspenders reluctantly holding \
 up a pair of faded and tattered pants more suited for hip-waders \
 than anything else.  This is probably going to be me in a few years' \
 time if I keep this lifestyle up.  God, what an incredibly depressing \
 vision that would be.  Bah!  Who needs sleep anyway?  Just a bunch of \
 people who have to be up for a 10:00 shift, that's who.  I didn't even \
 ask to come in at 10, I was more than willing to arrive around 2 and \
 that was the end of that.  Bastards, all of them!  If they want to \
 fsckin' keep me around like a slave, they had better damn well know that \
 I'm more than willing to do absolutely nothing in the store all day \
 tomorrow besides playing instant lottery tickets and coming up with \
 games like Shopping Cart Polo and Impersonate Your Favorite Dictator \
 Using Produce.  I should be paid more for this.  They don't pay \
 enough for this abuse.  Maybe tomorrow I'll get on the PA and become \
 Howard Beale for a while.  That'd be coool.  Ok.This sucks.  Now i cant \
 typge riht.  Fckufckufc



ok, this has become far too cathartic for public consumption, and I
apologize.  I've gotten much better, thank you, and am in a well-paying
job where they respect me for my talents, all that junk, and I promise to
release PUTPBAD2 before the next time Hale-Bopp shows up.

erm.
think I better lie down for a while.


-- 
Spatch conducts top-secret experiments at http://error.net/~spatula
remove the X from my email address when replying.  gads, i'm trendy.
          "Do you find my method acting unsound?"   "I see no acting at all."
                                                                  mstie#43790




From erkyrath@netcom.com Tue Mar 25 09:47:51 MET 1997
Article: 23622 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: ...and how do you write it? (was Re: What is Interactive Fiction?)
Message-ID: <erkyrathE7L205.5ty@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz> <33371367.51A4@oxford.com.au>
Date: Tue, 25 Mar 1997 05:02:29 GMT
Lines: 47
Sender: erkyrath@netcom13.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23622

Giles wrote:
>   When I give up for the night and emerge, red-eyed and reeking of
>   Chateau
>   Cardboard, to plonk myself down in front of the telly, visitors ask
>   my
>   flatmate what the hell I've been doing to look so ragged. My
>   flatmate,
>   whose idea of literature is the sports pages, invariably replies
>   that I
>   have taken my muse round the back and shot it.

Dancer (dancer@oxford.com.au) wrote:

> I always sat (sit) quietly at the computer, usually without music, and
> tap away at it, while holding a half-zillion online conversations at
> once, writing C++, C and C-- code, and sipping Coca Cola.

> Bizarre?You be the judge. Abowl of curried peanuts usually figures
> strongly into the creative equation somewhere.

Sitting quietly, doing nothing. Spring comes, and the program compiles by 
itself!

Oh, no, wait, that's Zen.

I sit in front of the Mac and hack. I have a tall jar of seltzer-and-
lime-juice nearby (but not on the computer desk itself.) I am not doing 
anything else. During the very long compiles of _So Far_ I would read a 
page or two of a book, but this is really to be avoided, as I'd rather 
keep reading than keep hacking. (I have since bought a faster machine, so 
the problem shouldn't arise again.)

I prefer to play music while I'm hacking, but if I'm writing a long prose
passage, I may have to turn it off. The music is always folk music, as 
I've said many times before. Unless the news is on, or some other 
educational program such as Peter Schickele's.

Very occasionally, I <<Strong computer>>.

--Z

(Sorry. Little Inform joke, there.)

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From kheath@1connect.com Wed Mar 26 14:38:52 MET 1997
Article: 23610 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.pbi.net!news.PBI.net!usenet
From: Kory Heath <kheath@1connect.com>
Newsgroups: rec.arts.int-fiction
Subject: [INFORM] GET ALL Solutions
Date: Sun, 23 Mar 1997 20:45:28 -0800
Organization: Pacific Bell Internet Services
Lines: 72
Message-ID: <333606E8.1AC@1connect.com>
NNTP-Posting-Host: mars.1connect.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23610

A little while back there was some discussion about how GET ALL in
Inform will not include objects that are on or in fixtures, yet are
still visible; my impression was that there's really no good existing
solution for this problem.  I'm very new to Inform (about two weeks!),
but I think I've come up with a pretty elegant and powerful solution,
requiring only a minor library extension (replacement of a small
parserm.h routine called ReviseMulti).  I thought I'd post about it here
because: a) there *ought* to be a solution to this one, damn it <g>,  b)
I'd like some more experienced Informers to take a look and make sure I
haven't done something insidious, and c) because I think the solution's
pretty cool <g>.

The entry point ChooseObjects() is supposed to give you control over
what's included in the object list generated by ALL, and this is the
logical place to force inclusion of objects that are (say) on a table in
plain sight.  Unfortunately, the parser executes some hard-coded rules
for filtering objects out of this list *after* ChooseObjects() has
already been called; so even if you force inclusion of all objects
visible on tables, the parser ends up throwing them out later anyway. 
This second filtering is useful and necessary (it happens after the
second noun has been parsed, so "GET ALL FROM BUCKET" can filter out
objects that aren't in the bucket).  The problem is, it does this
without *asking*.

The proposed solution is to add a few lines of code to the library
function ReviseMulti(), so that it calls ChooseObjects() *again* for
each object in the second-pass filter.  The new ChooseObjects()
functionality is the same, except that it's "code" variable will be 3 if
the object is about to be excluded from the second-pass ALL, and 4 if
the object is about to be included in the second pass ALL.  Here's a
sample ChooseObjects function that causes GET ALL to get all objects in
the room, including any visible on or in fixtures:
                                                              
[ ChooseObjects obj code;

! Exclude all scenery
  if (code == 0 || code == 1)
    if (obj has scenery)
      return 2; ! Force Exclusion

! Don't let it exclude those visible objects from Take!
  if (code == 3 || code == 4)
    if (action_to_be == ##Take)
      if (parent(obj) has scenery || parent(obj) has static)
        return 1; ! Force Inclusion

  rfalse;
];

That's it.  I like this solution because a) It only requires the
extension (replacement) of a single library function  b) it doesn't do
violence at all to the existing methodology; indeed, this is just what
ChooseObjects *should* do.  c) it actually does a lot more than solve
this one isolated problem.  Not only can you change the behavior of GET
ALL to something more complex (say, to exclude visible objects you
haven't found yet); you can also control the multiinside and multiexcept
filters, too.  In fact, I'm currently using this method to redirect
multiinside, so that "GET ALL FROM WELL", "GET ALL FROM WATER", and "GET
ALL FROM BOTTOM" all give me the same object list (of the items in the
BottomOfWell), even though WELL, WATER, and BOTTOM are three *other*
objects with three different descriptions and properties.  This is the
problem I initially set out to solve; the GET ALL thing was just an
added bonus.  <g>

As for the revised library function: I don't know what the etiquette is
for posting snippets of code.  How long is too long?  The function is
about 70 lines.  I think I'll not post it in this message; let me know
if anyone wants to see it.  
                                           
-- 
Kory Heath
kheath@1connect.com


From kheath@1connect.com Wed Mar 26 16:34:11 MET 1997
Article: 23610 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!news.pbi.net!news.PBI.net!usenet
From: Kory Heath <kheath@1connect.com>
Newsgroups: rec.arts.int-fiction
Subject: [INFORM] GET ALL Solutions
Date: Sun, 23 Mar 1997 20:45:28 -0800
Organization: Pacific Bell Internet Services
Lines: 72
Message-ID: <333606E8.1AC@1connect.com>
NNTP-Posting-Host: mars.1connect.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23610

A little while back there was some discussion about how GET ALL in
Inform will not include objects that are on or in fixtures, yet are
still visible; my impression was that there's really no good existing
solution for this problem.  I'm very new to Inform (about two weeks!),
but I think I've come up with a pretty elegant and powerful solution,
requiring only a minor library extension (replacement of a small
parserm.h routine called ReviseMulti).  I thought I'd post about it here
because: a) there *ought* to be a solution to this one, damn it <g>,  b)
I'd like some more experienced Informers to take a look and make sure I
haven't done something insidious, and c) because I think the solution's
pretty cool <g>.

The entry point ChooseObjects() is supposed to give you control over
what's included in the object list generated by ALL, and this is the
logical place to force inclusion of objects that are (say) on a table in
plain sight.  Unfortunately, the parser executes some hard-coded rules
for filtering objects out of this list *after* ChooseObjects() has
already been called; so even if you force inclusion of all objects
visible on tables, the parser ends up throwing them out later anyway. 
This second filtering is useful and necessary (it happens after the
second noun has been parsed, so "GET ALL FROM BUCKET" can filter out
objects that aren't in the bucket).  The problem is, it does this
without *asking*.

The proposed solution is to add a few lines of code to the library
function ReviseMulti(), so that it calls ChooseObjects() *again* for
each object in the second-pass filter.  The new ChooseObjects()
functionality is the same, except that it's "code" variable will be 3 if
the object is about to be excluded from the second-pass ALL, and 4 if
the object is about to be included in the second pass ALL.  Here's a
sample ChooseObjects function that causes GET ALL to get all objects in
the room, including any visible on or in fixtures:
                                                              
[ ChooseObjects obj code;

! Exclude all scenery
  if (code == 0 || code == 1)
    if (obj has scenery)
      return 2; ! Force Exclusion

! Don't let it exclude those visible objects from Take!
  if (code == 3 || code == 4)
    if (action_to_be == ##Take)
      if (parent(obj) has scenery || parent(obj) has static)
        return 1; ! Force Inclusion

  rfalse;
];

That's it.  I like this solution because a) It only requires the
extension (replacement) of a single library function  b) it doesn't do
violence at all to the existing methodology; indeed, this is just what
ChooseObjects *should* do.  c) it actually does a lot more than solve
this one isolated problem.  Not only can you change the behavior of GET
ALL to something more complex (say, to exclude visible objects you
haven't found yet); you can also control the multiinside and multiexcept
filters, too.  In fact, I'm currently using this method to redirect
multiinside, so that "GET ALL FROM WELL", "GET ALL FROM WATER", and "GET
ALL FROM BOTTOM" all give me the same object list (of the items in the
BottomOfWell), even though WELL, WATER, and BOTTOM are three *other*
objects with three different descriptions and properties.  This is the
problem I initially set out to solve; the GET ALL thing was just an
added bonus.  <g>

As for the revised library function: I don't know what the etiquette is
for posting snippets of code.  How long is too long?  The function is
about 70 lines.  I think I'll not post it in this message; let me know
if anyone wants to see it.  
                                           
-- 
Kory Heath
kheath@1connect.com


From graham@gnelson.demon.co.uk Thu Mar 27 08:10:45 MET 1997
Article: 23671 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!newsfeed.nacamar.de!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Announcing the 3rd Annual I-F Competition
Date: Tue, 25 Mar 1997 23:04:05 +0000 (GMT)
Organization: none
Message-ID: <ant2523050b0M+4%@gnelson.demon.co.uk>
References: <5ghdio$gll@agate.berkeley.edu> <5gq7ft$ie9$1@neko.syix.com> <3336AD9E.25B63403@alcyone.com> <m2ybbdov6s.fsf@hubert.wustl.edu> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 38
Xref: news.lth.se rec.arts.int-fiction:23671

In article <m2ybbdov6s.fsf@hubert.wustl.edu>, Alan Shutko
<URL:mailto:ats@hubert.wustl.edu> wrote:
> 
> Erik> Patrick Kellum wrote:
> 
> >> What if the entry is based on characters/setting/etc of another
> >> game by the same author?
> 
> Erik> That is copyright infringement.
> 
> How can an author infringe upon his own copyright?

An author can assign copyright to somebody else: newspapers, for
instance, usually require their journalists to give all rights
to them for ordinary news items.

However, an author cannot give away the moral right to be
identified as the author, nor to be misrepresented as the
author of something grossly distorted.  "Moral right" is a
rigorous concept in recent copyright law, and I think was
enacted into U.S. law a few years ago; it made it into U.K. law
in 1988.

If an author writes book X, and retains copyright, then uses some
of the same characters in book Y, which is made public domain,
then the author is granting himself permission and there's no
question of infringement.  Characters from book X remain copyright.
If the author had sold the copyright on book X, then Y would
indeed be an infringement.

In any case, the usual freeware conditions for rec.games.int-fiction
games are not public domain but merely a generous distribution
license.  Certainly my games are not public domain, and I retain
full copyright on them.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From graham@gnelson.demon.co.uk Thu Mar 27 08:10:57 MET 1997
Article: 23700 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Announcing the 3rd Annual I-F Competition
Date: Wed, 26 Mar 1997 19:24:34 +0000 (GMT)
Organization: none
Message-ID: <ant261934bc8M+4%@gnelson.demon.co.uk>
References: <5ghdio$gll@agate.berkeley.edu> <5gq7ft$ie9$1@neko.syix.com> <3336AD9E.25B63403@alcyone.com> <m2ybbdov6s.fsf@hubert.wustl.edu> <ant2523050b0M+4%@gnelson.demon.co.uk> <Pine.SGI.3.95L.970326114132.20025C-100000@ebor.york.ac.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 29
Xref: news.lth.se rec.arts.int-fiction:23700

In article <Pine.SGI.3.95L.970326114132.20025C-100000@ebor.york.ac.uk>,
Den of Iniquity <URL:mailto:dmss100@york.ac.uk> wrote:
> 
> On Tue, 25 Mar 1997, Graham Nelson wrote:
> 
> [blah blah blah blah.]
> 
> Very useful info, Graham, but you've just gone and made a funny thread
> extremely boring. Boo.

Oh, all right then:

    Higgledy-piggledy
    Emily Dickinson
    Liked to use dashes
    Instead of full stops.
    
    Nowadays, faced with such
    Idiosyncrasy,
    Critics and editors
    Send for the cops.

which is by Wendy Cope, from her inspired collection "Making Cocoa for
Kingsley Amis", and its only connection to this thread is that it's
a blatant copyright violation.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Thu Mar 27 19:17:22 MET 1997
Article: 23726 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!warm.news.pipex.net!pipex!tank.news.pipex.net!pipex!iafrica.com!uct.uni.net.za!csir.uni.net.za!wits.uni.net.za!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] String length
Message-ID: <erkyrathE7po2J.IBv@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <66.8019.1727@tabb.com>
Date: Thu, 27 Mar 1997 16:49:31 GMT
Lines: 63
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23726

Joe Mason (joe.mason@tabb.com) wrote:

> From page 39 of the Designer's Manual:

>       In addition to this, Inform provides arrays which have a little
> extra structure:  they are created with the 0th entry holding the number
> of entries.  A word array with this property is called a table; a byte
> array with this property is a string.

This is more or less a lie. That is, this kind of string has absolutely 
nothing to do with a String object (the kind which is created when you 
put a double-quoted string in your source code.)

>           Array password string "DANGER";

This construction is actually the only time that Inform creates a 
string-array. Any other use of a double-quoted string produces a 
string-object.

> This seems to imply that you can find the length of a string str at any 
> time by calling str->0.

Only on a string-array.

> UPDATE: 15 minutes later -

> It seems that the value of "len" changes each time the program is 
> compiled - apparently Inform reserves byte 0 of strings to store length 
> information, but doesn't actually keep anything there.  Here's the 
> solution I'm using so far, which works like a charm, but involves an 
> annoying dummy array:

> Array CenterStr string 80;

> [ Center str len i;
>   if (len==0) len=str.print_to_array(CenterStr);
>   if (len==0) len=str->0;

That's the way to do it. The data in a string-object is stored in the 
Z-machine's sorta-compressed format, which has no length field. It's 
terminated by a certain set of five bits, which means that to find the 
end you have to slog through looking at five-bit chunks, which is what 
print_to_array does anyway.

Different post:

> BTW, print_to_array seems to be hardcoded in the compiler instead of in
> the libraries - I can't find the definitions of the metaclasses anywhere

Right. It's pretty simple, though; it selects output stream 3, which 
writes to memory instead of the standard output, and calls the print 
opcode. 

The print opcode (and related opcodes) are the only way to access 
string-object data. This is because that data may be in high memory, 
beyond the reach of the unaided game file.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From Spectreman@Earthling.net Fri Mar 28 07:56:12 MET 1997
Article: 23657 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!math.ohio-state.edu!jussieu.fr!uvsq.fr!not-for-mail
From: Fredrik Ramsberg <Spectreman@Earthling.net>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: [warning: includes binary] Re: Competition logo
Date: Wed, 26 Mar 1997 06:24:21 +0100
Organization: Dr Gori's Secret Invasion Base
Lines: 47
Message-ID: <3338B305.63DECDAD@Earthling.net>
References: <33356ee5.719260800@news.gte.net> <3337EC37.204@acpub.duke.edu> <333c0795.4087210@news.u.washington.edu>
NNTP-Posting-Host: venus.prism.uvsq.fr
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (X11; I; SunOS 4.1.3C sun4m)
Xref: news.lth.se rec.games.int-fiction:22089 rec.arts.int-fiction:23657

Matthew Amster-Burton wrote:
> 
> Adam Cadre <adamc@acpub.duke.edu> wrote:
> 
> >I really shouldn't have this much time on my hands, but I actually
> >went ahead and designed one of these.  The theory's pretty simple:
> >virtually all IF revolves around the ">" prompt, so that's the symbol.
> >This is the third competition, so there's three of 'em.  Have a look:
> 
> That's a cool idea, but I don't know if it'll "Say IF" to even an
> experienced player.  In fact, I looked at the picture before I read
> your post, and I didn't get it.

I have to admit I think it's a bit far-fetched as well. On the other
hand, it's simple, which a logo should be.

> Also, I think a symbol that we can reuse each year without major
> modification would be better.

How about a troll killing a dragon with a sword inside a time machine,
with the 7 wonders and a mainframe computer standing next to it, perhaps
with
some more, rather fuzzy people, whose activities are free for
interpretation? Perhaps they are getting married or investigating the
killing going on, who knows? That should cover most of the games
produced...

Or, if we _do_ want something less complicated than that, how about a
compass rose of some sort? Andrew Plotkin used one for MaxZip, I think
it was, and it struck me as one of the most central concepts in IF
gaming. Particularly, it is a concept that sets it apart from both the
real world and other kinds of games; not many people except IF
players/authors consider the toilet to be the third door to the east.
The other people who do probably need help to get out of the strait
jacket before they go to the loo anyway.

/Fredrik





-- 
Fredrik Ramsberg, d91frera@und.ida.liu.se,
http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
Macintosh - 0.4% Actual Users!


From Spectreman@Earthling.net Fri Mar 28 07:56:41 MET 1997
Article: 23664 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!math.ohio-state.edu!jussieu.fr!uvsq.fr!not-for-mail
From: Fredrik Ramsberg <Spectreman@Earthling.net>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: [warning: includes binary] Re: Competition logo
Date: Wed, 26 Mar 1997 08:24:45 +0100
Organization: Dr Gori's Secret Invasion Base
Lines: 36
Message-ID: <3338CF3D.167EB0E7@Earthling.net>
References: <33356ee5.719260800@news.gte.net> <3337EC37.204@acpub.duke.edu> <333c0795.4087210@news.u.washington.edu> <3338B305.63DECDAD@Earthling.net> <jota.859360437@max.tiac.net>
NNTP-Posting-Host: venus.prism.uvsq.fr
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (X11; I; SunOS 4.1.3C sun4m)
Xref: news.lth.se rec.games.int-fiction:22093 rec.arts.int-fiction:23664

Admiral Jota wrote:

(Good suggestion snipped! Me likes it!)

> Or perhaps they're looking for something more... *graphical* ;)

We can of course release a demo featuring a raytraced 3D-image of the
logo that you can shoot at with the joystick or mouse, like a game. All
accompanied by some heavy techno beat...

> >Particularly, it is a concept that sets it apart from both the
> >real world and other kinds of games; not many people except IF
> >players/authors consider the toilet to be the third door to the east.
> >The other people who do probably need help to get out of the strait
> >jacket before they go to the loo anyway.
> 
> So what is it exactly that sets us apart from *them*?

I never did figure that out. Any time I start to think about it I get
all excited and start jumping up and down and then the nurse comes and
gives me the injection I should have in the evening even if it's only
morning and I know it's good for me and all but I get so _tired_ and I
can't get out in the sunshine and take my morning walk along the wall
because I get so _tired_ that I fall over sometimes I am happy though
when she has given me that injection because I don't worry so much and
she says I can finish my game tomorrow I don't need to release it now
because many of my friends here never release their games at all or at
least it takes a while and I'm so _tired_ just want to sleep...

/Fredrik - aren't we all a bit - Ramberg

-- 
Fredrik
Ramsberg,d91frera@und.ida.liu.se,http://www-und.ida.liu.se/~d91frera
------------------------------------------------------------------------------
Macintosh - 0.4% Actual Users!


From graham@gnelson.demon.co.uk Sun Mar 30 19:32:44 MET DST 1997
Article: 23758 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Classes (& Mac compiler too)
Date: Thu, 27 Mar 1997 22:56:40 +0000 (GMT)
Organization: none
Message-ID: <ant27224072bM+4%@gnelson.demon.co.uk>
References: <333AA04B.794B@x_greenhouse.llnl.gov> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 31
Xref: news.lth.se rec.arts.int-fiction:23758

In article <333AA04B.794B@x_greenhouse.llnl.gov>, Kathleen Fischer
<URL:mailto:kfischer@x_greenhouse.llnl.gov> wrote:
> 
> Stuck again...
> 
> 3. Bonus Question   :)
> 
>    I also know that you can use variables for attributes and properties
> 
>    c = container;
>    if (noun has c) then print "Yahoo".
>    c = dirTo
>    if (noun.c ~= 0) then print "Yehaa".
> 
>    But can I do the same thing with classes?
> 
>    c = Birds;
>    i = c.create();

Yes.  "Birds" is an object in the game, representing the concept
of birdness (avianity?).  The line

    Birds.create();

is not a syntactic con -- it genuinely is a message called "create"
being sent to an object called "Birds".  There's no problem with
the variable "c" holding the object reference to "Birds", anyway.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From thegoat@mindspring.com Sun Mar 30 19:38:09 MET DST 1997
Article: 23828 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.mindspring.com!usenet
From: Laralyn McWilliams <thegoat@mindspring.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Seeking "Quarterstaff: The Tomb Of Setmoth"
Date: Sat, 29 Mar 1997 21:25:22 -0500
Organization: The Gloating Goat Company, Inc.
Lines: 33
Message-ID: <333DCF12.2BF9@gloatinggoat.com>
References: <332cc0e2.5923842@news.warwick.net>
Reply-To: thegoat@mindspring.com
NNTP-Posting-Host: user-37kb9bo.dialup.mindspring.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Server-Date: 30 Mar 1997 02:25:01 GMT
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23828

Lela and Rich Neuburger wrote:
> 
> Towards the end of its existance, Infocom published a game called
> "Quarterstaff, The Tomb of Setmoth". It was supposed to be an
> excellent game merging RPG and text adventure.
> 
> I've been hunting around for a copy, but have had no luck to date.
> Anyone know where a copy can be obtained? Any and all help is much
> appreciated.
> 
> Lukas
> 
> PS. please email any information to uln@fang.cs.sunyit.edu


This message brings me out of lurking... :)

Quarterstaff was a GREAT game. It combined the usual Infocom parser with
limited graphics (an overhead map, if I recall), rpg elements, and
really good characters. It was the first, and as far as I know the only,
rpg in which you had to convince NPCs to join you by giving them things,
smiling a lot, talking to them, and generally schmoozing your way
around. Some NPCs could be or enemies, depending on your behaviour. It
was a very realistic environment, especially for the time.

That being said, it was Mac-only, as I recall. And the folks at
Activision, when I asked for a replacement for my bad second diskette,
said it is no longer in print. If anyone does have a working copy of it
out there, I'd be VERY interested, too. :)

Hope this info helps a little!

Laralyn


From cardinalt@earthlink.net Sun Mar 30 19:42:34 MET DST 1997
Article: 23669 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!news.sprintlink.net!news-peer.sprintlink.net!uunet!in1.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Is Matt Barringer the Antichrist?
Date: Wed, 26 Mar 1997 07:35:11 GMT
Organization: Earthlink Network, Inc.
Lines: 46
Message-ID: <5hajjv$idj@bolivia.earthlink.net>
NNTP-Posting-Host: max1-sc-ca-02.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:23669


Is it true that Matt Barringer is the Evil One of Scripture?

Is it true that the Bible says "He who knows not the name Matt
Barringer shall escape eternal boredom"?

Is it true that the coming of Matt Barringer was foretold nearly three
thousand years ago?

You can find the answers to these and many other questions in a new
tract, entitled "The Answers to These and Many Other Questions", now
being offered by the Fraternity of Anti-Barringites. See why it is
that real i-f authoring systems were invented. See how NPC interaction
should never, ever, under any circumstances be handled. See where not
to put a preposition at. "The Answers to These and Many Other
Questions" provides startling insights into these and many other
questions and problems, and it is free to you when you join the
Fraternity of Anti-Barringites. That's right! Free! 

About us:

The Absolutely Benign Fraternity of Anti-Barringites (ABFAB) is an
Order of like-minded wombats dedicated to the proposition that Matt
Barringer is a big fat poopyhead. As such, we are committed to
providing the best in Anti-Barringist literature available anywhere at
a reasonable price to you, the discerning consumer. Other famous FAB
tracts, including "Die, Matt Barringer, Die" and "Detective This,
Sucka", have sold millions of copies worldwide and have been
translated into dozens of languages. Even such lofty public journals
as the New York Times, the London Times, and Highlights magazine have
said of FAB that it is "possibly the only Anti-Barringist organization
of its kind in existence--certainly it is the most annoying." See for
yourself, then, why FAB and their work are raising such a stink
wherever they go!

Don't you owe it to yourself to give FAB a try? Perhaps you would like
to join us? ABFAB is now accepting applications for membership in the
Fraternity proper, and membership in ABFAB is open to anyone and
everyone who wishes to join--except of course for Matt Barringer and
the family and friends of Matt Barringer, who must be destroyed. So do
yourself a favor. Send in your membership to ABFAB today and become a
part of all the Barringer-bashing fun!

This is a limited time offer, so don't delay!




From boutel1g@wcc.govt.nz Sun Mar 30 19:42:44 MET DST 1997
Article: 23694 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!comp.vuw.ac.nz!wcc.govt.nz!wcc.govt.nz!nntp
Newsgroups: rec.arts.int-fiction
Subject: Re: Is Matt Barringer the Antichrist?
Message-ID: <01bc3a2b$1c2c47c0$09340a0a@SPAWN.wcc.govt.nz>
From: "Giles Boutel" <boutel1g@wcc.govt.nz>
Date: 27 Mar 97 09:16:38 NZST
References: <5hajjv$idj@bolivia.earthlink.net>
Organization: Wellington City Council
Nntp-Posting-Host: 10.10.52.9
X-Newsreader: Microsoft Internet News 4.70.1155
Lines: 30
Xref: news.lth.se rec.arts.int-fiction:23694



Cardinal Teulbachs <cardinalt@earthlink.net> wrote in article
<5hajjv$idj@bolivia.earthlink.net>...
> Is it true that Matt Barringer is the Evil One of Scripture?
> 
> Is it true that the Bible says "He who knows not the name Matt
> Barringer shall escape eternal boredom"?
> 
> Is it true that the coming of Matt Barringer was foretold nearly three
> thousand years ago?
> 
> You can find the answers to these and many other questions in a new
> tract, entitled "The Answers to These and Many Other Questions", now
> being offered by the Fraternity of Anti-Barringites. 

Ah - the joys of organised religion.

Matt Barringer is an Icon for us all, and you abfab-ers do nothing but heap
scorn upon his demi-god-like head. He is the true representation of
Beginner's Mind IF Authoring, throwing out the thrice cursed dogmas of
Plot, Character, and Literacy - which entrap us all. He is that without
which there is nothing, existing as he does on the lowest rung of the
lowest common denominator. He is our touchstone and our stepping stone to
the higher realms. And yet, those who are jealous of his hard-earned
position mock him, like the messiahs of old were mocked by those without
understanding. To you all I say "Let he who is without buggy release
version 1.0s cast the first stone."

-Giles


From florian.beck@stud.uni-muenchen.de Sun Mar 30 19:43:38 MET DST 1997
Article: 23767 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!uni-erlangen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Is Matt Barringer the Antichrist?
Date: Thu, 27 Mar 1997 19:39:12 GMT
Organization: Private GNU Site
Lines: 9
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m3hghxp1jz.fsf@ue801di.lrz-muenchen.de>
References: <5hajjv$idj@bolivia.earthlink.net> <01bc3a2b$1c2c47c0$09340a0a@SPAWN.wcc.govt.nz>
Reply-To: florian.beck@stud.uni-muenchen.de
NNTP-Posting-Host: dial202.ppp.lrz-muenchen.de
X-Newsreader: Gnus v5.4.37/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:23767

"Giles Boutel" <boutel1g@wcc.govt.nz> writes:

> Matt Barringer is an Icon for us all, and you abfab-ers do nothing but heap
> scorn upon his demi-god-like head. 

At least he is one of the most famous and influential IF authors ever.

-- 
Flo


From spatula@underground.error.neXt Sun Mar 30 20:07:40 MET DST 1997
Article: 23787 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news00.sunet.se!sunic!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!newsfeed.internetmci.com!avalon.net!spatula
From: spatula@underground.error.neXt (they got purple; purple's a fruit)
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Competition logo
Date: 28 Mar 1997 23:15:20 GMT
Organization: Pulling Mussels From The Shell
Lines: 67
Message-ID: <slrn5jok75.poc.spatula@underground.error.net>
References: <33356ee5.719260800@news.gte.net> <5hh8in$6r9@fido.asd.sgi.com>
NNTP-Posting-Host: underground.error.net
X-Newsreader: slrn (0.8.8.4 (BETA) UNIX)
Xref: news.lth.se rec.games.int-fiction:22169 rec.arts.int-fiction:23787

Blah blah blah, John Francis, <jfrancis@dungeon.engr.sgi.com>, blah:
> 
> I don't believe how much time a text-adventure newsgroup is spending
> discussing a graphical button!
> My suggestion:
>       _______
>      /       \
>     /         \
>     |   ___   |
>     |  (___)  |
>     <--)___(-->
>     / /     \ \
>    / /       \ \
>   |-|---------|-|
>   | |  \ _ /  | |
>   | | --(_)-- | |
>   | |  /| |\  | |
>   |-|---|_|---|-|
>    \ \__/_\__/ /
>     _/_______\_
>    |  f.m.i.c. |
>    -------------

Well, allow me to take that a little further...

> EXAMINE LOGO

Which do you mean, the Competition Logo, the Award Logo, or the Honorable
Mention Logo?

> EXAMINE COMPETITION LOGO

The 97 Competition Logo is a masterpiece of a logo, tastefully
rendered in full color, utilizing all the proper elements of logo design -
eye-catching yet not too overly garish, effective and to-the-point,
simple, yet it works on so many levels.  Easily portable to any graphical
format in amazingly compressed size, the logo rather appropriately
reflects the grandeur, the fun, and the spirit of friendly competition
that the rec.arts.interactive-fiction competition has come to represent.

> EXAMINE AWARD LOGO

A fitting award, properly encased in precious metals and mounted on an
ornate base.  The winner would no doubt be very proud to mount this on his
or her mantle, or perhaps just mount it as a disk drive.

> EXAMINE HONORABLE MENTION LOGO

Not a logo per se, it's actually a small, ill-fitting shortsleeved 
shirt with the, erm, logo on it.

> READ HONORABLE MENTION LOGO

"I entered my game in the 1997 rec.arts.interactive-fiction Competition
and all I got was this lousy t-shirt."




- spatch, it's an honor just to be nominated, or something -

-- 
Spatch conducts top-secret experiments at http://error.net/~spatula
remove the X from my email address when replying.  gads, i'm trendy.
          "Do you find my method acting unsound?"   "I see no acting at all."
                                                                  mstie#43790



From erkyrath@netcom.com Sun Mar 30 20:09:34 MET DST 1997
Article: 23756 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!news.stealth.net!news.maxwell.syr.edu!news-peer.gsl.net!news.gsl.net!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: V6 Infocom games
Message-ID: <erkyrathE7qtLM.Kwo@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <333af761.0@news.tamu-commerce.edu>
Date: Fri, 28 Mar 1997 07:46:34 GMT
Lines: 32
Sender: erkyrath@netcom8.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23756

Allen Garvin (earendil@) wrote:

> I was wondering how other Inform programmers feel about version 6.  Does
> anyone else have any desire to make a version 6 game?  There are only a
> couple of interpreters that support it (none under xwindows) and there are no 
> Inform libraries of graphics functions.  Are any planned in the future, or
> is the only "graphics" version dead for all purposes?

V6 hasn't received much attention from interpreter writers because there
are no V6 games. This interpreter-writer attitude is clearly not going to
change. So any movement will probably have to come from an author who
writes a V6 game. 

I don't know what's been agreed to, in the realm of how to format and 
package the graphics. I suspect that if a V6 game appears, whatever Frotz 
reads will become the standard.

Speaking as a game writer, I have no interest in writing graphical games. 
Well, not graphical Z-machine games, at least. 

Speaking as an interpreter writer, V6 terrifies me. I'd have to start 
nearly from scratch to "add" V6 support to XZip/MaxZip. I don't want to 
do this.

--Z



-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From whizzard@uclink.berkeley.edu Sun Mar 30 20:11:14 MET DST 1997
Article: 23786 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Yawn, stretch.
Date: 28 Mar 1997 23:17:54 GMT
Organization: University of California at Berkeley
Lines: 57
Message-ID: <5hhjj2$in@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23786


Well, I took the day off of writing my other projects to learn Inform
today.  I'm translating 'Underoos' from TADS to Inform to learn the
syntax, which is the major hump in learning a new language.  So far I've
got about 400 of the 900 lines of code translated.

Underoos is a good game to translate, I've found, because I did a lot of
futzing with various parser features originally, stuff like the socks
jumping you in the kitchen, the moment of silence for the broom, the
fifty-foot-tall-firebreathing-egg-laying-werewolf ending, etc.  Happily,
things have gone smoothly with a little creative searching through the
Inform manual.  The biggest hump in learning it seems to be the logic
behind the abbreviated print_ret format, which looks like "This is a
test."; but is really print_ret "This is a test.";

For those of you who don't know Inform yet, this is an important concept
because of the fact that print_ret immediately returns true after printing
the text it's given.  Any commands after it in your function get lost.
The solution is to slap a print in front of your text, which is like
print_ret, without the return true on the end.

The abbreviation saves space, but seems to be really hard for me to wrap
my brain around.  I've made the same error no less than 7 times.

On the bright side, Inform's verb handling is pretty much superior to
TADS' at first blush.  I'm a little leery of the way it handles actions
like 'give frog to princess' and 'throw dart at mickey' but maybe it'll
turn out to be easier than it looks.

Let's see, other weirdings...ah, an object inside another is considered to
be hidden from sight, which will pain TADS authors who traditionally use
that method of adding detail to moveable objects.  You have to give the
'main' object the transparent attribute, which is simple enough, save that
it is necessary to do it so often.

Hmm, oh yeah, you no longer have to type in the location of everything.
Instead you have to pay attention to which order you're adding objects in.
That was a real kick in the butt.  Felt like I was doing rules-based
programming in college again. (shudder)

But overall, Inform has held up well.  It generates smaller datafiles, is
(currently) supported on more computers, and looks a bit more like the old
Infocom games.

There are some syntaxes straight out of Wackyland, and a couple of
standard features make me feel like I'm doing a kludge everytime I use
'em, but it's not too bad.  Inform has bridged the gap to where it's as
good as, if not better than, TADS.

Of course, those of you who want a .z8 version of Avalon can just bugger
off.  Retyping 28,000 lines of code or so I'm not something I will ever do
for less than 50 cents a line.

I WILL however upload the Inform port of Underoos when I finish it up.
Shouldn't take more than another day or two.
-- 
	"Stress?  WHO ME???!!!  Never."


From whizzard@uclink.berkeley.edu Sun Mar 30 20:15:53 MET DST 1997
Article: 23799 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: [Inform] My first Inform Question.
Date: 29 Mar 1997 11:22:46 GMT
Organization: University of California at Berkeley
Lines: 50
Message-ID: <5hiu26$f1m@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23799


Well, I've ported as much of Underoos to Inform as I can manage on my own.
Unhappily, I still have a few lines left over :(  Here's the question.

You've all seen this particular thingy, right?:

>

I beg your pardon?


I need to trap that to perform a special function at one spot in underoos.
Let's not discuss the 'fairness' of this.  It isn't needed to win, and
Underoos has never claimed to be anything more than a coding exercise.
It's 2:20 AM or so, and I've been staring at this last wretched problem
since midnight.  I've found that the message relates to LM_10, but it
appears that the only way to alter that particular hush puppy is to
replace an obnoxiously large swath of code (like the entire english.inf or
so.)

Obviously if I can't do it w/o replacing all that junk I'll just leave
that little feature out of it, but I often like to replace the 'blank
line' response in my games.

Oh yes, if you can spot the error below you'll see my new number one most
annoying bug:

object "smee"
  with name "smee"
       description "Smee is a yorkshire terrier named after Mr. Smee
                   of ~Peter Pan~ fame because of his fawning nature.",
  has animate
;


What's that you say?  I left off the , after the 'with name' line?  
Ding ding!  My record is 9 all at once.  Bloody commas.


Other than my question above, I'm basically done.  I have to recreate my
scorerank setup and insert appropriate point awards in the file, but that
should be trivial according to the manual, and won't take up more than 30
lines at most.

Oh, and for the record, Inform is rather more compact than TADS.  Even the
way I spaced it, the Inform port is still longer by a fair margin than its
TADS cousin.
-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From jmdreyfuss@earthlink.net Sun Mar 30 20:37:45 MET DST 1997
Article: 23682 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!news1.best.com!bdt.com!nntp.earthlink.net!usenet
From: "Daniel R. Lackey" <jmdreyfuss@earthlink.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: ...and how do you write it? (was Re: What is Interactive Fiction?)
Date: Wed, 26 Mar 1997 06:40:07 -0600
Organization: Society for the Preservation of the Cigarette-Smoking Dan
Lines: 93
Message-ID: <33391927.5263@earthlink.net>
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz> <33371367.51A4@oxford.com.au> <erkyrathE7L205.5ty@netcom.com>
NNTP-Posting-Host: cust31.max4.chicago.il.ms.uu.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.0 (Win95; U)
CC: jmdreyfuss@earthlink.net
Xref: news.lth.se rec.arts.int-fiction:23682

> Giles wrote:
> >   When I give up for the night and emerge, red-eyed and reeking of
> >   Chateau
> >   Cardboard, to plonk myself down in front of the telly, visitors ask
> >   my
> >   flatmate what the hell I've been doing to look so ragged. My
> >   flatmate,
> >   whose idea of literature is the sports pages, invariably replies
> >   that I
> >   have taken my muse round the back and shot it.

For me, it's usually the other way around.  My muse has a horrible temper.

> Dancer (dancer@oxford.com.au) wrote:
> 
> > I always sat (sit) quietly at the computer, usually without music, and
> > tap away at it, while holding a half-zillion online conversations at
> > once, writing C++, C and C-- code, and sipping Coca Cola.
> 
> > Bizarre? You be the judge. A bowl of curried peanuts usually figures
> > strongly into the creative equation somewhere.

Andrew Plotkin wrote:
> Sitting quietly, doing nothing. Spring comes, and the program compiles by
> itself!
> 
> Oh, no, wait, that's Zen.

_Zen and the Art of Interactive Fiction_, an interactive koan by Andrew
Plotkin.  Just add water.

>PLOTKIN, WHAT IS THE SOUND OF ONE HAND CLAPPING?

"I don't know the word 'what' but I do know that it is not a verb.  The
distance between Boston and New York is... oh, forget it, I'm sick of
flogging that dead horse anyway."

Graham, when is that Zen compiler you've been promising us going to be done?

> I sit in front of the Mac and hack. I have a tall jar of seltzer-and-
> lime-juice nearby (but not on the computer desk itself.) I am not doing
> anything else. During the very long compiles of _So Far_ I would read a
> page or two of a book, but this is really to be avoided, as I'd rather
> keep reading than keep hacking. (I have since bought a faster machine, so
> the problem shouldn't arise again.)
>
> I prefer to play music while I'm hacking, but if I'm writing a long prose
> passage, I may have to turn it off. The music is always folk music, as
> I've said many times before. Unless the news is on, or some other
> educational program such as Peter Schickele's.

Get a glass of water or lemonade, throw on either the cable station that runs
the BBC World Service in the background, or some atmospheric music conducive
to the mood of the story (since my current project, _Memory_, is a gothic,
I've been playing Dimwitesque amounts of goth-rock... old Cure, Joy Divison,
Swans, etc.)

The other project, _Men in Black_, which is mostly pre-development, merits
the listening-to of Mark Snow's _The Truth and the Light, Music from "The
X-Files"_, 808 State's more otherworldly, and some louder classical pieces.

And (though I'm not proud of the fact, I do joke about it a lot) I smoke.  I
smoke a lot.  I once went through about three packs while implementing a
particularly hectic hedge maze.  (This was when I was writing _Memory_ in
TADS, which I'm no longer doing... I've since decided to implement it in AGT,
because I want to be ridiculed. [Footnote 1])

>FOOTNOTE 1

This is a joke.  I repeat, this is a joke, and NOT a sales campaign.  I'm
actually writing the game with Adventure Construction Set.

Since I have a night-job anyway, I do most of my work in the wee hours, and
find myself able to work for a good five or six-hour stint with minimal, if
any, interruption.  Unless the music's too loud and wakes someone up.

When I'm playing classical, this happens very, very often.
 
> Very occasionally, I <<Strong computer>>.

switch(3)
	{
	1: "Real IF authors do not use such language.";
	2: "Such language on a high-class newsgroup like this!";
	3: "I find it hard to believe that you do this only occasionally.";
	};

-- 
daniel r. lackey                  standing in       government denies knowledge
jmdreyfuss@earthlink.net          the shadows                    XVI. the tower
===============================================================================
"God is dead."                                                -- F.W. Nietzsche
"He's not dead, he's... pining for the fjords!"                     -- M. Palin


From erkyrath@netcom.com Sun Mar 30 20:38:03 MET DST 1997
Article: 23695 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: ...and how do you write it? (was Re: What is Interactive Fiction?)
Message-ID: <erkyrathE7o6LA.424@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz> <33371367.51A4@oxford.com.au> <erkyrathE7L205.5ty@netcom.com> <33391927.5263@earthlink.net>
Date: Wed, 26 Mar 1997 21:34:22 GMT
Lines: 31
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23695

Daniel R. Lackey (jmdreyfuss@earthlink.net) wrote:
> Zarf:
> > Very occasionally, I <<Strong computer>>.

> switch(3)
> 	{
> 	1: "Real IF authors do not use such language.";
> 	2: "Such language on a high-class newsgroup like this!";
> 	3: "I find it hard to believe that you do this only occasionally.";
> 	};

It really is only occasional. Somewhat more often, I say "Grn." 

If I'm in a very bad mood, very suddenly, I'll clap my hands as loudly as 
possible. My reasoning is... remember the "Great Shout" from the 
Riddlemaster of Hed series? I figure that if there is such a thing as 
telekinesis, my best bet to discover it is to try to use it at moments of 
strong emotion. So when something goes *really* wrong, I clap my hands as 
loudly as I can and slam the energy into the monitor.

I don't expect that this will ever have any effect.

But if, one day, the monitor implodes, I'll have proof. And I can buy a
new monitor with the money from the talk-show circuit. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From rglasser@penning.lanl.gov Sun Mar 30 20:38:47 MET DST 1997
Article: 23776 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: ...and how do you write it? (was Re: What is Interactive Fiction?)
Date: Fri, 28 Mar 1997 11:07:51 -0800
Organization: UCSD
Lines: 43
Message-ID: <333C1707.414E@penning.lanl.gov>
References: <5gf4r2$fqh@ecuador.earthlink.net> <erkyrathE760B4.AuD@netcom.com> <5gqan7$644@bolivia.earthlink.net> <01bc35b1$82a70a40$09340a0a@SPAWN.wcc.govt.nz> <33371367.51A4@oxford.com.au> <erkyrathE7L205.5ty@netcom.com> <33391927.5263@earthlink.net>
NNTP-Posting-Host: sdx-ca16-11.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Fri Mar 28 11:08:23 AM PST 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:23776

> Andrew Plotkin wrote:
> > Sitting quietly, doing nothing. Spring comes, and the program compiles by
> > itself!
> >
> > Oh, no, wait, that's Zen.
> 
> _Zen and the Art of Interactive Fiction_, an interactive koan by Andrew
> Plotkin.  Just add water.
> 
> >PLOTKIN, WHAT IS THE SOUND OF ONE HAND CLAPPING?
> 
> "I don't know the word 'what' but I do know that it is not a verb.  The
> distance between Boston and New York is... oh, forget it, I'm sick of
> flogging that dead horse anyway."
> 

	Oh boy, I can't wait for that one to come out.

>SCORELife doesn't work like that.

>HELPLife doesn't work like that.

>TAKE ALLLife doesn't work like that.

>LOOKLife doesn't work like that.

>           [user types nothing]Your inaction leads you to a state of higher consciousness...
(Your score has just gone up by ten points, which doesn't matter since
you can't keep score in this game.  In fact, I hate you for even trying
to get a higher score, so I'm dumping you right now until you learn
some manners.)

C:>dir *.z5
A cute little fox wanders by.

-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From florian.beck@stud.uni-muenchen.de Sun Mar 30 20:44:58 MET DST 1997
Article: 23765 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.nacamar.de!news.apfel.de!uni-erlangen.de!lrz-muenchen.de!ue801di!fb
From: Florian Beck <fb@ue801di.lrz-muenchen.de>
Newsgroups: rec.arts.int-fiction
Subject: Question Parsing
Date: Thu, 27 Mar 1997 19:33:08 GMT
Organization: Private GNU Site
Lines: 54
Sender: fb%h729ihqu@sun1.cip.fak14.uni-muenchen.de (Florian Beck)
Distribution: world
Message-ID: <m3iv2dp1u3.fsf_-_@ue801di.lrz-muenchen.de>
References: <Pine.SGI.3.95L.970320170827.10245A-100000@ebor.york.ac.uk> <66.7985.1727@tabb.com>
Reply-To: florian.beck@stud.uni-muenchen.de
NNTP-Posting-Host: dial202.ppp.lrz-muenchen.de
X-Newsreader: Gnus v5.4.37/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:23765

joe.mason@tabb.com (Joe Mason) writes:

> I think putting grammar for questions is the next big step we need to 
> take.  Right now the game only really understands imperative statements.  
> Now it's all very well to implement "What is" as a verb, but I think we 
> really should have a decent system of questions with well-defined 
> limits.  Possibly a completely separate grammar?
> 
> ie. in Inform you could write:
> 
> Question "why"
>   * "is" [something] ->
>   * "does" [something] ->
>   * "did" [something] ->
>   ...
> 
> Of course, this would be a big job.  But I think if we can get a 
> standardized format for questions that players get used to, it would 
> enhance the game and not expand the number of ways to say the same thing 
> *too* much.

Recently I've started writing a new game (it's really easy *not ever*
to release one's first buggy game, btw) and thought: Would be cool if
you could ask "Jim, what's your job" instead of "ask Jim about (his)
job". 

It's not difficult to do this very special syntax. Doing it a bit
more generally gets very hard. Firstly, we'd need some sort of
knowledge representation. If there were only a few keyword responses
I'm sure it would not be worth the hassle. Secondly, while it would be
a step towards natural conversation, it would only be a little
step. And I'm not sure natural conversation is desirable in IF
anyway.

Yes, I think IF parsers can do "things" unsolved in linguistics and
AI: IF doesn't have to understand. It only needs to pretend to.

[If anyone wants to work on really advanced parsing: I'd suggest not
to focus too much on Chomsky's generative grammar but on Montagues
papers "Universal Grammar" and "Quantification in Ordinary English".] 

Concerning handling questions in inform:

1. Aux-S-V		(e.g. Can you swim?)
2. Aux-S-V-O		(e.g. Do you know Jim?)
3. Q-aux-S		(e.g. Why do you... What is he called?)

Of course, there are lot's of special cases as "What is his name".

This far it easy. But now the trouble starts: The Object in (2) and
"..." in (3) can be pretty much anything.

-- 
Flo


From erkyrath@netcom.com Sun Mar 30 20:52:04 MET DST 1997
Article: 23754 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] goto
Message-ID: <erkyrathE7qu3o.LCt@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <333AA35D.59E2@x_greenhouse.llnl.gov> <ant272320e61M+4%@gnelson.demon.co.uk> <5hf3vh$lbf@nntp5.u.washington.edu>
Date: Fri, 28 Mar 1997 07:57:24 GMT
Lines: 40
Sender: erkyrath@netcom8.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23754

Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:
> In article <ant272320e61M+4%@gnelson.demon.co.uk> Graham Nelson <graham@gnelson.demon.co.uk> writes:

> >The trouble is that rooms do not ordinarily have names that the
> >parser can recognise -- after all, in most games the player never
> >needs to name them.  That's why the best compromise I could find
> >was to allow "goto <number>" (and you can find the numbers by,
> >e.g., using the "tree" verb) or "gonear <object>", which takes
> >you to the room containing the given object.  

> This brings up a weird question which I have had for some time.  What
> is a room?  The manual talks about them, but never defines them.  Is it
> an object whose parent is nothing? 

Essentially, yes. A better definition might be "an object that the player 
is somewhere inside, whose parent is nothing." The library treats the 
outermost-surrounding-object of the player as being the current room; it 
doesn't really care what else might be a room.

To put it another way: there's no such thing as a "potential room" or a 
set of "all the room objects in the game". There is only *the* current 
room. 

You might be able to figure out what's a room by seeing what has n_to,
s_to, ... cant_go properties. That's an obvious rule to use if you're 
reading someone's source code; if he gave it direction properties, it's 
probably a room. But in a game, this is not a useful test, because 
properties might be aliased (particularly in the older libraries.) 
Besides, there might *be* a room with no exits.

If you want to objectloop over all the rooms in the game, invent a Room 
class and make all your rooms instances of that class. Or, give them all 
a "roomy" attribute. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From gdr11@cl.cam.ac.uk Sun Mar 30 20:53:36 MET DST 1997
Article: 23781 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!newsfeed.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!cnn.exu.ericsson.se!uunet!in1.uu.net!128.230.129.106!news.maxwell.syr.edu!rill.news.pipex.net!pipex!netcom.net.uk!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!lyra.csx.cam.ac.uk!news
From: Gareth Rees <gdr11@cl.cam.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] goto
Date: 28 Mar 1997 20:10:44 +0000
Organization: Cambridge University Computer Lab
Lines: 31
Sender: gdr11@stint.cl.cam.ac.uk
Message-ID: <yxsybb7pykb.fsf@stint.cl.cam.ac.uk>
References: <333AA35D.59E2@x_greenhouse.llnl.gov>
	<ant272320e61M+4%@gnelson.demon.co.uk>
	<5hf3vh$lbf@nntp5.u.washington.edu>
NNTP-Posting-Host: stint.cl.cam.ac.uk
X-Newsreader: Gnus v5.3/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:23781

Mary K. Kuhner <mkkuhner@phylo.genetics.washington.edu> wrote:
> This brings up a weird question which I have had for some time.  What
> is a room?  The manual talks about them, but never defines them.  Is
> it an object whose parent is nothing?

That's right, but there's more to the story than that.  A room is an
object (1) whose parent is nothing, and (2) which the player can be
found somewhere inside (possibly inside a container or vehicle that's in
the room) at some point in the game.

> Does this mean that if the player's parent becomes nothing (don't
> laugh, I had a bug that did this) he becomes a room?

It follows that the player can't ever be a room, because he'd have to be
inside himself!

> Are objects which are "just lying around" waiting to be moved into a
> location (like my moonbeam, which only comes out at night) effectively
> rooms till they get a room to live in?

Not really, because the player can't enter them (except by using
debugging verbs or some other cheat).

Rooms and objects are built from the same basic data structure, but the
Inform library treats them differently.  Rooms aren't ever "in scope",
so the player can't refer to them; they have properties n_to, s_to and
so on, which are looked at when the player moves; it doesn't make sense
for anything except a room to have these properties.  And so on.

-- 
Gareth Rees


From whizzard@uclink.berkeley.edu Wed Apr  2 09:44:21 MET DST 1997
Article: 23906 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!hammer.uoregon.edu!newsgate.cuhk.edu.hk!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: I-F World News
Date: 1 Apr 1997 21:07:54 GMT
Organization: University of California at Berkeley
Lines: 63
Message-ID: <5hrtfa$e0@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23906


Well, let's see, lots of news coming in today, let's start small and work
our way up.

1.) Avalon has been cancelled due to lack of interest.

2.) Scott Adams and David Lebling will be doing a text adventure together
    in October.  Supposedly some sort of sequel to Adams' "Funhouse."

3.) Leon Lin has just sent word of his next game.  It's tentatively
    titled "To Die For" and is a gothic horror game, heavy on puzzles,
    and lacking any sentient NPCs at all.  He says he's tired of debugging
    them.

4.) Graham Nelson's latest is that he's going to redo Jigsaw, only this
    time the player will take the part of Black.

5.) The crowd that brought us "Shades of Grey" has reassembled to write
    another game based on Piers Anthony's series "Tarot."

6.) Douglas Adams is finally starting in on "Restaurant."  Activision
    convinced him to do a full graphics version in exchange for 2.3
    million dollars!  Apparently the gang from MST3K will be building
    Marvin the paranoid android.

7.) Andrew Plotkin has sworn off text adventures and joined a Buddhist
    monastery.  Let's all wish him luck in his search for enlightenment.

8.) Here's an odd little note that I read in an industry rag.  Sierra is
    apparently changing their interface yet again.  Apparently the current
    one requires too much reading.  So, the characters in the games will
    now 'speak' via 'thought bubbles' with pictures in them, ala the old
    game show "Concentration."  In addition, since Sierra has found that
    nine out of ten players are too stupid to beat their games, they are
    hiring David Baggett of Crash Bandicoot fame to redo their puzzles.
    David says that he's going to take a cue from his fictional group
    Akmi and develop the "eeziest parser in the world."  Supposedly, no
    matter where you click, the parser interprets that as the next correct
    action on the path to winning the game.  Guess King's Quest fans will
    be losing a lot less sleep.  Sierra says that since they no longer
    need the old interface, they will be giving it to Legend
    Entertainment, which has shown some interest in using it.

9.) Magnus Olssen has decided to do a sequel to "Uncle Zebulon's Will" at
    long last!  From what I hear, the cute fox from "Weather" will be
    making a guest appearance, and all NPCs will be based off the START
    AI system.  Uncle Zebulon will know the distance between all
    significant stellar objects.

10.) And finally, I have recently sold an article to Citadel Journal, a
    magazine that specializes in Games Workshop miniature wargames.  The
    article was titled "Tie a Yellow Ribbon...." and discussed an
    alternate form of magic for the Bretonnian army in GW's game
    Warhammer Fantasy Battles.  No news yet as to when the article will
    appear.



Anyways all, Happy April Fools' Day, and bear in mind that a few of these
bits of news might even be true...or not.
-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From erkyrath@netcom.com Wed Apr  2 09:44:27 MET DST 1997
Article: 23919 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: I-F World News
Message-ID: <erkyrathE7zCCx.L0D@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5hrtfa$e0@agate.berkeley.edu>
Date: Tue, 1 Apr 1997 22:12:33 GMT
Lines: 13
Sender: erkyrath@netcom4.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23919

Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:

> 7.) Andrew Plotkin has sworn off text adventures and joined a Buddhist
>     monastery.  Let's all wish him luck in his search for enlightenment.

Confirmed. 

--Z "om"

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From scythe@u.washington.edu Wed Apr  2 09:44:32 MET DST 1997
Article: 23914 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.uoregon.edu!tezcat!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!uunet!in2.uu.net!140.142.64.3!news.u.washington.edu!scythe
From: scythe@u.washington.edu (Dan Shiovitz)
Newsgroups: rec.arts.int-fiction
Subject: Re: I-F World News
Date: 1 Apr 1997 22:29:41 GMT
Organization: University of Washington, Seattle
Lines: 19
Message-ID: <5hs28l$1ic@nntp5.u.washington.edu>
References: <5hrtfa$e0@agate.berkeley.edu> <erkyrathE7zCCx.L0D@netcom.com>
NNTP-Posting-Host: saul6.u.washington.edu
NNTP-Posting-User: scythe
Xref: news.lth.se rec.arts.int-fiction:23914

In article <erkyrathE7zCCx.L0D@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:
>
>> 7.) Andrew Plotkin has sworn off text adventures and joined a Buddhist
>>     monastery.  Let's all wish him luck in his search for enlightenment.
>
>Confirmed. 

> ZARF, WHAT IS THE SOUND OF ONE HAND CLAPPING?
"Sorry, that's not how Zen works."

>--Z "om"
--
dan shiovitz scythe@u.washington.edu shiov@cs.washington.edu
slightly lost author/programmer in a world of more creative or more 
sensible people ... remember to speak up for freedom because no one else
will do it for you: use it or lose it ... carpe diem -- be proactive.
my web site: http://weber.u.washington.edu/~scythe/home.html some ok stuff.


From erkyrath@netcom.com Wed Apr  2 09:44:35 MET DST 1997
Article: 23916 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: I-F World News
Message-ID: <erkyrathE7zDuI.n3u@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5hrtfa$e0@agate.berkeley.edu> <erkyrathE7zCCx.L0D@netcom.com> <5hs28l$1ic@nntp5.u.washington.edu>
Date: Tue, 1 Apr 1997 22:44:42 GMT
Lines: 25
Sender: erkyrath@netcom4.netcom.com
Xref: news.lth.se rec.arts.int-fiction:23916

Dan Shiovitz (scythe@u.washington.edu) wrote:
> In article <erkyrathE7zCCx.L0D@netcom.com>,
> Andrew Plotkin <erkyrath@netcom.com> wrote:
> >Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:
> >
> >> 7.) Andrew Plotkin has sworn off text adventures and joined a Buddhist
> >>     monastery.  Let's all wish him luck in his search for enlightenment.
> >
> >Confirmed. 

> > ZARF, WHAT IS THE SOUND OF ONE HAND CLAPPING?
> "Sorry, that's not how Zen works."

Nah. The two correct answers are:

"A rather cute, short game written by Erica Sadun. (Advsys)."

"<whack!>"

--Z "om"

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From russotto@wanda.vf.pond.com Wed Apr  2 09:44:41 MET DST 1997
Article: 23932 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!cs.utexas.edu!howland.erols.net!worldnet.att.net!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-dc-5.sprintlink.net!news-dc-26.sprintlink.net!news.sprintlink.net!news-atl-21.sprintlink.net!news.pond.com!wanda.vf.pond.com!not-for-mail
From: russotto@wanda.vf.pond.com (Matthew T. Russotto)
Newsgroups: rec.arts.int-fiction
Subject: Re: I-F World News
Date: 1 Apr 1997 22:39:36 -0500
Organization: Ghotinet
Lines: 27
Message-ID: <5hskdo$9fn@wanda.vf.pond.com>
References: <5hrtfa$e0@agate.berkeley.edu>
NNTP-Posting-Host: 198.69.82.2
Xref: news.lth.se rec.arts.int-fiction:23932

In article <5hrtfa$e0@agate.berkeley.edu>,
Gerry Kevin Wilson <whizzard@uclink.berkeley.edu> wrote:
}
}Well, let's see, lots of news coming in today, let's start small and work
}our way up.
}
}1.) Avalon has been cancelled due to lack of interest.
}
}2.) Scott Adams and David Lebling will be doing a text adventure together
}    in October.  Supposedly some sort of sequel to Adams' "Funhouse."

Using Adams' new simplified one-word parser, no doubt. 

[...]
}4.) Graham Nelson's latest is that he's going to redo Jigsaw, only this
}    time the player will take the part of Black.

Ahh, too bad about the date.

}7.) Andrew Plotkin has sworn off text adventures and joined a Buddhist 
}    monastery.  Let's all wish him luck in his search for enlightenment.

Hey, no fair slipping a real news item in with all the jokes!
-- 
Matthew T. Russotto                                russotto@pond.com
"Extremism in defense of liberty is no vice, and moderation in pursuit
of justice is no virtue." 


From whizzard@uclink.berkeley.edu Wed Apr  2 09:47:21 MET DST 1997
Article: 23930 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: I-F World News
Date: 2 Apr 1997 04:21:29 GMT
Organization: University of California at Berkeley
Lines: 26
Message-ID: <5hsms9$ce5@agate.berkeley.edu>
References: <5hrtfa$e0@agate.berkeley.edu> <5hsl8v$ln8$1@news-s01.ca.us.ibm.net>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:23930

In article <5hsl8v$ln8$1@news-s01.ca.us.ibm.net>,
Steven Howard <blore@ibm.net> wrote:
>
>Isn't this actually true of "Phantasmagoria II"?

That's just depressing, if true.  Still, it wouldn't surprise me terribly,
as it would seem to be the next logical step in Sierra's 'quest' to muscle
the player out of the picture.

There ya go, a parody game if I ever saw one.  "Sierra Quest 84: Dumbing
Things Down"

You play the part of Rebecca Bobs, a hard-working game designer/tree
hugger out to rid the gaming industry of those pesky players.  Your
mission: design a game that plays itself from start to end, without any
help from those illiterate, idiotic players.  You've already planned out
the hint book.  It's going to be sixty pages of nothing but empty boxes.
There will be a little yellow marker included that 'reveals' the clues.
Once the players realize that their marker doesn't work, they can get a
replacement marker for $9.95.

In the sequel, "Sierra Quest 85: Chapter 11 Approacheth", you have to
design a game that not only plays itself, but also buys itself and walks
out of the store on its own.
-- 
	"Ha.  Made ya look!"


From graham@gnelson.demon.co.uk Wed Apr  2 10:03:56 MET DST 1997
Article: 23922 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Writing V6 (graphical) games (Was: Re: V6 Infocom games)
Date: Tue, 01 Apr 1997 23:43:16 +0100 (BST)
Organization: none
Message-ID: <ant012216345M+4%@gnelson.demon.co.uk>
References: <333af761.0@news.tamu-commerce.edu> <erkyrathE7qtLM.Kwo@netcom.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 45
Xref: news.lth.se rec.arts.int-fiction:23922

In article <erkyrathE7qtLM.Kwo@netcom.com>, Andrew Plotkin
<URL:mailto:erkyrath@netcom.com> wrote:
> 
> Allen Garvin (earendil@) wrote:
> 
> > I was wondering how other Inform programmers feel about version 6.  Does
> > anyone else have any desire to make a version 6 game?  There are only a
> > couple of interpreters that support it (none under xwindows) and there are no 
> > Inform libraries of graphics functions.  Are any planned in the future, or
> > is the only "graphics" version dead for all purposes?
> 
> V6 hasn't received much attention from interpreter writers because there
> are no V6 games. This interpreter-writer attitude is clearly not going to
> change. So any movement will probably have to come from an author who
> writes a V6 game. 

Andrew is making a fairish general point, but I disagree.  Version 6
has received an enormous amount of attention from (among others)
Stefan Jokisch, Kevin Bracey and Matthew Russotto, and the new
Standards Document (1.0, to appear shortly) codifies the version 6
format much better than any previous attempt.  "Frotz" and "Zip2000"
are both excellent V6 interpreters.

Inform itself generates perfectly good V6 code: to get further than
this you need some kind of utility program to make up graphics
files.  I see no reason why you shouldn't get in touch with (say)
Stefan J., if you're serious about writing a V6 game, and negotiate
some kind of arrangement where the pictures for this game would be
supplied to the interpreter as an archive directory of JPEGs or GIFs.
Potentially, you could then have photograph-quality graphics.

The Standards document is careful not to require any particular
format for graphics files.  So far V6 interpreters only bother to
read Infocom's somewhat arcane graphics file formats, but that's
only because nobody has bothered yet.

I must admit that I've been tempted before now to try a game with
a sort of "box" of graphical content, that is, a title page and
perhaps the occasional map or photograph to augment an otherwise
textual game.  A partial substitute for the old Infocom style of
box packaging, perhaps.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From mol@bartlet.df.lth.se Wed Apr  2 10:38:00 MET DST 1997
Article: 23947 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Novice's 2nd Question
Date: 2 Apr 1997 10:37:21 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 49
Message-ID: <5ht5s1$ab5@bartlet.df.lth.se>
References: <19970402053200.AAA19717@ladder01.news.aol.com> <erkyrathE7zxnn.4M@netcom.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23947

In article <erkyrathE7zxnn.4M@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>You can attach any number of variables (properties) to the player. You 
>can only attach one daemon. If you want several daemon effects, you can 
>either make the daemon routine do more than one thing, or create a clock 
>object somewhere whose only purpose is to have a daemon.

I think that this, while true, may be potentially confusing, so let me
try to clairfy it a bit. 

In Inform, each object can only contain one daemon: when you do
StartDaemon(foo), where foo is an object, then the daemon will run the
routine foo.daemon every turn; this behaviour is hard-coded into the
library, and in this sense there can be only one daemon "attached to" an
object.

However, there is nothing that says that a daemon that affects the
player needs to be a member of the player object. You could have
daemons whose routines are members of other objects, or you could
create an object whose sole purpose is to contain a daemon routine. 

It's easy to imagine cases where you really want two daemon routines
that are members of the same object, for example

object troll
with
    daemon1 [ ;
        ! Handle the troll's walking around and picking things up
    ],
    daemon2 [ ;
        ! Handle the troll's starving to death unless he eats
    ],
private
    ! Lots of private properties accessed by the daemons
;

You want both daemon routines to be members since otherwise they can't
access the private properties. However, Inform doesn't allow this.

So how do you solve this problem (if you don't want to re-design it to
use only one daemon)? Easy: you create two daemon rotuines that are
members of other objects that do nothing but call troll.daemon1 and
troll.daemon2, respectively.



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From russotto@wanda.vf.pond.com Wed Apr  2 11:09:21 MET DST 1997
Article: 23933 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!visi.com!mr.net!news.maxwell.syr.edu!news.sprintlink.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-fw-12.sprintlink.net!news-dc-26.sprintlink.net!news.sprintlink.net!news-atl-21.sprintlink.net!news.pond.com!wanda.vf.pond.com!not-for-mail
From: russotto@wanda.vf.pond.com (Matthew T. Russotto)
Newsgroups: rec.arts.int-fiction
Subject: ANNOUNCEMENT: New IF Hardware: Z-Code Execution Machine
Date: 1 Apr 1997 23:13:56 -0500
Organization: Ghotinet
Lines: 73
Message-ID: <5hsme4$d7b@wanda.vf.pond.com>
References: <5hq95m$ki6@news.inter.net.il> <E7z6vJ.KJp@undergrad.math.uwaterloo.ca>
NNTP-Posting-Host: 198.69.82.2
Xref: news.lth.se rec.arts.int-fiction:23933

In article <E7z6vJ.KJp@undergrad.math.uwaterloo.ca>,
Stephen van Egmond <svanegmo@undergrad.math.uwaterloo.ca> wrote:
}I can! (It might be explained in the rec.games.int-fiction faq.)
}
}The # in .z# refers to the "revision" of the z-machine the file is encoded
}for.  Imagine that the Frobozz Magic Computer Company came out with 8
}versions of the machine.  The .z# contains code that can be understood by
}only one of those machines.
}
}Recent interpreters from the Frobozz Magic Interpreter Company can
}pretend to be any of the 8 computers from the FMCC.  Some interpreters
}don't know how to do version 6 yet, though, since that has all the
}pictures, bells, and whistles.

Ahh, a perfect lead-in for my own announcement:  ZEM!  The Z-Code
Execution Machine.  That's right, it's a hardware implementation.
Based on a never-released workstation, ZEM executes all versions
of the Z-code, including V6.  The Z-code itself is executed on a
re-microcoded 68008 processor core, with a TI 34020 used for the
windowing, text, and graphics processing.  A separate 68008 handles disk and
keyboard I/O for both the Z-machine proper and the graphics engine, as
well as the bootstrapping of the Z-machine.  

Features include

1) Loadable fonts -- up to 65535 separate fonts may be used.  Comes
standard with scalable versions of Z-Machine Fixed, Variable, Picture,
and Rune (IBM and Mac variants) fonts.  Options include Apple //c Mousetext
and IBM PC Character Graphics fonts, as well as Egyptian Hieroglyphs
and Linear A and B.

2) Infocom (Apple II, IBM, Mac, Amiga, Atari 8bit, Atari ST, CP/M, or
PDP-11), Standard 0.2, or Standard 1.0 execution selectable during bootstrap.

3) All 31 Infocom Z-Machine games included in ROM at no extra cost.

4) Multi-undo, up to available memory.

5) Reads and writes all known Infocom, Frotz, ITF, and ZIP save file formats.

6) True Color support for V6 games

7) Up to 16-bit 44khz stereo sound samples using built-in speakers,
plus optional external MIDI support.

8) Kibitz mode analyzes your moves and offers helpful advice.  e.g.

> up
Darkness
It is dark.  You are likely to walk into the fangs of a slavering grue.
KIBITZ: What did you pick up that brass lantern for, your health?
KIBITZ: Turn it on.

> east
Oh no!  You have been eaten by a grue.
***YOU HAVE DIED***
KIBITZ: *SIGH*  I told you so.

9) Optional auto-play mode solves the game for you.  Warning: If game
has no solution, this may take a while and entail modification of
read-only memory.

10) Finally, an optional machine-level debugger for programmers.

ZEM is the state of the art in Interactive Fiction technology.  Order
one today.  Operators are standing by, have your credit card ready.
Monitor not included. Not responsible for incidental or consequential
damages. Cave Canem. April Fools.

-- 
Matthew T. Russotto                                russotto@pond.com
"Extremism in defense of liberty is no vice, and moderation in pursuit
of justice is no virtue." 


From mol@bartlet.df.lth.se Wed Apr  2 19:34:43 MET DST 1997
Article: 23976 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: What I've been up to lately (was: Yawn, stretch.)
Date: 2 Apr 1997 19:20:23 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 37
Message-ID: <5hu4gn$otk@bartlet.df.lth.se>
References: <5hhjj2$in@agate.berkeley.edu> <dsglasser-3003972208410001@207.41.27.59>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:23976

In article <dsglasser-3003972208410001@207.41.27.59>,
David Glasser <dsglasser@hotmail.com> wrote:
>In article <5hhjj2$in@agate.berkeley.edu>, whizzard@uclink.berkeley.edu
>(Gerry Kevin Wilson) wrote:
>
>> [lots of comments on Inform and TADS relations skipped]
>
>So, I'm not the only TADS user trying out Inform right now?

I've also been spending some of my copoius free time (ha!) on learning
Inform (as people no doubt have guessed from my frequent posts on
Inform-related topics). 

This is not because I find TADS in any way inadequate, and I have not
decided to abandon TADS. It's more that I'd like to learn a different
way of looking at things.

As a first Inform project, I've chosen to re-implement my old game
"Dunjin". Not just porting it, but re-implementing it as 
state-of-the-art IF. It's very nice to be working on a game were the
entire design is fixed and almost all the text is already written; I
can concentrate on implemention without having to thing about plot or
writing or puzzle design all the time...











-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
--- Not affiliated to Lund University or LTH ---


From gatewood@mail.athensnet.com Fri Apr  4 13:03:15 MET DST 1997
Article: 24049 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!news.maxwell.syr.edu!news.pbi.net!nntp.mainstreet.net!ns2.mainstreet.net!sloth.swcp.com!reader1.news.act.net!usenet
From: Dave Gatewood <gatewood@mail.athensnet.com>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Game using only standard responses
Date: Thu, 03 Apr 1997 00:18:43 -0500
Organization: American Commerce & Technology
Lines: 169
Message-ID: <33433DB3.3A20@mail.athensnet.com>
References: <5gqcfl$c8c@nntp5.u.washington.edu> <5gqdoj$jq2@agate.berkeley.edu> <Pine.OSF.3.91.970319232725.21305A-100000@alpha1.csd.uwm.edu> <ant210027bc8M+4%@gnelson.demon.co.uk> <333290DB.6A22@earthlink.net> <erkyrathE7En72.8y1@netcom.com> <ant220105313M+4%@gnelson.demon.co.uk>
Reply-To: gatewood@mail.athensnet.com
NNTP-Posting-Host: power108.athensnet.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
Xref: news.lth.se rec.games.int-fiction:22319 rec.arts.int-fiction:24049

Graham Nelson wrote:
> Andrew Plotkin wrote:
> > One day we're going to build a game made entirely of canned responses.
> ...any more, anyone?

I don't know the word "failure."  That's what you told yourself when you
set out on this voyage across Quendor in search of your one true love:
the Prince.  Ever since the dream, his vision has haunted you, his soft
beard has tickled your innocent cheeks.  Your passion and fire have
carried you this far, but now, as you stand in front of the castle, the
home of your chosen one, you begin to tremble - will he know you, will
he feel for you as you for him?  In the dream, he ran to you, embraced
you, took you for his bride.  But the dreadful truth is, this is not a
dream...


PURPLE REIGN
A Sample Transcript Made Pretty Much Entirely Out Of Default Responses
(Plus Some Fairly Atrocious Puns)
Inform Release 1

Audience Chamber
Even larger and grander than you had imagined it, the castle of King
Duncanthrax weighs down upon you just as unrequited love weighs upon
your battered heart.  The king and queen sit before you in the usual
royal splendor.

The king sends an elf to the kitchen to bring some refreshment, then
turns his attention to you.  "So, I'm told you've got a thing for the
prince.  Interesting."  Following standard Quendorian courting
etiquette, he takes a quick scan of your resume.  "Hmph.  An actress,
eh?  What are you appearing in?  Anything I might have heard of?"

> TELL KING ABOUT CURRENT PROJECT
But you aren't in anything at the moment.

"So, I guess that makes you an unemployed actress then, doesn't it? 
Skedaddle, babe, I haven't got the time."  He starts to wave you off,
but stops at the sight of the raw despair tearing at your gentle
features.  (And he thinks you're not an actress!)  His tone softens. 
"Listen, sweetheart, you aren't missing a thing.  That son of mine is no
Prince Charming - long hair, earrings, that girly dornberry beret he's
always crowing about.  He's a painter, he tells us, all he wants to do
is paint.  Paints some swoopy thing, says it's his name.  Then he
insists we call him 'The Artist Formerly Known as The Prince.' 
Whatever!  I tell you, when I was a lad, we didn't allow such
sissies..."

Gosh, the prince an artist!  He probably has paintings in all the most
prestigious galleries.  You can't help but wonder if he's well-hung.

> KING, CAN'T I JUST SEE THE PRINCE?
"You can't see 'him' (the prince) at the moment."

Your naughty thoughts continue to wander through increasingly forbidden
territory.  You feel as if you may faint.

> ASK KING ABOUT PRINCE'S ARTISTIC ABILITY
"I don't think much is to be achieved by that."

You'd better find some refreshment soon.  Where could that elf be?

> CHANNEL ELF
You are always elf-possessed.

An image of Fabio, brush in hand, tumbles through your mind.  If you
don't find some water soon, you're going to pass out!

> FIND SOME WATER
You aren't feeling especially dowsy.

Thank goodness!  The elf returns with a silver tray loaded with gourmet
food and drink.  You grab a bottle of water and take a swig.  Not bad.

"Well, young lady," the king mumbles through a mouthful of garlic and
hot peppers, "as you can see, it's time for my after-brunch snack.  I'm
sure it's been a pleasure making your acquaintance.  Now move along."

> WISH THE PRINCE WOULD COME CHARGING IN ON HIS PURPLE STEED AND WHISK ME AWAY FROM ALL THIS
Life doesn't work that way.

Your dismissal is interrupted by an insistent and ear-piercing yapping
coming from the east wing, followed closely behind by the most ugly
chihuahua you've ever seen (and that's saying something).  Its head is
approximately twice as big as the rest of its body, and its features are
so grotesquely twisted that you can't help but think it should be
sucking a can of spinach through a corn cob pipe.  To make matters
worse, some loon has dressed it in a lime green sequined jumpsuit.  The
freakish creature races past you and leaps headlong into the king's
"after-brunch snack," sending granola flying in all directions.

The queen sighs.  "Well, now you've met Willie.  'Winkie Willie,' we
like to say, because of, well, you know, the face thing."

> X WINKIE WILLIE
Wee!

In two bites Willie has consumed his entire body weight (the head is
another matter entirely), and appears to notice you for the first time. 
He turns his hideous face to you, and in horror your gaze is locked to
his.  You can't move!

> COVER WILLIE'S FACE
That isn't a veilable.

> QUEEN, SHOULDN'T YOU MOVE THE DOG TO A WARMER ROOM?
"Ah lass, it is clothed."  She beams.  "You know, I had the royal tailor
knit that jumpsuit for Willie myself," she says proudly.

But Fortune smiles on you once again!  Footsteps approach from behind,
and the grue-some Willie turns to greet the new arrival.  Whew!  You're
free to move again.

Temporarily, anyway.  "Hello, 'The Artist Formerly Known as The
Prince,'" the king drones sarcastically.

It's him!  Omigod!  Omigod omigod omigod!

> SHOW THE PRINCE MY OFT-REHEARSED "YOU COULD KISS ME IF YOU WANTED TO, NOT THAT I REALLY CARE" POUT
Nothing obvious happens.

"Hey there Willie!"  The prince carefully scratches _behind_ the little
dog's ears.  "So Pops, who's the broad?"

He's boorish too?  What a dreamboat.  You try not to be too obvious as
you devour his peach-fuzz beard, his greasy, stringy hair, and his pale
skinny body.  Yes, he's quite the hunk.  Your knees buckle.

> EXAMINE THE CUT OF HIS JIB
Not bad.

Your head is spinning.  Perhaps you'd better eat something.

> EAT LEFTOVERS
There's no good surfeit on the tray.

The prince turns to the queen.  "Ma, I'll be out late tonight.  Zilbo
wants to show me some card game he invented - Double Espresso or
something.  Man that's one hoopy frood.  We're gonna party like it's
699."

Weak from passion and lack of sustenance, you feel completely
unrestrained.  You are capable of anything.  You are woman, hear you
roar.

> PRINCE, HOW ABOUT A LOOK AT, YOU KNOW, THE "ROYAL JEWELS?"
"I only understood you as far as wanting to look."

> EXPLAIN WHAT I MEAN BY THE ROYAL JEWELS
"You can't see any such thing!" the prince exclaims.  His delicate
sensibilities trampled, he storms off in a huff, taking your lonely
heart with him.

The king steps beside you and puts an arm around your shoulders.  "Chin
up, kid, he'll get over it.  Although I must say you're better off
without him - I mean, really, what a flake."

> KING, ANY SUGGESTIONS?
"Beg pardon?"

No; you know the prince will never forgive your temerity.  Yet somehow
you must learn to live on, to face a thousand days spent without your
one true love.  But how?  How can life continue in the face of such
loss?  

> QUEEN, WHAT SHOULD I DO?
"End obsession."




From david_lebling@avid.com Sun Apr  6 09:46:56 MET DST 1997
Article: 24142 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!cam-news-feed5.bbnplanet.com!avid.com!news@avid.com
From: david_lebling@avid.com (Dave Lebling)
Newsgroups: rec.arts.int-fiction
Subject: Re: Writing V6 (graphical) games (Was: Re: V6 Infocom games)
Date: Fri, 04 Apr 1997 22:41:37 GMT
Organization: AVID Technology, Inc.  Tewksbury, MA
Lines: 19
Message-ID: <3345831c.32070919@news.avid.com>
References: <ant012216345M+4%@gnelson.demon.co.uk> <19970403230500.SAA22857@ladder01.news.aol.com>
NNTP-Posting-Host: dleblingpc.avid.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent .99g/32.339
Xref: news.lth.se rec.arts.int-fiction:24142

zaphod1342@aol.com (Zaphod1342) wrote:

>I'm not much of a Z-Machine buff, but if you could have photo-quality
>graphics (see: GNelson's posting on this subject), then I see no reason
>why it would be impossible (hypothetically speaking) to have animated
>graphics, completely mouse-based interface, and sound (e.g. Lurking
>Horror).
>
>Of course, I wouldn't want to be the one to program it.  I'm just making
>hypothetical statements.  But I'll try it if nobody else wants to...

We did several demo games in V6 that had animated graphics.  They just
used graphic sequences from a few Activision games and redid the
"driving" code as Z-code.  With a little additional work it would have
been indistinguishable from any other animated game.

        Dave
        (david_lebling@avid.com)



From mkkuhner@phylo.genetics.washington.edu Sun Apr  6 09:56:41 MET DST 1997
Article: 24144 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Infocom vs. r.*.if!
Date: 6 Apr 1997 04:27:07 GMT
Organization: University of Washington, Seattle
Lines: 22
Message-ID: <5i78mr$sr1@nntp5.u.washington.edu>
References: <5i0p1u$af3@flood.xnet.com> <3345fa99.11726902@news.netspace.net.au> <5i5ve9$5m2$1@crucigera.fysh.org>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.games.int-fiction:22365 rec.arts.int-fiction:24144

I played IF games as a teenager--discovered Adventure on the
university's brand-new mainframe, then Zork and a couple of Scott
Adams games on my Commodore.  I lost interest, though, partly
due to frustrating experiences with Planetfall and Hitchhikers.

I found raif via a discussion of Black's gender on a roleplaying
newsgroup, and was mildly intrigued, mainly by the idea that people
were *writing* games and discussing them.  (It had always been
a pretty solitary hobby for me).  So I downloaded Sherbet and
Jigsaw, and then got bitten by the idea of writing a game, and
things just went on from there.  I bought _Masterpieces_ when I
couldn't stand not being able to follow the discussions of Infocom
games, but I can't say I had particularly warmer memories of Infocom
than of Scott Adams.  My favorite game as a teenager was definitely
_The Count_, Scott's vampire game, for its dream sequences and
tight, cohesive setting.  

Working on Trinity now and enjoying it a lot, though of course I have
the wrong-headed and unfair impression that it's mildly derivative of
Jigsaw....

Mary Kuhner mkkuhner@genetics.washington.edu


From wheeler@moontower.com Mon Apr  7 10:04:37 MET DST 1997
Article: 24187 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news-peer.sprintlink.net!cs.utexas.edu!geraldo.cc.utexas.edu!newshost!wheeler
From: wheeler@moontower.com (J. Robinson Wheeler)
Newsgroups: rec.arts.int-fiction
Subject: Re: Writing V6 (graphical) games (Was: Re: V6 Infocom games)
Date: Mon, 7 Apr 97 05:33:10 GMT
Organization: The University of Texas at Austin, Austin, Texas
Lines: 34
Message-ID: <wheeler.1210778830D@newshost.cc.utexas.edu>
References: <ant012216345M+4%@gnelson.demon.co.uk> <19970403230500.SAA22857@ladder01.news.aol.com> <3345831c.32070919@news.avid.com>
NNTP-Posting-Host: slip-113-14.ots.utexas.edu
X-Newsreader: VersaTerm Link v1.1
Xref: news.lth.se rec.arts.int-fiction:24187

In Article <3345831c.32070919@news.avid.com>, david_lebling@avid.com (Dave
Lebling) wrote:
>zaphod1342@aol.com (Zaphod1342) wrote:
>
>>I'm not much of a Z-Machine buff, but if you could have photo-quality
>>graphics (see: GNelson's posting on this subject), then I see no reason
>>why it would be impossible (hypothetically speaking) to have animated
>>graphics, completely mouse-based interface, and sound (e.g. Lurking
>>Horror).
>
>We did several demo games in V6 that had animated graphics.  They just
>used graphic sequences from a few Activision games and redid the
>"driving" code as Z-code.  With a little additional work it would have
>been indistinguishable from any other animated game.
>
>        Dave
>        (david_lebling@avid.com)


See, this is making me feel quite strongly that V6 is a lurking mass of
potential waiting to be released by the right author and the right story
and the right game.  I bet you could do something fantastic with it as
long as you stayed in command of the graphics and didn't let them get 
out of control, and as long as the graphics were crucial to the richest
experience of the game.  (Ah, but that's the trick, isn't it...)

I still think I'm going to try, one of these days.  First things first.




Rob Wheeler
wheeler@moontower.com



From graham@gnelson.demon.co.uk Mon Apr  7 13:10:04 MET DST 1997
Article: 24190 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Inform library 6/5 released
Date: Sun, 06 Apr 1997 01:57:44 +0100 (BST)
Organization: none
Message-ID: <ant0600440b0M+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 377
Xref: news.lth.se rec.arts.int-fiction:24190


Inform library 6/5 released
===========================

I have recently upgraded the Inform compiler to v6.13, by making a
small patch to fix a minor bug in some new code in v6.12, but details
of that are posted elsewhere.  This post is to announce a more
substantial improvement: library 6/5 is the first version of the
Inform library to offer new game-design features for over a year
(changes 206 and 207), and there are also improvements for language
definition files and some bug fixes (one, change 208, quite important).

As for 6/3 and 6/4, the library consists of eight text files:

    parser.h   verblib.h   grammar.h
    parserm.h  verblibm.h
    linklv.h   linklpa.h
    English.h

(where "English.h" is the default language definition file).

The library files should appear at ftp.gmd.de shortly.  If you can't
wait, then as a temporary measure you can get hold of a tar file
containing all 8 from the Inform 6 Home Page:

    http://www.gnelson.demon.co.uk/inform.html

Please note that there may be a delay of one to three days before the
new file becomes "visible" from your region of the Internet, because
of the regrettable way that my Internet service provider organises its
WWW space.  So if it doesn't show up immediately, please be patient. 
The library history page at the above site has also been updated, and
again the update may not show at once.

My thanks, as ever, to those who have emailed me bug reports. I am
always grateful for these, though it can sometimes take me a couple of
weeks to reply when I have a serious email backlog, for which I
apologise.  Please try to send me a short piece of source code
demonstrating what you think is wrong, if possible: this saves on long
explanations and makes it much easier for me to find the problem.

Finally, apologies to everyone who has been promised that 6/5 would
appear "any day now".  I would like to blame the inventors of the
Spanish and German languages for this, or at least Jose Luis Diaz de
Arriba and Ralf Herrmann as their representatives on Earth.


    Graham Nelson
    26 March 1997

------------------------------------------------------------------------
The changes present in library 6/5, serial number 970405 are as
follows:

205. Grammar for "get" adjusted so that "get up" is not misinterpreted
    as "take the ceiling".  Grammar for "close up" fixed so that
    "close up noun" now works as it should (not that it occurs very
    often).

206. The library has been enhanced to make it possible for the player
    to be inside an object or a sequence of objects (for instance,
    in a box which is on top of a table).  One or more of these
    objects can now be closed and can even block off visibility,
    so that the player can be sealed in and unable to see the
    room outside.  The changes made have implications for scope,
    light and the handling of "take", "remove", "insert", "put", "empty",
    "look", "enter", "open" and "exit".

    The new rules extend the usual ones: you can see through anything
    which is "transparent", or a "supporter", or a "container" which
    is "open", and this affects both scope and the presence of light;
    you can take through anything which is a "supporter" or a
    "container" which is "open".  A special case is that, even in
    darkness, the immediate object containing the player is always in
    scope, as that prevents the player from shutting himself in a dark
    cupboard and then being unable to say "open cupboard" to get out
    again.  (To test these rules, you may want to use the "scope"
    debugging verb, which lists all the objects currently in scope.)

    The "enter" verb automatically moves the player out of and into
    as many intermediate stages as needed to reach its destination.

    Note that Receive and LetGo actions (asking containers and
    supporters if they mind objects being inserted or removed)
    are not generated when the player is already inside or on
    the holder.

    A new property has been created called "inside_description".
    Anything which is "enterable" may wish to provide a string or
    routine to print something here: perhaps what an interior looks
    like, or what a vehicle looks like to the occupant.

    For instance, here is a room description which results from
    the player getting into a huge cupboard, closing the door
    behind her, and then getting into a plastic cabinet inside that:
    
        The huge cupboard (in the plastic cabinet)
        -----------------

    (*) It's a snug little cupboard in here, almost a room in itself.

        In the huge cupboard you can see a pile of clothes.

    (*) The plastic walls of the cabinet distort the view.

    Note that the exterior room description has vanished altogether.
    The two lines marked (*) are values of "inside_description"
    for the cupboard and cabinet.  Note that there's absolutely
    no obligation to provide an "inside_description" for an "enterable"
    object.

    I wish to thank the many people who made suggestions on this
    subject, but especially Daryl McCullough and Fredrik Ramsberg,
    who analysed it in detail, and Admiral Jota, who organised a
    response.

207. A further significant change has been to introduce a formal idea
    of what the player can touch and manipulate.  Up to now, the
    library has confused together what can be seen with what can be
    touched: obviously, if the player is inside a closed glass cabinet,
    there's a significant difference.

    The rule is that you cannot touch something if there is a closed
    container between you and it.  This applies either if you're in
    the container, or if it is.  The former case will not have applied
    before, but the latter may cause inconsistencies with previous
    library behaviour.  That is, in the library as it stood, you could
    unlock something which was inside a closed glass box, and it's
    possible that some games have exploited this loophole.

    Note that the rule is only applied after "before" rules have been
    consulted.  The actions affected are as follows:

    Take, Remove: The item must be touchable.  Furthermore, it must
        not be (directly or indirectly) in the possession of anyone
        "animate", or (directly or indirectly) in the possession of
        anything which is neither a "container" nor a "supporter".
        (These last two rules have always been part of the library:
        only the touchable condition is new.)

    Insert, PutOn: The destination must be touchable.

    Empty: The container to be emptied must be touchable.  Since all
        the transfers of objects from it are made via Insert, PutOn
        or Drop actions, the destination must be touchable too.

    Enter: The item must be reachable by a sequence of Exit and Enter
        actions, which ensures that it is touchable.

    Search, Unlock, Lock, SwitchOn, SwitchOff, Open, Close, Disrobe,
    Wear, Eat, WakeOther, Touch, Wave, Pull, Push, Turn, Squeeze,
    ThrowAt, Kiss, Attack:
        The noun must be touchable.  Note that this includes a few
        actions which ordinarily have no effect (Push, Pull, Turn)
        simply to improve the messages produced.

    (The actions Give, Show, Drop, Insert and PutOn do have to have
        touchable nouns, but since they always required their nouns
        to be directly possessed by the player, this makes no change
        to the established rules.)

    Designers who want to apply the same kind of rule to their own
    actions can use the library routine
    
        ObjectIsUntouchable(obj)

    which determines whether obj is touchable or not.  If it is
    touchable, the routine returns false and nothing is printed.  If
    untouchable, the routine prints a suitable message explaining why
    and returns true.  This means that only a single line of code
    needs to be introduced to the action routine to handle this
    issue.  For instance, the library's Eat action routine now reads:

        [ EatSub;
          if (ObjectIsUntouchable(noun)) return;
          if (noun hasnt edible)
              ...etc.

    Finally, an optional second parameter to ObjectIsUntouchable
    will make the routine work silently:
    
        ObjectIsUntouchable(obj, true)

    returns true or false but prints nothing.

208. A serious but recent bug fixed: the recent tidy-up of the code for
    the Go action in 6/4 missed a case, so that if one walks into a
    door with a door_to routine which returns true (meaning: you can't
    proceed), the library moves one to a room numbered 1.  If the
    player has a light source, he can see that this room is actually
    "Class" and that the classes of the game are scattered about like
    objects (a somewhat Platonic journey into the world of forms).

209. Four library messages (Miscellany 42 and 47; Show 2; Take 9) have
    prints changed to print_rets, thus making sure they have a new-line
    printed after them.  Three further library messages (Look 1, 2 and 3)
    have been extended: these used to print the words "on", "in" and
    "as", but now print the phrases " (on the whatever)" and so on.
    (This should assist translations, as the named object may have
    to be named in the dative rather than accusative.)
    The library message Drop 1 has been reworded slightly to make better
    sense when the player isn't in a place with an obvious floor.
    The messages Miscellany 48 and 49 have been rewritten to include
    calls to a library routine which prints out the player's command.
    (These messages handle "What do you want to take?" and similar.
    The change makes it easier for language definition files to cope
    with this difficult case.)
    Both the library messages for Transfer (1 and 2) have been removed
    as redundant.
    Finally, there are two new library messages, Enter 6 and 7.

210. Games using 6/3 or 6/4 could crash when trying to print a suitable
    error message if the player uses a pronoun which has never been
    set in the course of the game (e.g. "her" in a generally masculine
    environment).

211. The pronouns system has a complicated mechanism, in English only,
    to carry on supporting the "itobj", "himobj" and "herobj" variables
    (for the sake of old code).  In 6/4 this didn't quite work and some
    settings of these variables would have no effect.

212. The official rewording-routine for language definition files,
    called LanguageToInformese, wasn't being called: instead, a routine
    called LanguageReword was.  I have changed this to
    LanguageToInformese as per the documentation.  Any routines called
    LanguageReword in language definition files will no longer work.
    Apologies for this elementary error.

213. Containers which are neither "open", "openable" nor "transparent"
    but which are empty are no longer reported as empty in inventory
    lists.  (After all, how could the player tell?)

214. The debugging verbs "purloin" and "abstract" are now protected
    against moving or taking classes or system objects like
    "InformLibrary", and also against moving objects so that they
    indirectly contain themselves, which can lead to Z-machine crashes
    or infinite recursions.

215. Problems saying things to unspecified people in large games might
    have occurred because of a complicated mistake in coding the
    new (6/3 and later) parser.  Thanks to Magnus Olsson for finding,
    diagnosing and correcting this mistake.

216. The "PrefaceByArticle" not correctly pluralising articles in
    some cases.  Thanks to Andreas Hoppler and Ralf Herrmann for
    fixing this.

217. The "objects" verb no longer reports items left on enterable
    supporters as being "in" rather than "on" something.

218. The parser now has a better system for handling extension input,
    that is, text typed by the player in response to a question like
    "What do you want to take?".  The previous system did not behave
    well in languages other than English, as Ralf Herrmann and Jose
    Luis Diaz de Arriba pointed out.  Similarly, the "again" system
    has been rewritten, which should make it work slightly better
    even in English.

219. Bug in handling of "short_name_indef" removed.  (This is a feature
    not needed in English language games.)  Thanks to Ralf Herrmann
    for mending this.

220. The library now calls "LanguageInitialise" immediately before
    calling "Initialise", if the language definition file provides
    one.  (This is convenient for German, for instance, to give the
    darkness-object "female".)

221. The language definition file can (optionally) provide a routine
    called "LanguagePrintShortName" to print the short name of an
    object.  Specifically,
    
       LanguagePrintShortName(o)

    (which will only be called if o is a valid object number) should
    either return false, or print the short name of o and return true.
    At the time of the call, the variable "indef_mode" will be set
    if an indefinite article has just been printed.
    The "English.h" definition doesn't use this feature, but if it
    did then the appropriate code would be:
    
       [ LanguagePrintShortName o;
         if (indef_mode && o provides short_name_indef
             && PrintOrRun(o,short_name_indef,1)) rtrue;
         if (o provides short_name && PrintOrRun(o,short_name,1)) rtrue;
         @print_obj o;
         rtrue;
       ];

    (Note that "PrintOrRun(o,X,1)" is very similar to sending the
    message X to object o, but doesn't print a new-line if o provides
    a string for property X.)

222. The parser's fundamental routine "Refers", which determines whether
    a given English word refers to a given game object, now calls
    "LanguageRefers" if the language definition file provides this.
    The syntax is LanguageRefers(obj, word_number), and the return value
    should be true or false to indicate the result, or -1 to indicate
    "make the decision as usual".  Note that the word doesn't have to
    be in the game dictionary, which is why it's referred to by its
    number (in the sequence of words typed in as the present command),
    not by its dictionary address.

223. And the language definition file can also optionally provide a
    routine called
    
       LanguageIsVerb(buffer, parse, word_number)

    If provided, this should look at the numbered word in the given
    text buffer (which has been tokenised into the given parse buffer
    already) and decide whether it's a verb.  If so, the routine should
    return a dictionary word for that verb.  If not, it should return
    false.  (This is provided to allow automatic inflection of verbs:
    e.g. automatic conversion of the various German alternative verb
    endings into one standard one.)

224. When printing short names, the variable "indef_mode" is now:
    true if an indefinite article has just been printed; false if a
    definite article has just been printed; and equal to NULL if no
    article was printed at all.  (For instance, it will be NULL when
    the list-writer prints a list with the NOARTICLE_BIT style set.
    This assists the German translation.)

225. In order to make it easier to adjust cases in lists written in
    inflected languages: a language definition file can now define
    a constant called LanguageCases, which should be a number.
    The default value is 1.  The library creates a variable called
    "short_name_case", initially with value 0, and which is free to
    be changed by the game or the language definition file routines.
    Its value should always be between 0 and LC-1 (thus, in English
    it will always be 0): I suggest that code like...

        Constant LanguageCases = 4;
        Constant NOMINATIVE_CASE = 0;
        Constant ACCUSATIVE_CASE = 1;
        Constant GENITIVE_CASE = 2;
        Constant DATIVE_CASE = 3;

    ...may simplify things.  The "LanguagePrintShortName" routine may
    want to make use of the value of "short_name_case", if such a
    routine is provided.  The library itself uses the case only when
    printing articles.  If LC is 1, so there are no cases, then the
    array LanguageArticles is unchanged from its old definition:

    Array LanguageArticles -->

    !   Contraction form 0:     Contraction form 1:
    !   Cdef   Def    Indef     Cdef   Def    Indef

        "The " "the " "a "      "The " "the " "an "          ! Articles 0
        "The " "the " "some "   "The " "the " "some ";       ! Articles 1

    But if LC is more than 1, then there extra rows for the extra cases.
    For example, if we had an extra case in English which required all
    articles to be given in capital letters, we could then have LC=2,
    with ordinary case as number 0, and the exotic new one as number 1:
    the table might look like...
    
    Array LanguageArticles -->

    !   Contraction form 0:     Contraction form 1:
    !   Cdef   Def    Indef     Cdef   Def    Indef

        "The " "the " "a "      "The " "the " "an "          ! Articles 0
        "THE " "THE " "A "      "THE " "THE " "AN "
        "The " "the " "some "   "The " "the " "some "        ! Articles 1
        "THE " "THE " "SOME "   "The " "THE " "SOME ";

    (The effect is actually quite interesting.)

226. Grammar tweaked slightly to ensure that "get X from Y" is handled
    better when X is ambiguous.

------------------------------------------------------------------------

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From whizzard@uclink.berkeley.edu Tue Apr  8 09:44:47 MET DST 1997
Article: 24225 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!news.maxwell.syr.edu!europa.clark.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: I-F 97 Trophies
Date: 8 Apr 1997 03:02:02 GMT
Organization: University of California at Berkeley
Lines: 14
Message-ID: <5iccfa$qmi@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:24225


Okay, I've figured out where I'm going to get the trophies and what
they're going to look like.  Third place will actually be a medallion
instead of a trophy.

The other two will look similar, the main difference being how tall they
are.  The cost is surprisingly reasonable, so that's a good thing.

I just have to get a compass rose that'll fit inside a 2" disk, now, and
all will be groovy.  I'd use Liza's directly except that 1) It needs to be
b&w. 2) I think it'll suffer if shrunk that small and 3) I'm feeling
particularly lazy this month. ;)
-- 
     Losing the war against dirty laundry...


From boutel1g@wcc.govt.nz Tue Apr  8 12:28:41 MET DST 1997
Article: 24234 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!newsfeed.nacamar.de!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in1.uu.net!202.37.60.10!comp.vuw.ac.nz!wcc.govt.nz!wcc.govt.nz!nntp
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Infocom vs. r.*.if!
Message-ID: <01bc43b5$d8888b20$09340a0a@SPAWN.wcc.govt.nz>
From: "Giles Boutel" <boutel1g@wcc.govt.nz>
Date: 8 Apr 97 12:42:28 NZST
References: <5i0p1u$af3@flood.xnet.com> <5i78mr$sr1@nntp5.u.washington.edu><3347D49A.3BD5@
 earthlink.net> <ant070708d07M+4%@gnelson.demon.co.uk><5ibjev$im5@bartlet.df.lt
 h.se> <erkyrathE8AEvH.LMC@netcom.com> <33497053.15B4@cogentex.com>
Organization: Wellington City Council
Nntp-Posting-Host: 10.10.52.9
X-Newsreader: Microsoft Internet News 4.70.1155
Lines: 22
Xref: news.lth.se rec.games.int-fiction:22439 rec.arts.int-fiction:24234



Daryl McCullough <daryl@cogentex.com> wrote in article
<33497053.15B4@cogentex.com>...
> Excuse me, but what does "segmented style of game" mean? Is
> it necessary to play Jigsaw or Trinity to understand what that
> means?
> 
A segmented game is one with distinct, unconnected areas, although objects
>from one area might be used in another. One type of this game (such as
Trinity) uses a particular area as a jumping point to several
geographically separate, though thematically linked environments. The
different areas could be different dimensions, different time zones,
different people (as in Hitchhiker's guide), or just different areas of the
same land (eg spellbreaker). One advantage they have over other styles is
the sub-areas generally require little mapping because they're really
smaller sub-games and easy to keep in your head.

My guess as to the earliest game in this genre is Scott Adams Strange
Odyssey.

-Giles 


From erkyrath@netcom.com Tue Apr  8 19:17:15 MET DST 1997
Article: 24244 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] strings & class properties
Message-ID: <erkyrathE8Bw5p.6GD@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <334A6AF9.15FB@x_greenhouse.llnl.gov>
Date: Tue, 8 Apr 1997 16:51:24 GMT
Lines: 66
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24244

Kathleen Fischer (kfischer@x_greenhouse.llnl.gov) wrote:
> Well, things are going poorly on the home front. I have purloined the
> baptise code from Balances.inf:

> where TextReader(1) just copies a word (input by the player) into
> cube_text_buffer one byte at a time.

Ok, you got your array of bytes.

> And this code works great.  However, I want to be able to name my "cube"
> programmatically as well.  I want to be able to write

> [ NameMyCube item text i;
>     for (i = 0 : i < text->0 : i++) (item.&number)->i = text->i;
>     ! pad the rest with zeros... etc
> ];

> [ TestRoutine;
>   NameMyCube (mycube, "ralph");    ! mycube of class FeaturlessCube
> ];

Remember that double-quoted strings are compressed in memory. Use 
print_to_array to uncompress "ralph" into cube_text_buffer, and then copy 
it in just like before.

> ps. Extra credit to anyone who can explain to me what the last half of
> TextReader (when input variable ~= 1) is doing. Specificially, what is
> the 3rd line doing?

>    for (i=0:i<8:i++) cube_text_buffer->i = 0;
>    if (wn > parse->1) { wn++; rfalse; }
>    i=wn*4+1; j=parse->i; point=j+buffer; len=parse->(i-1);
>    for (i=0:i<len && i<7:i++) cube_text_buffer->i = point->i;
>    wn++; rtrue;

Ok. When text input is done, "buffer" is filled up with the text that was 
input (an array of bytes.) Also "parse" is filled up with a bunch of 
four-byte data blocks, one for each *word* which was input. Each data 
block contains info about which dictionary word that word matches, and 
the start and length of that word in "buffer". If the word was not found 
in the dictionary, the dictionary-word field is zero, but the start and 
length fields are still valid -- exactly because of cases like this, 
where we want to pull the original text out. 

(This construction of the "parse" data blocks, BTW, is done by the 
Z-machine. It's the *only* part of the parsing operation which is done by 
the Z-machine; everything else is done by the Inform library.)

So that third line is, approximately,
  i = the position of the "start" field of the wn'th data block
  j = the contents of the "start" field
  point = the position of the j'th character in "buffer", which is the 
    start of the wn'th word
  len = the contents of the "length" field (of the wn'th data block)

Gasp. This is esoteric stuff; I only needed to learn it a few weeks ago, 
for some highly experimental code (I was writing my own parser, for very 
obscure purposes.) I don't remember whether it is documented in the 
designer's manual. I found the dirt in the Inform technical manual.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From jfrancis@dungeon.engr.sgi.com Wed Apr  9 09:39:23 MET DST 1997
Article: 24255 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!news.maxwell.syr.edu!EU.net!enews.sgi.com!news.corp.sgi.com!news.sgi.com!walter.cray.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Infocom vs. r.*.if!
Date: 8 Apr 1997 21:16:50 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 46
Message-ID: <5ieck2$8a0@fido.asd.sgi.com>
References: <33356ee5.719260800@news.gte.net> <33430F25.1405@acpub.duke.edu> <5i0p1u$af3@flood.xnet.com> <3345fa99.11726902@news.netspace.net.au>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.games.int-fiction:22451 rec.arts.int-fiction:24255

In article <3345fa99.11726902@news.netspace.net.au>,
>
>What is the situation of the people in this newsgroup who have bought any of
>these re-releases?
>
First exposure was to the original (MDL) Zork on a DECSystem-20.
I bought an Atari 800 just so I could play Enchanter/Sorcerer,
but I also bought Zork I-III.
Later on I got an Atari ST, so of course I had to buy new versions.
I bought the Enchanter/Sorcerer/Spellbreaker boxed set, and the
reboxed Zork Trilogy (which also got me the Zorkmid).
Eventually I got a PC.  I did buy a few games for the PC platform,
but the ST could write PC disks, so I could copy the game files
to the PC and use one or more of the early freeware interpreters.
(I initially started writing my own interpreter, but eventually
decided to avail myself of the good work done by Mark Howell et al.
Maybe one of these days I'll get round to fitting some of my own
features to Frotz or Jzip - I had some useful game debugging stuff).
I believe Zork Zero was the only game that I had just for the PC.

Then the "Lost Treasures" collections came out, so I bought them.
This meant I had three copies of IZ1-5, two copies of several
other games, and one copy of all the rest. Yippee! I now had
a complete set of Infocom games for the PC. (I already had LGOP,
once for the Atari ST, and the "Solid Gold" version for the PC).
I bought the CD version of LTII, even though I didn't have a CD
drive, to get the three additional titles.

I think I have the Zork Anthology collection somewhere, as well -
I seem to remember it was bundled with RTZ as a promotional deal.

I still haven't bought Zork Nemesis, but when I do it will probably
be in the bundled package.  After all, if I've already bought four
copies of some of the games, why not buy a fifth?

>
> ---------------
> James Cole
> jrcole@ozemail.com.au


-- 
John Francis  jfrancis@engr.sgi.com  Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 02U-923
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From graham@gnelson.demon.co.uk Wed Apr  9 09:40:38 MET DST 1997
Article: 24271 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Infocom vs. r.*.if!
Date: Tue, 08 Apr 1997 18:50:21 +0100 (BST)
Organization: none
Message-ID: <ant0817210b0M+4%@gnelson.demon.co.uk>
References: <3347D49A.3BD5@earthlink.net> <ant070708d07M+4%@gnelson.demon.co.uk> <5ibjev$im5@bartlet.df.lth.se> <5ic3n5$hi4@nntp5.u.washington.edu> <5icsvu$qum@bartlet.df.lth.se> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 30
Xref: news.lth.se rec.games.int-fiction:22467 rec.arts.int-fiction:24271

In article <5icsvu$qum@bartlet.df.lth.se>, Magnus Olsson
<URL:mailto:mol@bartlet.df.lth.se> wrote:
> 
> In article <5ic3n5$hi4@nntp5.u.washington.edu>,
> Mary K. Kuhner <mkkuhner@phylo.genetics.washington.edu> wrote:
> >In article <5ibjev$im5@bartlet.df.lth.se> mol@bartlet.df.lth.se (Magnus Olsson) write
> s:
> >>Graham Nelson  <graham@gnelson.demon.co.uk> wrote:
> >>>Seriously, Infocom did not invent the "segmented" style of game:
> >>>they merely did it rather well.
> >
> >>Just out of curiosity: if Infocom didn't, who did?

My personal view is that it's inherent in the structure of
early dungeon-based adventure games, in that the segmentation
of the map follows from the basic collection-puzzle which makes
the game.  Thus: "Advent", "Zork", "Adventureland" and "Acheton"
all show the rudimentary signs of a modular structure, based
on the idea of regions which can't be entered until certain
puzzles are solved, each with their own treasure and key-object.

Later dungeon games invented systems to move rapidly across
the map (a la XYZZY, but more flexibly) and this too tended
to divide maps into regions.  Just my view, of course -- one day
somebody ought to write a critical history of adventure games.
Perhaps when the corpus of worthwhile works is a little larger.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Sat Apr 12 00:38:34 MET DST 1997
Article: 24291 of rec.arts.int-fiction
Newsgroups: comp.ai.games,rec.arts.int-fiction
Path: news.lth.se!solace!nntp.se.dataphone.net!nntp.uio.no!newsfeed.nacamar.de!news.apfel.de!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Chris Crawford's new IF engine
Message-ID: <erkyrathE8Dooz.L5E@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ibi0s$gen$1@venus.mcs.net> <5igdcg$1dq$1@Jupiter.Mcs.Net>
Date: Wed, 9 Apr 1997 16:05:23 GMT
Lines: 57
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se comp.ai.games:8497 rec.arts.int-fiction:24291

Jorn Barger (jorn@MCS.COM) wrote:
> [newsgroup-list expanded, followups trimmed]

> In article <5ibi0s$gen$1@venus.mcs.net> I wrote:
> >I just had a chat with Chris Crawford for the first time in a couple
> >of years, and here's the latest news: [...]
> >- his game "Morte d'Arthur" is on hold
> >- the IF (interactive fiction) engine for the game is in beta for
> >independent release under his own label [...]
> >- he has a website at www.erasmatazz.com that gives massive detail
> >about the engine, called the Erasmatron, and will eventually offer a lot
> >of his IF-theory essays [...]
>  
> when i posted this i hadn't begun to look at the Erasmatron docs
> there, but now that i have i'm very excited-- i don't know if it will
> make great IF or not, but it certainly raises the IF-ante to an
> entirely new level...

See, this is the sort of claim which turns me off from the beginning. 
It's not "raising the ante", it's striking off in an entirely new 
direction. It doesn't invalidate anything that's gone before.

(Note: I speak as a rec.arts.int-fiction regular. I don't hang out on 
comp.ai.games. Maybe your world *has* been turned upside down, I dunno.)

I've looked at the erasmatazz site and it looks extremely nifty. I don't 
think I can decide whether it's a Good Idea until I play the first few 
worlds that come out of it. It seems like it might have too many 
personality attributes hardwired -- or maybe I'm nuts.

I'd play with the software, but it seems to be only available to
beta-testers, and they want people who can devote a lot of time to
beta-testing. I am not lot-of-time-boy right now. 

> i'm considering whether i can rewrite my AI-faq to be centered around
> Chris's solutions to various problems of social simulation, eg:
>  
> - eliminating character-motion, and substituting segues from 'scene'
> to 'scene'  (a great and daring simplification)
>  
> - building in a character-model at the basic level, with a full set
> of attributes

> - analysing the branching-problem as a verb-web

> - tracking characters' knowledge of all events, and the 'grapevine'
> of rumors' paths (cf Chris's Trust and Betrayal)

> and various other simplifications that offer definite (though
> problematic) solutions to many AI challenges...

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From graham@gnelson.demon.co.uk Sat Apr 12 00:39:02 MET DST 1997
Article: 24404 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Infocom vs. r.*.if!
Date: Fri, 11 Apr 1997 09:00:41 +0100 (BST)
Organization: none
Message-ID: <ant1108411cbM+4%@gnelson.demon.co.uk>
References: <5i0p1u$af3@flood.xnet.com> <3345fa99.11726902@news.netspace.net.au> <5i5ve9$5m2$1@crucigera.fysh.org> <5i78mr$sr1@nntp5.u.washington.edu> <3347D49A.3BD5@earthlink.net> <ant070708d07M+4%@gnelson.demon.co.uk> <334D14AF.1042@ucla.edu> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 21
Xref: news.lth.se rec.games.int-fiction:22564 rec.arts.int-fiction:24404


In article <334D14AF.1042@ucla.edu>, Jon Petersen
<URL:mailto:enoto@ucla.edu> wrote:
> 
> Besides the segmented plot and "fix-it" aspect of both Trinity and
> Jigsaw, the writing style you adopted for Jigsaw reminds me much
> more of Moriarty's style than of the earlier Infocom games.  I'd say
> Moriarty's games were the only Infocom games written with a style
> *immediately* distinctive from other Infocom games.

Authors tend not to be the best judges of their own influences and
plagiarisms.  But I think it's not so much that my writing is
similar to Mr Moriarty's (indeed I think we have quite different
styles) as that room descriptions in both Trinity and Jigsaw are
trying to cram historically accurate detail into a pretty short
space.  For many locations, it really is true that the room
description could be twice as long without running out of
inspiration; both games have been, in effect, summarised.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From whizzard@uclink.berkeley.edu Sun Apr 13 00:06:59 MET DST 1997
Article: 24426 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: MIB retitled (was: Far-in-advance announcement: MEN IN BLACK)
Date: 12 Apr 1997 20:04:41 GMT
Organization: University of California at Berkeley
Lines: 56
Message-ID: <5iopsp$7i9$1@agate.berkeley.edu>
References: <3346471E.5147@earthlink.net> <slrn5ko4an.42p.darin@connectnet1.connectnet.com> <5ii8ic$c3v@bartlet.df.lth.se> <slrn5kr5p6.7nl.darin@connectnet1.connectnet.com>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:24426 rec.games.int-fiction:22592

In article <slrn5kr5p6.7nl.darin@connectnet1.connectnet.com>,
Darin Johnson <darin@usa.net.delete_this_part> wrote:

>O(N^2) interactions is "perfection"; after all, if "put pebble in
>nose" says "you can't do that" rather than something witty, no one's

I haven't quite gone that far off the deep end, but you can 'wiggle your
ears'. (and that's about all you can do with them.)  You can listen and
hear the appropriate noises in the appropriate places, the 'general smell'
is in place, I have yet to allow you to 'smell <item>', but I probably
will.  If you fill a hat with water and wear it, you get water dumped on
your head.  Essentially I'm trying to stick to the basic physical
properties/reactions, which is plenty to work with.  Later, when the
betatesters play with stuff, I add the 'eat grenade' 'ask merlin about
camelot' etc sort of things.

>he responded "don't you think that's a bug though?".  You can't handle
>every wierd thing the customer might do; and you can't handle every
>thing a player might do; sure, the more you do handle, the happier
>people will be, but things take longer and longer to ship.

The point here is that I'm in no hurry.  This may well be my only full
scale text adventure that I ever do, I'd like it to be memorable, so I've
taken my time with it, tried to think things through carefully and plan
for as many contingencies as I can think of.  I try and add clues where
puzzles are too hard, improve NPC reactions to events, etc.  Mostly I work
on keeping the story consistant (you see how easy it is to remember that
NPC's maiden name after three years...)

>motivator.  You can't blame flaws on anyone else, and there's no
>management to muck up the works, and no one has announced a release
>without consulting you, etc.

Exactly.  Which is the other reason I'm taking my time.  Avalon is a
resume, and you always want a resume to look as good as it can.

>And don't get me wrong, I'm not trying to hurry him up! It'll probably
>take a few months before I get around to getting the game anyway.  And

That's true.  I mean, I'd hate to screw up someone's Grad School. :)

>you do one of the other 20 open puzzles.  Were the Zorks any less fun
>than Dungeon though?  (excepting those people that think being stuck
>for months is good)

Precisely.  The fact is that I wanted t keep programming difficulty low
and player sanity high.

>Or they'll complain that they can't do it the easy way anymore :-)

I've got news for you.  They always complain.  About everything, sooner or
later.  Just take it in stride and don't worry about it.  If it needs
fixin', fix it.  If it ain't broke....

-- 
	"Ha.  Made ya look!"


From 104312.2206@compuserve.com Mon Apr 14 09:35:28 MET DST 1997
Article: 24478 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!howland.erols.net!usc!chi-news.cic.net!newsgate.compuserve.com!not-for-mail
From: Bryan Scattergood <104312.2206@compuserve.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: [offtopic] Archimides (was Compiling inform?)
Date: Mon, 14 Apr 1997 06:19:49 +0100
Organization: CompuServe Incorporated
Lines: 50
Message-ID: <VA.00000045.00354a4d@104312.2206>
References: <5ih72m$1dg@staff.cs.su.oz.au>
 <5ii4se$t92@bartlet.df.lth.se>
 <E8Fvqu.2Gs@undergrad.math.uwaterloo.ca>
 <5ik2b7$na8@staff.cs.su.oz.au> 
 <ant110839868M+4%@gnelson.demon.co.uk>
 <334FF4AB.6FAE6D62@alcyone.com>
Reply-To: 104312.2206@compuserve.com
NNTP-Posting-Host: ld02-194.lon.compuserve.com
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
Xref: news.lth.se rec.arts.int-fiction:24478

Erik Max Francis <max@alcyone.com> asked:

<< What in the world _is_ an Archimides, anyway?  I know it's some kind 
of tiny machine, but I've never heard anything about it except 
references to games being ported to it here in rec.arts.int-fiction. >>

'Archimedes' was the designation for a family of RISC-based Acorn 
computers launched in the mid 1980s.  The successor to Acorn's 
successful 6502-based BBC micro they are built around Acorn's ARM CPU. 
(Many Acorn owners were severely annoyed when Apple claimed that the 
PowerMac was the first personal computer built round a RISC CPU.)

The machines run Acorn's own operating system (RISC-OS) which has a 
number of fine features

* Excellent GUI
(even schoolkids can be productive with it in less than 5 minutes.)

* Anti-aliased outline font technology
(capable of generating readable text on a television-class display.)

* Present in ROM
(a RISC-OS machine is usable with as little as 2M of RAM.)

The file system (ADFS) is slightly weird.  Filenames are limited to 10 
characters and there are *no* filename extensions.  (A 10-bit filetype 
is used to associate files with applications.) 

Because of Acorn's experience in the educational market the machines 
tend to be indestructible.  My seven year old machine is still working 
fine (and is still useful--a seven year old PC would be a doorstop.)

The original family of machines A30x/A4xx were replaced by the 
A3000/4000/5000 family which in turn have been replaced by the RISC-PC. 
 This has two slots for processor cards ... the supplied ARM6 or ARM7 
CPU can be augmented by another ARM or a 486 coprocessor. The slots 
will also take a StrongARM CPU card clocked at around 200MHz.

They are *not* 'tiny machines' (other than in market share.) They have 
a loyal following in the UK education and hobbyist market. Think of 
them as the computer equivalent of a British sports-car: impractical 
for some things, but also a lot more fun than a standard PC.

    Bryan

(Who was forced to switch to a PC as his main machine about four years 
ago and still regrets it. And also suspects he stole the 'sports-car' 
analogy from Graham :-)




From erkyrath@netcom.com Mon Apr 14 12:38:09 MET DST 1997
Article: 24477 of rec.arts.int-fiction
Newsgroups: comp.ai.games,rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!Norway.EU.net!uninett.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Chris Crawford's new IF engine
Message-ID: <erkyrathE8LzL2.40w@netcom.com>
Followup-To: comp.ai.games,rec.arts.int-fiction
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5ibi0s$gen$1@venus.mcs.net> <5igdcg$1dq$1@Jupiter.Mcs.Net> <erkyrathE8Dooz.L5E@netcom.com> <5ih385$r45$1@news.NL.net>
Date: Mon, 14 Apr 1997 03:41:26 GMT
Lines: 54
Sender: erkyrath@netcom2.netcom.com
Xref: news.lth.se comp.ai.games:8538 rec.arts.int-fiction:24477

Dirk Coppelmans (dcoppelm@solair1.inter.nl.net) wrote:
> erkyrath@netcom.com (Andrew Plotkin) wrote:

> >I've looked at the erasmatazz site and it looks extremely nifty. I don't 
> >think I can decide whether it's a Good Idea until I play the first few 
> >worlds that come out of it. It seems like it might have too many 
> >personality attributes hardwired -- or maybe I'm nuts.

> Sounds like you're happy with the tools you have right now.
> But why not having an open mind on new developments. 

You're reading something into my post that I didn't intent. I have nothing
against new developments. And as for an open mind -- I can't decide
whether it's good until I try it. I don't think I can get any more open
than that. :)

> I think this engine has a lot of potential. OK, maybe limited
> in its current (very preliminary) version, but the ideas behind 
> it make sense. 

And are very nifty.

> I seriously believe that engines that provide more high level
> features like the personality stuff in Erasmatazz will provide 
> tools that are more powerful than the ones we have today. 

I seriously don't know.

> Sure, there is a long way to go, but this is a start from 
> IF *programming* to true IF *writing*. There is a difference.
> And maybe this implies that the IF community will change
> and attract more writers.

I think the success of Infocom-style IF has *been* the very good writers
that it has attracted. The problem is that thus far it's only
(successfully) attracted writers who are also programmers. 

I don't get the impression that this is the problem that Crawford is 
trying to solve here, though. I think (and this is only what I've picked 
up from his web site, so I could be wrong) that he started out desiring to
make a tool for non-programmers, but changed focus along the way -- the 
tool got so complex that using it was, well, programming. 

I can hardly argue with that -- it's the classic programmer's flaw, and 
I've given up trying to avoid it myself. In any case, this has nothing to 
do with erasmatazz's capabilities *as* a tool -- which I look forward to 
trying out, both as a player and a programmer.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From baf@max.tiac.net Wed Apr 16 09:39:25 MET DST 1997
Article: 24508 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in3.uu.net!199.0.65.182!news-in.tiac.net!posterchild!max.tiac.net!baf
From: baf@max.tiac.net (Carl Muckenhoupt)
Newsgroups: rec.arts.int-fiction
Subject: Thoughts on Time and So Far
Date: 15 Apr 97 20:18:40 GMT
Organization: The Internet Access Company, Inc.
Lines: 62
Message-ID: <baf.861135520@max.tiac.net>
NNTP-Posting-Host: max.tiac.net
Xref: news.lth.se rec.arts.int-fiction:24508

I was just writing some email to the author of "Time: All Things Come to an End",
and it occured to me that much of what I was saying would be of interest to
this newsgroup.  I missed the discussion of Time back when it was being discussed,
so I don't know what everyone else thought of it; I find it quite poorly designed.
The following explains, in part, why.  Includes mild spoilers for Time and So Far.



[bug reports deleted]

Finally, some general criticism.  I have, by now, finished your game, but only by making extensive use of 
Paul Godfrey's walkthrough.  Now, I am not a stupid person, nor am I unlearned in the ways of adventure 
games.  (Spellbreaker took me three days without hints.  The authors of "GC: A Thrashing Parity Bit of 
the Mind" say that I am the first person to solve it unaided.)  Nor did I consult the hints frivolously, 
but referred to them only when reasonably certain that I was never going to figure out the answer.  Thus, 
I think I am justified in saying that much of your game is unduly obscure.  You have probably heard this 
before, and may even have taken steps to remedy matters, but it is not a problem easily solved.

Consider the machine in Atlantis.  To activate it, you have to hit it.  Is this an unreasonable thing to 
expect the player to try?  Well, I didn't think of trying it.  But also consider: In Andrew Plotkin's 
excellent game "So Far", there comes a point where you also have to think of hitting a box in order to 
produce a sound.  On the face of it, hitting a recalcitrant machine seems more intuitive than using a box 
as a drum - especially since the machine is something that you know you want to activate, whereas there's 
no reason to think you need a drum in So Far until you try it and observe the effects.  So why did I try 
hitting the box and not the machine?

In part, it's context.  The box is not the only percussion instrument in So Far; there are drummers at a 
tribal dance you witness, and there is a sculpture in a park that produces pleasing tones when struck.  
The sculpture is described in enough detail that the player wants to fiddle with it, and its structure 
(taut wires and hanging pans) makes it almost inevitable that the player will try hitting it.  This gets 
the player thinking in percussive terms.  The machine in Time, on the other hand, is alone; nothing else 
in the game, as far as I know, invites hitting or responds positively to being hit  - on the few 
occasions where it produces anything but a default response, the player is punished for trying it.

Consider also the thought process leading up to the solution.  Hitting the box in So Far is done in a 
spirit of exploration and experiment - and, as pointed out above, the author goes to some pains to guide 
the player's experiments along certain lines.  Hitting the machine in Time, on the other hand, can only 
be motivated by a desire to solve a specific puzzle.  Now, the machine has an access panel, by means of 
which the player must make some repairs, and a plastic box into which items can be put.  There is no 
indication what sort of thing should be put in the box, or what the machine will do with it - these are 
things the player must discover, by experiment, once he or she has figured out how to activate the 
machine.  Not knowing this, however, the player is bound to spend time trying to activate the machine by 
putting various items in the container, or, when that fails, making futile attempts at further repairs 
via the panel.  In short, where So Far subtly guides the player towards the solution, Time guides the 
player away from it.

There are other considerations as well.  The box in So Far is acquired early in the game, and the player 
will probably spend time fiddling with it over the course of the game, searching for ways to open it, 
when frustrated by other puzzles.  Thus, it is entirely possible that the player will try hitting it 
before finding the sculpture and well before it becomes relevant.  This is hardly the case for the 
machine.  I could go on and on - indeed, I already have.  This is but one example of Time's weakness, and 
a relatively innocuous one at that.  What I'm trying to point out is that making puzzles work (and a 
puzzle which the player feels compelled to cheat on is one that has failed, IMHO) is a gestalt process.  
Seemingly irrelevant factors contribute vastly to the player's experience of the thing.  It is doubtful 
that many of the puzzles in Time could be improved without major reworking of their contexts - in other 
words, rewriting the game from the ground up.  This is a pity, as a great deal of effort has obviously 
been put into the game as it stands.

-- 
Carl Muckenhoupt              | Text Adventures are not dead!
baf@tiac.net                  | Read rec.[arts|games].int-fiction to see
http://www.tiac.net/users/baf | what you're missing!


From erkyrath@netcom.com Wed Apr 16 09:40:15 MET DST 1997
Article: 24514 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.eng.convex.com!cs.utexas.edu!swrinde!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Thoughts on Time and So Far
Message-ID: <erkyrathE8p9vv.Hsy@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <baf.861135520@max.tiac.net>
Date: Tue, 15 Apr 1997 22:16:43 GMT
Lines: 103
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24514

Carl Muckenhoupt (baf@max.tiac.net) wrote:

> I missed the discussion of Time back when it was being discussed, so I
> don't know what everyone else thought of it; I find it quite poorly
> designed. The following explains, in part, why.  Includes mild spoilers
> for Time and So Far. 

Hm. This is interesting enough that I will give into the temptation to 
talk about my own game. Even bigger spoilers for So Far ahead...

(note: long lines in postings suck. 'nuff said.)





> Consider the machine in Atlantis.  To activate it, you have to hit it. 
> Is this an unreasonable thing to expect the player to try?  Well, I didn't
> think of trying it.  But also consider: In Andrew Plotkin's excellent game
> "So Far", there comes a point where you also have to think of hitting a box
> in order to produce a sound.  On the face of it, hitting a recalcitrant
> machine seems more intuitive than using a box as a drum - especially since
> the machine is something that you know you want to activate, whereas
> there's no reason to think you need a drum in So Far until you try it and
> observe the effects.  So why did I try hitting the box and not the machine? 

> In part, it's context.  The box is not the only percussion instrument in
> So Far; there are drummers at a tribal dance you witness, and there is a
> sculpture in a park that produces pleasing tones when struck.  The
> sculpture is described in enough detail that the player wants to fiddle
> with it, and its structure (taut wires and hanging pans) makes it almost
> inevitable that the player will try hitting it.  This gets the player
> thinking in percussive terms.  The machine in Time, on the other hand, is
> alone; nothing else in the game, as far as I know, invites hitting or
> responds positively to being hit - on the few occasions where it produces
> anything but a default response, the player is punished for trying it. 

> Consider also the thought process leading up to the solution.  Hitting
> the box in So Far is done in a spirit of exploration and experiment - and,
> as pointed out above, the author goes to some pains to guide the player's
> experiments along certain lines. [...]

> There are other considerations as well.  The box in So Far is acquired
> early in the game, and the player will probably spend time fiddling with it
> over the course of the game, searching for ways to open it, when frustrated
> by other puzzles.  Thus, it is entirely possible that the player will try
> hitting it before finding the sculpture and well before it becomes
> relevant. [...]

Oookay. The interesting thing about this is that hitting the box is a
*third-rate* solution to that particular problem. That is, it's an
alternate solution; and the "preferred" solution can itself be done "right"
or "wrong". The second-rate solution -- well, I said there were spoilers
here -- is to "sing" while holding the box. (This is more effective than
hitting the box; you don't have to do it as often.) The first-rate 
solution -- I won't say what it is, but it's even more effective; you only
have to do it once. 

So no, I really wasn't trying to guide players towards percussion. I just
like bells. I thought the musical disc sculpture was a neat idea, and
hitting it obviously has to do something. (And the sculpture has other
connections of meaning, of course -- too many to describe in this 
margin. :)

(And I put in responses to all sorts of actions -- many of which had 
nothing to do with anything the player *needed* to do.)

On the other hand, I *was* trying to guide players towards the idea of 
musical instruments, and sound in general. So in that sense (hearing, heh 
heh) you're quite right. In a more specific sense, hitting musical 
instruments -- not exactly. Of course, I don't rule out the possibility 
that my own subconscious was being sneaky. That happens a lot. 

(And I was *definitely* trying to evoke a spirit of exploration and 
experiment. That is, after all, the plot hook for the entire storyline.)

What about "sing" -- did I try to lead players towards that? Not a lot,
although the grasslands "tribal" musicians are singing as well as drumming,
and there's an even more explicit clue if you examine them. I mostly
intended players to pick up on the general theme of music and sound in the
game, and the very specific theme of important sound in the puzzle where
you need the box. 

In feedback, I found that most players picked up on "sing". Fewer picked 
up on the first-rate solution, and many of *them* thought it was unfair or 
insufficiently hinted at. 

On the third hand, or fourth or however many we've got here: this is why I
allowed multiple solutions. You didn't figure out "sing", but you got
through anyway, and it was satisfying to you (because the solution you
found made sense) and to me (because even though I think of it as a
non-ideal solution, it still wound up making the correct connection --
sound as a tool.)

So -- you tell me whether you've changed your mind. I don't think I was 
planning nearly as carefully as you think I was. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Wed Apr 16 19:43:32 MET DST 1997
Article: 24535 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] Newbie wants followers
Message-ID: <erkyrathE8qoD2.MvH@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5j0dh2$719@hiway1.exit109.com> <3353CE54.446B9B3D@Earthling.net> <5j2nt0$lhv@hiway1.exit109.com>
Date: Wed, 16 Apr 1997 16:27:01 GMT
Lines: 39
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24535

John Ruschmeyer (jruschme@hiway1.exit109.com) wrote:
> Let's say I have a gun object and that I have defined a Fire action for it.
> This Fire action generates a ShootAt fake action which assesses damage, etc.
> to the target object.

> Now, suppose I want to have an NPC pick up the gun and fire it at something.
> Ho do I set it up so that the NPC, rather than the player, is the one firing
> the gun, etc?

The library has no direct support for this kind of thing. (The "actor" 
variable is used by the parser, not the verb library. If you type "fred, 
take the gun" then the parser gets run with actor==fred, but the outcome 
is to run fred's orders property. It doesn't go into the usual 
before/TakeSub/after process. The TakeSub and associated functions work 
strictly on the player.)

I think the best thing to do (not terrific, but effective) is to write a 
fake action "NPCTake". And then "NPCFireGun". The latter can probably use
your existing ShootAt fake action, by calling <ShootAt target> as usual.

This is a pain in the butt, since NPCTake will probably duplicate much of 
the code from TakeSub (well, RTakeSub, actually, since that's what does 
most of the work.) This is inevitable, however. The library does not 
include messages like 
  "Fred already has that."
  "Fred tries to take the gun, but it's fixed in place."
  "Fred is carrying too many things already."
and for a full implementation of NPCTake, you'd really need them.

The sane approach is to write a minimal NPCTake -- do only the checks 
absolutely necessary. If you know the NPC is only going to pick up the 
gun, and nothing else, it can be fairly simplistic.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From dylanw@demon.net Thu Apr 17 23:58:49 MET DST 1997
Article: 24552 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!dispatch.news.demon.net!demon!crucigera.fysh.org!news.fysh.org!not-for-mail
From: dylanw@demon.net (Dylan O'Donnell)
Newsgroups: rec.arts.int-fiction
Subject: Re: Hey IF fans: Readme =)
Date: 17 Apr 1997 09:25:57 +0100
Organization: Spod East
Sender: psmith@fysh.org
Message-ID: <5j4mqm$s2c$1@crucigera.fysh.org>
References: <5incma$5tt@cdc2.cdc.net> <ant1415060b0c4bn@arnod.demon.co.uk> <5ivlu0$gqj$1@crucigera.fysh.org> <dsglasser-1604971801450001@11.ts1.icdc.com>
NNTP-Posting-Host: crucigera.fysh.org
X-NNTP-Posting-Host: crucigera.fysh.org
Lines: 26
Xref: news.lth.se rec.arts.int-fiction:24552


In article <dsglasser-1604971801450001@11.ts1.icdc.com>,
David Glasser <dsglasser@hotmail.com> wrote:

>Just wondering...What _is_ demon?  Everywhere I look, there's a 'demon'
>site!  There's Graham's site, and Jools' site, and several I've seen over
>at rec.arts.tv.mst3k.misc, and this one, and that...is it an ISP, or a
>province of England :-) (I'm just a dumb American who knows nothing about
>England except it's across that big blue wet thing.)

<grin> It's not a province of England yet, unless Cliff's megalomaniac
plans are further along than we've been told... It's an ISP, one of
the oldest (1992) and largest (100,000 punters^Wcustomers) in the
UK (covering all of it - Britain lends itself rather better to national
coverage than the US), and the company I happen to work for. It also
tends to have less of a blinkered "you don't have a PC? Duh... we dunno
anything about that" view than most, which means there's a higher
proportion of Demon users in r*if (IF being an area where "other" systems
seem to be competing on a much more level playing field) than you might
otherwise expect.

Can't explain the MiSTies, though...

-- 
Dylan O'Donnell
http://www.fysh.org/~psmith/ or http://www.pedantic.demon.co.uk/
Demon Internet Ltd (http://www.demon.net/), slave deck


From erkyrath@netcom.com Fri Apr 18 09:49:08 MET DST 1997
Article: 24577 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Am I stealing a puzzle from any other game?
Message-ID: <erkyrathE8sz56.LAI@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <01bc4b74$fbac64c0$e3a6b5c7@rhorn>
Date: Thu, 17 Apr 1997 22:15:06 GMT
Lines: 23
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24577

Devin Horn (darkvari@seanet.com) wrote:
> I wan't to put a puzzle into a game I'm working on where you have to find
> pieces from a shredded paper.  Each piece contains directions for
> completing a maze.  When all the pieces are found and put together, you
> know what directions to go through the maze.  Have there been any other
> puzzle like this before?

I can't recall any text game that has this. It's been in puzzle-books 
(_Treasure_, I think) and it's such an obvious trick in a graphical game 
that I'm certain it's been used in one. Can't think of one off-hand, though.

For what it's worth, there's no such thing as "stealing" a puzzle. Ideas 
get reused. "Weather" copied a puzzle from _Unnkulia 2_, practically 
identically, and nobody even squeaked about it. (Or maybe nobody's played 
U2 in too long... :-) I claim innocence in that case -- *I* hadn't played 
U2 at the time I wrote "Weather", and came up with it entirely on my own.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mkkuhner@phylo.genetics.washington.edu Fri Apr 18 09:49:30 MET DST 1997
Article: 24580 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!newsfeeds.sol.net!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Am I stealing a puzzle from any other game?
Date: 18 Apr 1997 00:44:14 GMT
Organization: University of Washington, Seattle
Lines: 24
Message-ID: <5j6g4u$d5g@nntp5.u.washington.edu>
References: <01bc4b74$fbac64c0$e3a6b5c7@rhorn> <erkyrathE8sz56.LAI@netcom.com>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:24580


Devin Horn (darkvari@seanet.com) wrote:
> I wan't to put a puzzle into a game I'm working on where you have to find
> pieces from a shredded paper.  Each piece contains directions for
> completing a maze.  When all the pieces are found and put together, you
> know what directions to go through the maze.  Have there been any other
> puzzle like this before?

The PC game _Fool's Errand_ (a collection of word and logic puzzles with 
static pictures and a frame story) features a map which is obtained
in bits and must be put together.  I quite liked this puzzle; the map
was fun to put together and a nice measure of progress.

Don't worry about stealing it.  There aren't that many basic puzzles;
as long as your game flows well people will enjoy it even if some of
the puzzles are recycled.

Incidentally, _Errand_ contains my vote for "most unfair puzzle".  I had to
ask about it on the Net, and got three responses all of which said
"Here is how I solved it, but I'm sure that was cheating."  All three
solutions were the same, and as far as I know that's the only solution.
(It involves using a detail of the interface that I would not normally
consider part of the game.)

Mary Kuhner mkkuhner@genetics.washington.edu


From graham@gnelson.demon.co.uk Fri Apr 18 14:07:40 MET DST 1997
Article: 24604 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: one name to rule them all...(was: 'Places' verb)
Date: Thu, 17 Apr 1997 20:33:01 +0100 (BST)
Organization: none
Message-ID: <ant1719011cbM+4%@gnelson.demon.co.uk>
References: <5ifsc3$ouu$1@studs2.sci.kun.nl> <ant091944b49c4bn@arnod.demon.co.uk> <334CD38A.5EDF@earthlink.net> <LxvI0JA8BTTzEw$d@highmount.demon.co.uk> <334D4153.17E8@iusb.edu.delete-me> <Pine.SGI.3.95L.970417134041.10319A-100000@ebor.york.ac.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 32
Xref: news.lth.se rec.arts.int-fiction:24604


In article <Pine.SGI.3.95L.970417134041.10319A-100000@ebor.york.ac.uk>,
Bruce of Iniquity <URL:mailto:dmss100@york.ac.uk> wrote:
> 
> On Thu, 10 Apr 1997, Bruce Kinyon wrote:
> 
> >This is starting to sound like Monty Python's "Australian philosophers
> >sketch". So on that note, let me propose that we all be named "Bruce".
> >It would make things less confusing.

(Bruce here teaches Hegelian philosophy, and is also in charge of
the sheep dip.  Etc., etc.)

I was going to change my name to Bruce, until I came across:

   "The story of King's Quest II: Romancing the Throne, for example,
    dealt with King Graham having to rescue a damsel in distress
    from a far-away tower. She then became so enraptured with him 
    that she married him on the spot."

This is the kind of thing I'm keen to encourage, and King Bruce
just doesn't have that regal tone to it.

[From Matthew Murray's vague but interesting discussion of Sierra's
point-and-click games: see

    http://www.wwu.edu/~n9641343

for more.  Quite worth a link for IF-reviews-and-theory pages.]

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Fri Apr 18 18:46:51 MET DST 1997
Article: 24619 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!newsfeed.direct.ca!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Am I stealing a puzzle from any other game?
Message-ID: <erkyrathE8uDMq.BKs@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <01bc4b74$fbac64c0$e3a6b5c7@rhorn> <erkyrathE8sz56.LAI@netcom.com> <5j6g4u$d5g@nntp5.u.washington.edu>
Date: Fri, 18 Apr 1997 16:25:38 GMT
Lines: 30
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24619

Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:

> Incidentally, _Errand_ contains my vote for "most unfair puzzle".  I had to
> ask about it on the Net, and got three responses all of which said
> "Here is how I solved it, but I'm sure that was cheating."  All three
> solutions were the same, and as far as I know that's the only solution.
> (It involves using a detail of the interface that I would not normally
> consider part of the game.)

Ok, give. Which puzzle? (SPOILERS to follow, etc.)

Fool's Errand was an early inspiration to my game-writing career. Not as 
early as Infocom, I mean, but it actually got me started putting together 
puzzle-games in college. (The Praser 5 thing was the immediate result. Not 
that you can tell from the Tarot symbolism, or anything. :)

I liked it because it was a black-box kind of puzzle, like those Chris
Manson puzzle books. No rules, no instructions, and therefore anything is
fair; you must pay attention to everything. So I'm curious what you thought
was outside the bounds. 

(The Infocom games were definitely *not* this way; that's the whole point 
of the mimesis discussion, etc.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mkkuhner@phylo.genetics.washington.edu Fri Apr 18 21:07:03 MET DST 1997
In article <erkyrathE8uDMq.BKs@netcom.com> erkyrath@netcom.com (Andrew Plotkin) writes:

>Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:

>> Incidentally, _Errand_ contains my vote for "most unfair puzzle".  I had to
>> ask about it on the Net, and got three responses all of which said
>> "Here is how I solved it, but I'm sure that was cheating."  All three
>> solutions were the same, and as far as I know that's the only solution.
>> (It involves using a detail of the interface that I would not normally
>> consider part of the game.)

>Ok, give. Which puzzle? (SPOILERS to follow, etc.)

Spoilers for _Fool's Errand_ below....













We solved Death's puzzle (where you have to tag the white eye before
the red eye tags you) by pulling a pull-down menu (with "save game" and
so forth on it, Mac-style) until it was nearly on top of the white eye,
then whisking across.  The game froze while a menu was being pulled, so
this manuver let you outrun the red eye.

This struck me as the moral equivalent of having to use "save" or
"verbose" to solve an Inform game.  Is there another solution?
My thought when I was playing was that it might be solvable on
a slower machine, but I was playing it on a Pentium.  This annoyed
me enough to ask for help, yielding the given technique.

I can see the argument that beating Death should take some degree of
thinking outside the lines, but I still found the puzzle inesthetic.

>Fool's Errand was an early inspiration to my game-writing career. Not as 
>early as Infocom, I mean, but it actually got me started putting together 
>puzzle-games in college. (The Praser 5 thing was the immediate result. Not 
>that you can tell from the Tarot symbolism, or anything. :)

That's certainly what I thought of when I looked at Praser.  Only your
puzzles seemed significantly harder. :-)

Mary Kuhner mkkuhner@genetics.washington.edu


From erkyrath@netcom.com Sat Apr 19 22:43:07 MET DST 1997
Article: 24633 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news-peer.sprintlink.net!news.sprintlink.net!sprint!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Am I stealing a puzzle from any other game?
Message-ID: <erkyrathE8uHoA.25G@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <erkyrathE8sz56.LAI@netcom.com> <5j6g4u$d5g@nntp5.u.washington.edu> <erkyrathE8uDMq.BKs@netcom.com> <5j897q$qsg@nntp5.u.washington.edu>
Date: Fri, 18 Apr 1997 17:52:58 GMT
Lines: 80
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24633

Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:
> In article <erkyrathE8uDMq.BKs@netcom.com> erkyrath@netcom.com (Andrew Plotkin) writes:

> >Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:

> >> Incidentally, _Errand_ contains my vote for "most unfair puzzle". 

> Spoilers for _Fool's Errand_ below....

> 











> We solved Death's puzzle (where you have to tag the white eye before
> the red eye tags you) by pulling a pull-down menu (with "save game" and
> so forth on it, Mac-style) until it was nearly on top of the white eye,
> then whisking across.  The game froze while a menu was being pulled, so
> this manuver let you outrun the red eye.

Ok, I remember that. It worked the same way on the Mac version.

> This struck me as the moral equivalent of having to use "save" or
> "verbose" to solve an Inform game.  

Exactly. The point is, an Inform game has conventions of play. There is a 
mutually-agreed-upon "way to play the game", which includes the 
assumption that this is a simulation of a fictional, consistent world; the 
character in the story could get through the fictional situation, and you 
win the game by finding how he/she does it. That's what I meant when I said 
mimesis.

Fool's Errand simply lacks that assumption, or any assumptions. (You 
recall the thread about the "Prisoner" game, where I opined that the game 
was deliberately shipped with a bug in it, and part of the winning was to 
figure this out and fix the bug.) Nothing is unfair.

I'm currently fooling around with "MadVenture" on my Apple II emulator. It 
also stomps a few conventions, although within the overall context of 
traditional IF. I may go so far as to port it to Inform. Just for fun.

> Is there another solution?
> My thought when I was playing was that it might be solvable on
> a slower machine, but I was playing it on a Pentium.  This annoyed
> me enough to ask for help, yielding the given technique.

No, I first played Fool's Errand on a Mac SE, and you still couldn't 
outrace the thing.

> I can see the argument that beating Death should take some degree of
> thinking outside the lines, but I still found the puzzle inesthetic.

Well, that's a separate problem. :) I treasure the memory of sitting in a 
computer cluster late at night, with a stack of paper, scribbling notes.
Every time I got a piece of the final puzzle, another sheet would get 
crumpled up and tossed over my shoulder.

> >Fool's Errand was an early inspiration to my game-writing career. Not as 
> >early as Infocom, I mean, but it actually got me started putting together 
> >puzzle-games in college. (The Praser 5 thing was the immediate result. Not 
> >that you can tell from the Tarot symbolism, or anything. :)

> That's certainly what I thought of when I looked at Praser.  Only your
> puzzles seemed significantly harder. :-)

Like I said, it was an early effort.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From daly@PPD.Kodak.COM Sat Apr 19 22:43:13 MET DST 1997
Article: 24634 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!ifi.uio.no!hermod.uio.no!uninett.no!news.algonet.se!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!cam-news-feed5.bbnplanet.com!news.bbnplanet.com!bloom-beacon.mit.edu!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: "Cheating" puzzle from FE (WAS Re: Am I stealing a puzzle from any other game?)
Date: 18 Apr 1997 17:57:34 GMT
Organization: Eastman Kodak Company
Lines: 61
Message-ID: <5j8cme$go0$1@kodak.rdcs.Kodak.COM>
References: <5j6g4u$d5g@nntp5.u.washington.edu> <erkyrathE8uDMq.BKs@netcom.com> <5j897q$qsg@nntp5.u.washington.edu>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com
Xref: news.lth.se rec.arts.int-fiction:24634

In article <5j897q$qsg@nntp5.u.washington.edu> mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) writes:
>
>Spoilers for _Fool's Errand_ below....



>We solved Death's puzzle (where you have to tag the white eye before
>the red eye tags you) by pulling a pull-down menu (with "save game" and
>so forth on it, Mac-style) until it was nearly on top of the white eye,
>then whisking across.  The game froze while a menu was being pulled, so
>this manuver let you outrun the red eye.

That's exactly what you have to do.  That isn't cheating, IMHO, it's
lateral thinking.  

What did you think about the "fisherman" puzzle, where you had to
click on the button that kept hopping away from your mouse?  I
think that puzzle is even more unfair, since it is the only time
in "Stage One" that you have to pay attention to the text to get
hints.

To me, the most unfair puzzle was the pre-Despair puzzle where you
had to build the crossword from the individual levels.  The first
wave had you building three five-letter words from fifteen letters,
but it didn't make it clear that switching letters between the
words wasn't necessary, and once you start down THAT road, you're
stuck forever.  Even if you come up with the correct three words
(and, after an exhaustive wordsearch, I can tell you that it isn't
unique), you would have to Know that the words need to be in a
specific order too, and there isn't any clue of that.  All they had
to do was to disable between-word switching on that first wave and
it would have been fair, too.

>This struck me as the moral equivalent of having to use "save" or
>"verbose" to solve an Inform game.  Is there another solution?
>My thought when I was playing was that it might be solvable on
>a slower machine, but I was playing it on a Pentium.  This annoyed
>me enough to ask for help, yielding the given technique.

Yes, I know what you mean.  I replayed the game on my Penty a few
months ago and thought "Gee, after that method fails a few times,
I'm not sure a first-time player would think to stick with it."
Guess I was right. :-)

For what it's worth, on a 386, you have plenty of time to make the
connection.  They didn't build it to be a hand-eye coordination puzzle,
just to get you to realize that you had to take advantage of the UI
to solve the puzzle.

>I can see the argument that beating Death should take some degree of
>thinking outside the lines, but I still found the puzzle inesthetic.

<shrug> I think that's my favorite puzzle in the game.  Certainly
the one that I remember the most fondly.  Diff'rent strokes, I guess.

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From erkyrath@netcom.com Mon Apr 21 08:53:58 MET DST 1997
Article: 24692 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Thoughts on Time and So Far
Message-ID: <erkyrathE8y4xE.HFu@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <baf.861135520@max.tiac.net> <3359ebe2.324832589@news.u-net.com>
Date: Sun, 20 Apr 1997 17:08:02 GMT
Lines: 101
Sender: erkyrath@netcom18.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24692

Paul Avery (scorpion@deepthought.sirius.com) wrote:
> Well, I knew my posting would be taken as controversial, and would get
> some response, but only Andrew seems to have even begun to perceive
> what I was getting at.
>
> For a start, Fredrik, could you demonstrate one iota of *intolerance*
> in my posting? Of course you couldn't, as it doesn't exist - you
> simply displayed a youthful knee-jerk reaction.

Do you really want to get into this? Not everything I thought went into 
my post. Let's lay off personal accusations.

> And this leads to the point of my original posting, which is that this
> newsgroup (together with rgif) is highly self-selected and cannot, by
> definition, be representative of the IF-playing public at large.

I did not understand this point at all, when I read your original post. 

> As an
> extrapolation from this, both criticism and praise within the group
> carry little weight, and cannot be taken as an indication whether or
> not any single work of IF will "succeed" or "fail" in the real world.

I think your concept of the "real world" is naive. For example...

> It's all very well patting one another on the back and saying, "Great
> game - Wonderful, cutting-edge, state-of-the-art IF" and so on, but at
> the end of the day r*if is a small pond. Try putting some of the
> acclaimed games on to a Compuserve adventure game forum and see how
> often it's downloaded.

...In the "real world", Mozart is a failure -- if you insist on looking at
it that way. Go into a randomly-selected CD store, and you'll note that
the "classical" section is about a twelfth the size of the "pop/rock"
section. Does this mean that Neville Mariner cries himself to sleep at
night? Of course not; he's interested in how *classical music fans* react
to his work. 

So tell me, are you talking about *text adventure* fans, or *computer 
game* fans, or *computer users*, or *fans of any kind of English prose*, 
or what? Within each of those group, I can make a guess how popular _So 
Far_ is. By the end, it's a pretty small number. As a friend of mine once 
said -- no matter who you are and what you do, a billion Chinese people 
don't give a shit.

Several TADS and Inform works are posted on the Info-Mac archive, which 
is the largest Mac shareware/freeware archive, and I think comparable to 
the Compuserve forum. I don't have download stats, but questions about 
them turn up every once in a while, on the Mac game newsgroups. I don't 
think they're being totally snubbed. (Perhaps one of the authors who asks 
for shareware fees could post stats about who registers these things.)

> So how on Earth is a specialist newsgroup not representative of the
> specialty at large? I base this observation on two things - Firstly,
> of all the contacts I have made in the field of IF over a period of
> many years, there are exactly *three* who access r*if, and in the case
> of two of them this is an infrequent occurrence. There are lots of
> people out there who own computers but don't access the 'net.
> Secondly, how often do you see postings from people such as Steve
> Meretzky, Brian Moriarty, the Magnetic Scrolls authors, and so on.

A couple of Infocom authors are known to lurk here, although they post 
rarely.

But I think we are very far from each other's opinion of what "the
specialty" is. Text games, or story-games in general? This is really a
text IF newsgroup; we don't pretend otherwise. (I mean, we could
theoretically be writing graphics games, but we're not, and we really only
discuss graphical games in terms of how they affect our topic -- the
aspects that are common to all story games.)

(I know exactly why _So Far_ is not as big a hit as current graphical
games; it's because I can't spend millions of dollars on CGI rendering and
then hire Tia Carriere to pose for a camera wearing a low-cut jumpsuit.)

So, of all the contacts you have in the field of *text* IF, how many fail 
to frequent this newsgroup? And I mean people who are working on text IF 
now, not in 1985. 

One name that was just discussed here is Chris Crawford, and the
Erasmatron stuff. Is that the kind of thing you mean? If so, why on earth
did you start out talking about "enjoying the kind of music you've always
enjoyed", when his concept bears practically no resemblance to anything
Infocom did? It seems to be a *much* more radical innovation than anything
in _So Far_. 

And if this newsgroup is so far out of touch, how come you liked _Time_? 
There's plenty of that kind of stuff in TADS and Inform. I never claimed 
I was *the* future of IF -- only that I wanted to try out a nifty idea.

In fact, I don't think I understand your point at all. If this post seems 
to go off on a lot of tangents, it's because I'm trying to figure out all 
the possible points you might be making, and respond to all of them.

--Z


-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From svanegmo@undergrad.math.uwaterloo.ca Mon Apr 21 08:54:30 MET DST 1997
Article: 24700 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.maxwell.syr.edu!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!torn!kwon!watserv3.uwaterloo.ca!undergrad.math.uwaterloo.ca!svanegmo
From: svanegmo@undergrad.math.uwaterloo.ca (Stephen van Egmond)
Subject: Re: Thoughts on Time and So Far
Sender: news@undergrad.math.uwaterloo.ca (news spool owner)
Message-ID: <E8yCus.2uv@undergrad.math.uwaterloo.ca>
Date: Sun, 20 Apr 1997 19:59:16 GMT
References: <baf.861135520@max.tiac.net> <3359ebe2.324832589@news.u-net.com>
Nntp-Posting-Host: landen.math.uwaterloo.ca
Organization: University of Waterloo
Lines: 65
Xref: news.lth.se rec.arts.int-fiction:24700

Paul Avery <scorpion@deepthought.sirius.com> wrote:
>And this leads to the point of my original posting, which is that this
>newsgroup (together with rgif) is highly self-selected and cannot, by
>definition, be representative of the IF-playing public at large. As an
>extrapolation from this, both criticism and praise within the group
>carry little weight, and cannot be taken as an indication whether or
>not any single work of IF will "succeed" or "fail" in the real world.
>
>It's all very well patting one another on the back and saying, "Great
>game - Wonderful, cutting-edge, state-of-the-art IF" and so on, but at
>the end of the day r*if is a small pond. Try putting some of the
>acclaimed games on to a Compuserve adventure game forum and see how
>often it's downloaded.

I'm not sure how Compuserve is any more "real world" than Usenet or, say,
rgif.  There are a lot of people who frequent rgif who don't frequent
raif even though they know it's here.  Probably too ivory-tower for
them.  Discussion on rgif has forever been more practical and
down-to-earth thhan here.

When I think of rec.arts.int-fiction (and, by extension the Web site I'm
trying to put together containing some of its collected knowledge and
disagreeements), I think of the dilemma faced by the narrator of Zen and
the Art of Motorcycle Maintenance -- except his field was rhetoric and
technical writing.   

At first, there were adventure games which were, in essence programming
exercises; you had games with bugs (logical contradictions) and you had
games with relatively few bugs.  There was a clear classical notion of
"good" and "bad" in assessing the game.  But the form of IF (here's a
description, now what are you going to do?) includes a lot more than that,
and people here have within the past few years noticed that there is more
to a work of IF than just classical beauty, there's a romantic side to it
too that deals with the surface of the game.  We try to break this down
into plot, characterization, atmosphere, mimesis, and so on -- not because
these rules are True, but because in many cases they're necessary (but in
themselves insufficient) for a good work.

>So how on Earth is a specialist newsgroup not representative of the
>specialty at large? I base this observation on two things - Firstly,
>of all the contacts I have made in the field of IF over a period of
>many years, there are exactly *three* who access r*if, and in the case
>of two of them this is an infrequent occurrence. There are lots of
>people out there who own computers but don't access the 'net.

>Secondly, how often do you see postings from people such as Steve
>Meretzky, Brian Moriarty, the Magnetic Scrolls authors, and so on.

I don't think Mr. Moriarty is in this industry any more, and I'm confused
whether Magnetic Scrolls is one of the old-timer companies or is still in
business.    (I should know these things, I'm the rgif faq handler.)

On the other hand, it's worth noticing that many of the people
working in the "field" of IF (I suspect you mean the industry) are
working on stuff that sells, whereas we prefer to stick to our belief that
we're working on what's good.

	"What is good, Phaedrus, and what is not good - need we ask anyone
	to tell us these things?"

        ,,,
       (. .)
+--oOO--(_)--OOo-----+
| Stephen Van Egmond +- svanegmo@undergrad.math.uwaterloo.ca +--- -   -   -
| Bring your brain.


From mythago@agora.rdrop.com Mon Apr 21 08:55:27 MET DST 1997
Article: 24709 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!newsxfer3.itd.umich.edu!rill.news.pipex.net!pipex!tank.news.pipex.net!pipex!iafrica.com!psgrain!hermes.rdrop.com!not-for-mail
From: mythago@agora.rdrop.com (Laurel Halbany)
Newsgroups: rec.arts.int-fiction
Subject: Re: Thoughts on Time and So Far
Date: Mon, 21 Apr 1997 00:42:53 GMT
Organization: RainDrop Laboratories/Agora(sm)
Lines: 79
Message-ID: <335a2c80.1342586@hermes.rdrop.com>
References: <baf.861135520@max.tiac.net> <3359ebe2.324832589@news.u-net.com>
NNTP-Posting-Host: slip-dd.rdrop.com
X-Newsreader: Forte Free Agent 1.1/16.230
Xref: news.lth.se rec.arts.int-fiction:24709

scorpion@deepthought.sirius.com (Paul Avery) wrote:

>For a start, Fredrik, could you demonstrate one iota of *intolerance*
>in my posting? Of course you couldn't, as it doesn't exist - you
>simply displayed a youthful knee-jerk reaction.

Well, *I* certainly found the following to be intolerant and
patronizing:

>The counter argument is, of course, that people *do* enjoy playing
>these games, but of course there will always be acolytes willing to
>pay obeisance, and one is reminded of the Emperor's New Clothes.

(cut from your original post)

Now, unless you have some truly obscure meaning I'm overlooking, the
"Emperor's New Clothes" line is generally a reference to people who
collectively agree to something nonexistent or bad being true and
good, because everybody else does and they're afraid to be different.
"Acolytes willing to pay obesiance" suggests that the respondents are
hoping to be like the person discussed, and are offering homage.

So it seemed to *me* that this comment of yours meant that the only
reasons *others* might actually claim to like these games you find
awful are

1) they are aspiring programmers and want to be like Andrew Plotkin,
so they praise him

2) everybody really thinks the game was awful but we are all afraid to
say so lest we be thought of as I-F dunderheads.

Now, perhaps you did not *mean* this to be patronizing and intolerant,
but I don't see that finding such in your post was "knee-jerk" or
farfetched.

>And this leads to the point of my original posting, which is that this
>newsgroup (together with rgif) is highly self-selected and cannot, by
>definition, be representative of the IF-playing public at large. As an
>extrapolation from this, both criticism and praise within the group
>carry little weight, and cannot be taken as an indication whether or
>not any single work of IF will "succeed" or "fail" in the real world.
>
>It's all very well patting one another on the back and saying, "Great
>game - Wonderful, cutting-edge, state-of-the-art IF" and so on, but at
>the end of the day r*if is a small pond. Try putting some of the
>acclaimed games on to a Compuserve adventure game forum and see how
>often it's downloaded.

....So r.a.i-f is *not* the "real world," but a Compuserve forum *is*
the "real world"? What definitions are you using here--volume? Ease of
accessibility? Numerosity of sites? And success is defined as the
number of downloads from a particular site?

As far as I know, there is nothing preventing anybody from posting to
a Compuserve forum (except perhaps not having a Compuserve account)
with their games--most of them are freely-distributable. And plenty of
them make their way from 'pond to pond,' as Matt Baringer
unfortunately discovered. 

Mostly, though, these games are a work of love; there is practically
no commercial market anymore. Nobody is writing to try and win over
adoring throngs of I-F groupies; nobody is expecting to be nominated
for a literary prize, or to resurrect Infocom. (These things might be
nice, but nobody is EXPECTING them.) So to say that a game is
pointless because it isn't as popular as, I don't know, "Doom" is
irrelevant. 

>Secondly, how often do you see postings from people such as Steve
>Meretzky, Brian Moriarty, the Magnetic Scrolls authors, and so on.

Have you looked at _XYZZYnews_ at all? Most of the 'old Implementors'
are no longer writing adventure games, or are not writing the sort of
i-f games that are part of r.a.i-f's discussion.

----------------------------------------------------------
Laurel Halbany
mythago@agora.rdrop.com
http://www.rdrop.com/users/mythago/


From egh@uclink4.berkeley.edu Mon Apr 21 09:45:07 MET DST 1997
Article: 24697 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer3.itd.umich.edu!agate!uclink4.berkeley.edu!egh
From: egh@uclink4.berkeley.edu ()
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Hypertext and MUDS (WAS Re: Announce: The Space Under the Window)
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Date: 20 Apr 1997 21:07:48 GMT
Organization: Lies, Inc.
Lines: 46
Message-ID: <5je0j4$7pv$1@agate.berkeley.edu>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <3359cd1b.7271477@news.netspace.net.au>
Reply-To: egh@uclink4.berkeley.edu
NNTP-Posting-Host: raisin.hip.berkeley.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24697 rec.games.int-fiction:22794

James Cole (jrcole@ozemail.com.au) wrote:

: How can you say that about Hypertext and MUDs? 

> Hypertext* 

>   When playing 'The Space Under the Window' I actually got the
>   impression that it was a lot like hypertext.  In fact, I don't see
>   any reason why it couldn't be implemented in hypertext.  If this
>   is the case,,,,

There is no reason it couldn't. The way it's done, it'd have to be
computer generated, not just a whole bunch of different files, but it
could be done.

>   Furthermore, I think that 'The Space Under the Window' (TSUW)
>   would be more suited to a medium such as hypertext.  As far as I
>   can tell, you can only refer to objects in TSUW.  More
>   particularly, only a subset of the ones displayed in the current
>   narritive on the screen.  This is the sort of thing which
>   hypertext's "restricted" interface is suited to.  Hypertext would
>   be a "cleaner", and more user friendly, interface than a prompt;
>   as you could just on "click" on the object you want to
>   "concentrate on".

I agree, except that I found that there was /no/ object in the game
that I couldn't refer to. None. I only got `You can't see that now.'
messages when I misspelled things.

>   Perhaps you're thinking of MUDs in terms of what they are now.
>   There is absoultely no reason why a multiplayer text based game
>   (as a very loose definition of a MUD) couldn't be, or contain, the
>   "next great thing in IF".

I have great respect for the potential of MUDs. I find them sort of
boring and depressing right now, but I respect the concept. Nothing
seperates the concept of a MUD from the concept of IF in my mind but
the fact that a MUD has multiple players. I would say also that
objects can be dynamically programmed, but this could be possible in IF,
too.

Has anybody tried programming a work of IF in LambdaMOO or something?
Distribute the database file or something? Doesn't seem like a very
good idea, but it's very experimental. :)
----- Erik Hetzner -----  In a perfect world we'd all sing in tune,
egh@uclink4.berkeley.edu  But this is reality so give me some room.


From jools@arnod.demon.co.uk Mon Apr 21 11:05:28 MET DST 1997
Article: 24657 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!uunet!in3.uu.net!207.172.3.52!feed1.news.erols.com!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: [Review] The Space Under the Window
Date: Sun, 20 Apr 1997 02:55:46 +0100 (BST)
Organization: Stephen Promulgation Society
Message-ID: <ant2001460b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 94
Xref: news.lth.se rec.arts.int-fiction:24657


TITLE  :  The Space Under the Window
AUTHOR :  Andrew Plotkin (erkyrath@netcom.com)
LICENCE:  Freeware
VERSION:  Release 2 / Serial number 970402
DETAILS:  (ftp://ftp.gmd.de/if-archive/games/infocom/sutwin.z5)
          Needs a Z-Machine interpreter,
          (ftp://ftp.gmd.de/if-archive/infocom/interpreters/)


"The Space Under the Window" was announced as an experimental work. 
Heed the warning!  As a game "Window" is slight, and will not satisfy. 
Considered for what it is, an experiment in techniques of interactive
storytelling, it is more interesting.

The narrative, such as it is, appears to involve two children, a boy
(the player) and a girl, playing grown-ups, and staging a candle-lit
dinner for two in their tree-house.  Apart from the small amount of
detective work necessary to come to this conclusion, the narrative is
mostly uninteresting, and plays second fiddle to the method of input,
the interface.

In traditional text adventures the player issues specific commands,
involving, in essence, a verb and, optionally, a direct object (and
optionally again, one or more indirect objects).  In other words, the
player informs the game of an action he wishes his character to take. 
The game, once it has decided the requested action is allowable,
responds by informing the player of the reaction(s) of the simulated
environment, or elements of that environment.  The process repeats to
the end of the game.

The approach taken here is that the player picks out elements of the
game-text, instead of giving the specific commands mentioned above.  The
precise action taken is then decided upon by the game itself.  Or, from
the game's instructions:
	Instead, your part is to type the names of objects (or
	attributes or aspects of objects) that you see in the narrative.
	When you refer to an object, it will be brought into greater
	prominence, changing the course of the narrative thread. Or it
	might be reduced to lesser stature, or removed entirely.

Thus, the first two moves will probably play like this:
	The window is closed, so you can't go inside.
	
	    ***
	
	>window
	
	
	The window is open, so you can go into the room.
	
	    ***
	
	>room
	
	
	The window is open, so you climb down inside. The table is set
	for two.
	
	    ***
	
	>

As is clear from this transcript, the approach severely curtails
interactivity.  Of course, such curtailment is present in all
interactive fiction, to some degree, but this particular interface makes
it infinitely more apparent; the player is never even under the illusion
of freedom of choice.

In fact, this interface most resembles a textual adaptation of the point
'n click interface used by such graphical games as "Myst", or perhaps a
non-hypertext version of hyperfiction.  When thought of in these terms,
"Window's" interface can be seen as a step backwards, or at best a step
sideways, in interactive storytelling.

A further problem with the interface is that it imposes a distinct
restriction on the number of elements which go to make up the player's
commands.  Most modern text adventures allow up to three elements in the
player's input-- a verb, a direct object, and an indirect object (the
subject may be specified, or is inferred, under certain cirucumstances
but is most frequently the default, the player character, and so may be
discounted).  "Window" only allows the player to specify the direct
object; the verb, the precise action, is inferred by the game, based on
circumstance; the indirect object has been done away with altogether.

It may seem that I have been quite hard on "The Space Under the Window". 
I will temper my comments by repeating that "Window" is an experiment in
interactive fiction.  In this it can claim some measure of success and
deserves the attention of anyone interested in interactive fiction
theory and techniques.
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"



From scythe@u.washington.edu Mon Apr 21 11:05:45 MET DST 1997
Article: 24668 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!ais.net!uunet!in2.uu.net!140.142.64.3!news.u.washington.edu!scythe
From: scythe@u.washington.edu (Dan Shiovitz)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: 20 Apr 1997 05:35:23 GMT
Organization: University of Washington, Seattle
Lines: 65
Message-ID: <5jc9ur$t56@nntp5.u.washington.edu>
References: <ant2001460b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: saul5.u.washington.edu
NNTP-Posting-User: scythe
Xref: news.lth.se rec.arts.int-fiction:24668


In article <ant2001460b0c4bn@arnod.demon.co.uk>,
Julian Arnold  <jools@arnod.demon.co.uk> wrote:
[..]
>"The Space Under the Window" was announced as an experimental work. 
>Heed the warning!  As a game "Window" is slight, and will not satisfy. 
>Considered for what it is, an experiment in techniques of interactive
>storytelling, it is more interesting.

I agree, more or less.  Like someone else said, the story is more like
a poem than a short story or a novella, and probably more like a
memory than like any of those.

>The narrative, such as it is, appears to involve two children, a boy
>(the player) and a girl, playing grown-ups, and staging a candle-lit
>dinner for two in their tree-house.  Apart from the small amount of
>detective work necessary to come to this conclusion, the narrative is
>mostly uninteresting, and plays second fiddle to the method of input,
>the interface.

Well .. clearly the story isn't so slight that we can't disagree on
things about it ;).  This simply wasn't my impression at all.
Although the "you" character and the other (pro/an)tagonist sometimes
do things that are childish or have childish fears, I think they were
intended to be demonstrations more of a .. different state of mind,
not precisely a younger one.  There's evidence that the relationship
has been going on for some time, much longer than children commonly go
for, and the issues between the two are clearly *not* children's
issues, even if it's never clear precisely what they are.  At least,
that's what I got from playing all the endings (almost .. can't figure
out one).  There are some endings that are more suggestive of
childhood than others, but I don't think that's a plausible reading if
you look at more than two paths or so.

In a way, it's the fault of the narrative that it's possible to end
with a shallow picture of things and not realize it, but I don't know
how I'd change it.  As usual, I found it unsatisfactory that there was
no clean ending (and yeah, I had to disassemble it to make sure), but 
it's interesting to compare my two favorite non-endings.  

[..]
>In fact, this interface most resembles a textual adaptation of the point
>'n click interface used by such graphical games as "Myst", or perhaps a
>non-hypertext version of hyperfiction.  When thought of in these terms,
>"Window's" interface can be seen as a step backwards, or at best a step
>sideways, in interactive storytelling.

"Sideways" is what I'd call it.  If you agree there's a continuum
between player freedom and having a story, (as opposed to
realism/simulation vs having a story), then this is definitely more
towards the "having a story" end than standard i-f is.  This is, of
course, not necessarily a bad thing.  It's interesting to see what
effects it does have, however.  Heightening the disconnection between
player and character is the first thing that springs to mind.

I can't see this as becoming the next big trend in i-f, though.  I
think there are a limited number of things that can be done with this
interface before it gets cloying (and besides, my GameInProgress will
have a much better way of doing a "story".)

--
dan shiovitz scythe@u.washington.edu shiov@cs.washington.edu
slightly lost author/programmer in a world of more creative or more 
sensible people ... remember to speak up for freedom because no one else
will do it for you: use it or lose it ... carpe diem -- be proactive.
my web site: http://weber.u.washington.edu/~scythe/home.html some ok stuff.


From jarobe@po.eecs.berkeley.edu Mon Apr 21 11:06:09 MET DST 1997
Article: 24707 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in1.uu.net!204.253.4.5!news.bridge.net!news.this.com!news1.best.com!nntp1.ba.best.com!not-for-mail
From: Jake Roberts <jarobe@po.eecs.berkeley.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: Sun, 20 Apr 1997 21:15:01 -0700
Organization: No
Lines: 71
Message-ID: <335AE9C5.15BA@po.eecs.berkeley.edu>
References: <ant2001460b0c4bn@arnod.demon.co.uk> <5jc9ur$t56@nntp5.u.washington.edu>
Reply-To: jarobe@po.eecs.berkeley.edu
NNTP-Posting-Host: dynamic16.pm03.wc.best.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:24707

Dan Shiovitz wrote:

[...]
> >The narrative, such as it is, appears to involve two children, a boy
> >(the player) and a girl, playing grown-ups, and staging a candle-lit
> >dinner for two in their tree-house.  Apart from the small amount of
> >detective work necessary to come to this conclusion, the narrative is
> >mostly uninteresting, and plays second fiddle to the method of input,
> >the interface.
> 
> Well .. clearly the story isn't so slight that we can't disagree on
> things about it ;).  This simply wasn't my impression at all.

Yes, that was quite a brave leap of interpretation.  "Her face, her
dress, are soft curves" does not strike me as the description of a child
(of course, lately something *has* been inducing puberty in girls as
young as eight...but then that's a rather disturbing thing to bring up,
so enough about that).  Keep in mind that the basic subject matter of
the story may vary substantialy from thread to thread.  That sort of
thing wouldn't surprise me in the least.

> In a way, it's the fault of the narrative that it's possible to end
> with a shallow picture of things and not realize it, but I don't know
> how I'd change it.  As usual, I found it unsatisfactory that there was
> no clean ending (and yeah, I had to disassemble it to make sure), but
> it's interesting to compare my two favorite non-endings.

The endings that I reached, in addition to having little meaning or
impact for me, also felt stifling, in that I seemed to lose control as I
progressed further into the story.  Toward the beginning, the narrative
felt much more fluid, seemed to alter organically according to my
"commands".  It was during these early stages that the potential of the
medium glimmered through to me.  But then as each thread developed, just
when the story was starting to get interesting, things became stiff and
unresponsive.  Of course I realise that the author had only so much time
to put into the work, but I feel there just isn't enough here to get a
fell for this medium and its possibilities.

> 
> [..]
> >In fact, this interface most resembles a textual adaptation of the point
> >'n click interface used by such graphical games as "Myst", or perhaps a
> >non-hypertext version of hyperfiction.  When thought of in these terms,
> >"Window's" interface can be seen as a step backwards, or at best a step
> >sideways, in interactive storytelling.

Which is why I'd like to see the interface accept words that are not in 
the narrative text.  When I read the sentence, "An empty vase sits on
the table", I should be able to enter the word "flowers", since its
implicitly, if not explicitly, present in the sentence.  Or if I see
"The candle flickers brightly" I should be able to say "flame", or
"light", or "warmth", or anyhow some of those things.  This would break
the similarity to point-and-click, hypertext-style interfaces and
exploit the expressive freedom of the command line interface (and let's
face it, that's the only thing it has going for it). True, it may be
difficult for the author to anticipate everything the player is going to
type, but that's a problem inherent to IF in general, isn't it?  

All in all, I can't tell if Plotkin's experiment works for me or not. 
The oblique, poetic quality of the writing made it less engaging, but
I'm not sure such an impressionistic technique would work very well with
more traditional prose or narrative story telling.  I don't hink there's
any question of it becoming the future of what we now called interactive
fiction, since it is in
a completely different category from the games we're used to, involving
substantially different kinds of motivation on the part of both its
author and players.  Still, it is as much, if not more, deserving of the
term "interactive fiction" than are the good old Infocom-style games,
IMO.

- Jake


From jools@arnod.demon.co.uk Mon Apr 21 11:06:39 MET DST 1997
Article: 24702 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: Sun, 20 Apr 1997 22:11:15 +0100 (BST)
Organization: Stephen Promulgation Society
Message-ID: <ant202115b49c4bn@arnod.demon.co.uk>
References: <ant2001460b0c4bn@arnod.demon.co.uk> 
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 75
Xref: news.lth.se rec.arts.int-fiction:24702

In article <ant2001460b0c4bn@arnod.demon.co.uk>, Julian Arnold
<URL:mailto:jools@arnod.demon.co.uk> wrote:
> 
> TITLE  :  The Space Under the Window
> AUTHOR :  Andrew Plotkin (erkyrath@netcom.com)
> LICENCE:  Freeware
> VERSION:  Release 2 / Serial number 970402
> DETAILS:  (ftp://ftp.gmd.de/if-archive/games/infocom/sutwin.z5)
>           Needs a Z-Machine interpreter,
>           (ftp://ftp.gmd.de/if-archive/infocom/interpreters/)
> 
>
> [...]

Sorry if this seems a bit sloppy, but I'd like to add a further bit to
my review.  This doesn't change anything I said before, but adds a
little.  The following insert should go before the final paragraph of
the original:

An effect of this interface is that the player does not directly
progress the narrative.  Rather, due to the implicit nature of the
player's input, he causes an influence on the direction of the story,
nudging it, often through trial and error, to a point where it does
advance.  This works in both directions, and it is entirely possible to
devolve the story as well.  For example:
	The window is open, so you climb down inside. The table is set
	for two. An empty vase, white glass, stands beside a single lit
	candle.
	
	You are arranging your flowers when the door opens. She climbs
	up, drops it firmly back into place. Her eyes meet yours coolly.
	Candlelight-shadows chase each other around the floor.
	
	"So you did come," she begins. The lines of her face have gone
	hard. "You could tell me that it makes a difference."
	
	    ***
	
	>door
	
	
	The window is open, so you climb down inside. The table is set
	for two. An empty vase, white glass, stands beside a single lit
	candle.
	
	You are arranging your flowers when the door opens.
	
	    ***
	
	>door
	
	
	The window is open, so you climb down inside. The table is set
	for two. An empty vase, white glass, stands beside a single lit
	candle.
	
	You are arranging your flowers when the door opens. She climbs
	up, drops it firmly back into place. Her eyes meet yours. They
	are cool, her eyes, and her lips.

This seems to curiously (or perhaps not so curiously) detract from the
flow of the story.  It is somewhat akin to UNDO gone rampant-- it could
strike at any time, and without reason.  This is another example of how
"Window" has moved away from the subjective branch of interative fiction
(ie, text adventures) and towards the objective branch (ie,
hyperfiction); the player essentially (though this is by no means the
case throughout) influences the presentation of events, rather than
controlling, or initialising, those events himself.

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"



From robbj95@octarine.cc.adfa.oz.au Mon Apr 21 17:20:58 MET DST 1997
Article: 24706 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!munnari.OZ.AU!harbinger.cc.monash.edu.au!newshost.carno.net.au!euryale.cc.adfa.oz.au!octarine!robbj95
From: Barbara Robson <robbj95@octarine.cc.adfa.oz.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: 21 Apr 97 02:13:01 GMT
Organization: ADFA News Service
Lines: 43
Message-ID: <robbj95.861588781@octarine>
NNTP-Posting-Host: 131.236.1.1
X-No-Archive: yes
Originator: robbj95@octarine
Xref: news.lth.se rec.arts.int-fiction:24706

I'd just like to add my voice to the chorus of comment.  I found the
first couple of minutes of interacting with this piece to be
frustrating (what was going on? why why wasn't I getting anywhere?  why
wouldn't it accept the word I want to follow up on?), but then I got
the hang of the way it worked and figured out what Andrew Plotkin was
trying to do with it (or at least an interpretation that worked for
me).

It's beautiful.  Hypnotic.  I have to agree with the poster who
described it as 'interactive poetry', or I'd be lost in trying
to define it.  It is clearly artwork and not a game.

<SPOILERS FOLLOW>









_The Space Under the Window_ is a mood piece, and captures perfectly,
when played through a number of times, the feeling of a memory, as
if the protagonist were going over and over the scene, trying to
understand what happened and trying to find a path through to what
might have been.  I even found myself caught up in this after a while:
having once found a path through to laughter and forgotten how I
reached it, I found myself searching the paths of the 'memory', looking
for that smile and trying to elicit again the laughter.  Part of the
beauty of the piece, though, is the variety of moods in the endings.
There seems to be lots of sadness, melancholy, bitterness.  There are
also paths through to peace, to acceptance, fear, anger, to perhaps a
hint of passion, to wry smiles and, of course, to laughter.  There
are probably others that I haven't found yet.

I'm not sure whether my interpretation is precisely what the author
intended, but this is what I got out of the piece.

Anyway, the point of all this rambling is:
                       <APPLAUSE! ENCORE!>

Barbara


From sgranade@phy.duke.edu Mon Apr 21 19:04:39 MET DST 1997
Article: 24716 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!uunet!in1.uu.net!130.168.70.138!news.eng.convex.com!newsgate.duke.edu!nebula.phy.duke.edu!sgranade
From: Stephen Granade <sgranade@phy.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Playing the game vs. fighting the author (was Thoughts on Time and So Far)
Date: Mon, 21 Apr 1997 10:21:30 -0400
Organization: Duke University, Durham, NC, USA
Lines: 41
Message-ID: <Pine.SUN.3.91.970421101155.8364B-100000@nebula.phy.duke.edu>
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <3359ad81.2067034@netnews.netaxs.com> <Pine.SUN.3.95.970420230426.27878B-100000@accord>
NNTP-Posting-Host: nebula.phy.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <Pine.SUN.3.95.970420230426.27878B-100000@accord> 
Xref: news.lth.se rec.arts.int-fiction:24716

On Sun, 20 Apr 1997, Mark Tilford wrote:
> 
> On Sun, 20 Apr 1997, Mike Fessler wrote:
> 
> > I
> > found "Time" to be excessively dependent on intricate puzzles, knowledge of
> > "previous lives" (i.e. saving and restoring), and doing things in precisely the
> > right order with the right timing. Its unforgiving nature and linear path really
> > destroyed any mimesis for me -- I was extremely conscious that I was playing a
> > game and trying to outwit the author. 
> 
> That's how I felt when I played "A Change in the Weather".

This brings up a dichotomy which I often wrestle with when I play IF: at 
what point do I stop playing the game and begin fighting with the author?

There are some obvious things which make me feel as if I am having to 
outthink the author: poor syntax, being required to wait in one spot for 
no particular reason, guess-the-verb puzzles.

However, there are some very non-obvious things which send me over that 
line. For instance, I felt that way all throughout "A Change in the 
Weather." The game's warning had a lot to do with it; when Andrew said that 
the game was difficult and rather unfair, I immediately thought, "Aha! So 
Andrew meant for me to have difficulty!" The troubles I had with the game 
were no longer due to the game's universe. Instead, they were due to an 
author. My suspension of disbelief was lessened.

The opposite occured in _So Far_, despite its difficulty. I was more 
frustrated with _So Far_ than with "A Change in the Weather," yet I 
attributed my frustration to the game rather than the author. In one case 
my frustration served to divorce me from the game. In the other case it 
served to deepen my immersion.

Stephen

--
  Stephen Granade                | "It takes character to withstand the
  sgranade@phy.duke.edu          |  rigors of indolence."
  Duke University, Physics Dept  |    -- from _The Madness of King George_



From erkyrath@netcom.com Mon Apr 21 19:04:43 MET DST 1997
Article: 24722 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Playing the game vs. fighting the author (was Thoughts on Time and So Far)
Message-ID: <erkyrathE8zv3x.A1K@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <3359ad81.2067034@netnews.netaxs.com> <Pine.SUN.3.95.970420230426.27878B-100000@accord> <Pine.SUN.3.91.970421101155.8364B-100000@nebula.phy.duke.edu>
Date: Mon, 21 Apr 1997 15:31:09 GMT
Lines: 26
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24722

Stephen Granade (sgranade@phy.duke.edu) wrote:

> However, there are some very non-obvious things which send me over that 
> line. For instance, I felt that way all throughout "A Change in the 
> Weather." The game's warning had a lot to do with it; when Andrew said that 
> the game was difficult and rather unfair, I immediately thought, "Aha! So 
> Andrew meant for me to have difficulty!" The troubles I had with the game 
> were no longer due to the game's universe. Instead, they were due to an 
> author. My suspension of disbelief was lessened.

Oh, so not only will players complain if the game is unexpectedly hard, 
they'll complain if the game is too hard and you *warn* them about it.

Great.

Dammit, I'm ordering another truckload of Zarf-sucking sycophants. This 
batch has gone rancid.

--Z

(:-))

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From sgranade@phy.duke.edu Mon Apr 21 19:04:47 MET DST 1997
Article: 24729 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!arclight.uoregon.edu!gatech!news-relay.ncren.net!newsgate.duke.edu!styx.phy.duke.edu!sgranade
From: Stephen Granade <sgranade@phy.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Playing the game vs. fighting the author (was Thoughts on Time and So Far)
Date: Mon, 21 Apr 1997 12:38:29 -0400
Organization: Duke University, Durham, NC, USA
Lines: 24
Message-ID: <Pine.SUN.3.91.970421123630.7332A-100000@styx.phy.duke.edu>
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <3359ad81.2067034@netnews.netaxs.com> <Pine.SUN.3.95.970420230426.27878B-100000@accord> <Pine.SUN.3.91.970421101155.8364B-100000@nebula.phy.duke.edu> <erkyrathE8zv3x.A1K@netcom.com>
NNTP-Posting-Host: styx.phy.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <erkyrathE8zv3x.A1K@netcom.com> 
Xref: news.lth.se rec.arts.int-fiction:24729

On Mon, 21 Apr 1997, Andrew Plotkin wrote:

> Oh, so not only will players complain if the game is unexpectedly hard, 
> they'll complain if the game is too hard and you *warn* them about it.
>
> Great.

We certainly will complain; we'll just complain about different nit-picky 
things.

> Dammit, I'm ordering another truckload of Zarf-sucking sycophants. This 
> batch has gone rancid.

"Sorry, sir, but those are on back-order. Seems several other authors 
liked the specs enough to order modified versions. We'll put you on the 
list; it will only be four to six weeks before the next shipment is in."

Stephen

--
  Stephen Granade                | "It takes character to withstand the
  sgranade@phy.duke.edu          |  rigors of indolence."
  Duke University, Physics Dept  |    -- from _The Madness of King George_



From mol@bartlet.df.lth.se Mon Apr 21 20:20:44 MET DST 1997
Article: 24732 of rec.arts.int-fiction
Path: news.lth.se!news
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Thoughts on Time and So Far
Date: 21 Apr 1997 19:34:06 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 109
Message-ID: <5jg8ee$6fr@bartlet.df.lth.se>
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <335A7F09.55B4@romulus.sun.csd.unb.ca>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:24732

In article <335A7F09.55B4@romulus.sun.csd.unb.ca>,
Brad O`Donnell  <s7m6@romulus.sun.csd.unb.ca> wrote:
>Paul Avery wrote:
>> In that case, I ask myself, why do modern composers produce works
>> which to me are cacophonous, malsonorous, disjointed conglomerations
>> of sound with absolutely no attraction whatsoever. 
>
>  Because it sells, and people listen to it.

Hmmm. Interesting. I think Brad and Paul are talking about different
sets of composers (composers of "modern classical" music, aka
"serious" composers, vs. composers of certain kinds of modern popular
music, such as techno (real techno, not the quickened-up disco passed
of as "Eurotechno") or hard-core rap).

This is interesting because it sort of confirms my own view of it: the
problem with modern composers (the ones Paul are complaining about) is
not the music in itself - sure, it sounds awful if you're not used to
it, but as the current popularity of techno music shows, people can
get used to music that is radically different from the traditional
ideals - but in the composers' attitude towards their audience.

An excursion into history: Mozart and his contemporaries wrote music
primarily to entertain. That's what they were paid for.  Mozart tried
to live as an independent artist towards the end of his life, writing
the music *he* liked, but didn't survive very well. The notion of music
art for art's sake started with the romantics.

It's also interesting that people have *always* complained that
"modern music is too difficult". Many people didn't like Mozart's
later works when they were first performed - "Too modern, too
difficult, no nice tunes". Beethoven's "Eroica" was shocking for its
day - people had never heard such strange dissonances in a symphony
before!

But Beethoven didn't lose his audience. People got used to his music
and learned to love it. 

Late-romantic music (like Mahler or Richard Strauss) is *extremely*
advanced compared to Mozart. Mozart's audience would probably have
booed and hissed at a Strauss symphony. 

But my feeling is that "serious" composers lost contact with their
audience sometime in the early 20th century, writing for a small elite
rather than for a broader audience (OK, Mozart wrote for the elite,
too, but that was for the economic elite, who could afford to pay him,
not for the self-styled artistic elite).

If I interpret Paul's article correctly, he's concerned about
something similar happening in IF: that we should get a circle of
artsy If authors who wrote games for each other, patting each other on
the back for conforming to some "high artistic standards", looking
down on the "populist" authors who write for the low-brow masses.

Frankly speaking, while there may be a small risk for that happening,
I think this is *not* what is happening right now. I think the reasons
people speak highly of "So Far" is that they liked it, not that they
want to impress anybody ("Look, I must be really smart, I actually
understood 'So Far'"). 

So you didn't like it, Paul. Well, don't feel that you have to like
it, or that people will look down on you for not liking it. We aren't
that snobbish around here :-). But please don't insult our
intelligence by telling us that we're just saying we liked it to
impress people.

I can only speak for myself, of course, but I liked "So Far" primarily
for the same reasons I liked the Infocom games: excellent writing,
nice worlds to explore, fascinating puzzles that can actually be
solved without having to read the author's mind. The symbolic stuff,
the depth and so on, that's more of a bonus.

>> On the other hand, I found SoFar *totally* incomprehensible. Even with
>> the help of a walkthru I couldn't make *any* sense or get any
>> enjoyment out of this game. 

Too bad. But tastes differ.

There are some things in "So Far" that you obviously aren't *supposed*
to understand - like why you're not allowed to enter any buildings in
the silent town, or what's inside the castle. But I think the key to
the enjoyment of this is to realize that you don't need to know
that. Of course, you may not like that: tastes differ.

>> I agree that the writing is first class,
>> but I am left with the distinct impression that the author is using
>> the game as a vehicle for self-aggrandizement rather than to entertain
>> the player.

You mean "Look how clever I am, I can write a game that nobody
understands?" Well, I never got that impression - not any more than
>from a zillion other works. An artist, an author, or even a
programmer, *must* be allowed to show off at times.

It's of course easy to say "I don't understand this, so it must be
humbug." Lots of people say "I can't understand the theory of
relativity. Einstein must be a charlatan." as well. 

It's also very easy to call people saying that philistine. 

But let's refrain from ad hominem arguments, and accept that we have
different tastes, shall we?



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From erkyrath@netcom.com Tue Apr 22 12:57:50 MET DST 1997
Article: 24753 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!bloom-beacon.mit.edu!thetimes.pixel.kodak.com!news.kodak.com!news.sprintlink.net!news-pen-16.sprintlink.net!news-dc-26.sprintlink.net!news-east.sprintlink.net!news-peer.sprintlink.net!news.sprintlink.net!sprint!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Thoughts on Time and So Far
Message-ID: <erkyrathE90AJu.Kz9@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <335A7F09.55B4@romulus.sun.csd.unb.ca> <5jg8ee$6fr@bartlet.df.lth.se> <335bc0aa.100182060@news.u-net.com>
Date: Mon, 21 Apr 1997 21:04:42 GMT
Lines: 37
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24753

Paul Avery (scorpion@deepthought.sirius.com) wrote:
> >So you didn't like it, Paul. Well, don't feel that you have to like
> >it, or that people will look down on you for not liking it. We aren't
> >that snobbish around here :-). But please don't insult our
> >intelligence by telling us that we're just saying we liked it to
> >impress people.

> Perhaps I *did* go a little too far in that direction, but remember
> that the whole reason for my original posting was Carl's extremely
> patronising letter. As I see it, to post such a letter by email would
> be acceptable, but to post it as an open letter on a newsgroup and
> thus publicly humiliate (again *perhaps* slightly too strong a word)
> the author smacked of elitism - you *must* see what I'm getting at.

I don't.

I'm going to be presumptous now and defend Carl Muckenhaupt's criticism of
_Time_ -- even more so, because he was criticizing it in comparison to my
game, but bear with me for a moment. 

I never saw Carl's post as elitist, patronising, or intended to humiliate
Andy Phillips. He posted a description of what he didn't like about the
game, and why; giving specific examples from the game, and also contrasting
examples from a different game. That's *exactly* what this newsgroup is
for. It's a writers' discussion group. We want *more* of that kind of 
post.

We need feedback from each other and from players. If the feedback happens
in public, then we each benefit from exponentially more discussion. Yes?
No? 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From ctt20@hermes.cam.ac.uk Tue Apr 22 14:35:13 MET DST 1997
Article: 24690 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!rill.news.pipex.net!pipex!netcom.net.uk!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!lyra.csx.cam.ac.uk!news
From: Chuan-Tze Teo <ctt20@hermes.cam.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: Sun, 20 Apr 1997 16:36:49 -0700
Organization: University of Cambridge
Lines: 50
Message-ID: <335AA891.3BE@hermes.cam.ac.uk>
References: <ant2001460b0c4bn@arnod.demon.co.uk>
NNTP-Posting-Host: atum.trin.cam.ac.uk
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.0 (Win16; I)
Xref: news.lth.se rec.arts.int-fiction:24690

Julian Arnold wrote:

> The narrative, such as it is, appears to involve two children, a boy
> (the player) and a girl, playing grown-ups, and staging a candle-lit
> dinner for two in their tree-house.  

I never got that impression at all. There are at least 5 "endings" I think, 
and possibly more - I didn't disassemble it - most of which seem (to me, 
anyway) to be inconsistent with this interpretation.

> In fact, this interface most resembles a textual adaptation of the point
> 'n click interface used by such graphical games as "Myst", or perhaps a
> non-hypertext version of hyperfiction.  When thought of in these terms,
> "Window's" interface can be seen as a step backwards, or at best a step
> sideways, in interactive storytelling.

It strikes me that this style is better suited to WWW-based IF than the 
traditional prompt interface. Sometimes, typing a word on the screen 
results in the irritating message "XXX isn't near the narrative", which 
would be avoided if the textual objects that had an effect on the game were 
highlighted in some way. Also, by the nature of the approach there are no 
"dead ends" that require use of the backtrack feature of a web browser.

> A further problem with the interface is that it imposes a distinct
> restriction on the number of elements which go to make up the player's
> commands.  Most modern text adventures allow up to three elements in the
> player's input-- a verb, a direct object, and an indirect object (the
> subject may be specified, or is inferred, under certain cirucumstances
> but is most frequently the default, the player character, and so may be
> discounted).  "Window" only allows the player to specify the direct
> object; the verb, the precise action, is inferred by the game, based on
> circumstance; the indirect object has been done away with altogether.

SUTWIN is essentially a journey through a "narrative web" in which the 
player influences the development of a particular thread through focusing 
on various objects. There is no real element of time; everything is freely 
reversible without UNDO until an "ending" occurs. The endings are very 
divergent, the roles of objects depending on how the player chooses to 
perceive them, which is the main point of the game IMO. Perhaps the 
verb-object model is appropriate; typing the name of an object changes the 
way the character perceives it rather than carrying out an action. Indeed, 
most objects are not directly manipulated by the player, which can be 
frustrating at times, and I suspect this would make it quite difficult to 
write a work with an extended plot in this idiom.

I can't really say how much potential this has. It's an interesting 
experiment, though, and certainly I had fun with it for a while.


- Chuan


From ldaly@bu.edu Tue Apr 22 14:35:35 MET DST 1997
Article: 24756 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.nacamar.de!news-feed.inet.tele.dk!enews.sgi.com!decwrl!purdue!news.bu.edu!cgl!ldaly
From: ldaly@bu.edu (Liza Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: 21 Apr 1997 21:14:49 GMT
Organization: Real address in .sig
Lines: 38
Message-ID: <5jglc9$jil@news.bu.edu>
References: <ant2001460b0c4bn@arnod.demon.co.uk> <335AA891.3BE@hermes.cam.ac.uk> <335d7e59.17682277@news.concentric.net>
NNTP-Posting-Host: cgl.bu.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24756

Erik Ostrom (eostrom@acm.org) wrote:

: >It strikes me that this style is better suited to WWW-based IF than the 
: >traditional prompt interface. Sometimes, typing a word on the screen 
: >results in the irritating message "XXX isn't near the narrative", which 
: >would be avoided if the textual objects that had an effect on the game were 
: >highlighted in some way.

: Well, I would like to see that message less.  However, I think the way
: I'd like to see that happen is for all of the visible objects to be
: "near", rather than for those objects that _are_ "near" to be
: highlighted.

: When I read web pages, I'm all too likely to skim through them,
: noticing only the words that are blue.  I'm already doing too much of
: this in "Window"--scanning through the text, searching for any nouns I
: could get my hands on.  I think this has led me to miss much of the
: prose, thus, perhaps, missing the point.

You could design the page with style sheets or HTML hacks
to make the hyperlinks the same color as the text.  Of course, a
user could always pan the pointer over the links and look for URLs,
and it wouldn't work in non-Netscape or MSIE browsers, but hey.

As an experiment, btw, I liked it a lot.  And I never got the
children feeling, except that the treehouse would explain why the door
was in the floor.  Maybe adults meeting in a place they'd known
as children?

--Liza, wondering if Andrew is amused by our attempts to decipher it. 

--
"Why should we endeavour to make the web exciting, interesting,
 interactive and aesthetically pleasing?" - The House of Erotic Massage
                                            March edition
 gecko@retina.net                           http://fovea.retina.net/~gecko/




From mulveyr@frontiernet.net Tue Apr 22 14:35:51 MET DST 1997
Article: 24778 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!europa.clark.net!newsfeed2!news.vivanet.com!node2.frontiernet.net!katy
From: katy@katy.aa2ys.ampr.org (Katy Mulvey)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: 22 Apr 1997 03:24:50 GMT
Organization: Complete and Utter Chaos
Lines: 21
Message-ID: <slrn5lobon.938.katy@katy.aa2ys.ampr.org>
References: <ant2001460b0c4bn@arnod.demon.co.uk> <335AA891.3BE@hermes.cam.ac.uk> <335d7e59.17682277@news.concentric.net> <5jglc9$jil@news.bu.edu>
Reply-To: mulveyr@frontiernet.net
NNTP-Posting-Host: usr4-20.dial.roc.frontiernet.net
X-Newsreader: slrn (0.9.2.0 BETA UNIX)
Xref: news.lth.se rec.arts.int-fiction:24778


On 21 Apr 1997 21:14:49 GMT, Liza Daly <ldaly@bu.edu> wrote:
>As an experiment, btw, I liked it a lot.  And I never got the
>children feeling, except that the treehouse would explain why the door
>was in the floor.  Maybe adults meeting in a place they'd known
>as children?

Door in the floor? Not at all -- it was more like one of those 
garage-door type doors you see in loft-type apartments in the 
city (at least in the movies).  Whoever said "interactive
poetry" captured an essence.

I enjoyed it, at least the parts I've seen. I won't pretend
to have seen all of it yet -- I'm convinced there's a happy
ending buried in there somewhere, and I'm having fun teasing
through the threads of the story.

  Katy
-- 
Katy Mulvey
Home: mulveyr@frontiernet.net  http://www.frontiernet.net/~mulveyr/Katy



From baf@max.tiac.net Tue Apr 22 14:36:25 MET DST 1997
Article: 24731 of rec.arts.int-fiction
Path: news.lth.se!solace!demos!demos2!hermes.sovam.com!sovam!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!howland.erols.net!newshub2.home.com!newshub1.home.com!news.home.com!news1.best.com!wizard.pn.com!news.gte.com!news-in.tiac.net!posterchild!max.tiac.net!baf
From: baf@max.tiac.net (Carl Muckenhoupt)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Announce: The Space Under the Window
Date: 21 Apr 97 16:32:18 GMT
Organization: The Internet Access Company, Inc.
Lines: 72
Message-ID: <baf.861640338@max.tiac.net>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <5j9rp7$mbq@er5.rutgers.edu>
NNTP-Posting-Host: max.tiac.net
Xref: news.lth.se rec.arts.int-fiction:24731 rec.games.int-fiction:22812


edharel@eden.rutgers.edu (Wallace and Gromit) writes:

>Florian Beck <fb@ue801di.lrz-muenchen.de> writes:

>>erkyrath@netcom.com (Andrew Plotkin) writes:

>>> --------------------------
>>> The Space Under the Window
>>> (an experiment)
>>> by Andrew Plotkin

>[Snip... available at an incoming directory of an if-archive near you...]

>>A completely new way of story telling.

>True... Very interesting new approach (though there are many
>flaws... repetitions of the same thing.. incorrect descriptions,
>things included in the description that're not near..., etc)

The repetition seems to me to be part of the effect.  This is
more like interactive poetry than interactive fiction.  The
mechanics of the thing are suggestive of the workings of the mind.
If I had to give a literal explanation of the piece, I would say
that it consists of the player character's thoughts, possibly
while anticipating the encounter portrayed.  Thinking about
the flowers brings up memories of picking them, etc.  That's
why the commands are nouns instead of verbs.  You're exploring
associations.

>>Please play this AND *imitate* it. It's not plagiarism. It can't
>>be, because this is a future of IF. This may be a real alternative to
>>Infocom-style IF (not that I have any problems with

I'm not sure it's so imitable.  The mechanics and the style seem
rather closely bound.  (Can you imagine an action thriller told in
this way?)  Plus, part of what makes this peice work as well as it does
is the fact that it's experimental.  This lends it a certain freshness
that would not be inherited by imitations.  Please, if you're going
to imitate, introuce variations in form as well as content.

>>I definitely will imitate this technique. When I've figured out how to
>>do this, of course, he he he...

>Not to hard.,...  You could probably do it in annother language almost
>as easily.  But in inform, you'd probably constantly move the objects
>into view or away (or move the player into different rooms depending on
>the state). I'm not quite sure how to get it that it will only accept
>commands of objects, though.

Somehow, I get the impression that very little of the standard Inform
libraries were used.  The piece isn't quite a state machine, but it's
close enough that pretty much everything that goes into an adventure
would be useless.  I'd be very surprised if there were any "rooms" or
"items" in the ordinary sense.

>It's not unique (at least, I seem to remember simmilar stuff.  Certainly 
>the web has simmilarstuff. I think.)  But by concentrating on a lot of
>objects and not the actions that can be operated onto them, you both simplify
>the game, give the story less interactivity (as now the author decides what
>actions are taken with regard to an object... What if you wanted to close the
>window?), and yet allow it to branch much more.

It is, as has been pointed out, rather like a Myst-style point-and-click
adventure done in text.  I, too, have seen things that allow you to focus
on elements of the text to determine what gets shown next, but they're
typically just equivalent to hypertext.  This piece at least shows some
lingering effects of your choices.

-- 
Carl Muckenhoupt              | Text Adventures are not dead!
baf@tiac.net                  | Read rec.[arts|games].int-fiction to see
http://www.tiac.net/users/baf | what you're missing!


From erkyrath@netcom.com Tue Apr 22 14:39:25 MET DST 1997
Article: 24750 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Announce: The Space Under the Window
Message-ID: <erkyrathE90639.3HG@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <5j9rp7$mbq@er5.rutgers.edu> <baf.861640338@max.tiac.net>
Date: Mon, 21 Apr 1997 19:28:21 GMT
Lines: 121
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24750


Carl Muckenhoupt (baf@max.tiac.net) wrote:
> Somehow, I get the impression that very little of the standard Inform
> libraries were used.  The piece isn't quite a state machine, but it's
> close enough that pretty much everything that goes into an adventure
> would be useless.  I'd be very surprised if there were any "rooms" or
> "items" in the ordinary sense.

I guess it's time for the author to start commenting, at least on 
technical matters.

You may have noticed that "Window" is about 30K. A one-room, no-object 
game built with the Inform standard library is about 45K or 50K, I 
believe.  You may take that as a hint. :)

I copied out the innermost read-a-line-of-text loop from the libraries; 
that includes the "undo" handler. I copied the verb handlers for save, 
restore, and so on. Everything else is hand-rolled, and as simple as 
possible. 

(For example, the word-recognizer *does* recognize multiple-word names --
that is, you can type "lit candle", or "candle lit", or "candle candle lit
candle lit" for that matter -- much as you can in regular Inform games. 
However, there is no facility to do "Which do you mean, the lit candle or
the unlit candle?" If there is any name overlap, the player probably gets
horked. To avoid this, I had to hack up a routine to print out the entire
available word list in the current state, and check it for duplicates.)

(And before you ask, that routine is not compiled into the final version 
of the game file. :)

To other questions --

Is it hypertext? Frankly, I would say "yes". The text does get built up 
out of inserted and variant elements, but conceptually that's just a 
shortcut. I could have typed each page out separately, if I'd been willing 
to copy and paste a lot of text. (And in fact there's already a lot of 
repeated text in the source code, because I wasn't trying to be 
particularly neat.)

So yes, it could be done on the Web. Except:

I was strongly considering leaving *in* the list-available-words command. 
(Very much analogous to the "exits" command that was discussed in 
tradition IF.) Obviously if I did a Web version, this would be automatic, 
because all the available words would be highlighted as hyperlinks. I 
could also have gotten this effect (in Inform) by boldfacing the available 
words in the text.

In the end, I decided to leave the command out. I (and the beta-testers)
thought that hunting for words is really the only thing that the player 
*does*, and automating it would just lead to players zapping around the 
branches of the work without really reading the main text at all. (And 
at least one person on this newsgroup made the same point when talking 
about a Web version.)

Of course, just because you think of "Window" as hypertext -- assuming you 
do -- isn't a condemnation. Inform is a perfectly usable basis for 
hypertext of this sort. And it does make it easier to preserve state 
across a wide range of variations -- although I'm afraid I didn't use this 
capability nearly as much as I hoped to.

Another thing I considered adding was scenery. That is, the moral
equivalent of "That's not important right now," when you type a word which
*is* in the text but which I didn't program an effect for. I ultimately
decided against this, partially because I'm lazy, and partially because I
couldn't think of a good way to phrase the message. After trying several
stilted variations, I realized they all boiled down to being identical to
the *existing* "There's no such thing here" message, and what really was
the difference anyway? I couldn't think of one. 

Is it easier to write than trad. IF? Er, damned if I know. It's much
shorter -- I spent about three weeks on this, as opposed to two or three
months on "Weather". Or is that because "Window" is much smaller than
"Weather"? Or is it? I really have no clue. 

Writing in this form was much more of a pain in the butt for me
(for whom writing prose is harder than programming.) To get the effect I 
wanted, I had to write single-page static fiction stories, over and over. 
Acceptable single-page stories, I mean. And then figure out how to slice 
them up and put in variations, without any seams. 

In other words, in trad.IF I rarely have to write more than a paragraph at
a time -- bar the opening and closing scenes, of course. And it makes no
sense to worry if two paragraphs sound good together, because it's all
going to depend on what the player does anyway. In "Window", I'm writing
whole pages of text, and all the variations have to read as well as those
pages. This is hard. 

(The reason "Window" is the size that it is, is that I ran out of steam. 
Writing steam, not programming steam. Didn't want to write another damn 
page of text, so I declared it finished. Maybe this is a form for people 
who find writing easy. Or have have more willpower than me.)

And then the programming turns out to be kind of a pain too. I nested a
whole lot of if statements in the printing code, but the system isn't very
elegantly put together, so I have to have identical if statements in the
code that decides what names are available. So I have to pay attention to
keep those in sync. And then it's a further pain to arrange things so that 
phrases link together right. I mean, in places I wanted stuff like

  You drink a beer.
  You drink a beer; the room spins around you.
  You drink a beer, and you drop like a rock.
  You drink a beer. The room spins around you, and you drop like a rock.

as possible variants, based on separate "beer", "roomspin", and "passout" 
flags. So you can imagine how much fun I had getting the punctuation and 
capital/lowercase letters right. I originally meant to write a awesomely 
powerful utility library to handle this automagically, but I never got 
around to it. 

I expect I ought to clean up the whole mess and make a usable library out 
of it. I'm a little hesitant, though. To a certain extent, that would tie
down anybody who used it to *my* approach, which is not what I want. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From rglasser@penning.lanl.gov Tue Apr 22 14:40:06 MET DST 1997
Article: 24773 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Announce: The Space Under the Window
Date: Mon, 21 Apr 1997 16:31:10 -0700
Organization: UCSD
Lines: 27
Message-ID: <335BF8BE.1152@penning.lanl.gov>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <5j9rp7$mbq@er5.rutgers.edu> <baf.861640338@max.tiac.net> <erkyrathE90639.3HG@netcom.com>
NNTP-Posting-Host: sdx-ca23-61.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Mon Apr 21  4:32:28 PM PDT 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:24773

Andrew Plotkin wrote:

> I was strongly considering leaving *in* the list-available-words command.
> (Very much analogous to the "exits" command that was discussed in
> tradition IF.) Obviously if I did a Web version, this would be automatic,
> because all the available words would be highlighted as hyperlinks. I
> could also have gotten this effect (in Inform) by boldfacing the available
> words in the text.

	Not necessarily.  You could highlight EVERY word on the browser and 
have most of them lead nowhere new.  Of course it might be tedious to type 
all those <a href>s, but a short Perl script could do that for you quickly 
and painlessly.  I think I would prefer to play this game as hypertext, 
especially since I'd like to have a "back" button for comparing new and old 
test.
	By the way, I got to the ending after typing "breath".  Is there 
more than one ending?  I know it's not very zen-like of me, but I'm lost 
trying to figure out whether this ending is "*good*" or not.

-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From erkyrath@netcom.com Tue Apr 22 14:41:34 MET DST 1997
Article: 24752 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Path: news.lth.se!solace!nntp.uio.no!Norway.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Hypertext and MUDS (WAS Re: Announce: The Space Under the Window)
Message-ID: <erkyrathE90CHM.65w@netcom.com>
Followup-To: rec.arts.int-fiction
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <erkyrathE8uECI.DyG@netcom.com> <3359cd1b.7271477@news.netspace.net.au> <m37mhxdhym.fsf@ue801di.lrz-muenchen.de> <335b3d26.4097459@news.netspace.net.au> <5jgg05$hv9@falcon.ccs.uwo.ca>
Date: Mon, 21 Apr 1997 21:46:34 GMT
Lines: 73
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24752 rec.games.int-fiction:22825

J. Blustein (jamie@csd.uwo.ca) wrote:
>     Usually I just lurk in rec.games.int-fiction (and haven't read
> the arts group for a long time) but I wrote and maintain the
> alt.hypertext FAQ and want to clear up what I see as misconceptions
> about hypertext.  

> >>I probably could be implemented as hypertext. I don't know. But what
> >>SUTW is like and how it could be implemented is not important. What's
> >>important is the idea behind. And that's not hypertext.
>
>     Hypertext is an idea.  There are many ways to implement the idea
> however.  The methods used to implement hypermedia links on the WWW
> are just one (rather impoverished) way.  Exception that proves the
> rule about WWW hypertext model: dynamic programming (client or server
> side) on the WWW provides an escape hatch.

Sure. I think the problem is that just about all use of hypertext,
including most of the Web, is *informative*. Its primary purpose is to hand
pedantic information to the user, in the way the user wants it.  The HTML
sort of link is the obvious choice for this -- the anchor is some concept
that the user might know about, and it jumps to separate information which
explains that concept, so that users who want to can jump, and those who
don't need to can continue unhindered. 

What I'm doing has a completely different purpose, so the links don't have 
any reason to behave that particular way. That doesn't take it outside the 
idea of hypertext.

> >>=> somewhere in the text a sentence/expression/word is changed,
> >>   omitted or inserted; with hypertext you'd have to provide a new
> >>   version of the whole text.

>      Absolutely not.  One of Nelson's main ideas was `translocution'
> as a way of including parts of documents in other documents and having
> them automatically updated.

Yup. I'm not exactly doing that either, because I don't really have a 
bunch of "documents" -- unless you're willing to count individual phrases 
as "documents" as I assemble them into sentences. But it's closer.

(The definitions in and around the hypertext-faq seem to take for granted 
that a link goes to some *external* node. Not necessarily external to the 
database/work/website in question -- there's a distinction between 
"internal" and "external" links, but that's not what I mean. I mean the 
idea that you have a bunch of nodes, each a little self-contained lump of 
content, and a link jumps to (or transcludes, if you like) a node.

I'm not sure that's really open-minded enough; I'd count anything which 
dynamically transforms itself as the user whaps on it. Consider a link 
which transforms the document from American to British spellings. 
Conceptually this has nothing to do with nodes (although on the Web it 
might be implemented by writing two similar HTML files.) That's a whole 
lot more like what I'm doing.

Of course, if you really want, you can stretch the definition of 
"hypertext" to include Zork. It's a dynamic document, which mutates 
itself based on the user's input. 

>     Answers to questions frequently asked in alt.hypertext are available at
>          <URL:ftp://rtfm.mit.edu/pub/usenet/news.answers/hypertext-faq>
>              <URL:http://www.csd.uwo.ca/~jamie/hypertext-faq.html>

So, have you looked at the thingie in question? 
(http://www.edoc.com/zarf/zplet/sutwin.html) Should I drop a mention of it 
onto alt.hypertext?

--Z


-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From egh@uclink4.berkeley.edu Tue Apr 22 14:42:10 MET DST 1997
Article: 24783 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!agate!uclink4.berkeley.edu!egh
From: egh@uclink4.berkeley.edu ()
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Hypertext and MUDS (WAS Re: Announce: The Space Under the Window)
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Date: 22 Apr 1997 05:09:45 GMT
Organization: Lies, Inc.
Lines: 45
Message-ID: <5jhh6p$7p6$2@agate.berkeley.edu>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <3359cd1b.7271477@news.netspace.net.au> <5je0j4$7pv$1@agate.berkeley.edu> <5je1p5$c8i@nntp5.u.washington.edu>
Reply-To: egh@uclink4.berkeley.edu
NNTP-Posting-Host: raisin.hip.berkeley.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24783 rec.games.int-fiction:22839


Dan Shiovitz (scythe@u.washington.edu) wrote:
: In article <5je0j4$7pv$1@agate.berkeley.edu>,
:  <egh@uclink4.berkeley.edu> wrote:
: >I agree, except that I found that there was /no/ object in the game
: >that I couldn't refer to. None. I only got `You can't see that now.'
: >messages when I misspelled things.

: Hmm.  Maybe you weren't trying hard enough ;)

Certainly possible -- I've always been a little bit lazy. :)

: For instance (SPOILERS)

: From the start: window. room. two. surprise. shadow.

Except for suprise, I could use all of these. Er...shadow too, but I
never saw a shadow.

And I just noticed that I couldn't focus on the glow.

I'm not sure if I liked this narrative or not -- it was a little too
vague for my taste. But! I thought it had a good deal of branching.  I
felt, in a way, like I was interacting /more/ than I do in a
traditional IF game. Perhaps this needs explaining: I was restricted,
because all I could do was focus, not interact. But this made things
simpler for the author, it seems. I couldn't pick up the candle and
smash the window with it. Plotkin could create more endings because
/he/ choose what I did. I just choose what to do it to. So his endings
were sensible, and he didn't guide me into certain things, as I often
am in IF.

Much as I like IF, the truth is they all seem to have one `correct'
ending.  Or at most three or so. /The Space Under the Window/ seemed
more restricted in the body of the work, but more open in the endings.

Maybe. :)

: dan shiovitz scythe@u.washington.edu shiov@cs.washington.edu
: slightly lost author/programmer in a world of more creative or more 
: sensible people ... remember to speak up for freedom because no one else
: will do it for you: use it or lose it ... carpe diem -- be proactive.
: my web site: http://weber.u.washington.edu/~scythe/home.html some ok stuff.

----- Erik Hetzner -----  In a perfect world we'd all sing in tune,
egh@uclink4.berkeley.edu  But this is reality so give me some room.


From baf@max.tiac.net Tue Apr 22 20:39:08 MET DST 1997
Article: 24790 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!uunet!in2.uu.net!199.0.65.182!news-in.tiac.net!posterchild!max.tiac.net!baf
From: baf@max.tiac.net (Carl Muckenhoupt)
Newsgroups: rec.arts.int-fiction
Subject: Re: Thoughts on Time and So Far
Date: 22 Apr 97 15:46:48 GMT
Organization: The Internet Access Company, Inc.
Lines: 35
Message-ID: <baf.861724008@max.tiac.net>
References: <baf.861135520@max.tiac.net> <3358a7f0.241890286@news.u-net.com> <335A7F09.55B4@romulus.sun.csd.unb.ca> <5jg8ee$6fr@bartlet.df.lth.se> <335bc0aa.100182060@news.u-net.com> <erkyrathE90AJu.Kz9@netcom.com>
NNTP-Posting-Host: max.tiac.net
Xref: news.lth.se rec.arts.int-fiction:24790

erkyrath@netcom.com (Andrew Plotkin) writes:

>I never saw Carl's post as elitist, patronising, or intended to humiliate
>Andy Phillips. He posted a description of what he didn't like about the
>game, and why; giving specific examples from the game, and also contrasting
>examples from a different game. That's *exactly* what this newsgroup is
>for. It's a writers' discussion group. We want *more* of that kind of 
>post.

I'll have to disagree with you a little.  Now that it's been pointed
out, I can easily see my criticisms as patronising, from the
"I know more about games than you"-ish intro to the "Your game is
beyond redemption"-ish ending.  I have send Mr. Phillips a note of
apology, pointing out that I would not have bothered to criticise his
game if I did not consider him capable of writing something better.
It was certainly not my intention to humiliate him.  The only reason
I posted anything was the theoretical content - ie, how context
changes the experience of two outwardly-similar puzzles.

When I saw the number of followups to my post, I was pleased, thinking
I had sparked discussion about the usage of puzzles.  Then I saw the
content, and was ashamed.  Please, everyone, stop defending me; Mr. Avery
has valid points, and calling him names gets us nowhere.

On the other hand, I heartily agree with everything else Zarf says.
If there is one thing that can save us from becoming an elitist bunch
of artsy types patting each other on the back, it's reasoned criticism.

Now if only Andy Phillips would join the discussion, so we can hear his
side...

-- 
Carl Muckenhoupt              | Text Adventures are not dead!
baf@tiac.net                  | Read rec.[arts|games].int-fiction to see
http://www.tiac.net/users/baf | what you're missing!


From darin@usa.net.delete_this_part Tue Apr 22 20:43:12 MET DST 1997
Article: 24772 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!Norway.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!uunet!in2.uu.net!207.110.0.61!news.connectnet.com!darin
From: darin@usa.net.delete_this_part (Darin Johnson)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Hypertext and MUDS (WAS Re: Announce: The Space Under the Window)
Date: 21 Apr 1997 20:54:32 GMT
Organization: CONNECTnet Internet Network Services (619-638-2020)
Lines: 150
Message-ID: <slrn5lnl2i.4ba.darin@connectnet1.connectnet.com>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <3359cd1b.7271477@news.netspace.net.au> <5je0j4$7pv$1@agate.berkeley.edu> <335fb993.32846763@news.concentric.net>
NNTP-Posting-Host: connectnet1.connectnet.com
X-Newsreader: slrn (0.9.2.0 BETA UNIX)
Xref: news.lth.se rec.arts.int-fiction:24772 rec.games.int-fiction:22837

>>I have great respect for the potential of MUDs. I find them sort of
>>boring and depressing right now,
>
>On behalf of those of us who've been building MUDs, thank you very
>much. :-)

Actually, although the average may be boring, the above average can be
outstanding.  I've hear people say "I was going to give up on MUDs,
but someone recommended this one, and now I'm hooked again."  Don't
expect typical IF though.

>  - In general, one doesn't distribute MUD database files for people
>to download; rather, one just creates the work as a site, or as a part
>of a site, for people to connect to.  Admittedly, distributing
>separate databases to each group of players solves some logistical
>problems; however, it means that anyone who wants to try out your work
>has to download a server and a database, probably compile the server,
>and find some other people to log in.  High cost of entry.

Database oriented muds would be hard, but in the LP world,
distributing areas is not that difficult and is often done.  However,
it's usually done badly, and it's often only the new muds that are
desparate for real estate that use such prebuilt areas.  The biggest
problems are that such areas don't integrate well with other areas;
reward/challenge ratios may be out of wack, it may have conflicting
themes, or other problems (ie, the baby dragon in one area may be
harder to kill than the full grown one in an imported region).

But such things are viable to "play it by yourself" MUDs.  The drawback
of having to set up your own mud is big though.

I had thought, at one time, about writing a MUD/IF language.  It would
be viable for standalone IF, but also be essentially the same language
for a full MUD as well.  Then an IF area could be imported to a MUD,
or vice versa (with some appropriate conditional compilation or such).
Ie, an IF game that has an NPC that you can have help would make a good
multiplayer MUD puzzle as well.

>  - It'd be entirely possible to make something that was just like
><your favorite adventure game here> on a MUD--in fact, there's at
>_least_ one MUD implementation of Colossal Cave--but, like, why
>bother?  The point of MUDs is that there are multiple people on them;
>so why have a Colossal Cave that only one person can go into at a
>time, or where it doesn't matter if there's more than one person in
>it?

Yep, nothing like having someone shout to the entire mud "where's the
Frobozz Magic Window Cleaner?"  The problems are somewhat solvable, in
various ways:

  - the original MUD (and descendents, ala AberMUD) has "resets".  At
    certain intervals, the game state would all suddenly revert.  The
    objects were unique.  Thus after a reset, you could run around and
    try to get all the puzzle items for an area.  Still can't have
    two players doing it at once without conflicing; but it's realistic
    in that you don't have duplicated puzzle items needlessly.
    And you can't solve half the puzzle today, and the other half tomorrow,
    as a reset would have gone by.  (such worlds do tend to have
    more internal consistency though)  After awhile though, all the treasure
    ends up found, and all the monsters slain, etc, so you have to have a
    reset (not too soon, and not too late).

  - LPmud and variants have resets, but of a different sort.  Rooms can
    regenerate items that aren't there at a reset, making multiple
    copies.  Thus if you find that the key you need is not there, come
    back in an hour and it may be there again (and there may be multiple
    copies of the key in various hands).  Usually there's a way to make
    something unique so this doesn't happen (you don't want all your
    players to have Excalibur equipped).  This tends to make sure there's
    always something to do on the mud, and no one shouts "reset, reset!".

  - If the MUD is programmable, it's possible to add variants.  For
    instance, at least one area I've seen had virtual puzzle objects.
    Each new player in the area could find the key to pick up, but
    the next player would see a key to pick up as well.  Things got a
    little complex to program if you wanted to do it right, and the areas
    generally had to prevent removal of the objects into the surrounding areas.
    If you dropped the virtual objects, they would often vanish.
    This way, multiple people could do an area at the same time, without
    getting in each others way too much and without waiting for resets.

>  - You can make something that's much like a puzzle-based adventure
>game, but is designed expressly for multiple people.  Designing
>enjoyable puzzles for multiple people--and especially for many
>people--is _hard_, though.  If you just let anyone wander through your
>puzzle area, you run into all sorts of issues you may not have
>before--someone picks up the golden key and wanders around with it and
>everyone else can't continue, for example, or three players conspire
>to make a really cool two-player puzzle you worked out into a really
>easy three-player puzzle.

I have a two-player puzzle in an area I wrote.  The biggest problem
were the players not realizing it was a two-player puzzle.  They
would, however, try to get NPCs to help, but usually not other
players.  Part of the problem was that helping someone out with an
area was considered cheating (ie, no author likes having everyone do
their area via a walkthough ftp'd from the net, and authors being the
ones that decide the rules thus decide that such things aren't
allowed).

One thing I did see, which was amusing, was that players would get
friends to help indirectly.  That is, they would get someone to stand
in a certain room to see if anything would happen when they pulled a
switch in another room nearby.  I saw one group do this for hours,
without realizing that both switches could have been pulled at the
same time; so even though they had two players working on the area at
once, they still tried doing the actions as if it were single player.


>  - If one way to talk about adventure games is as the intersection of
>game and story, then puzzles may take care of the game part.  What
>about stories?  Well, some MUDs emphasize role-playing and the
>cooperative creation of narratives, and that's pretty cool.  But they
>don't rely on puzzles, and arguably there's not much that's gamelike
>about them.  Is that IF?  Is there an author?  Does it matter?  I
>don't know.  I'm a stranger here, myself.

One of the most interesting things I think, is the sociology that
happens in response to the game.  People solve difficult areas, and
then go brag about it in the bar; or display trophies (we allowed
making boots from skins of defeated monsters, and they turned into
signs of status almost).  Some areas develop a certain mythology about
them over time, and even the normally brain dead NPCs with nearly
nonexistent programming end up with perceived personalities.  Often,
listening to stories and tales in the bar, I would wonder if they were
talking about the same MUD or not.

You don't see that as much in IF.  I don't hear players reciting
"well, Floyd and I sauntered over to the machine, when Floyd does his
spas routine, and I slap him around a bit, when..."

>If you and
>another player character are in a room with King Arthur, and your
>friend saysto you, "By the way, I made love to Guinevere last night,"
>and King Arthur has only keyword-spotting and says only, "So, you've
>met Guinevere, my wife," well, how's that suspension of disbelief?

Yes, this is generally a problem.  Parsers could be be written to make
this better, but performance could be bad.  If is different, in that
generally you have a fixed set of items, so that even if you always
use the entire set of items when disambiguating, you're not doing that
much extra work; and certainly not enough extra work that the player
notices.  But with 30 players or more online, all typing as fast as
they can and with thousands or objects, the typical TADS or Inform
style of parsing won't cut it.  (LPmud does have a more advanced
parser, but it is rarely used)

-- 
Darin Johnson
darin@usa.net.delete_me


From egh@uclink4.berkeley.edu Tue Apr 22 20:43:42 MET DST 1997
Article: 24754 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!agate!uclink4.berkeley.edu!egh
From: egh@uclink4.berkeley.edu ()
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Re: Hypertext and MUDS (WAS Re: Announce: The Space Under the Window)
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Date: 21 Apr 1997 22:11:26 GMT
Organization: Lies, Inc.
Lines: 88
Message-ID: <5jgome$cc3$1@agate.berkeley.edu>
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <3359cd1b.7271477@news.netspace.net.au> <5je0j4$7pv$1@agate.berkeley.edu> <335fb993.32846763@news.concentric.net>
Reply-To: egh@uclink4.berkeley.edu
NNTP-Posting-Host: raisin.hip.berkeley.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24754 rec.games.int-fiction:22827


Erik Ostrom (eostrom@acm.org) wrote:
: Erik Hetzner (egh@uclink4.berkeley.edu) wrote:
: >I have great respect for the potential of MUDs. I find them sort of
: >boring and depressing right now,

: On behalf of those of us who've been building MUDs, thank you very
: much. :-)

:) Whoops.

I'm not saying I hate them. I've used them, and enjoyed it, but the
chatting usually seems pretty dull. Admittedy, it's ten thousand times
better than IRC as a conversation medium. Oh, I don't know. I wouldn't
like to make friends with people who I'll never see.

: From what I've seen, there are numerous things on MUDs that take on
: various aspects of IF, without ever doing something that exactly _is_
: IF.  There's some question whether one would want to, and some
: question whether one could.  Random thoughts:

:   - In general, one doesn't distribute MUD database files for people
: to download; rather, one just creates the work as a site, or as a part
: of a site, for people to connect to.  Admittedly, distributing
: separate databases to each group of players solves some logistical
: problems; however, it means that anyone who wants to try out your work
: has to download a server and a database, probably compile the server,
: and find some other people to log in.  High cost of entry.

I realize this. I'm not entirely sure why I asked that question. :)
Except that I know people do some silly things. :) Actually, I've
compiled LambdaMOO for my Linux box, just to have a little fun with
it. The database it starts with is pretty bare, though.

Come to think of it, MOO and IF developers ought to co-operate a
little more. MOO developers could teach about dynamically programming
(is that the word? something along those lines) objects, and we could
show them a little about command parsing. :)

:   - You can make something that's much like a puzzle-based adventure
: game, but is designed expressly for multiple people.  Designing
: enjoyable puzzles for multiple people--and especially for many
: people--is _hard_, though.  If you just let anyone wander through your
: puzzle area, you run into all sorts of issues you may not have
: before--someone picks up the golden key and wanders around with it and
: everyone else can't continue, for example, or three players conspire
: to make a really cool two-player puzzle you worked out into a really
: easy three-player puzzle.

Right, I imagine that's quite hard. It seems as if there's other ways
to do this, without making hard on yourself, but I can't think of
them. :) Transplanting traditional IF puzzles into a multi-player
world doesn't seem like the best of ideas.

:   - If one way to talk about adventure games is as the intersection of
: game and story, then puzzles may take care of the game part.  What
: about stories?  Well, some MUDs emphasize role-playing and the
: cooperative creation of narratives, and that's pretty cool.  But they
: don't rely on puzzles, and arguably there's not much that's gamelike
: about them.  Is that IF?  Is there an author?  Does it matter?  I
: don't know.  I'm a stranger here, myself.

: Of course, if you design IF without NPCs--like, if you rely on players
: to supply all your characters--you don't have this problem.

Right. This requires more role-playing than character on a M** are
often willing to do, it would seem. At least ones I've known. But
it's a neat idea.

Of course, who wants to be an NPC for somebody else's PC? Things have
to be done quite differently -- every character must play a role.

[...]
: knows different aspects of what happened.  You can read a little more
: about it, and get minimal instructions for trying it out, at
: <http://www.well.com/user/jmalloy/kitchen.html>.  Be forewarned:  By
: IF standards, the LambdaMOO command parser is baroque and primitive.

I'll check this thing out.

: --Erik, running off at the mouth
--
Erik `sprinting off at the mouth' Hetzner <egh@uclink4.berkeley.edu>








From jools@arnod.demon.co.uk Tue Apr 22 23:34:32 MET DST 1997
Article: 24796 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!arnod.demon.co.uk!jools
From: Julian Arnold <jools@arnod.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Review] The Space Under the Window
Date: Tue, 22 Apr 1997 13:51:02 +0100 (BST)
Organization: Stephen Promulgation Society
Message-ID: <ant221202b49c4bn@arnod.demon.co.uk>
References: <ant2001460b0c4bn@arnod.demon.co.uk> <335AA891.3BE@hermes.cam.ac.uk> <335d7e59.17682277@news.concentric.net> <5jglc9$jil@news.bu.edu> 
NNTP-Posting-Host: arnod.demon.co.uk
X-NNTP-Posting-Host: arnod.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.08]
Lines: 23
Xref: news.lth.se rec.arts.int-fiction:24796


In article <5jglc9$jil@news.bu.edu>, Liza Daly
<URL:mailto:ldaly@bu.edu> wrote:
> 
> [...]
> As an experiment, btw, I liked it a lot.  And I never got the
> children feeling, except that the treehouse would explain why the door
> was in the floor.  Maybe adults meeting in a place they'd known
> as children?

Now that's interesting, and actually only a short step from my
interpretation.  If Andrew cares to explain himself (fat chance!) I'll
explain how I arrived at my "shallow" yet "brave" interpretation. :)

BTW, describing the story as "uninteresting" in my review was clearly a
poor choice of words.  I meant I wanted to concentrate on the mode of
input in the review.

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"



From erkyrath@netcom.com Tue Apr 22 23:34:34 MET DST 1997
Article: 24787 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Review] The Space Under the Window
Message-ID: <erkyrathE91rHE.HHo@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <ant2001460b0c4bn@arnod.demon.co.uk> <335AA891.3BE@hermes.cam.ac.uk> <335d7e59.17682277@news.concentric.net> <5jglc9$jil@news.bu.edu>
Date: Tue, 22 Apr 1997 16:08:01 GMT
Lines: 13
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24787

Liza Daly (ldaly@bu.edu) wrote:
> --Liza, wondering if Andrew is amused by our attempts to decipher it. 

Fascinated. As usual, there are some ideas which match what I was thinking 
of when I wrote it; some ideas that I find totally strange; and some ideas 
that I wasn't thinking of, but like at least as much!

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Tue Apr 22 23:35:11 MET DST 1997
Article: 24802 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!xinit!newsfeed.tip.net!sn.no!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Announce: The Space Under the Window
Message-ID: <erkyrathE91z2B.3yD@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <erkyrathE8uECI.DyG@netcom.com> <m3u3l4kv7m.fsf@ue801di.lrz-muenchen.de> <5j9rp7$mbq@er5.rutgers.edu> <baf.861640338@max.tiac.net> <erkyrathE90639.3HG@netcom.com> <335BF8BE.1152@penning.lanl.gov> <erkyrathE91rJG.HsM@netcom.com> <335cfeb5.8215250@news.u.washington.edu>
Date: Tue, 22 Apr 1997 18:51:47 GMT
Lines: 35
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24802

Matthew Amster-Burton (mamster@u.washington.edu) wrote:

> erkyrath@netcom.com (Andrew Plotkin) wrote:

> >I've read the Perl manual, and I think this word "painless" doesn't
> >mean what you think it means. :)

> Andrew, you've now confirmed my theory that Mac users would like Lisp
> but not Perl.

Mm, but I'm a Mac user *and* a Mac programmer *and* a Unix geek. 
It's kind of schizophrenic sometimes. I'm happy as any bivalve using 
Emacs on a Unix box, but I don't touch it on the Mac, even though I have 
a Mac Emacs port. 

I don't actually like Lisp, but I like the Lisp way of thinking, as 
expressed in other languages like SML. On the other hand, as far as I can 
tell, Perl is a bad joke.

> Is harboring prejudices about computer users as bad as harboring other
> sorts of prejudices?

Yes, but who cares?

Or: No, because computer prejudices are *justified*. vi users really *do* 
have abnormally low sex drive. 

(Oh, er, was that out loud?)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Tue Apr 22 23:35:41 MET DST 1997
Article: 24800 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!demos!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Space Under the Window Thoughts
Message-ID: <erkyrathE91zqG.67r@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5jivms$24f$1@joe.rice.edu>
Date: Tue, 22 Apr 1997 19:06:16 GMT
Lines: 19
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24800

Lucian Paul Smith (lpsmith@rice.edu) wrote:
> It also is completely symbiotic.  The author and the viewer act together 
> to create a vignette.  It creates a completely new definition of 
> 'Interactive Fiction'; one that more closely resembles 'Interactive Art', 
> or, as someone said, 'Interactive Poetry'.

Ok, several people have used this phrase. You may be interested to know 
that I used it too, when I was developing "Window". 

So what did you mean by "Interactive Poetry"? I wasn't sure what I meant, 
even as I was thinking of the phrase. It's obviously nothing to do with 
rhyme or meter.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From lpsmith@rice.edu Wed Apr 23 13:20:20 MET DST 1997
Article: 24817 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news-peer.sprintlink.net!news.sprintlink.net!sprint!uunet!in3.uu.net!128.42.5.19!rice!ural.owlnet.rice.edu!lpsmith
From: lpsmith@rice.edu (Lucian Paul Smith)
Newsgroups: rec.arts.int-fiction
Subject: Space Under the Window Thoughts
Date: 22 Apr 1997 18:23:24 GMT
Organization: Rice University, Houston, Texas
Lines: 22
Message-ID: <5jivms$24f$1@joe.rice.edu>
NNTP-Posting-Host: ural.owlnet.rice.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24817

This is a followup to the 'Review' posts, which have not made it (if 
indeed they ever will) to my server.

Anyway, what TSUTW does is live up to its goal to be an experiment.  I 
saw it almost as a kind of narrative Rorshach (sp?) test.  I'm certain 
it's not what Andrew intended, but I do think that it says something 
psychological about the 'viewer' as to which ending they got to first 
(for myself, it was the 'footsteps' one.  Then again, almost the next one 
was the 'laughter' one, so who knows).

It also is completely symbiotic.  The author and the viewer act together 
to create a vignette.  It creates a completely new definition of 
'Interactive Fiction'; one that more closely resembles 'Interactive Art', 
or, as someone said, 'Interactive Poetry'.

As to what the completed vignettes _said_, that's an entirely different 
matter.  It was a little too spartan for my tastes, and was vague enough 
that I eventually gave up on trying to get much out of it.  I guess it 
didn't mean much to me, but it sure was pretty.

-Lucian "Lucian" Smith



From scythe@u.washington.edu Wed Apr 23 13:27:12 MET DST 1997
Article: 24808 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!worldnet.att.net!news.u.washington.edu!scythe
From: scythe@u.washington.edu (Dan Shiovitz)
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under the Window Thoughts
Date: 22 Apr 1997 22:11:08 GMT
Organization: University of Washington, Seattle
Lines: 39
Message-ID: <5jjd1s$stc@nntp5.u.washington.edu>
References: <5jivms$24f$1@joe.rice.edu> <erkyrathE91zqG.67r@netcom.com>
NNTP-Posting-Host: saul1.u.washington.edu
NNTP-Posting-User: scythe
Xref: news.lth.se rec.arts.int-fiction:24808


In article <erkyrathE91zqG.67r@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>
>Lucian Paul Smith (lpsmith@rice.edu) wrote:
>> It also is completely symbiotic.  The author and the viewer act together 
>> to create a vignette.  It creates a completely new definition of 
>> 'Interactive Fiction'; one that more closely resembles 'Interactive Art', 
>> or, as someone said, 'Interactive Poetry'.
>
>Ok, several people have used this phrase. You may be interested to know 
>that I used it too, when I was developing "Window". 
>
>So what did you mean by "Interactive Poetry"? I wasn't sure what I meant, 
>even as I was thinking of the phrase. It's obviously nothing to do with 
>rhyme or meter.

Well .. one fairly obvious reason is that it's short.  Although poetry
doesn't have to be short, of course, it often is, especially compared
to short stories (which is what most IF is like).
I thought of it as poetry because, for me, poetry isn't as enveloping
a medium as a short story or a novel.  I read it, and it's pretty, but
it's clearly separate from me, in the same way that I felt separate
>from _Window_.  Also .. hmm.. well, that's the main reason.  There are
other similarities between _Window_ and poetry vs "standard IF" and
short stories: _Window_ doesn't develop its characters very much, just
kinda presents them to you and says "here, look at these."  The
specific words used in _Window_ are important, moreso than in standard
IF, since you have to type in certain ones.  That's about all I can
think of off the top of my head.  I'm sure there's a better single
reason that would explain all these, but I can't think of it at the moment.

>--Z
--
dan shiovitz scythe@u.washington.edu shiov@cs.washington.edu
slightly lost author/programmer in a world of more creative or more 
sensible people ... remember to speak up for freedom because no one else
will do it for you: use it or lose it ... carpe diem -- be proactive.
my web site: http://weber.u.washington.edu/~scythe/home.html some ok stuff.



From mulveyr@frontiernet.net Wed Apr 23 13:27:29 MET DST 1997
Article: 24830 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!newsfeed.internetmci.com!news.vivanet.com!node2.frontiernet.net!katy
From: katy@katy.aa2ys.ampr.org (Katy Mulvey)
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under the Window Thoughts
Date: 23 Apr 1997 03:47:36 GMT
Organization: Complete and Utter Chaos
Lines: 39
Message-ID: <slrn5lr1fd.cet.katy@katy.aa2ys.ampr.org>
References: <5jivms$24f$1@joe.rice.edu> <erkyrathE91zqG.67r@netcom.com>
Reply-To: mulveyr@frontiernet.net
NNTP-Posting-Host: usr13-75.dial.roc.frontiernet.net
X-Newsreader: slrn (0.9.2.0 BETA UNIX)
Xref: news.lth.se rec.arts.int-fiction:24830

On Tue, 22 Apr 1997 19:06:16 GMT, Andrew Plotkin <erkyrath@netcom.com> wrote:
>So what did you mean by "Interactive Poetry"? I wasn't sure what I meant, 
>even as I was thinking of the phrase. It's obviously nothing to do with 
>rhyme or meter.

I didn't say it originally, but I latched on to the phrase -- I think 
it fits "The Space Under the Window" perfectly. I'm not quite sure 
why, but here are some factors:

+ The piece paints words around emotions/feelings, without coming
  right out and saying "she felt this", and "you felt that."

+ The prose is very tight -- like many poems, it seems that every
  single word was carefully chosen and placed just so.

+ The changing text reminded me of poetry -- where each stanza
  changes the focus somewhat. (And no, I can't think of any 
  specific examples -- "13 ways of looking at a Blackbird",
  perhaps?)

+ It was fiction that made me think; poetry does that more than
  prose for me. I read for enjoyment, mostly the science
  fiction and fantasy that form the backdrop for lots of IF,
  and I don't generally read it in depth, in an anyalytical way.
  Poetry, on the other hand, I read in a deeper way -- there's
  less of it there, so I give more of myself to try to 
  illuminate it. "The Space Under the Window" required that
  sort of approach from me -- it felt the same as reading poetry.

Were you aiming at these sorts of effects when you were writing
the piece? Or was it more of an experiment of getting rid of
verbs?

  Katy

-- 
Katy Mulvey
Home: mulveyr@frontiernet.net  http://www.frontiernet.net/~mulveyr/Katy



From scythe@u.washington.edu Wed Apr 23 18:16:43 MET DST 1997
Article: 24810 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!worldnet.att.net!news.u.washington.edu!scythe
From: scythe@u.washington.edu (Dan Shiovitz)
Newsgroups: rec.arts.int-fiction
Subject: Re: Playing the game vs. fighting the author (was Thoughts on Time and So Far)
Date: 22 Apr 1997 22:19:32 GMT
Organization: University of Washington, Seattle
Lines: 44
Message-ID: <5jjdhk$t4j@nntp5.u.washington.edu>
References: <baf.861135520@max.tiac.net> <Pine.SUN.3.91.970421101155.8364B-100000@nebula.phy.duke.edu> <ant2119260b0c4bn@arnod.demon.co.uk> <Pine.SUN.3.91.970421201455.10879B-100000@nebula.phy.duke.edu>
NNTP-Posting-Host: saul1.u.washington.edu
NNTP-Posting-User: scythe
Xref: news.lth.se rec.arts.int-fiction:24810


In article <Pine.SUN.3.91.970421201455.10879B-100000@nebula.phy.duke.edu>,
Stephen Granade  <sgranade@phy.duke.edu> wrote:
>On Mon, 21 Apr 1997, Julian Arnold wrote:
>
>> Maybe it's not a question of fighting the author vs. playing the game,
>> but one of the degree to which the player is aware of the author's
>> "presence" during play?
>
>Not for me. I have played games in which the author was a very present 
>voice but which gave me no trouble. Contrariwise, I have played games in 
>which the author barely appears at all, yet I feel as if (s)he is always 
>there, attempting to frustrate me.
>
>Perhaps what I feel is a refinement of your statement, Jools: it's a 
>question of the degree to which I am aware of the author's _inimical_ 
>presence during play.


>LOOK
The inimical Andrew Plotkin is here.  He grins evilly at you.

>REPAIR BRIDGE
You start frantically repairing the bridge.  Andrew Plotkin watches
with interest.

>KEEP REPAIRING
You keep going.  Andrew Plotkin pulls a log out from under, and the
bridge collapses in a heap.  "Whoops!" he says.

>REPAIR BRIDGE
Working even faster, you start again.  Andrew Plotkin checks his
watch.  "Uh-oh, you started a turn too late," he says, "you'll never
complete it now.  Guess you'd better RESTART."

>THROW A BRICK AT PLOTKIN
I don't think Andrew Plotkin would appreciate that.

>Stephen
--
dan shiovitz scythe@u.washington.edu shiov@cs.washington.edu
slightly lost author/programmer in a world of more creative or more 
sensible people ... remember to speak up for freedom because no one else
will do it for you: use it or lose it ... carpe diem -- be proactive.
my web site: http://weber.u.washington.edu/~scythe/home.html some ok stuff.


From graham@gnelson.demon.co.uk Wed Apr 23 21:06:45 MET DST 1997
Article: 24845 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Thoughts on Time and So Far
Date: Wed, 23 Apr 1997 14:46:42 +0100 (BST)
Organization: none
Message-ID: <ant2313420b0M+4%@gnelson.demon.co.uk>
References: <baf.861135520@max.tiac.net> <335A7F09.55B4@romulus.sun.csd.unb.ca> <5jg8ee$6fr@bartlet.df.lth.se> <ant2209180b0M+4%@gnelson.demon.co.uk> <5jknps$st2@bartlet.df.lth.se> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 40
Xref: news.lth.se rec.arts.int-fiction:24845

In article <5jknps$st2@bartlet.df.lth.se>, Magnus Olsson
<URL:mailto:mol@bartlet.df.lth.se> wrote:
> 
> Of course, Philip Glass is considered a shallow populist by some people :-).

Anyone who can write a six-hour opera on the life of Einstein
whose only moment of narration or plot comes when someone says
at the end of Act II, "Berne, Switzerland, 1905", cannot be
entirely populist...  Though my favourite is "Akhnaten", to which
I sing along in Akkadian.

> This is totally off topic, of course, but it'd be interesting to make
> a short list of "serious" (== "classical") post-WWI composers who have
> managed to reach a large audience. 
> 
> Some names that come into mind:
> 
> Stravinsky
> Bartok
> Hindemith
> Holst
> Britten
> Orff (really just "Carmina Burana")
> Bernstein (even if you don't count "West Side Story")
> Glass
> Prokofiev (or however you spell him in English)
> Shostakovich
> Rachmaninov (shouldn't count, since he continued to write like in 
> 		the 19th century). 

Gershwin?  Part?  Nyman?  Gorecki?  Taverner?  It's a longer list
than one necessarily expects.

And of course John Williams, author of the themes to Star Wars,
Close Encounters, Raiders of The Same Bars From Star Wars, Schindler's
List, etc.  Or perhaps he ~= serious.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From carl@earthweb.com Wed Apr 23 23:06:46 MET DST 1997
Article: 24852 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!warm.news.pipex.net!pipex!rill.news.pipex.net!pipex!newsfeed.nacamar.de!azure.xara.net!xara.net!news.genuity.net!not-for-mail
From: Carl Muckenhoupt <carl@earthweb.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under the Window Thoughts
Date: Wed, 23 Apr 1997 14:03:42 -0400
Organization: EarthWeb
Lines: 26
Message-ID: <335E4EFE.7757@earthweb.com>
References: <5jivms$24f$1@joe.rice.edu> <erkyrathE91zqG.67r@netcom.com> <slrn5lr1fd.cet.katy@katy.aa2ys.ampr.org>
Reply-To: carl@earthweb.com
NNTP-Posting-Host: ben.earthweb.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:24852

> On Tue, 22 Apr 1997 19:06:16 GMT, Andrew Plotkin <erkyrath@netcom.com> wrote:
> >So what did you mean by "Interactive Poetry"? I wasn't sure what I meant,
> >even as I was thinking of the phrase. It's obviously nothing to do with
> >rhyme or meter.

Partly, it's the fact that it's more descriptive than narrative.  The
form of interactivity is a crucial part of this.  As players, we're more
affected by what we do (can do, are forced to do) than by the results -
that's why, for example, killing the skink in Trinity bothered people so
much.  Lighting lamp, going north, killing troll with sword are prosy
things to do.  Paying attention to a candle - not even examining it, but
making it more important in the totality of one's perceptions - is
decidedly more poetic.

There's also the repetition factor.  Think of the piece not as a single
screenful of text that results from the player's manipulations, but as a
series of such screenfuls, each repeating the last and building on it. 
(I don't know if we're meant to read it this way, but we do.)  This is a
poetic device.  If there's one thing that distinguished poetry from
prose, it's regularity; rhyme and meter are just specific examples of
forms this regularity can take.  The repetition of text with slight
modifications is another.

-- 
Carl Muckenhoupt		carl@earthweb.com
EarthWeb			http://www.earthweb.com/


From erkyrath@netcom.com Thu Apr 24 12:30:32 MET DST 1997
Article: 24857 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!hole.news.pipex.net!pipex!plug.news.pipex.net!pipex!bowl.news.pipex.net!pipex!rill.news.pipex.net!pipex!netcom.net.uk!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Groundhog Day as Interactive Fiction
Message-ID: <erkyrathE93tHD.My5@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5jjdn8$qfa@lori.zippo.com>
Date: Wed, 23 Apr 1997 18:46:25 GMT
Lines: 41
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24857

Daryl McCullough (daryl@cogentex.com) wrote:
> If you haven't already seen it, I highly recommend the movie
> "Groundhog Day" starring Bill Murray and Andy McDowell. Catch
> it on video. I know it would be easy to lump this comedy in with
> the usual lame-brained efforts of Saturday Night Live alumni
> ("Vacation", "Meatballs", "Stripes", "Caddyshack", etc.) but this
> would be a big mistake. In spite of its silliness, and Bill Murray's
> general unlikeableness, Groundhog Day is, I think, a thoughtful
> exploration of what it means to live a good life (or a good day).

I also recommend the movie. (It was nominated for a Hugo (SF) award, 
interestingly. Lost out to whatever megabudget effects special came out 
that year. Jurassic Park, I think.)

> But there is one element that Groundhog Day had that is missing from
> most (if not all) interactive fiction: the motive of the "player"
> evolves as he "plays the game".

Hey, that's actually a pretty old trope. Many games start with a 
motivation of "explore a neat place" and then develop a serious plot. 
_Trinity_, for example. In _AMFV_ you start out doing a job, and then 
discover an important angle that you have to figure out yourself. In 
_Wishbringer_ you start out wanting to deliver a letter... you see what I 
mean.

(I guess you could distinguish between changing *goals* and changing 
*motivation*, but is there really a difference?)

>  I don't know, maybe it would be enough
> to discover Zarf's bridge from "A Change in the Weather" while searching
> for the magic sword.

Well, I did try to establish an opening motivation in "Weather" which 
radically changes as the game goes on. That's sort of the point.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From daryl@cogentex.com Thu Apr 24 12:32:42 MET DST 1997
Article: 24850 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!stdio!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!news.emi.com!usenet
From: Daryl McCullough <daryl@cogentex.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Wed, 23 Apr 1997 15:29:47 -0400
Organization: CoGenTex
Lines: 31
Message-ID: <335E632B.6AD4@cogentex.com>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com>
NNTP-Posting-Host: mali.cogentex.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (WinNT; I)
Xref: news.lth.se rec.arts.int-fiction:24850

Andrew Plotkin wrote:

> > But there is one element that Groundhog Day had that is missing from
> > most (if not all) interactive fiction: the motive of the "player"
> > evolves as he "plays the game".
> 
> Hey, that's actually a pretty old trope. Many games start with a
> motivation of "explore a neat place" and then develop a serious plot.
> _Trinity_, for example. In _AMFV_ you start out doing a job, and then
> discover an important angle that you have to figure out yourself. In
> _Wishbringer_ you start out wanting to deliver a letter... you see what I
> mean.
> 
> (I guess you could distinguish between changing *goals* and changing
> *motivation*, but is there really a difference?)

Well, I would like to make a subtle distinction. In the examples you
give,
the original goal is filler until the player discovers his *true* goal.
What I would like, (but maybe this is slightly harder to pull off) is a
game in which there is a surface-level goal---and the player can, if he
wishes, win the game by pursuing this goal---but there are also subtler
goals that the player can discover for themselves, and choose to pursue
or not. Maybe, even if you *can* win the game, that isn't what you
really
want to do. In real life, not everyone becomes a billionaire, and
(in the words of Stewart Smalley) that's OK.

Daryl McCullough
CoGenTex, Inc.
Ithaca, NY


From mkkuhner@phylo.genetics.washington.edu Thu Apr 24 12:33:27 MET DST 1997
Article: 24864 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: 23 Apr 1997 20:19:20 GMT
Organization: University of Washington, Seattle
Lines: 40
Message-ID: <5jlqs8$kqg@nntp5.u.washington.edu>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <335E632B.6AD4@cogentex.com>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:24864

In article <335E632B.6AD4@cogentex.com> Daryl McCullough <daryl@cogentex.com> writes:

>Well, I would like to make a subtle distinction. In the examples you
>give,
>the original goal is filler until the player discovers his *true* goal.
>What I would like, (but maybe this is slightly harder to pull off) is a
>game in which there is a surface-level goal---and the player can, if he
>wishes, win the game by pursuing this goal---but there are also subtler
>goals that the player can discover for themselves, and choose to pursue
>or not. Maybe, even if you *can* win the game, that isn't what you
>really want to do.

I thought _Jigsaw_ was fairly successful at this--and illustrated, in
the process, one of the hazards.  I found myself impatient with the
episode right before the epilogue, because I'd figured out what my
real goals were, but the game stubbornly wanted me to save the world 
first. 

If you don't want to hit the player over the head with "This is your
goal", you're going to have to write a very flexible game with a lot
of options and endings.  If you want the player/character to really
experience the kind of thing that happens in _Groundhog Day_ you need
not to put the player in the position of "Do it this way or you can't
progress".  (This is a common failing of RPG scenarios that try to
deal with personal growth.) 

I've never tried this in IF, but in RPGs dealing with such issues I've 
found it fundamentally important not to cut the game off when it goes 
down a "wrong" path.  Whether the message is positive or not, having
the game end early tells the player "That wasn't what you were supposed
to do."  (How many people found the instant-win solutions to "A Change 
in the Weather" or "I-0" satisfactory?)  The player needs to have time
to explore the consequences of her choices, or they aren't meaningful
ones.  This makes for a nasty decision tree.  In RPGs I cope by only
planning one session ahead, and by using various tricks to keep the
decision space managable--in particular, setting the game in a carefully
restricted locale can help.  If you know *all* the people the PC can
meet, you can't be surprised by who he decides to shack up with.

Mary Kuhner mkkuhner@genetics.washington.edu


From lpsmith@rice.edu Thu Apr 24 23:05:33 MET DST 1997
Article: 24900 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeed.nacamar.de!uunet!in1.uu.net!128.42.5.19!rice!ural.owlnet.rice.edu!lpsmith
From: lpsmith@rice.edu (Lucian Paul Smith)
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under the Window Thoughts
Date: 24 Apr 1997 16:52:51 GMT
Organization: Rice University, Houston, Texas
Lines: 27
Distribution: world
Message-ID: <5jo353$kt2$1@joe.rice.edu>
References: <erkyrathE91zqG.67r@netcom.com> <5jllcj$2ja@news.cuny.edu>
NNTP-Posting-Host: ural.owlnet.rice.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:24900

: In Article <erkyrathE91zqG.67r@netcom.com>
: erkyrath@netcom.com (Andrew Plotkin) writes:
: >So what did you mean by "Interactive Poetry"? I wasn't sure what I meant, 
: >even as I was thinking of the phrase. It's obviously nothing to do with 
: >rhyme or meter.

There were a few reasons.  First of all, "it just felt like it".  I think 
the reason a lot of people have used this phrase is because it connects 
on some visceral level, way before it gets analyzed.

However, not to let this stop me from analyzing it,...

Although it is not broken visually into short phrases, it is still 
segmented this way conceptually.  (This would be even more obvious 
looking at the source code, where it _would_ be broken up visually.)

Also, the 'message' of the piece is left indistinct, ready for the reader 
to superimpose their own experiences and beliefs before anything clear 
can be realized.  Alternately, it can be left alone, and simply 
appreciated for the beauty of the vagueness there already.

One way to sum it up would be to say that if you took all the qualities 
that 'poetry' might embody, then subtract those qualities that a limerick 
embodies, you'd end up with the set of poetic qualities which 'Window' 
still contains ;-)

-Lucian "Lucian" Smith


From mkkuhner@phylo.genetics.washington.edu Sun Apr 27 20:38:16 MET DST 1997
Article: 24948 of rec.arts.int-fiction
Path: news.lth.se!solace!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!hunter.premier.net!newsfeeds.sol.net!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Decorations for hiding objects - your o
Date: 26 Apr 1997 14:46:59 GMT
Organization: University of Washington, Seattle
Lines: 22
Message-ID: <5jt4h3$nfc@nntp5.u.washington.edu>
References: <9704260059.1hig@darkside.demon.co.uk>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:24948

In article <9704260059.1hig@darkside.demon.co.uk> adam@darkside.demon.co.uk writes:

> DH> What if
> DH> a piece was hiding in the grass (which is mentioned in the ldesc), but
> DH> is only a decoration so it isn't mentioned as its own important object. 
> DH> Would this seem unfair to you or strike you as hard?

>It's no more unfair than a whole barrel-load of similar puzzles. However, it is
>a very unfulfilling puzzle; it's one of those things that you need to stumble
>across rather than solve by logical means...

You could make it more fulfilling.  Perhaps an NPC says "I must have
dropped the piece when I was running from the grue!" and now you 
need to figure out where he was when he was running from the grue,
and then search there.

In general I'm okay with such puzzles when there is a solid reason to
search the particular locale, but a game that forces me to search 
*every* locale will annoy me very fast.  This also applies to "look
under" and "look behind" type concealment.

Mary Kuhner mkkuhner@genetics.washington.edu


From dsglasser@hotmail.com Mon Apr 28 10:06:03 MET DST 1997
Article: 24949 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!rill.news.pipex.net!pipex!howland.erols.net!cam-news-hub1.bbnplanet.com!cam-news-feed3.bbnplanet.com!news.bbnplanet.com!news.inc.net!news.itis.com!25.ts3.icdc.com!user
From: dsglasser@hotmail.com (David Glasser)
Newsgroups: rec.arts.int-fiction
Subject: [ANNOUNCE] MIB A.K.A. Avalon
Date: Sat, 26 Apr 1997 11:48:16 +0325
Organization: TAFA
Lines: 20
Message-ID: <dsglasser-2604971148170001@25.ts3.icdc.com>
NNTP-Posting-Host: olaf.viewnetinc.com
Xref: news.lth.se rec.arts.int-fiction:24949

We've been hearing a lot about copyright on names on this group.  Well,
now AFAT Games is coming out with

MIB A.K.A. Avalon
An Interactive Copyright Claim

by Divad Ressalg

"The best game since Silence of the Lambs!" --PLUGHnews

Yes, this game will provide seconds of fun for the whole family!  With a
record breaking 1 room and 3 objects, you can do such great things as use
an automatic travel thingy to go to Avalon from Cape May, wear a black
suit, and more!!  (Well, actually there isn't more.)

Not related to the movie, comic book, or *good* piece(s) of IF of the same name.

Coming soon to an IF-ARCHIVE near you...
dsglasser@hotmail.com
http://www.geocities.com/SoHo/6028/


From -@-.- Mon Apr 28 10:08:16 MET DST 1997
Article: 24973 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!news.maxwell.syr.edu!howland.erols.net!usc!chi-news.cic.net!ihug.co.nz!news
From: - <-@-.->
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Screen Size Parameters and "Amusing" Alternatives
Date: Mon, 28 Apr 1997 14:52:18 +1300
Organization: -
Lines: 46
Message-ID: <336402D1.7713@-.->
References: <862181192.28955@dejanews.com>
Reply-To: -@-.-
NNTP-Posting-Host: 203.29.162.120
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)
To: ravipind@linux.kirbynet.lafayette.edu
Xref: news.lth.se rec.arts.int-fiction:24973

ravipind@linux.kirbynet.lafayette.edu wrote:
> 
> Hi.
> 
> I had a couple quick INFORM questions that I'm hoping the gurus can
> answer:
> 
> 1) How do I get data on the size of the screen my game is being played on?
>  I already know about screen width (by seeing how center.h does it), but
> what about the LENGTH? (ie how many lines can I print before a [more]
> shows up?)  This is important to me because I want the screen formated
> exactly the same way no matter who's playing the game.
> 
The screen height is stored in byte $20 of memory so you access it using
(0->$20)
The width is in byte $21
(0->$21)

> For example, I want to put a single line at the bottom of the screen.  How
> do I know how many carriage returns (^s) to put?
Have a look in the Z-machine specification, I think there's an assembly
opcode for setting cursor position

 
> [Problem: Don't some interpreters print from the top-down and others from
> the bottom-up?  How does TRINITY do this at the beginning of the game?]
I don't think so, they should all print from the top down.  Some games
may print a whole lot of carriage returns to make the other seem to
happen.

-- 
Nicholas Daley
<mailto:daleys@ihug.co.nz>

Everyone agreed it was a splendid funeral, but no one enjoyed it more
than the deceased himself.
--Pt1 C11 Red Dwarf  Grant Naylor

Anybody sending unsolicited advertising to my email address, or adding
this
email address to a mailing list or database without my permission, or
the
permission of any of the other people using this email address WILL face
legal action for collection of personal information without permission
under
the New Zealand Privacy Act.


From erkyrath@netcom.com Mon Apr 28 10:13:16 MET DST 1997
Article: 24971 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.uoregon.edu!tezcat!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news-peer.sprintlink.net!news.sprintlink.net!sprint!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] Screen Size Parameters and "Amusing" Alternatives
Message-ID: <erkyrathE9Bu5E.Cro@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <862181192.28955@dejanews.com>
Date: Mon, 28 Apr 1997 02:41:38 GMT
Lines: 56
Sender: erkyrath@netcom12.netcom.com
Xref: news.lth.se rec.arts.int-fiction:24971

ravipind@linux.kirbynet.lafayette.edu wrote:

> 1) How do I get data on the size of the screen my game is being played on?
>  I already know about screen width (by seeing how center.h does it), but
> what about the LENGTH? (ie how many lines can I print before a [more]
> shows up?)  This is important to me because I want the screen formated
> exactly the same way no matter who's playing the game.

> For example, I want to put a single line at the bottom of the screen.  How
> do I know how many carriage returns (^s) to put?

You don't. On my interpreters, at least, this information is not 
accessible. 

There's a way for the game to find the screen width and height -- see the
z-spec -- but I have to use those slots to store the *status window's*
width and height. (The status window is the one which supports cursor 
positioning, after all.) 

Since the game window is a separate window, whose size is different, and
has no meaningful width anyway (since it uses proportional fonts), and can
in any case be resized by the user at any time, there's no meaningful
information for me to store and no place for me to store it. 

> [Problem: Don't some interpreters print from the top-down and others from
> the bottom-up? 

Yes. At the beginning of the game, or after the screen is cleared, some 
interpreters leave the cursor at the top of the screen and some at the 
bottom.

> How does TRINITY do this at the beginning of the game?]

It doesn't. On interpreters that leave the cursor at the top, the initial 
copyright message and then the opening text appear at the top.

> 2) I want an AMUSING section, but I don't want the command to be AMUSING.
>  How do I change the command?  I know already how to change the MESSAGE
> that's printed at the end of the game (by fidling with the library
> messages) but how do I change the command typed it?  Also, I want it to
> work exactly as AMUSING works (ie you can't get to it until you finish the
> game).

> Would the easiest way to go about this be disabling AMUSING, changing the
> library message, and then making a command that checks the deadflag?

It's not too hard to hack -- er, adjust -- the library so that it checks 
for a programmer-defined word, rather than 'amusing'. Just look at the
end-of-game code.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mkkuhner@phylo.genetics.washington.edu Mon Apr 28 12:23:18 MET DST 1997
Article: 24906 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.radio.cz!CESspool!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news-peer.sprintlink.net!news.sprintlink.net!sprint!uunet!in2.uu.net!140.142.64.3!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: 24 Apr 1997 22:08:32 GMT
Organization: University of Washington, Seattle
Lines: 43
Message-ID: <5joll0$gtd@nntp5.u.washington.edu>
References: <335E632B.6AD4@cogentex.com> <5jlqs8$kqg@nntp5.u.washington.edu> <5jlu6f$b5k@lori.zippo.com>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:24906

In article <5jlu6f$b5k@lori.zippo.com> daryl@cogentex.com (Daryl McCullough) writes:
>mkkuhner@phylo.genetics.washington.edu (Mary Kuhner) says...

>>I thought _Jigsaw_ was fairly successful at this--and illustrated, in
>>the process, one of the hazards.  I found myself impatient with the
>>episode right before the epilogue, because I'd figured out what my
>>real goals were, but the game stubbornly wanted me to save the world 
>>first.

>I haven't played that game (I'm embarrassed to admit), but maybe it's
>because you came up with a notion of "winning" that the author didn't
>anticipate?

Jigsaw seems intrinsically to have several goals, and the one I fixed on
was certainly part of the author's intent, but we disagreed on relative
importance.  I latched onto the little personal goal by preference to
the Big Thing, which made my last few encounters with the Big Thing
rather frustrating (in a very in-character way; I had a distinct sense
of the character saying "But what about ....?")

I was pleased, on the whole, with how Jigsaw handled this; I fixed on
my little personal goal well before it was clear to me that the game
really supported it, and I was happy not to find it intractable.  There
were just some problems with pacing and emphasis.

A looser plot structure would help.  Not really possible for Jigsaw, but
something to remember in general.  If the PC has to go through certain
key scenes in a certain order, there's a lot less room for player-
determined goals.

For me, avoiding tightly timed puzzles and highly lethal situations
helps if you want me to think about character motivations.  If the game
is not too lethal, I can fool around with various character-driven
goals and even indulge in characterization activities (like a second
"LOOK" at something that really surprised the character, or "PRAY"
when confronted with something scary, or trying to tie up the mouth of
the corpse in Trinity).  If I know I'll get clobbered for this, I'll
stop trying.

Room to move about, both physically and logically, provides more scope
for character decisions.

Mary Kuhner mkkuhner@genetics.washington.edu


From graham@gnelson.demon.co.uk Mon Apr 28 12:23:25 MET DST 1997
Article: 24924 of rec.arts.int-fiction
Path: news.lth.se!solace!mn6.swip.net!weld.news.pipex.net!pipex!burn.news.pipex.net!pipex!hose.news.pipex.net!pipex!warm.news.pipex.net!pipex!rill.news.pipex.net!pipex!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Fri, 25 Apr 1997 14:58:43 +0100 (BST)
Organization: none
Message-ID: <ant251343345M+4%@gnelson.demon.co.uk>
References: <335E632B.6AD4@cogentex.com> <5jlqs8$kqg@nntp5.u.washington.edu> <5jlu6f$b5k@lori.zippo.com> <5joll0$gtd@nntp5.u.washington.edu> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 30
Xref: news.lth.se rec.arts.int-fiction:24924

In article <5joll0$gtd@nntp5.u.washington.edu>, Mary K. Kuhner
<URL:mailto:mkkuhner@phylo.genetics.washington.edu> wrote:
> 
> Jigsaw seems intrinsically to have several goals, and the one I fixed on
> was certainly part of the author's intent, but we disagreed on relative
> importance.  I latched onto the little personal goal by preference to
> the Big Thing, which made my last few encounters with the Big Thing
> rather frustrating (in a very in-character way; I had a distinct sense
> of the character saying "But what about ....?")
> 
> I was pleased, on the whole, with how Jigsaw handled this; I fixed on
> my little personal goal well before it was clear to me that the game
> really supported it, and I was happy not to find it intractable.  There
> were just some problems with pacing and emphasis.

Yes, I think this is a just criticism.  In mitigation, the fact that
the middle 15 scenes need to be playable in many different orders makes
it very hard to achieve narrative development -- though there is some,
I hope, and somewhere I have a tree diagram of all possible orders
the game can be played in.  And a few lines of dialogue float from
scene to scene in the sense that they only occur after a certain time
has elapsed, and so on.

Of course I might remark that it's not obvious that Black is entering
the time zones in the same order that White is, and if that doesn't
complicate personal relations I'm not sure what does...

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From max@alcyone.com Mon Apr 28 12:24:04 MET DST 1997
Article: 24917 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!howland.erols.net!newshub2.home.com!newshub1.home.com!news.home.com!enews.sgi.com!news.corp.sgi.com!news.sgi.com!news.spies.com!nixon.area.com!not-for-mail
From: Erik Max Francis <max@alcyone.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Thu, 24 Apr 1997 22:37:11 -0700
Organization: Alcyone Systems
Lines: 19
Message-ID: <33604307.3C466314@alcyone.com>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <5jmkim$7vt@kjahds.com> <5jo9iv$ni8@lace.colorado.edu>
NNTP-Posting-Host: newton.alcyone.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (X11; I; Linux 2.0.29 i686)
Xref: news.lth.se rec.arts.int-fiction:24917

Matthew Crosby wrote:

> Floyd used to comment when you saved, as well as when you quit.  But
> that was tounge in cheek and nothing ever came out of it.

He'd also say something amusing like, "Oh boy, I've never seen my name in
print before!" when you type SCRIPT, and something like, "Be sure to give
me a copy of the output!" when you typed UNSCRIPT.

I enjoyed Planetfall as it was the first Infocom game I solved without any
outside help whatsoever.

-- 
       Erik Max Francis, &tSftDotIotE / email / max@alcyone.com
                     Alcyone Systems /   web / http://www.alcyone.com/max/
San Jose, California, United States /  icbm / 37 20 07 N  121 53 38 W
                                   \
                      "The future / is right there."
                                 / Bill Moyers


From jota@tiac.net Mon Apr 28 12:24:11 MET DST 1997
Article: 24919 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!europa.clark.net!newsfeed.nacamar.de!uunet!in3.uu.net!199.0.65.182!news-in.tiac.net!posterchild!jota
From: jota@tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: 25 Apr 97 09:25:38 GMT
Organization: The Internet Access Company, Inc.
Lines: 18
Message-ID: <jota.861960338@sunspot>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <5jmkim$7vt@kjahds.com> <5jo9iv$ni8@lace.colorado.edu> <33604307.3C466314@alcyone.com>
NNTP-Posting-Host: sunspot.tiac.net
X-Newsreader: NN version 6.5.0 #2 (NOV)
Xref: news.lth.se rec.arts.int-fiction:24919


Erik Max Francis <max@alcyone.com> writes:
>Matthew Crosby wrote:

>> Floyd used to comment when you saved, as well as when you quit.  But
>> that was tounge in cheek and nothing ever came out of it.

>He'd also say something amusing like, "Oh boy, I've never seen my name in
>print before!" when you type SCRIPT, and something like, "Be sure to give
>me a copy of the output!" when you typed UNSCRIPT.

And you can't forget about when you type VERSION: "Last version was
better. More bugs. Bugs make game fun."


--
                                      /<-= Admiral  Jota =->\
                                    -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  -= -=->/


From jarobe@po.eecs.berkeley.edu Mon Apr 28 12:29:34 MET DST 1997
Article: 24914 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!news1.best.com!nntp1.ba.best.com!not-for-mail
From: Jake Roberts <jarobe@po.eecs.berkeley.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Thu, 24 Apr 1997 21:27:19 -0700
Organization: No
Lines: 79
Message-ID: <336032A6.285E@po.eecs.berkeley.edu>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com>
Reply-To: jarobe@po.eecs.berkeley.edu
NNTP-Posting-Host: dynamic22.pm01.wc.best.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:24914


Andrew Plotkin wrote:

> I also recommend the movie. (It was nominated for a Hugo (SF) award,
> interestingly. Lost out to whatever megabudget effects special came out
> that year. Jurassic Park, I think.)

Wow, that's interesting.  Now that I think of it, the movie was a far
better example of speculative sci-fi than one normally sees in the
movies.  Not just because the concept was clever, but because the movie
wrung the possibilities out of it so thoroughly.  There wasn't much I
would think of doing, if I had the same day over and over again, that
Bill Murray didn't try in the film.  It was funny, too.

> 
> > But there is one element that Groundhog Day had that is missing from
> > most (if not all) interactive fiction: the motive of the "player"
> > evolves as he "plays the game".
> 
> Hey, that's actually a pretty old trope. Many games start with a
> motivation of "explore a neat place" and then develop a serious plot.
> _Trinity_, for example. In _AMFV_ you start out doing a job, and then
> discover an important angle that you have to figure out yourself. In
> _Wishbringer_ you start out wanting to deliver a letter... you see what I
> mean.
 
My impression was that the original poster meant something different
than what you're describing here.  Rather than the PC's motivations
changing between the beginning of the game (or story, if you like) and
the end, what if they changed between one complete playing of the game
and the next.  So
you could play through from beginning to end, achieving an experience
that was complete in sense (you got all the treasures stuffed in a
glass-topped case), but apon playing through again (which in itself is
an unusual activity, at least for me) you would discover new dimensions
to the game world, people places and things that were only in your
peripheral vision when you were working through the first time, gain new
signifigance, and in the process of investigating them more closely, you
develop new and hopefully more compelling objectives.  It's like having
one (or more) games hidden inside another.

I'm quite taken with the idea of explicitly encorporating into the
game's story, or logic, or broad concept, the fact that the player will
be entering and exiting the game world and different points in time,
replaying the same scenarios over and over again.  

I see games (notably "A Change In the Weather") criticized because there
is (practically speaking) no way to win without replaying parts of the
game more than once.  Why?  Well I suppose because when using
meta-commands, one is retracting oneself from the level of the story and
operating at a higher, fundamentally distinct level.  Meta commands
should be transparent at the story level, because conceptually there is
only one story, only one timeline, no matter how many times we save and
restore.  If saving and restoring is required for the player/character
to finish the game (and thus complete the story) then this abstraction
is violated, and the illusion is ruined.

But why shouldn't an IF game exploit the peculiarities of its medium,
trancend the level distinction between interpreter commands and acts
taken within the story world.  A Groundhog Day-like time loop would be a
very direct way of doing this, making explicit and reasonable the need
to die-and-restart in order to win.  (The puzzle from Fool's Errand
mentioned in another thread (although I don't remember it myself)
embodies this same kind of trancendance, IMO.) 

> (I guess you could distinguish between changing *goals* and changing
> *motivation*, but is there really a difference?)

The difference I'm trying to highlight is whether the change happens
within a plotline, or across multiple plotlines. 

- Jake

> 
> --Z
> 
> --
> 
> "And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
> borogoves..."


From rglasser@penning.lanl.gov Mon Apr 28 12:31:45 MET DST 1997
Article: 24958 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Sun, 27 Apr 1997 01:13:27 -0700
Organization: UCSD
Lines: 108
Message-ID: <33630AA7.2A59@penning.lanl.gov>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <336032A6.285E@po.eecs.berkeley.edu> <Pine.SGI.3.95q.970425144947.20066A-100000@irix.bris.ac.uk>
NNTP-Posting-Host: sdx-ca11-21.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Sun Apr 27  1:19:42 AM PDT 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:24958


Samuel DAF Barlow wrote:
> 
> On Thu, 24 Apr 1997, Jake Roberts wrote:
> 
> > Andrew Plotkin wrote:
> >
> > My impression was that the original poster meant something different
> > than what you're describing here.  Rather than the PC's motivations
> > changing between the beginning of the game (or story, if you like) and
> > the end, what if they changed between one complete playing of the game
> > and the next.  So
> > you could play through from beginning to end, achieving an experience
> > that was complete in sense (you got all the treasures stuffed in a
> > glass-topped case), but apon playing through again (which in itself is
> > an unusual activity, at least for me) you would discover new dimensions
> > to the game world, people places and things that were only in your
> > peripheral vision when you were working through the first time, gain new
> > signifigance, and in the process of investigating them more closely, you
> > develop new and hopefully more compelling objectives.  It's like having
> > one (or more) games hidden inside another.
> >
> 
> I'm always trying this when I replay games - especially infocom's
> detective games (which I mentioned about a month ago in a post about
> "save/restore" as time-travel-esque devices, which is kind of like some
> of the ideas in the "groundhog" posts). The fact that there are
> characters in the games who change with time and whose motivation you
> only understand when you have won the game means that when re-playing
> one often thinks "Right now Mr.X is in the Kitchen disposing of the
> murder weapon..although to win the game I have to hide and then fish the
> weapon out of the bin, couldn't I suprise him and bribe half of the
> inheritance out of him?". This kind of attitude arises out of the game
> having characters who have
>         (a) Motivations
>         (b) Actions which they carry out
> So the "ground-hog changing motivation" concept already exists in
> these games, it's just that the programmers haven't allowed for it in
> their games.

	You're talking about gaining free knowledge through some elaborate 
sequence of actions, then restoring the game, still keeping a mental image 
of what's coming later.  By doing this you gain advanced knowledge of what 
will happen soon, without making your character go through the motions of 
acquiring that knowledge.
	This approach makes more sense for some genres than for others.  For 
example, in a game like "So Far" which is almost self-consciously surreal, 
or a game like "Tapestry" where the whole POINT is to explore the various 
possibilities of how things could have turned out differently, it's entirely 
fitting and proper that replaying the game should add more to the 
experience.
	On the other hand, in the detective games I find it bothersome, 
since it seems like these stories should be more similar to real life. That 
whole "I know Mr. X is in the kitchen now because I accidentally barged in 
on him before I restored, so now I should hide" syndrome sounds awfully 
familiar.

	[WARNING: Spoilers for Suspect ahead]


	I think "Suspect" was one of the worst offenders of this kind of 
thinking.  I remember very clearly thinking "Gee, I need to talk to Richard 
before he comes in contact with other characters and learns about the 
murder, but I don't know where he is when the game begins."  So I save the 
game, wait for him to appear, restore, go to the place where he came from, 
and repeat the process until I find his starting room.  It's hard to 
reasonably invent a situation where a real detective could have this luxury, 
and that is one heck of a mood breaker.
	Many other times in Suspect, you absolutely have to "happen to" be 
in the right place at the right time.  Fail to answer the door and notice 
the rain when Alicia rings, and you can't win.  In order to understand what 
Michael is up to, you have to hide behind the car, THEN race him to the 
library and hide behind the chair, THEN catch up to him at the fireplace 
before his document burns.  How would a reasonable person guess all that, 
given that he would only have one chance to get it right in real life?  He 
wouldn't.
	I don't mind dying or getting stuck when I make the wrong moves; 
it's part of the game.  But when all's said and done and the game is over, I 
would like to think "It's at least within the realm of possibility that I 
could have won the game on the first try without ever restoring, simply by 
virtue of good logical thinking and insights which I eventually had.  Maybe 
I would have survived if I were actually thrust into this situation."  Most 
of the later, plot-driven Infocom games were "fair" in this sense; you 
didn't really have to die in order to find what you were looking for.  
"Border Zone", although tricky, just barely passes the test.  ("Okay, I know 
that patch of blood is suspicious, and I shouldn't be caught with these 
physical documents on me, so logically I should...")  I even thought "Change 
In The Weather" passed this test successfully, in spite of its apparent 
unfairness.  Games which failed quite miserably in this regard included 
Suspect, Trinity (Who would ever have completed the entire New Mexico 
sequence successfully without mapping out a route based on previous life 
experience?), Suspended (positioning those robots with perfect timing is 
nearly impossible), and Starcross (How many times did you lose those colored 
disks too early?  How many times did you kill yourself in the endgame when 
you were using trial and error on the controls?).
	I think "A Mind Forever Voyaging" handled this more gracefully than 
any other game in history, one of the many reasons why it's probably my 
favorite text adventure.  You DO learn more and discover additional nuances 
by replaying the game.  But "replaying the game" actually makes sense given 
the context of running a computer simulation.  Sort of like Groundhog Day.  
(Glasser makes a heroic effort to get back on topic!!!  He fails!!!!!)
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From obrian@ucsu.Colorado.EDU Mon Apr 28 12:32:14 MET DST 1997
Article: 24926 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in3.uu.net!128.138.243.15!csnews!boulder!ucsu.Colorado.EDU!obrian
From: Paul O'Brian <obrian@ucsu.Colorado.EDU>
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: Fri, 25 Apr 1997 08:34:58 -0600
Organization: University of Colorado at Boulder
Lines: 44
Message-ID: <Pine.GSO.3.96.970425082124.24777A-100000@ucsu.Colorado.EDU>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <336032A6.285E@po.eecs.berkeley.edu>
NNTP-Posting-Host: ucsu.colorado.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
NNTP-Posting-User: obrian
In-Reply-To: <336032A6.285E@po.eecs.berkeley.edu>
Xref: news.lth.se rec.arts.int-fiction:24926

On Thu, 24 Apr 1997, Jake Roberts wrote:

> So you could play through from beginning to end, achieving an experience
> that was complete in sense (you got all the treasures stuffed in a
> glass-topped case), but apon playing through again (which in itself is
> an unusual activity, at least for me) you would discover new dimensions
> to the game world, people places and things that were only in your
> peripheral vision when you were working through the first time, gain new
> signifigance, and in the process of investigating them more closely, you
> develop new and hopefully more compelling objectives.  

One big difference is that the Bill Murray character in "Groundhog Day"
was *forced* to "Restart". To extend the IF analogy, it would be as if
after a predetermined number of moves, the game automatically restarted
whether the player said so or not. In fact, I think the movie makes pretty
clear that the character would not have discovered these deeper dimensions
in life if he had not been forced to live through the same day over and
over, and by the end his real goal is to escape the time loop so that he
can start his new life. 

If an IF game were to adopt this strategy, it would avoid the problems of
all data being lost at every restart. The game could enforce a limited day
length at the end of which the player must sleep (a la Planetfall) and
upon waking would find herself back aboard the Feinstein, or whatever the
starting locale for that game was. This loop would continue until a
certain flag gets tripped (the player_in_love flag, for example) which
would allow the player to wake up in the endgame. Perhaps subtle things
could even change in later iterations. In this scenario, if the player
herself commanded "Restart," it would put her at the top of the first
iteration of the time loop.

Hmm. Sounds interesting, eh? If I didn't already have too many ideas and
too little time for the competition, I might be tempted to give it a try
myself. Maybe not, though. I think it would take some exceptionally
skilled writing to create a world that can gradually reveal such depth in
a limited number of moves. I'd love to see it happen, though.

Paul O'Brian                                     obrian@ucsu.colorado.edu
Remember Zork & Planetfall? Explore the Interactive Fiction Renaissance!
WWW: XYZZYnews at www.xyzzynews.com * FTP: The IF Archive at ftp.gmd.de
USENET: rec.arts|games.int-fiction * CD: Masterpieces of Infocom (US $20)





From graham@gnelson.demon.co.uk Mon Apr 28 12:34:19 MET DST 1997
Article: 24923 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.se.dataphone.net!nntp.uio.no!newsfeed.nacamar.de!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: comp.ai.games,rec.arts.int-fiction,alt.hypertext
Subject: Re: Chris Crawford's new IF engine
Date: Fri, 25 Apr 1997 14:52:59 +0100 (BST)
Organization: none
Message-ID: <ant251359868M+4%@gnelson.demon.co.uk>
References: <5ibi0s$gen$1@Venus.mcs.net> <5iljpp$ahu@nntpb.cb.lucent.com> <335F8763.4BCF6407@alcyone.com> <5jo9sb$8sm$1@news0.xs4all.nl> <335fc6df.0@news.tamu-commerce.edu> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 55
Xref: news.lth.se comp.ai.games:8730 rec.arts.int-fiction:24923 alt.hypertext:15263

In article <335fc6df.0@news.tamu-commerce.edu>, <URL:mailto:earendil@> wrote:
>
> Bad example.  The copyrights on Sherlock Holmes ran out many years ago.
> Hence Infocom's game "Sherlock: Riddle of the Crown Jewels".  Copyright
> law has changed a lot as the 20th century has progressed, but pretty much
> everything up to the first World War is out of copyright in the States.

(Queasy noises)  U.S. copyright law is tangled because the Berne
convention's most recent 70-year rule and "moral right" have only
just been incorporated (1993?), and the rules about transition are fiddly.
But note that it is far from true in Europe, anyway, that pretty much
everything up to WW1 is out of copyright.  E. M. Forster's novel
"Where Angels Fear to Tread", published 1905 or so, will only escape
copyright in 2030 or so.

Unhappily, the most recent copyright law in the U.K. (introducing
the above Berne rules over here) actually brought back into copyright
a fair slice of works which had lost it in the previous 20 years.
This overturned previous conventions that once out, copyright could
never be restored...  The case law on this will be horrid.

For the sake of an anthology of modern French poetry for teaching
purposes, I actually read the whole of the U.K.'s copyright
legislation.  (Because a university legal office was being absurdly
obstructive and trying to block the whole project, for fear that we
might do something that would involve them in liability -- they
actually refused even to tell us what would be permitted.)

There's one very nice moment -- normal copyright law applies to every
work by every author _except_ "Peter Pan", by J. M. Barrie.  Barrie
left all his royalties in this to Great Ormond's Street Hospital
for Sick Children, in London, and they're worth enough to keep the
hospital going, even today, apparently.  Copyright should have expired
at the end of (I think) 1987, just as the new law was being put
through Parliament.  But Lord Callaghan (a much-loved Prime Minister,
for those not of these shores) pulled off a legally ridiculous
amendment in the House of Lords, with hearts melting on all sides,
to keep it in copyright forever.  (Only in the U.K., of course.)
The irony of this is irresistable to legal commentators --
"all books go out of copyright, that is their tragedy; Peter Pan
never does, and that is his."

> The copyright on the Zork will last well into the next century.  The
> trademark will last only as long as Activision actively uses the name.  If
> Infocom had patented the z-machine in 1979, the patent would have run out
> last year...

Which presumably applies to "Interlogic [tm]", whatever that was.

(Actually, I wouldn't be surprised if copyright on "Zork" is effectively
prolonged by the Zork sequels.)

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From daly@PPD.Kodak.COM Tue Apr 29 17:53:03 MET DST 1997
Article: 24996 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news-peer.sprintlink.net!sprint!news-pull.sprintlink.net!news.sprintlink.net!news-fw-22.sprintlink.net!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disabling Undo
Date: 29 Apr 1997 14:46:59 GMT
Organization: Eastman Kodak Company
Lines: 44
Message-ID: <5k51l3$dp7$1@kodak.rdcs.Kodak.COM>
References: <862320337.25100@dejanews.com>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com
Xref: news.lth.se rec.arts.int-fiction:24996

In article <862320337.25100@dejanews.com> ravipind@linux.kirbynet.lafayette.edu writes:
>
>Would you be annoyed if a game disabled the UNDO command temporarily.  If,
>during the course of this puzzle, the player typed UNDO, the message would
>come back:
>
>[I'm sorry, but the UNDO command is temporarily disabled.]

Yup.  Is there another way around it?  Here is a transcript that
would get around it in some instances.

--------

The troll raises his club over his head and runs toward you, screaming
"Me spare your life if you know me favorite color!!"

> TROLL, YELLOW

The troll pauses in mid-run and looks deep in thought, as if he cannot
remember his favorite color.  "That might be it.  Me not sure."

> WAIT

The appearance of a 20-watt bulb appears in the troll's mind.  "Me
remember now -- you wrong!"  The club takes your head clean off
-- relatively painless, actually.

You have died.  Would you like to Restart, Restore, Undo, or Quit?

> UNDO

[Move undone]

The troll pauses in mid-run and looks deep in thought, as if he cannot
remember his favorite color.  "That might be it.  Me not sure."

------------

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From jota@tiac.net Wed Apr 30 12:31:44 MET DST 1997
Article: 25006 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!uunet!in2.uu.net!199.0.65.182!news-in.tiac.net!posterchild!jota
From: jota@tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction
Subject: Re: Breaking the fourth wall in IF
Date: 30 Apr 97 07:42:13 GMT
Organization: The Internet Access Company, Inc.
Lines: 14
Message-ID: <jota.862386133@sunspot>
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathe93thd.my5@netcom.com> <5jmkim$7vt@kjahds.com> <5jo9iv$ni8@lace.colorado.edu> <33604307.3c466314@alcyone.com> <33630132.21e4@penning.lanl.gov> <5k68ms$4goa@newssvr02-int.news.prodigy.com>
NNTP-Posting-Host: sunspot.tiac.net
X-Newsreader: NN version 6.5.0 #2 (NOV)
Xref: news.lth.se rec.arts.int-fiction:25006

MKST21C@prodigy.com (Chris Lang) writes:

>    Incidentally, here are a few things to try in Arthur: The Quest for 
>Excalibur.
>ASK IDIOT ABOUT IDIOT. ASK IDIOT ABOUT KRAKEN. ASK IDIOT ABOUT BATES. ASK 
>IDIOT ABOUT MERETZKY. ASK IDIOT ABOUT PLANETFALL. ASK IDIOT ABOUT ZORK. 
>(You can also ask Merlin about Enchanter). 

At one point he'll tell you he's not as dumb as he looks, and tell you to
ask him about anything. ASK IDIOT ABOUT ANYTHING.
--
                                      /<-= Admiral  Jota =->\
                                    -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  -= -=->/


From joe.mason@tabb.com Wed Apr 30 15:53:52 MET DST 1997
Article: 25014 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!torn!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under The Windo
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.8909.1727@tabb.com>
References: <erkyrathE9BuHA.D39@netcom.com>
Date: Tue, 29 Apr 1997 22:04:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 44
Xref: news.lth.se rec.arts.int-fiction:25014

"Re: Space Under The Windo", declared Andrew Plotkin from the Vogon 
ship:

AP>Good point. The problem (if you think it's a problem) is that it
AP>leaves a  lot of unusable words in the text. That is, in your
AP>example, the candle gets  closed off, then the vase gets closed off,
AP>and you get more and more  words which are readable and *used* to
AP>work, but don't any more.

I agree that this is ugly.  In a perfect world, the candle would still 
expand, just in a different way that fits the current track.  This would 
be much more work, though (does the term "exponential" fit here?  Yes, I 
believe it does.)

AP>Plus, coding was ugly enough when I only had to worry about turning
AP>words  *on*. Having to turn them *off*, too, would have been painful.
AP>(But  possibly worth it.)

There could be a "you focus on the candle and learn nothing" message 
that merely loops you back to the current description.  That way the 
player would know that the candle was still active, just not doing 
anything at the moment.

AP>> BTW, I noticed in one part, looking at the candle would take you to
AP>> the message "You are arranging your flowers when..."  Is this
AP>> intentional? It seems to violate the premise that typing a word
AP>> focuses on that word.

AP>I don't stick to any of the premises very fanatically.

Since this was the only time that this particular violation happened, 
though, I was left wondering if it was a bug.  That particular jump was 
more then I could take, especially since there was no point to it - 
there was a way to reach the same spot in a path that wasn't disjointed.

AP>As I said (did I say it? I forget) I wanted to do more with the
AP>flower  choices; I just ran out of energy before I programmed
AP>anything. Darn.

I don't believe you did.  Consider it said. :-)

Joe

 CMPQwk 1.42 9550 Don't anthropomorphize computers. They hate that.


From joe.mason@tabb.com Wed Apr 30 15:54:45 MET DST 1997
Article: 25012 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!torn!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Inte
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.8907.1727@tabb.com>
References: <5jmkim$7vt@kjahds.com>
Date: Tue, 29 Apr 1997 22:04:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 34
Xref: news.lth.se rec.arts.int-fiction:25012

"Re: Groundhog Day as Inte", declared Kenneth Albanowski from the Vogon 
ship:

KA>By saving and restoring (or undoing) you can effectively shift
KA>probability in your favour (except of course for well-designed
KA>Balancing-type puzzles. :-) Shouldn't the NPC's eventually notice
KA>that there is something odd about the PC, and that no matter what
KA>their evil plans are, the PC somehow manages to escape.

KA>I've no idea what to do with this idea, though. It seems to perhaps
KA>be more relevant to an atmospheric game (like Christminster), but
KA>even then I'm not sure what it would be worth.

Yeah, that's a good idea.  But I wouldn't have the NPC's notice the 
saving/restoring/undoing directly.  Instead, I'd have them keep track of 
what happens to the player, and if none of the bad things happen then 
they would start to comment on the player's amazing luck and stuff like 
that.  So if you manage to play through perfectly on the first try, you 
get the same reactions as if you'd restored a game everytime something 
bad happened to you.

Reactions could range from awe: "He is a wetlander, but he walks through 
the sands like a desertborn!  Surely, this must be the Kwisatz 
Haderach!" to fear: "Stay back!  You have the Dark One's own luck!  I 
won't help you!"

Actually, this could be a good way to make the player choose a branching 
path subtly.  If he succeeds in all his tasks right away, someone won't 
help him later on, which gives some motivation to see the side of the 
story that would happen if he failed at a certain task.

Joe

 CMPQwk 1.42 9550 Madness takes its toll.  Please have exact change


From dmss100@york.ac.uk Fri May  2 15:41:28 MET DST 1997
Article: 25031 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!azure.xara.net!xara.net!uknet!usenet1.news.uk.psi.net!uknet!uknet!yama.mcc.ac.uk!news.york.ac.uk!ebor.york.ac.uk!dmss100
From: Den of Iniquity <dmss100@york.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Space Under The Window
Date: Thu, 1 May 1997 16:07:58 +0100
Organization: The University of York, UK
Lines: 38
Sender: dmss100@york.ac.uk
Message-ID: <Pine.SGI.3.95L.970501155749.21017A-100000@ebor.york.ac.uk>
References: <66.8842.1727@tabb.com> <erkyrathE9BuHA.D39@netcom.com>
NNTP-Posting-Host: ebor.york.ac.uk
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <erkyrathE9BuHA.D39@netcom.com>
Xref: news.lth.se rec.arts.int-fiction:25031

On Mon, 28 Apr 1997, Andrew Plotkin wrote:

>Joe Mason (joe.mason@tabb.com) wrote:
>> Another neat idea, which probably would take a lot to implement, would
>> be to have the encounter with the woman change depending on what flowers
>> you choose.
>
>As I said (did I say it? I forget) I wanted to do more with the flower 
>choices; I just ran out of energy before I programmed anything. Darn.

Grrr... And I spent ages trying out all kinds of different combinations of
flowers. RRRRRRRrrrrrr. <throttles Plotkin-mannikin>

My main impression of the piece was how much it felt like a dream to me...
And not a particularly good one, at that.:) There was only one ending I
came to that I considered to be an optimistic one.

Oh, and I was very impressed at the innovation. I'd like to see more of
this. My suggestion would be to have a number of named characters rather
than objects; naming one character would bring that character into focus
in the story, naming two characters would entwine their lives, as threads
weaved around each other on the loom of fate. (Yeah, back to Piers Anthony
again. Sorry!)

<<<<<<<

"So, Mr Smith, tell me about this recurring nightmare."

"Oh, it's awful - there's this window and these flowers and I go through
the window and there's this candle, and it _scares_ me and there's this
woman, and she doesn't like me, and the vase, for the flowers, but it
doesn't make a difference - and there are eyes, watching me, cold, and
flat, and aloof - and the window - it always, always, always shatters. It
makes me shiver." 

--
Den   Sending unsolicited mail? Insert '.ignore.this.bit' after my address.



From kjfair@midway.uchicago.edu Sat May  3 14:57:24 MET DST 1997
Article: 25056 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!feed1.news.erols.com!howland.erols.net!vixen.cso.uiuc.edu!uchinews!kjfair
From: kjfair@midway.uchicago.edu (Kenneth Fair)
Subject: Re: A note to Avalon Betatesters
X-Nntp-Posting-Host: ntcs-ip255.uchicago.edu
Content-Type: text/plain; charset=ISO-8859-1
Message-ID: <kjfair-ya02408000R0205972254360001@uchinews.uchicago.edu>
Sender: news@midway.uchicago.edu (News Administrator)
Content-Transfer-Encoding: 8bit
Organization: University of Chicago School of Law
X-Newsreader: Yet Another NewsWatcher 2.4.0
References: <5k8mc5$4sp$1@agate.berkeley.edu>
Mime-Version: 1.0
Date: Sat, 3 May 1997 03:54:36 GMT
Lines: 27
Xref: news.lth.se rec.arts.int-fiction:25056


In article <5k8mc5$4sp$1@agate.berkeley.edu>, whizzard@uclink.berkeley.edu
(Gerry Kevin Wilson) wrote:

>If you've been helping to betatest Avalon, read on, otherwise this info is
>of no use to you.
>
>I just put up the latest betatest, and sent out a notice, but got bounced
>e-mail on about half the addresses.  When you consider how old the
>addresses are, that's not too unreasonable.  Anyways, if you've been a
>betatester and wish to continue to be one, drop me an e-mail and I'll clue
>you in on where to ftp to.
>
>Imposters will be 'SNAVIG SLUG'ed.

Evidently there are so many betatesters of Avalon out there that Whizzard
finds it more efficient to post to r.a.i-f than email them individually.

I figure that by the time Avalon actually comes out, everyone reading
the newsgroup will actually *be* a betatester.  It's like having a parade
in a small town; only three people actually show up to watch it, because
they're the only ones not in it.

-- 
KEN FAIR - U. Chicago Law  | <http://student-www.uchicago.edu/users/kjfair>
Of Counsel, U. of Ediacara | Power Mac! | CABAL(tm) | I'm w/in McQ - R U?
   When you go for a job interview, I think a good thing to ask is if
   they ever press charges.


From graham@gnelson.demon.co.uk Sat May  3 14:57:46 MET DST 1997
Article: 25061 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: ATTENTION Hugo Users (both of you)
Date: Fri, 02 May 1997 22:45:37 +0100 (BST)
Organization: none
Message-ID: <ant022137bbaM+4%@gnelson.demon.co.uk>
References: <5k33hq$22b@ecuador.earthlink.net> <yS$28FAU7wZzEwax@highmount.demon.co.uk> <ant301444d07c4bn@arnod.demon.co.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 19
Xref: news.lth.se rec.arts.int-fiction:25061

In article <ant301444d07c4bn@arnod.demon.co.uk>, Julian Arnold
<URL:mailto:jools@arnod.demon.co.uk> wrote:
> 
> BTW, ISTR it took months (maybe 2-3 years) before anyone other than
> Graham released any games in Inform (Brendon Wyber's "Theatre"), and now
> look at it.

Yes, indeed, about eighteen months, and then there was a rush.
"Christminster" was hot on the heels of "Theatre", as I recall.

There were a fair number of shorter works before that: "Busted"
springs to mind, and several AGT conversions were made by various
people the moment Inform 5 came out.  A system only comes of
age when someone writes a full-scale work for it, I suppose,
but there's no rush.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Mon May  5 10:08:00 MET DST 1997
Article: 25085 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!weld.news.pipex.net!pipex!rill.news.pipex.net!pipex!tank.news.pipex.net!pipex!iafrica.com!uct.uni.net.za!csir.uni.net.za!wits.uni.net.za!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [INFORM] found_in
Message-ID: <erkyrathE9MxGH.HpE@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <E9II48.KAo.0.queen@torfree.net> <862621973.17560@dejanews.com> <5kfd9j$otj@bartlet.df.lth.se> <5kfi6j$2hm@nntp5.u.washington.edu> <5kg7th$nft@bartlet.df.lth.se>
Date: Sun, 4 May 1997 02:26:41 GMT
Lines: 40
Sender: erkyrath@netcom15.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25085

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> >>The found_in property is only evaluated when the player moves to a new
> >>location. 
> >
> >And it's only evaluated when he gets there in a "normal" fashion (by a
> >Go verb, or by using PlayerTo directly).  If you "move player to room"
> >you will catch the floating objects with their pants down.

Right.

> Which is one of the reasons why you should *never* *ever* do
> "move player to room".

Right.

I would add another rule, which may be obvious after the foregoing 
commentary: Never try to make an object which sometimes floats and 
sometimes doesn't. A floating object should never be taken by the player, 
or put inside another object, or anything like that. Just let it float. 
Never move it yourself. If you want to make it disappear, do
  give obj absent;
  remove obj;
(You have to do both.)

It is *possible* to have an object change from floating to non-floating 
status, by careful management of the absent attribute. But I recommend 
against it. It's too easy to screw up.

If you want the player to be able to take a floating object, write two 
separate objects. Chances are, you'll want to make other differences 
between them anyway.

--Z



-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From daly@PPD.Kodak.COM Wed May  7 09:44:43 MET DST 1997
Article: 25128 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news-peer.sprintlink.net!Sprint!news-pull.sprintlink.net!news.sprintlink.net!news-dc-9.sprintlink.net!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disabling Undo
Date: 6 May 1997 15:37:07 GMT
Organization: Eastman Kodak Company
Lines: 60
Message-ID: <5knj73$9tu$1@kodak.rdcs.Kodak.COM>
References: <9705022133.1jrg@darkside.demon.co.uk> <MPG.dd52d0e29e28cd1989683@news.one.net> <erkyrathE9Mwu8.Gvp@netcom.com>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com
Xref: news.lth.se rec.arts.int-fiction:25128

erkyrath@netcom.com (Andrew Plotkin), if that is your REAL name, said: 

[much snipped]

>And it's all very well to say "Write a different damn puzzle", but 
>I don't believe in making barriers for the author. 

The alternative is making barriers for the player, and I don't generally
believe in that.

Well, there are different ways of doing that, and some are more
pleasant than others.  If I'm trying to open a combination safe,
and the games says "Yeah, like I'm really going to enter every
possible combination," then I'll understand that brute-force isn't
the solution.

To give a concrete example, I didn't make it through the first
hundred moves of Jigsaw without a walkthrough.  I searched high
and low for instruction manuals for all of the different "wierd"
items that had been given to me, and I thought that my problem
was that I couldn't find them.  The actual problem was that I
didn't realize that I was expected to fiddle with the devices long
enough to figure out how they worked.

I thought that I was playing a Zork II type of game, and I was
actually playing a Savage Island II type of game.  No harm, except
that I felt that MAYBE I could have figured it out if I knew that
I had to figure it out.

So now I've gone to play Curses, and I'm stuck inside this book
that I don't know how to get out of.  I'll be damned if I have
a walkthough spoil the challenge for me this time, although I
admit that I haven't played the game in some time now because
I can't figure it out and still don't have enough of a feel to
know if I'm lacking information or equipment or if I need to
accomplish some quest or just find the right command to type in.

I don't know where all of this is going (except as just a general
rant), but let me try to sum up.  When a game is written well and
I click well with it, I don't get syntax errors (except for spelling).
I'm telling my player character what to do, and she does it.  But
when the game is talking to me instead of my player character, I'm
not interacting with a universe any more, I'm sitting in front of
a computer.  If I run across a puzzle that is amenable to brute
force, I SHOULD be so deeply engrossed in the universe that it wouldn't
strike me as possible to unwrite my history.  But If I make an earnest
search for the solution, and it's not there, I'd damn well better
be able to unwrite my history.

If I typed UNDO and the game said "I'm sorry, Dave, I can't do that",
you're in dire jeapordy of my next command being QUIT and the one
after that starting with DEL. :-)  (And yes, Spellbreaker came really
close to that line with the pile of cubes puzzle.)

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From erkyrath@netcom.com Wed May  7 09:45:08 MET DST 1997
Article: 25129 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!news.webspan.net!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Disabling Undo
Message-ID: <erkyrathE9roIF.BDw@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <9705022133.1jrg@darkside.demon.co.uk> <MPG.dd52d0e29e28cd1989683@news.one.net> <erkyrathE9Mwu8.Gvp@netcom.com> <5knj73$9tu$1@kodak.rdcs.Kodak.COM>
Date: Tue, 6 May 1997 16:01:27 GMT
Lines: 22
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25129


Matthew Daly (daly@PPD.Kodak.COM) wrote:
> erkyrath@netcom.com (Andrew Plotkin), if that is your REAL name, said: 

> [much snipped]

> >And it's all very well to say "Write a different damn puzzle", but 
> >I don't believe in making barriers for the author. 

> The alternative is making barriers for the player, and I don't generally
> believe in that.

If the author makes a puzzle (scene, whatever) then the players can decide 
whether they like it or not. If the author is blocked from making the 
puzzle -- because of convention, or technology flaws, or whatever -- then 
neither the players nor the author have anything at all.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Wed May  7 14:43:32 MET DST 1997
Article: 25133 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!news-peer.sprintlink.net!news.sprintlink.net!Sprint!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Groundhog Day as Interactive Fiction
Message-ID: <erkyrathE9s0I7.MDF@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5jjdn8$qfa@lori.zippo.com> <erkyrathE93tHD.My5@netcom.com> <5kbatb$23q$1@nixon.area.com> <5kkrof$8di$1@europa.frii.com> <336F8DCF.7979@earthweb.com>
Date: Tue, 6 May 1997 20:20:30 GMT
Lines: 36
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25133

Carl Muckenhoupt (carl@earthweb.com) wrote:
> John Holder wrote:
> > 
> > In a fit of lunacy, Matt Ackeret (mattack@area.com) escribed:
> > : I guess this is somewhat off topic for this group.. But does anyone have
> > : good time loop movies/stories/TV to recommend?

> My former roommate speaks highly of a certain George Alec Effinger novel
> involving
> someone who travels back in time to an early World's Fair, only to wind
> up living
> a few hours over and over again. I've forgotten the name of it, but part
> of the premise is that the protagonist isn't part of the loop.  He needs
> to eat and sleep, and that's pretty difficult in the middle of a World's
> Fair in full swing without any money.  It gets quite nasty, apparently.

_The Nick of Time_ and _The Bird of Time_. A two-book series; I'm pretty 
sure the World's Fair scene was in the first one. 

It's really more comedy than anything else -- well, it's surreal wacko 
stuff. I really like these books.

> This was before Mr. Effinger ran out of ideas and was reduced to writing
> things like
> "The Zork Chronicles".

Yeah, pretty much. Although the Zork book has Glorian of the Knowledge, a 
character who was first introduced in _Heroics_, which was another early 
novel which was very good. I like Glorian of the Knowledge.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Wed May  7 17:49:47 MET DST 1997
Article: 25084 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!xinit!newsfeed.tip.net!news.jos.net!dos.canit.se!seunet!mn7.swip.net!mn6.swip.net!weld.news.pipex.net!pipex!rill.news.pipex.net!pipex!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ais.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Disabling Undo
Message-ID: <erkyrathE9Mwu8.Gvp@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <9705022133.1jrg@darkside.demon.co.uk> <MPG.dd52d0e29e28cd1989683@news.one.net>
Date: Sun, 4 May 1997 02:13:20 GMT
Lines: 65
Sender: erkyrath@netcom15.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25084

athol-brose (cinnamon@one.net) wrote:
> In article <9705022133.1jrg@darkside.demon.co.uk>, 
> adam@darkside.demon.co.uk says...

> > But again, all the interpreters that have out-of-game-context undo functions
> > (Frotz, for example) can undo (multiple times) without requiring the use of the
> > UNDO command. AFAICS, you're never going to get around that..

> This is one good reason why this thread should not be called "Disabling 
> Undo". Instead, we should be thinking about how we can design compelling 
> adventure-game puzzles which do not fall into the "screw-it-up-once-and- 
> you're-dead-or-unable-to-continue" mold.

That's actually not quite right. There are lots of puzzles around which 
you only get one shot at; I consider this acceptable if (A) I know it's 
that kind of a game, and (B) save and undo are available (ie, just about 
always.)

The problem comes when this kind of puzzle *also* has the feature that a
moron can solve it by trying every possibility, mechanically. That makes
it a boring puzzle, because I, at least, am going to solve it mechanically
rather than bothing to think. And then I will complain that I was bored.
This is thoroughly annoying of me, but it's what I'm going to do. Heh. 

Disabling undo makes this situation less boring, because I can't go 
through and solve it by brute force. This is really how I react, as a 
player. (Of course, you'd better make it *clear* that brute force won't 
work. If I try every possibility, restoring each time, and *none* of them 
work, because you silently jiggered the restore function, I'm going to be 
thoroughly pissed.)

If disabling save/undo is not to your taste -- or impossible --  
we have a large library of other ways around this situation:

* Don't let the player guess. "You spin the dial a few times, but since 
you have no idea what the combination is, you give up."
* Jigger the answer so that it's never what the player tries, until the 
player gets the correct information.
* Build the puzzle so that there are an nigh-infinite number of 
possibilities to try. "You set the orange dial to 34513, the green dial 
to 82211, and the mauve dial to 14227..."
* Give the player the benefit of the doubt, and allow a brute-force 
solution, but print enough information so that the player at least *sees* 
the storyline. "'Aha,' you say, 'if I ask you about the *left* door, then 
you'll lie, so whether it's a Thursday or not, the sentence will mean the 
opposite of what you said...'"
* Write a different damn puzzle.

All of these are varyingly useful. The worst case is probably logic 
puzzles, where there is no other information in the game for the player 
to stumble across. The player *can* figure out the answer without any 
typing, so there's no way for the game to distinguish logic from a lucky 
guess. 

And it's all very well to say "Write a different damn puzzle", but 
I don't believe in making barriers for the author. If you want to throw a 
logic puzzle into your game, you can legitimately ask how to do it; it's 
no fair me telling you "don't do that".

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From erkyrath@netcom.com Thu May  8 10:34:56 MET DST 1997
Article: 25151 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: A newbie enters the IF arena
Message-ID: <erkyrathE9tvvn.17r@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3370CA87.2FDA@drizzle.com>
Date: Wed, 7 May 1997 20:35:45 GMT
Lines: 48
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25151

C.A.Dahl (pusro@drizzle.com) wrote:

>  1) How is the IF Fiction genre going?  As an "underground" game
> creator, I can understand that the "mainstream" audience isn't into IF
> anymore.  (What the mainstream audience likes is also 99 44/110%
> codswallop, but I digress).  But is there still a significant number of
> "hard core" IF peers out there to make major IF projects worthwhile?

I would say yes. (No surprise, since I've been doing major IF projects. 
:-) Now, I don't know about money; but if you're looking for feedback and 
attention, there are a lot of us out here. 

(No, not every game generates discussion and feedback. I think people 
would agree that I have a knack for writing controversial games. Heh.)

It may be worthwhile for you to look through the ftp.gmd.de archives and 
list directories in order of date. (The FTP server there will do that if 
you type "ls -t" in your FTP client.) That will show you the upload rates 
for games in the past few years. Although of course you're only seeing 
the most recent version of each game. And then remember that the 1996 
short IF competition got 12 entries, and the 1997 competition got 
thirty-odd. 

>  2) What's the general opinion on AGT?  I first started using it about 3
> years ago; in fact, is was my dialogue with David Malmberg that led to
> MAGT 1.7 being released as freeware.  Personally, I like the
> program--it's very easy to use, has a fair parser, and you don't have to
> struggle too much if you want to do something outside of its default
> capabilities.  I shrugged off TADS because of its similarity to
> C-slash-complex-programming (BASIC is about the most I can handle), and
> know very little about INFORM.

Inform is also very similar to C. 

The general opinion of AGT is, well, the average is low. Many people
disagree in particular with your statement that going outside the default
capabilities is relatively easy. 

There are some AGT proponents around, though. I'll leave the defense 
to them. :)

--Z


-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From cardinalt@earthlink.net Thu May  8 10:35:35 MET DST 1997
Article: 25158 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!mr.net!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: A newbie enters the IF arena
Date: Thu, 08 May 1997 02:25:36 GMT
Organization: Earthlink Network, Inc.
Lines: 60
Message-ID: <5krdnd$d4r@bolivia.earthlink.net>
References: <3370CA87.2FDA@drizzle.com>
NNTP-Posting-Host: max2-sc-ca-39.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:25158

"C.A.Dahl" <pusro@drizzle.com> made so bold as to state:

> 1) How is the IF Fiction genre going?  As an "underground" game
>creator, I can understand that the "mainstream" audience isn't into IF
>anymore.  

That's because the mainstream audience is about thirteen years old. Us
IF'ers tend to be older and less mature.

>(What the mainstream audience likes is also 99 44/110%
>codswallop, but I digress).  But is there still a significant number of
>"hard core" IF peers out there to make major IF projects worthwhile?

I guess it all depends on what you're after. I wrote a game for an
audience of one a couple of years ago--a friend of mine who was the
only one in the world who could have ever possibly gotten the jokes in
it. Was it worthwhile to me and to him? Yeah.

All the same, I think there's a sizeable enough general audience out
there ready and willing to play/read well-written works of i-f if
that's the direction you want to go.

Of course, whether they're willing to *pay* for the privilege is
another matter entirely :)

>years ago; in fact, is was my dialogue with David Malmberg that led to
>MAGT 1.7 being released as freeware.  Personally, I like the
>program--it's very easy to use, has a fair parser, and you don't have to
>struggle too much if you want to do something outside of its default
>capabilities.  I shrugged off TADS because of its similarity to
>C-slash-complex-programming (BASIC is about the most I can handle), and
>know very little about INFORM.

The game's the thing. If you've got the skill and talent to write an
entertaining piece of i-f in AGT, then go for it. Nobody's going to
refuse to play something just because it's written in AGT. They *are*
going to refuse to play it, however, if it's poorly conceived, poorly
written, and/or basically just a chore to slog through. The game's the
thing. The game's the thing. 

And then there's the game.

--Cardinal T

          I mean, what the hell kind of villain thwarts the hero's
	  progress with soup cans in the kitchen pantry?
	                                         --Russ Bryan
	
         Are there any text games prominently featuring dinosaurs?  
         If not, does anyone besides me think it would be cool? 
                                                 --Matthew Amster-Burton

         "Hey! *I* wanted to be Envy!"
                                                 --joe dot mason
         
         "Bathroom?  Yeah.  Go through that door, on the end
         of the hall, on your left."  "Pardon?"  "South twice,
         than east."  "Ah."
                                                  --Clyde "Fred" Sloniker



From earendil@ Thu May  8 10:35:51 MET DST 1997
Article: 25153 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Subject: Dungeon, 20th anniversary edition
Organization: Gee Library, Texas A&M at Commerce
From: earendil@ (Allen Garvin)
NNTP-Posting-Host: faeryland.tamu-commerce.edu
Message-ID: <33710027.0@news.tamu-commerce.edu>
Date: 7 May 97 22:20:23 GMT
Lines: 26
Path: news.lth.se!solace!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!cnn.exu.ericsson.se!uunet!in3.uu.net!128.83.139.5!cs.utexas.edu!news.tamu.edu!news.tamu-commerce.edu!!earendil
Xref: news.lth.se rec.arts.int-fiction:25153


With the spring semester over with, I've found an excuse to put off working
on my thesis during the summer.  I'm going to port Dungeon to Inform to
mark its 20th anniversary.  Because I'm not a masochist, I'm working from
Darin Johnson's excellent TADS port instead of the Fortran.  Features it will 
offer:

  1) Footnotes to objects and puzzles and features, taken from New Zork Times
     issues, articles and interviews, and maybe correspondence with Blank
     and Lebling, if they are interested.
  2) Online hints and histories of the game and authors.
  3) Ability to change directions between rooms from those of Dungeon to
     those of the published Zork (I always get confused, since I know
     Zork's map completely) Descriptions will not change, however.

If anyone is interested in my awful code (I'm really inexperienced with
Inform) or a beta copy of the game, ftp to faeryland.tamu-commerce.edu and
look in /pub/dungeon.  I've ported all the simple stuff.  Now working on
the more complicated puzzles.

By the way, does anyone know the name of the person in DECUS who ported 
Dungeon from MDL to Fortran.  The NZT history of Zork refers to him by
simply "Bob the Lunatic".


Allen Garvin


From jfrancis@dungeon.engr.sgi.com Thu May  8 10:36:01 MET DST 1997
Article: 25154 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!ix.netcom.com!enews.sgi.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.arts.int-fiction
Subject: Re: Dungeon, 20th anniversary edition
Date: 8 May 1997 00:35:10 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 45
Message-ID: <5kr73u$7kh@fido.asd.sgi.com>
References: <33710027.0@news.tamu-commerce.edu>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.arts.int-fiction:25154

In article <33710027.0@news.tamu-commerce.edu>, Allen Garvin <earendil@> wrote:
>
>With the spring semester over with, I've found an excuse to put off working
>on my thesis during the summer.  I'm going to port Dungeon to Inform to
>mark its 20th anniversary.  Because I'm not a masochist, I'm working from
>Darin Johnson's excellent TADS port instead of the Fortran.  Features it will 
>offer:
>
>  1) Footnotes to objects and puzzles and features, taken from New Zork Times
>     issues, articles and interviews, and maybe correspondence with Blank
>     and Lebling, if they are interested.
>  2) Online hints and histories of the game and authors.
>  3) Ability to change directions between rooms from those of Dungeon to
>     those of the published Zork (I always get confused, since I know
>     Zork's map completely) Descriptions will not change, however.
>
>If anyone is interested in my awful code (I'm really inexperienced with
>Inform) or a beta copy of the game, ftp to faeryland.tamu-commerce.edu and
>look in /pub/dungeon.  I've ported all the simple stuff.  Now working on
>the more complicated puzzles.
>
>By the way, does anyone know the name of the person in DECUS who ported 
>Dungeon from MDL to Fortran.  The NZT history of Zork refers to him by
>simply "Bob the Lunatic".
>
>
>Allen Garvin

Later versions of the source identify the aforementioned lunatic as
one Bob Supnik. (Earlier versions give no identification information
at all, referring to "a somewhat paranoid DEC engineer who prefers to 
remain anonymous", IIRC).

Now if only I could remember the name of the Infocommie who was using
our DECSystem-2020 (in the DEC Federal System Group) to break the MDL
sources into smaller chunks!  At least this meant that I got to play
a version of mainframe Zork that had the latest features in it - I'm
glad to see that the multiple palantirs (and the last one lousy point)
have eventually made it into widely available versions.

-- 
John Francis  jfrancis@engr.sgi.com  Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 43U-991
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From jfrancis@dungeon.engr.sgi.com Sat May 10 10:27:29 MET DST 1997
Article: 25199 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!zdc!super.zippo.com!enews.sgi.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.arts.int-fiction
Subject: Re: Dungeon, 20th anniversary edition
Date: 10 May 1997 00:23:53 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 23
Message-ID: <5l0f6p$jsp@fido.asd.sgi.com>
References: <33710027.0@news.tamu-commerce.edu> <Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.arts.int-fiction:25199

In article <Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA>,
Paul Shrimpton  <shrimppd@mcmail.CIS.McMaster.CA> wrote:
>
>I think the version you're working from has a couple of puzzles that 
>weren't written by the original Imps, but I don't recall what they are.
>
>Paul
>

AFAIK the last puzzles added to the FORTRAN sources (and to the TADS port)
were the Palantirs (a.k.a. the sooty room), and the last "One Lousy Point".
A variant of the palantirs puzzle did turn up in the Infocom Zorks.

These are canonical puzzles written by the original imps - they were in the
last mainframe MDL version of Zork/Dungeon (and I've still got my old hand-
drawn map to prove it :-).  For many years, however, they were not to be
found in the widely-available DECUS FORTRAN version.

-- 
John Francis  jfrancis@engr.sgi.com  Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 43U-991
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From erkyrath@netcom.com Sat May 10 15:43:00 MET DST 1997
Article: 25195 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Design Patterns for implementing IF?
Message-ID: <erkyrathE9xEqu.5s3@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <337163cd.49542@news.worldonline.nl> <5kvngk$olm$1@joe.rice.edu>
Date: Fri, 9 May 1997 18:16:06 GMT
Lines: 52
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25195

Lucian Paul Smith (lpsmith@rice.edu) wrote:

> Wow!  I like it!  I like the concepts discussed here.  For those of you 
> who don't want to fight with their search engine, you can find this page at:

> http://st-www.cs.uiuc.edu/users/patterns/patterns.html

> From there, I found my way to:

> http://www.enteract.com/~bradapp/docs/patterns-intro.html

> which was an excellent introduction to patterns.

I've never taken the time to look at this "pattern" thing before today --
not with respect to software. But, weirdly, I own copies of _A Pattern
Language: Towns, Buildings, Construction_ and _The Timeless Way of
Building_ (discussion of patterns in architecture and city planning.) I
haven't gotten to _TWoB_ yet, but _PL_ is stunningly coherent and
interesting. 

> :     Then, this morning, I woke up with this thought: would it
> : perhaps be possible and useful to write down a set of patterns
> : for IF authors?

> I heartily agree.  Just reading some of the stuff about patterns 
> crystalized some thoughts that have been gestating in my head about scope 
> for some time now.  I think they'd be more appropriate for a separate 
> post, so I'll mention them there.

> Generally, though, I think that Inform (and, presumably, TADS, though I 
> know nothing about the latter) acts as a kind of 'pattern 
> language'--Graham has thoght about the different patterns needed to write 
> a piece of IF so that we don't have to.  Rooms, exits, doors, characters, 
> display, etc.

This is definitely true. There are also design patterns -- recall my post 
a few days ago about ways to design puzzles which might be solved by brute 
force. 

My only reservation is that we must be careful that nobody views an IF 
pattern catalog as complete. We're constantly coming up with new ways to 
do things, each of which (after a few attempts and variations) can be 
written down as a pattern. One of the purposes of "The Space Under the 
Window" was to demonstrate how far we from knowing *all* the possible IF 
patterns. :)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From goetz@cs.buffalo.edu Sat May 10 15:48:54 MET DST 1997
Article: 25197 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.uoregon.edu!news.acsu.buffalo.edu!acsu.buffalo.edu!goetz
From: goetz@cs.buffalo.edu (Phil Goetz)
Newsgroups: rec.arts.int-fiction
Subject: Re: Groundhog Day as Interactive Fiction
Date: 9 May 1997 21:53:31 GMT
Organization: State University of New York at Buffalo/Computer Science
Lines: 29
Message-ID: <5l06cr$94h@prometheus.acsu.buffalo.edu>
References: <5jjdn8$qfa@lori.zippo.com> <5kbatb$23q$1@nixon.area.com> <5kkrof$8di$1@europa.frii.com> <5km322$4l1@wanda.vf.pond.com>
NNTP-Posting-Host: mira.cs.buffalo.edu
NNTP-Posting-User: goetz
Xref: news.lth.se rec.arts.int-fiction:25197

In article <5km322$4l1@wanda.vf.pond.com>,
Matthew T. Russotto <russotto@wanda.vf.pond.com> wrote:
>In article <5kkrof$8di$1@europa.frii.com>,
>John Holder <jholder@deimos.frii.com> wrote:
>}In a fit of lunacy, Matt Ackeret (mattack@area.com) escribed:
>}: I guess this is somewhat off topic for this group.. But does anyone have
>}: good time loop movies/stories/TV to recommend?
>}
>}My all time favorite Star Trek:The Next Generation episode is a time
>}loop episode.  It's called "Yesterday's Enterprise"
>}
>}I'll describe it if you like...
>
>There's Heinlein's "-All You Zombies-".  Wouldn't make much of an IF
>game, but it's hard to top as a time loop short story.

It's hard to top for professional reasons.  Science fiction writers
overdid time-loop stories in the 1940s.  Heinlein's "All You Zombies"
and John Campbell's "By his bootstraps" are the most famous.  (Campbell
rejected "All You Zombies", BTW.  He said it was too circular.  Maybe
I'm getting something confused here, because that doesn't all fit...)

If you try to write another time-loop story you will find it extremely
hard to sell to SF editors; it's one of a small set of story ideas,
like the one where a spaceship crashes on a planet and the pilot and
co-pilot are named Adam and Eve, that provoke an instantaneous
wastebasket reflex in SF editors.

Phil Goetz@cs.buffalo.edu


From dsglasser@hotmail.com Sun May 11 08:58:50 MET DST 1997
Article: 25226 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!cam-news-feed3.bbnplanet.com!news.bbnplanet.com!news.inc.net!news.itis.com!29.ts3.icdc.com!user
From: dsglasser@hotmail.com (David Glasser)
Newsgroups: rec.arts.int-fiction
Subject: Re: floatingItem containers in TADS
Date: Sat, 10 May 1997 20:43:32 +0325
Organization: TAFA
Lines: 94
Message-ID: <dsglasser-1005972043330001@29.ts3.icdc.com>
References: <5krouj$5ks@csu-b.csuohio.edu> <5ksnlu$rst@news1.zippo.com> <fake-mail-1005971619550001@van-as-09b16.direct.ca> <dsglasser-1005972027520001@29.ts3.icdc.com>
NNTP-Posting-Host: olaf.viewnetinc.com
Xref: news.lth.se rec.arts.int-fiction:25226

In article <dsglasser-1005972027520001@29.ts3.icdc.com>,
dsglasser@hotmail.com (David Glasser) wrote:

[snipped a lot]

> I think that this is because the only objects considered in deepverb's
> list of objects that can be used for a verb includes those "in scope",
> plus those of class floatingItem.  It might not take *too* long to modify
> that part of ADV (that is, whatever refers to floatingItem's) to also
> allow objects in (and on, etc.) floatingItem's to be considered.

I found the relevant passage in ADV.  It is in the initSearch function:

initSearch: function
{
    local o;
    
    o := firstobj(hiddenItem);
    while (o <> nil)
    {
   if (o.searchLoc)
       o.searchLoc.searchCont := o.searchLoc.searchCont + o;
   else if (o.underLoc)
       o.underLoc.underCont := o.underLoc.underCont + o;
   else if (o.behindLoc)
       o.behindLoc.behindCont := o.behindLoc.behindCont + o;
   o := nextobj(o, hiddenItem);
    }
    
    global.floatingList := [];
    for (o := firstobj(floatingItem) ; o ; o := nextobj(o, floatingItem))
    global.floatingList += o;
}

The bottom three lines is our problem.  Inserting

replace initSearch: function
{
    local o,p,x;
    
    o := firstobj(hiddenItem);
    while (o <> nil)
    {
   if (o.searchLoc)
       o.searchLoc.searchCont := o.searchLoc.searchCont + o;
   else if (o.underLoc)
       o.underLoc.underCont := o.underLoc.underCont + o;
   else if (o.behindLoc)
       o.behindLoc.behindCont := o.behindLoc.behindCont + o;
   o := nextobj(o, hiddenItem);
    }
    
    global.floatingList := [];
    for (o := firstobj(floatingItem) ; o ; o := nextobj(o, floatingItem))
    {
    global.floatingList += o;
    x := length(o.contents);
    for (i := 1; i <= x; i++)
    {
    p := o.contents[i];
    global.floatingList +=p;
    }
    }
   
}

would sort of work.  However, this would happen:

>put bag in floating container
Done.

>x container
In the container is a bag.

>x bag
In the bag is a key.

>get bag
Taken.

>put bag in container
Done.

>get key
You don't see any key here.

Or something like this.  Something needs to be put after the line that
adds p to global.floatingList.  Help, anyone?

David Glasser
dsglasser@hotmail.com
http://www.geocities.com/SoHo/6028/
TADS Programming Tip of the Week (or whatever time period)
Read ADV.T.  Even if you are using WorldClass.  Then read WorldClass, even if you aren't using it.  Then read ADV.T again.  NOTE: Don't try reading TADS libraries, Inform parser/libraries, and C source for TADS or Inform in the same day, unless you're insane.  I read them all in the same day.  And I didn't even know how to program in C.  Now, I can't even manage to make short .sigs.  Sorry for the rambling.


From fake-mail@anti-spam.address Sun May 11 08:59:10 MET DST 1997
Article: 25229 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!Sprint!newsfeed.direct.ca!newsgate.direct.ca!van-as-11a13.direct.ca!user
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: floatingItem containers in TADS
Date: Sat, 10 May 1997 21:07:22 -0700
Organization: tela design
Lines: 25
Message-ID: <fake-mail-1005972107230001@van-as-11a13.direct.ca>
References: <5krouj$5ks@csu-b.csuohio.edu> <5ksnlu$rst@news1.zippo.com> <fake-mail-1005971619550001@van-as-09b16.direct.ca> <dsglasser-1005972027520001@29.ts3.icdc.com> <dsglasser-1005972043330001@29.ts3.icdc.com>
NNTP-Posting-Host: van-as-11a13.direct.ca
x-no-archive: yes
Xref: news.lth.se rec.arts.int-fiction:25229

In article <dsglasser-1005972043330001@29.ts3.icdc.com>,
dsglasser@hotmail.com (David Glasser) wrote:

> I found the relevant passage in ADV.  It is in the initSearch function:
>
> The bottom three lines is our problem.  Inserting

 Um, no... I'm fairly sure that's not the problem at all. Don't touch
initSearch, as it won't help you. initSearch is only called once, and
during the game compilation, at that. (ie: the interpreter will never see
that code unless you're running a debugger version of the game) The
contents of global.floatingList are used by the game to determine which
items are floating items. You don't want to be adding non floating items
to that list - it defeats the purpose.

 I'm still reasonably certain that the change I suggested in an earlier
post - modifying the deepverb class's validDoList() method - is the right
way to go. You want that method to return recursively all the visible
contents of any open floating item that's also visible to the actor.

 - Neil K. Guy

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From earendil@ Mon May 12 10:09:59 MET DST 1997
Article: 25210 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Subject: Re: Dungeon, 20th anniversary edition
References: <33710027.0@news.tamu-commerce.edu> <Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA> <5l0f6p$jsp@fido.asd.sgi.com>
Organization: Gee Library, Texas A&M at Commerce
From: earendil@ (Allen Garvin)
NNTP-Posting-Host: faeryland.tamu-commerce.edu
Message-ID: <33748ef9.0@news.tamu-commerce.edu>
Date: 10 May 97 15:06:33 GMT
Lines: 33
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!news-peer.sprintlink.net!news.sprintlink.net!Sprint!cs.utexas.edu!news.tamu.edu!news.tamu-commerce.edu!!earendil
Xref: news.lth.se rec.arts.int-fiction:25210

In article <5l0f6p$jsp@fido.asd.sgi.com>,
John Francis <jfrancis@dungeon.engr.sgi.com> wrote:
>In article <Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA>,
>Paul Shrimpton  <shrimppd@mcmail.CIS.McMaster.CA> wrote:
>
>AFAIK the last puzzles added to the FORTRAN sources (and to the TADS port)
>were the Palantirs (a.k.a. the sooty room), and the last "One Lousy Point".
>A variant of the palantirs puzzle did turn up in the Infocom Zorks.
>
>These are canonical puzzles written by the original imps - they were in the
>last mainframe MDL version of Zork/Dungeon (and I've still got my old hand-
>drawn map to prove it :-).  For many years, however, they were not to be
>found in the widely-available DECUS FORTRAN version.

By the way, after John Francis told me that Bob Supnik was the porter to
Fortran, I looked around, and found a copy of the original fortran version
distributed by Decus in 1979.  If anyone is interested, you can find it at

		    	     sunsite.unc.edu
at

    pub/academic/computer-science/history/pdp-11/rt/decus/fall79/dungeo.sav

Unfortunately, though several pdp11 emulators exist, it appears RT-11 can't
be gotten.  I'm not sure if there's anyway to run it...

I wonder if there are any tapes floating around with the executable of the
MDL version (from zork history: "Although people could get runnable ZORKS, 
they couldn't get sources.").  But I suppose one would need a pdp10 
emulator and ITS, neither of which seem to be available anywhere.


Allen Garvin


From lpsmith@rice.edu Mon May 12 17:29:05 MET DST 1997
Article: 25193 of rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.sesqui.net!rice!ural.owlnet.rice.edu!lpsmith
From: lpsmith@rice.edu (Lucian Paul Smith)
Newsgroups: rec.arts.int-fiction
Subject: Thoughts on Scope (from the 'Design Pattern' thread)
Date: 9 May 1997 18:31:12 GMT
Organization: Rice University, Houston, Texas
Lines: 103
Message-ID: <5kvqhg$olm$2@joe.rice.edu>
NNTP-Posting-Host: ural.owlnet.rice.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25193

After reading Marnix's 'Design Pattern' post, I looked at the Patterns 
Home Page (http://st-www.cs.uiuc.edu/users/patterns/patterns.html) and my 
imagination was fired.  I got to thinking about scope, and my 
dissatisfaction with the way things stand now.

Currently, in Inform (and presumably TADS as well, though I really don't 
know), an object is 'in scope' if it is within a 'line-of-sight' of the 
player.  If you need to manipulate an object that is not in a line of 
sight, you need to mess with scope.  Conversely, if something _is_ in 
your line of sight, but you shouldn't be able to manipulate it, you need 
to do other programming tricks.

I think, ultimately, that 'scope' tries to do more than it should.  It is 
too broad a concept to work consistently well, although it does tend to 
work consistently decently.

At one point, I read someone's post proposing a set of six different 
'scopes':  see_scope, smell_scope, hear_scope, taste_scope, touch_scope, 
and think_scope.  This, I think, is too far to the other extreme--it is 
too complex to easily implement.

Instead, I propose three different 'scopes':  a passive scope, an active 
scope, and a concept scope.

An object would have 'passive scope' if it could interact with the player 
with the player remaining passive.  The player could examine, listen to, 
smell, or talk to (by default) an object within 'passive scope'.

An object would have 'active scope' if the player could interact with the 
object in some active way.  The player could manipulate, pick up, etc. 
(by default) any object within 'active scope'

An object would be in 'concept scope' if the personna could think about 
it, and discuss it with others.  The player could as 'What is a ...', or 
'Tell so-and-so about the ...' if an object was within concept scope.

Different things would then fit logically and consitently into these 
three categories.  Any normal object (say, a ball) would, upon being seen 
by the player, be put within passive, active, and concept scope.  Trees 
on a distant mountain, once seen would be put into passive and concept 
scope, but not active scope.  A telephone could put the person on the 
other end into passive scope, but not active scope.  If the person was 
not already in concept scope to begin with, the player might not be able 
to dial their number!

This would help the library with default responses, too.  If all objects 
were put into concept scope when first encountered, and never removed, 
the library could, like TADS, say "I don't know what you're talking 
about" to both unknown words and items not in concept scope.  It could 
say "You left the silver key on the dresser" when the player tried to 
'Unlock door with silver key', but forgot to pick it up when they found it.

Items could exist only as concepts, as appropriate to the setting.  A 
priest might know about 'God', 'life', 'religion', etc.  An architect 
might know about 'buildings'.

In my 'Comp96' game, all of the game objects have blurbs written on them, 
giving the player more information about that game.  However, if a player 
typed "READ BLURB" I didn't want the game to say "which blurb do you 
mean, the blurb on Alien Abduction, the blurb on Aayela, the blurb 
on...", etc. ad nauseum.  Instead, I implemented the _concept_ of a blurb 
as a static concealed object in the room.  When refered to, the game 
simply responded, "All the games have blurbs on them.  I'm afraid you'll 
have to be more specific."  Had the idea of 'concept space' been a part 
of Inform, this would have been easier to implement, and probably more 
intuitive, as well.

The nickel in 'Lost New York' would start out, when seen, in 'concept' 
and 'passive' scope.  In this way, the author wouldn't have to code for 
every possible way to interact with the nickle ('Touch nickle', 'Put 
nickle in bucket', 'Taste nickle', etc.), but doing the correct series of 
actions would put the nickle into active scope.

One could also implement a way to override the standard response, if a 
player tried to interact with an item not in active scope--"The trees are 
a long ways away", "The nickle is at the bottom of the grate, and you 
can't reach it.", "'buildings' are just a concept."

Another concept I would like to add to this discussion is that of 
'channels'.  I would define a 'channel' as the sense through which a 
particular item can interact with a passive player.  The normal channels 
would be sight, sound, and smell.  A bird in a tree would have the sight 
and sound channel open, but not the smell (unless, say, the player was a 
cat.)  A radio in the next room (a la 'Curses') would have the sound 
channel open, but not sight or smell.

I think Graham is headed this way with the most recent release of the 
Inform library.  In it, he allows for the player to be in a container in 
a room, and for him to interact reasonably with items still in the room.  
If the container is transparent, the player can look at them and listen 
to them, but not touch them or interact with them.  If you'll notice, 
what has happened is that he has differentiated between items in 'active 
scope' and items in 'passive scope'.

I want this capability, too!  I want to be able to put an item out of 
reach of the player, but still examinable, and not have to mess with 
kludgy scope rules!

Anyway, this is _way_ too long already, so I'll stop.  Any comments?

-Lucian




From erkyrath@netcom.com Mon May 12 17:29:31 MET DST 1997
Article: 25194 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!xinit!newsfeed.tip.net!sn.no!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Thoughts on Scope (from the 'Design Pattern' thread)
Message-ID: <erkyrathE9xMMy.ICw@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5kvqhg$olm$2@joe.rice.edu>
Date: Fri, 9 May 1997 21:06:33 GMT
Lines: 97
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25194

Lucian Paul Smith (lpsmith@rice.edu) wrote:

> Currently, in Inform (and presumably TADS as well, though I really don't 
> know), an object is 'in scope' if it is within a 'line-of-sight' of the 
> player.  If you need to manipulate an object that is not in a line of 
> sight, you need to mess with scope.  Conversely, if something _is_ in 
> your line of sight, but you shouldn't be able to manipulate it, you need 
> to do other programming tricks.

> I think, ultimately, that 'scope' tries to do more than it should.  It is 
> too broad a concept to work consistently well, although it does tend to 
> work consistently decently.

> At one point, I read someone's post proposing a set of six different 
> 'scopes':  see_scope, smell_scope, hear_scope, taste_scope, touch_scope, 
> and think_scope.  This, I think, is too far to the other extreme--it is 
> too complex to easily implement.

> Instead, I propose three different 'scopes':  a passive scope, an active 
> scope, and a concept scope.

In general, if you can think of three of something, someone will want 
more. There must be some way for the author to define more scopes. Then 
you can have a fairly minimal library which can easily be twiddled.

(For example, is your idea of concept-scope conflating things *you* know 
about with things that the NPC you're talking to knows about? There will 
be situations where these have to be different. Or maybe not, but you can 
think of something else. Entries in an encyclopedia are the classic 
example of a special-use scope.)

[long set of ideas snipped]

These are all good. Some games would make good use of some or all of them.

However, I don't want to see a large library addition which handles 90% of
the cases. We *already* have a system which handles 90% of the cases. 

> I think Graham is headed this way with the most recent release of the 
> Inform library.  In it, he allows for the player to be in a container in 
> a room, and for him to interact reasonably with items still in the room.  
> If the container is transparent, the player can look at them and listen 
> to them, but not touch them or interact with them.  If you'll notice, 
> what has happened is that he has differentiated between items in 'active 
> scope' and items in 'passive scope'.

Right. However, to continue my attitude from above, I am still undecided 
whether I like this change. I haven't tried to use it; when I do, I will 
decide whether to use it as-is or patch it out (effectively returning to 
an earlier library version.) It may not be what I want in my game, and any 
library change of this magnitude is going to screw up some of my existing 
knowledge of Inform. It may not be worth it. (Or it may be. Like I said, I 
haven't tried to use it.)

> I want this capability, too!  I want to be able to put an item out of 
> reach of the player, but still examinable, and not have to mess with 
> kludgy scope rules!

It is convenient that, right now, "examine" is the *only* verb that applies
to out-of-reach objects. (Well, and "ask npc about x", but this is a rare
case and really kind of different from scenery.) 95% of the out-of-reach
scenery objects you want can be done like this: 

Class distantthing
with before [;
  Examine: rfalse;
  default: "That is out of reach.";
],
has scenery;

Object sky
class distantthing,
with description "It's big and blue";

(Or maybe toss in another property for the "That is out of reach" line, so 
that it can also be overridden easily.)

I'm not trashing your proposal; I'm pointing out that the existing scope 
system, while not super-generalized, handles a great deal of stuff 
*without* explicit use of scope rules, and without even requiring a lot of 
typing.

I also realized (re-reading) that I'm slightly off-track, because I'm 
talking about library additions and you're talking about a conceptual 
approach. I think the points apply, though.

And as long as I'm changing my mind: the within-reach change in the new 
Inform library really has nothing to do with *scope*; it's more like 
*channels* as you described them. Things you can see but not touch, smell 
but not see, hear but not take, etc, etc are *all* in scope. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From russotto@wanda.vf.pond.com Tue May 13 10:39:43 MET DST 1997
Article: 25266 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!newsfeeds.sol.net!feed1.news.erols.com!news-peer.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!Sprint!news.pond.com!wanda.vf.pond.com!not-for-mail
From: russotto@wanda.vf.pond.com (Matthew T. Russotto)
Newsgroups: rec.arts.int-fiction
Subject: Re: Dungeon, 20th anniversary edition
Date: 12 May 1997 23:10:01 -0400
Organization: Ghotinet
Lines: 36
Message-ID: <5l8m29$l1c@wanda.vf.pond.com>
References: <33710027.0@news.tamu-commerce.edu> <Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA> <dsglasser-1205971959470001@7.ts4.icdc.com>
NNTP-Posting-Host: 198.69.82.2
Xref: news.lth.se rec.arts.int-fiction:25266

In article <dsglasser-1205971959470001@7.ts4.icdc.com>,
David Glasser <dsglasser@hotmail.com> wrote:
}In article
}<Pine.SOL.3.91.970509114640.21047B-100000@mcmail.CIS.McMaster.CA>, Paul
}Shrimpton <shrimppd@mcmail.CIS.McMaster.CA> wrote:
}
}> On 7 May 1997 earendil@.MISSING-HOST-NAME. wrote:
}> 
}> > 
}> > With the spring semester over with, I've found an excuse to put off working
}> > on my thesis during the summer.  I'm going to port Dungeon to Inform to
}> > mark its 20th anniversary.  Because I'm not a masochist, I'm working from
}> > Darin Johnson's excellent TADS port instead of the Fortran.  Features
}it will 
}> > offer:
}
}Just one question--this may be completely wrong, but wasn't the whole
}point of splitting Dungeon up into three parts so that they would fit into
}a .z3?

More like a .z1 :-)

} And isn't a .z5 only twice as big as a .z3, not leaving enough
}room for the whole game?

Three things save the day here:

1) Not all the Zork I,II,III puzzles existed in the original.  

2) The Zorks were actually pretty small, as V3 games go. 

3) We've got V8 now!
-- 
Matthew T. Russotto                                russotto@pond.com
"Extremism in defense of liberty is no vice, and moderation in pursuit
of justice is no virtue." 


From g.effinger2@genie.com Tue May 13 22:41:57 MET DST 1997
Article: 25278 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!howland.erols.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!mindspring!uunet!in1.uu.net!204.238.120.21!jump.net!grunt.dejanews.com!not-for-mail
Date: Tue, 13 May 1997 14:41:42 -0600
From: g.effinger2@genie.com
Subject: Re: Groundhog Day as Interactive Fiction
Newsgroups: rec.arts.int-fiction
Message-ID: <863552365.7127@dejanews.com>
Organization: Deja News Usenet Posting Service
References: <5jjdn8$qfa@lori.zippo.com> <5kkrof$8di$1@europa.frii.com> <336F8DCF.7979@earthweb.com> <erkyrathE9s0I7.MDF@netcom.com> <5l06ko$96c@prometheus.acsu.buffalo.edu>
X-Article-Creation-Date: Tue May 13 19:39:32 1997 GMT
X-Originating-IP-Addr: 153.34.79.199 (1Cust71.Max19.Los-Angeles.CA.MS.UU.NET)
X-Http-User-Agent: Mozilla/2.0 (compatible; MSIE 3.02; Windows 95)
X-Authenticated-Sender: g.effinger2@genie.com
Lines: 125
Xref: news.lth.se rec.arts.int-fiction:25278

In article <5l06ko$96c@prometheus.acsu.buffalo.edu>,
  goetz@cs.buffalo.edu (Phil Goetz) wrote:
>
> > This was before Mr. Effinger ran out of ideas and was reduced to writing
> > things like "The Zork Chronicles".
>
> He didn't run out of ideas.  More likely he ran out of money.
> Go to your bookstore and check out the names on the new Star Trek
> and Star Wars and Dragonlance and Battletech and Horseclans and White Wolf
> etc. etc.  etc. etc. etc. novels.  You'll find some famous names writing
> dreck.
>
> That's because a great author who writes a great SF book might sell
> 100,000 copies.  But whoever writes the next Star Trek book is
> going to sell 500,000 copies.  With media tie-ins, even the best
> authors can be bought.
>
> Phil Goetz@cs.buffalo.edu
> http://www.cs.buffalo.edu/~goetz
>
> Subject your friends or enemies to the thought of the week
> at http://www.cs.buffalo.edu/~goetz/thought.html

I've read with a lack of amusement the opinion that I wrote THE ZORK
CHRONICLES because I ran out of ideas.	Generally, I don't respond to
negative opinions of my work--I really don't expect everyone to like
everything I write.  I don't like everything I write.  I'm interested to
hear why some of my stories or novels don't work for particular readers;
however, "Mr. Effinger ran out of ideas" doesn't convey any useful
information to me.

I hadn't responded previously and I wouldn't be responding now, except to
clear up a couple of factual points.  First, although I've faced large
medical debts for a considerable time, I didn't write ZORK for money.  I
was paid $5,000 for it, a flat fee from the packager, with no
royalties--something I tell my writing class not to do (work-for-hire
it's called).  I did it, knowing I'd never see another penny and knowing
that the $5,000 was probably not enough to cover my living expenses
during the time it took to write the book, because it was a book I'd
always wanted to write.  Not THE ZORK CHRONICLES, but the third book
about the character of Glorian; he was in WHAT ENTROPY MEANS TO ME and
HEROICS, and this was to be his apotheosis.  I was discouraged in writing
such a book because my Budayeen series looked more promising, and because
my earlier humorous books never did well in a commercial sense (BIRD,
NICK, and HEROICS have never even been in paperback).  I wanted to write
the novel and this was an opportunity to do it.  Also, I had worked with
Infocom when I wrote a game for them, "Circuit's Edge," based on
characters and locations in WHEN GRAVITY FAILS, and I liked the Infocom
people.  They asked if I'd be interested in doing a novelization for
them, and they offered me what they called "the big one"--the Zork games.
 I'd played all the games enthusiastically when I got my first computer,
years before, and I was glad they thought of me for the book.  I had to
use locations in the game but I couldn't use any of the characters or
events.  That made it more difficult.  I personally feel I was as
inventive in ZORK as I ever was in the earlier humor books and that I
showed no thinness of ideas.  I admit there were a lot of obscure
references in it: I relied heavily on Lord Raglan's study of heroic
patterns in mythology as well as Joseph Campbell's books on that topic; a
lot of satire on the Science Fiction Writers of America (another
organization in the book is called the SFWA); unlabeled appearances by
Nero Wolfe's house, etc.--a different genre or fictional game in each
chapter.  The only way I could write something about three entire games
and do justice to all that material was by making the book episodic.  I
myself had a lot of fun writing it, and I regret that you disapprove. 
It's not to me clear if you read it.

Second--and this gets me furious whenever I see it, about myself or any
of my colleagues--is the suggestion that somehow we gear down for tie-in
books.	Speaking for myself, I don't have speeds.  I write everything the
same way.  I don't think, "Well, this is only a game book, I don't have
to give them my best stuff."  Aw hell.	When I did a short story for Neil
Gaiman's anthology of "Sandman" stories, I did the best story I was
capable of; the same is true of anything I decide to turn my attention
to.  And be careful what you say about "Star Trek" and "Star Wars"
fiction: I'm engaged to Barbara Hambly, who's written both, and I can
testify that she is was as concerned and careful and creative and honest
while writing CHILDREN OF THE JEDI and PLANET OF TWILIGHT as she was
while writing any of the books in her own several series.  If you don't
like stories and novels set in other people's universes, okay, that's an
opinion.  Saying something like "You'll find some famous names writing
dreck" does not sound like an opinion.	It sounds like some kind of
Revealed Truth.  You didn't say "I think it's dreck," but left me
wondering if you truly believe every Star Trek, Star Wars, Dragonlance,
Battletech, Horseclans title is dreck.	If you've read them all and
believe that, I'm curious why you read them all.  If you haven't read
them all, surely there's possibility that some of the books are good and
you are in error.

I am currently engaged in helping to develop a game entitled "Aeon" with
White Wolf, and I'll be  doing more work-for-hire books for them.  A
legal situation has prevented me from delivering any new books under my
name using previous characters or series--especially finishing the last
two books in the WHEN GRAVITY FAILS series.  I may never be allowed to
publish them, so I've had to turn entirely to work-for-hire until the
final judgment is made later this year.  However, although I'm making the
same money now that I made for the Zork book (i.e., not very much
although White Wolf will pay me royalties), I'm eager about the project. 
Andrew Bates, the game's developer, has some wonderful SF ideas, and he's
been enthusiastic about my thoughts and suggestions.  I was approached
originally about doing only an 8,000 word short story for the game's
original book, but the novels happened only after I decided I liked the
intelligence and possibilities of the setting and theme.  The novels'
story and most of the characters are mine, not White Wolf's, and will be
incorporated in the game itself.

There's been only one project in 25 years that I took just for the money:
four "Planet of the Apes" novelizations in 1975, when I spent a total of
seven months in the hospital.  I had to get something to pay those bills,
and to this day I wonder if the books are good, merely okay, or just
plain terrible.  I don't know--I've never been able to re-read them.  On
the other hand, I turned down a hardcover "Star Trek" offer for triple
the money I've ever made, because after a while I thought it would be
less enjoyable than what I was working on at the time.

I don't think I'm in the least unusual about that, either.  Most writers
have a lot more integrity than some readers think.  I also believe that
just because a book is connected to a series not the author's own
creation, that's not enough to label it dreck.	And the line about "even
the best authors can be bought" is one of the most offensive I've ever
read.

George Alec Effinger

-------------------==== Posted via Deja News ====-----------------------
      http://www.dejanews.com/     Search, Read, Post to Usenet


From daly@PPD.Kodak.COM Fri May 16 09:22:01 MET DST 1997
Article: 25322 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!03-newsfeed.univie.ac.at!sbg.ac.at!cosy.sbg.ac.at!newsfeed.Austria.EU.net!EU.net!feeder.chicago.cic.net!news.altair.com!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!daly
From: daly@PPD.Kodak.COM (Matthew Daly)
Newsgroups: comp.sys.ibm.pc.games.adventure,rec.arts.int-fiction
Subject: Re: Text vs Graphics, Status? (Was: Re: The Best Storyline In Adventures)
Date: 15 May 1997 20:25:23 GMT
Organization: Eastman Kodak Company
Lines: 50
Message-ID: <5lfrfj$ido$1@kodak.rdcs.Kodak.COM>
References: <5lduph$s36$1@mhadf.production.compuserve.com> <Pine.ULT.3.91.970515081443.16389H-100000@statler.cc.wwu.edu>
Reply-To: daly@PPD.Kodak.COM (Matthew Daly)
NNTP-Posting-Host: titan.ppd.kodak.com
Xref: news.lth.se comp.sys.ibm.pc.games.adventure:162220 rec.arts.int-fiction:25322

Matthew Murray <mmurray@statler.cc.wwu.edu>, if that is your REAL name, said: 
>On 15 May 1997, Michael Feir wrote:
>
>> I haven't come across anything like AMFV recently, although I've found many
>> games which, in my judgement at least, equal it in quality.
>> Jigsaw is the first title to spring to mind, followed closely by 
>> Spiritwrahk. Sofar is also interesting. 
>
>	Those games are all interesting, and not too bad, but there is 
>just something about AMFV that makes it stand out.  While a lot of 
>today's Inform games are very good, and often almost indistinguishable 
>from some of the older text adventures, I still think that AMFV is 
>unsurpassed.  It had a brilliance that was particularly rare in computer 
>games in 1985, and that is even more rare now.  The games you mentioned 
>are all good, but they just don't have "it."

If I might be so bold as to suggest what "it" is, AMFV is ... easy!

I don't mean that as an insult at all!  In the parts of AMFV that
are exceptionally beautiful (Acts 1 and 2), there are no "puzzles" to
solve at all, and what few challenges there are to solve (like
figuring out where you live and how to order a meal in a restaurant)
are extremely intuitive.  There is virtually no need to save and
restore games, since even death can be overcome in the simulator
(unless you do something extremely and obviously stupid outside
the simulator after being warned not to).  In short, there is
nothing to keep you from fully exploring the world and immersing
yourself into it.

Compare this with Curses, Jigsaw, heck, even other "best" Infocom
games like Trinity.  You are reincarnated more often than Buddha
and forced to endure taking the same actions in the same scene
more times than a hack actor in an overbudget movie -- even
the most brilliant scenes can become trite when you've tried
to play them over thirty times.

I'd love to see more games where the purpose was to explore than to
have to fight the environment to "win" in some grander sense -- there
certainly haven't been many people who have tried to match AMFV in
that regard.  The Space Under the Window is just about the closest
that I can think of, in fact.

-Matthew

-Matthew
--
Matthew Daly       I feel that if a person has problems communicating
mwdaly@kodak.com   the very least he can do is to shut up - Tom Lehrer

My opinions are not necessarily those of my employer, of course.


From masenten@hans.math.upenn.edu Fri May 16 13:13:21 MET DST 1997
Article: 25333 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!jupiter.nic.dtag.de!news-peer.gsl.net!uwm.edu!msunews!netnews.upenn.edu!hans.math.upenn.edu!masenten
From: masenten@hans.math.upenn.edu (Robert Masenten)
Newsgroups: rec.arts.int-fiction
Subject: Re: A newbie enters the IF arena
Date: 16 May 1997 03:52:51 GMT
Organization: Univ. of Pennsylvania Dept. of Mathematics
Lines: 45
Message-ID: <5lglmj$hud@netnews.upenn.edu>
References: <3370CA87.2FDA@drizzle.com> <5lbi3k$igd$1@news01a.micron.net> <5lck9p$6ei@wanda.vf.pond.com> <5le3i5$ia1$1@news01a.micron.net>
NNTP-Posting-Host: hans.math.upenn.edu
Xref: news.lth.se rec.arts.int-fiction:25333

In article <5le3i5$ia1$1@news01a.micron.net>,
Jay Goemmer  <jgoemmer@micron.net> wrote:
>russotto@wanda.vf.pond.com (Matthew T. Russotto) wrote:
>
>> How about an AGT->Z-machine compiler?  That would seem to solve the 
>problem.
>
>   How *right* you are.  *That* just happens to be on Robert's "to do" 
>list right after he finishes the "Universal" compiler, which he is 
>persuaded won't take too long.  (I can't tell you how many times I've
>wished "AGT to Inform" was already available.)  
>
>   It's a real drag trying to do the conversion by hand.  I have 
>absolutely *no* idea how to begin "translating" the AGT commands to 
>Inform.  

  One of the problems with converting AGT to Inform is that AGT games
are structured monolithically (a single large block of metacommands)
whereas Inform games tend to be much more modular, with code split
among the various objects in the game.  

  In a similar vein, AGT uses global variables and flags; many of
these would become object properties and attributes (respectively) in
a (well-written) Inform game.

  AGT2Inf _will_ create Inform code that sits on top of Graham's
library. It's not clear, however, that it will be able to create
"good" Inform code, and so it's not clear how useful it will be for
people trying to move from AGT to Inform.  

   One of my long term goals *is* to produce decent Inform code... but
this requires analyzing the metacommands, figuring out when they run,
and using this information to try to associate them with the right
object. 

  It's much easier to just stick them all in one large routine,
mirroring the structure of the original AGT game, and this is all the 
early versions of my program are going to do.  This works
perfectly well if you just want to get an AGT game running on the
Z-machine; it is almost completely useless if you are moving from AGT
to Inform (from the point of view of translating the metacommands; the
room/noun/creature definitions transfer without difficulty).


Robert Masenten


From pfg@yallara.cs.rmit.EDU.AU Sun May 18 17:01:07 MET DST 1997
Article: 25337 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!harbinger.cc.monash.edu.au!news.rmit.EDU.AU!goanna.cs.rmit.edu.au!yallara!pfg
From: pfg@yallara.cs.rmit.EDU.AU (Paul Francis Gilbert)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Announcement] InCorrect - Debugger for inform
Date: 15 May 1997 23:22:17 GMT
Organization: Comp Sci, RMIT University, Melbourne, Australia.
Lines: 86
Message-ID: <5lg5r9$ahb$1@goanna.cs.rmit.edu.au>
References: <lrafm1dnws.fsf@szspc2.ira.uka.de> <erkyrathEA2pwn.9rv@netcom.com> 	<5lb3te$mvd$1@goanna.cs.rmit.edu.au> <lrraf9uxmz.fsf@szspc2.ira.uka.de>
NNTP-Posting-Host: yallara.cs.rmit.edu.au
NNTP-Posting-User: pfg
X-Newsreader: NN version 6.5.0 #1 (NOV)
Xref: news.lth.se rec.arts.int-fiction:25337

kessinger@szspc2.ira.uka.de writes:

>pfg@yallara.cs.rmit.EDU.AU (Paul Francis Gilbert) writes:

>> 
>> erkyrath@netcom.com (Andrew Plotkin) writes:
>> 
>> >There's also an official debug-file format, which Graham has already 
>> >implemented for Inform.
>> 
>> >It's up to you to deal with this information. :-(
>> 
>> THERE IS???!! I spoke with Graham late last year and he told me the current
>> debugging format is insufficient, since with the one-pass compilation with
>> backtracking, line numbers couldn't be directly/easily associated with a 
>> specific address.

>You couldn't? I think I did or I made a mistake - otoh I'm trying to
>do 2 impossible things every week.

>> 
>> [Background: I've been working on a IDE system for designing text adventure
>> games in Windows 95. I'm up to the final stages, and only have to still
>> 1) make an edit window which can support syntax highlighting, setting of
>> breakpoints, and have a common document [so several windows can modify a
>> single file], 2) finish up the compiler/interpreter (finished the compiler,
>> about to start on the interpreter). You can get a precis at:
>> http://yallara.cs.rmit.edu.au/~pfg/

>I understand it has a built in debugger? I will look at it _even_ if
>its windows95 :-(

>Ingo

Yes indeed it has a debugger. I originally started the project for 3 reasons:
1) To have something nice and large to teach me all the intracacies of the 
   win95 language (like OLE, Structured storage, interfacing different 
   languages)
2) To make a universal tool that containing debugging features.
3) To make a design environment where it would be easy to plug in new features
   (eg. all the loose utilities like the linit's, word counts, etc.), instead
   of having to have utilities lying all over your hard disk.


Current project schedule will have a beta release date for just after the
mid-year holidays. The beta will likely include:

o Design support for both TADS and Inform projects
o Compiler and Interpreter for Inform, hopefully with basic debugging 
  facilities.

Note that it's a bit iffy whether the first beta will contain an evaluator
for Inform expressions (I'm not 100% familiar with Inform yet to fully design
it. If that's the case, I'll probably open it up for someone to design after
I finalise the debugging interface.

Another good thing about the system is that I've designed it to be fully
modular. That is, I can plug in a new language object, and as long it has the
standard interfaces I design, it'll integrate automatically without having to
recompile anything. So if someone wants to create an AGT project module, they
only have to design the language object without having to ask me to recompile
my code to include the new language.

[Note: The language object contains a set of interfaces for interfacing with
 syntax highlighting for edit windows, calling up the appropriate help file
 for keyword/content searches, parsing a source file to determine which files
 it needs, setting the compiler and interpreter].

I've just got Delphi 3, so I'm currently reworking the modules using the
simplified COM interfacing standards provided.

On a final note, one of the beauties of using COM is that it crosses the
language barrier. Thus I can use Borland C++ to compile the source code for
compilers/interpreters without having to try and convert it to Delphi... I just
need to wrap them in a small COM shell.

Anyway, as things happen I'll update my IF-IDE information page at
http://yallara.cs.rmit.edu.au/~pfg/ 

  

--
Paul Gilbert           | pfg@yallara.cs.rmit.edu.au
Bach App Sci, Bach Eng | The opinions expressed are my own, all my own, and
Year 4, RMIT Melbourne | as such will contain no references to small furry
Australia	       | creatures from Alpha Centauri.


From Linards.Ticmanis@post.rwth-aachen.de Sun May 18 17:07:38 MET DST 1997
Article: 25350 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!news.apfel.de!fu-berlin.de!news-ber1.dfn.de!news-ham1.dfn.de!news-han1.dfn.de!news-koe1.dfn.de!news.ruhr-uni-bochum.de!news.rwth-aachen.de!not-for-mail
From: Linards Ticmanis <Linards.Ticmanis@post.rwth-aachen.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 15 May 1997 01:42:55 +0200
Organization: RWTH Aachen, Germany
Lines: 111
Message-ID: <337A4DFE.2FBB85D@post.rwth-aachen.de>
References: <3379b653.10392540@news.netspace.net.au>
NNTP-Posting-Host: s3m159.dialup.rwth-aachen.de
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (X11; I; Linux 2.0.30 i486)
Xref: news.lth.se rec.arts.int-fiction:25350

James Cole wrote:
> 
> How ya didalin'
> 
> NPC conversation can have a profound effect on the experience of 
>playing a
> game.  Done well it can add an extra dimension to a game and it's
> characters.  Done poorly it can make characters seem like cardboard 
>and
> also destroy suspension of disbelief.  At the moment the 'ask <x> 
>about
> <y>' form of NPC conversation seems by far the most prevalant in 
>Infocom
> style IF.
> 
> I prefer Monkey Island style NCP conversations (A while back I 
>uploaded a
> utility for implementing it onto GMD - plug!).  Without saying why I 
>think
> this form is better than the 'ask <x> about <y>' form, I'd be 
>interested in
> the what you think about each of the two forms.  What do you think is
> better/worse about either of them?

Well I have to say I don't like the "menu" style for about the same
reaosns I don't like DOS Shells (like e.g. Windows..). Some reasons:

1.) Typing is quicker once you're used to it, so it distracts less. The
"that's _me_ in the story," as opposed to "that's some puppet I control"
is more there.
2.) You can say exactly what you want in one step, don't have to go
through menus, sub-menus etc.
3.) If you've ever played "Ultima 7" you'll have noted that there's a
problem in that sometimes you want to ask somebody about something you
were't explicitly told to ask about, or maybe that finding out what he
could know about is part of the fun. Another Ultima example, while it's
not IF as such, it certainly is one of the strongest series in NPC
conversation, at least in quantity: In U4 (where NPC conversation was
keyword-based) asking just about everybody about rune, stone and mantra
even though he hadn't mentioned it could save you a lot of time and
trouble, while in similar situations in U7 (menu-based) you had to
follow the whole "line of people with knowledge" to get your final info.
4.) You don't get the feeling "That's all I can say to him? Duh!" which
won't hit you as hard with text input (at least until you txd the
game..)
5.) It fits in better with the text interface. Of course, if you want to
write the second part of "Journey," you'd prefer the other form.
6.) Speaking of "Journey," what does make that game worse than other IF?
It's limited freedom and lack of creativity on the _player_ side. Real
IF is a sort of communication between a creative writer and an also
creative reader/player imho.

Of course, the "ask x about y" just by itself can also be a nuisance (it
is in one place in "Tapestry", an otherwise doubleplusgood game) if it's
not fleshed out with "give x to y", "show x to y", "x, tell me about y",
"x, kiss me" etc. I'll admit that realistic NPC conversation is probably
the weakest point of current IF (and it's about the hardest problem on a
technical level, since it's basically natural language parsing which
would have to be done on a far more complex level than what's needed for
interpreting "normal" commands.)

Taking all into account, if you want many, not-so-deeply implemented
characters, I'd use either a menu system or a keyword system (a la
Ultima 4-6). If you want few (one to maybe three) very fleshed-out
characters (which will probably be guilty of at least doubling your game
code if done realllly wellll) I'd read the parsing chapters in the
Manual of your design system very carefully and then start coding.

(As a side issue, isn't it amazing that deafness seems to be a
wide-spread plague among existing NPCS? E.g. The Old Sailor in BZ, The
Bubble Boy in Trinity, the gravedigger in Wishbringer, etc.)

Appendix: The keyword system of NPC communication, as invented by Lord
British aka Richard Garriot, for those who don't know it.

All characters respond to some standard keywords, "name" means what's
your name, "job" means what are you doing, etc. You can ask about other
one-word topics, gained from what he/she said before, mostly using "job"
as starting point, but most characters will know about one or two more
things only.

Example:

You see a thief with a long stiletto.
>TALK TO THIEF
"Hello to you. Finally somebody who doesn't assume I'm a stong, silent
type without even trying."
>>JOB
"Well, robbing adventurers blind, cleaning up and sometimes even waxing
mazes, carrying bags, and just being a general nuisance. Sometimes I
wield my stiletto as well, and sometimes I even open some tough locks
for others on my social day."
>>MAZES
"Yeah, people tend to use them as garbage disposals, so I clean them up.
Necessary work is often met with disrespect, I assume, but who'd really
like to wade through heaps of rotting small leaflets? Nobody."
>>STILETTO
"Isn't it shiny? I've found out a mixture of grue's spit and dam water
will remove all the bloodstains in seconds. Want me to show you?"
>>YES
Well, as it's currently shiny (didn't you listen?), he had to produce
some stains first.

      *** You have died ***

-- 

Linards Ticmanis

 The Master said, "The business of laying on the colors follows the
preparation of the plain ground."


From jrcole@ozemail.com.au Sun May 18 17:08:16 MET DST 1997
Article: 25344 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!masternews.telia.net!newsfeed.internetmci.com!newsfeed.internetmci.com!gatech!csulb.edu!hammer.uoregon.edu!news-xfer.netaxs.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Fri, 16 May 1997 13:00:23 GMT
Organization: Netspace Online Systems
Lines: 22
Message-ID: <337c5a50.17763782@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au> <337a6ae9.0@news1.ibm.net>
NNTP-Posting-Host: dialup-m1-10.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25344

blore@ibm.net    (Steven Howard) wrote:

>In <3379b653.10392540@news.netspace.net.au>, jrcole@ozemail.com.au (James Cole) writes:
[...]
>
>I haven't played Monkey Island, but I'll assume it's menu-based.  
>
I should've explained how the "Monkey Island style" NPC conversation works,
so I'll post a description elsewhere in this thread.

[advantages and disadvantages cut]

>
>What's your utility called?  What language is it for?
>
It's called Converse, and it's for TADS.  It's on GMD at:

ftp.gmd.de/if-archive/programming/tads/library/contributions/converse.zip

 ---------------
 James Cole
 jrcole@ozemail.com.au


From jrcole@ozemail.com.au Sun May 18 17:08:50 MET DST 1997
Article: 25338 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!news.uni-c.dk!hunter.premier.net!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Fri, 16 May 1997 13:03:15 GMT
Organization: Netspace Online Systems
Lines: 41
Message-ID: <337c5ad3.17894867@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au>
NNTP-Posting-Host: dialup-m1-10.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25338

Here's a description of how the Monkey Island style of NPC conversation
works:

To start a conversation with a NPC you need to 'talk to <character>'.
Typically, you'll initially be given a choice of things to say to the
character.  These might be something like:

   1) Hi there, I'm new in these parts.
   2) Hi, could you tell me where a hotel or something is?
   3) Hey, is there anywhere round here where I can get a drink?
   4) Uhhhh... nothing.  See ya.

(the number of choices you are given might range from 1 to 6).

After choosing what to say, the NPC will reply.  
In response to what the NPC has said you will be given a new set of things
to say.  The conversation continues in this fashion till either party ends
it.  This is done by choosing an appropriate ending comment, like "Ok,
well, I've got to get going now".  Of course, the NPC may also end the
conversation.

As can be seen, it's more like a natural conversation between people.

The set of permutations that the conversation can have (depending on what
you choose to say) form a directed graph.

 -------------

As an aside, here's why I've referred to the technique as "Monkey Island
style" NPC conversation.

This style of NPC conversation seems to be associated with Monkey Island.  
Even though The Secret of Monkey Island wasn't the first game to implement
this, none had done it so well.  It really was something special; I still
haven't seen it implemented better.  

Also, I can't think off a good term to describe the technique.  Others have
used some, but none of which I think really suit it.
 ---------------
 James Cole
 jrcole@ozemail.com.au


From jrcole@ozemail.com.au Sun May 18 17:18:01 MET DST 1997
Article: 25345 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!pumpkin.pangea.ca!news.mira.net.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 17 May 1997 11:13:16 GMT
Organization: Netspace Online Systems
Lines: 45
Message-ID: <337d92b9.8316679@news.netspace.net.au>
References: <337c5ad3.17894867@news.netspace.net.au> <19970516170400.NAA02345@ladder02.news.aol.com>
NNTP-Posting-Host: dialup-m1-10.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25345

nulldogma@aol.com (Nulldogma) wrote:

>James Cole wrote, re: "Monkey-Island-style" conversation:
>
>> As can be seen, it's more like a natural conversation 
>> between people.
>
>Actually, it feels to me much more stilted, since the game is not only
>putting words in my mouth, it's restricting what I can or can't say. I'm
>used to restrictions on syntax, as "TELL/ASK X ABOUT Y" is when you get
>down to it; restrictions on content I'm not so crazy about.

There were two reasons why I said it's more like a natural conversation.  

Firstly, because you say something, the other person replies, you reply to
them, and so on.  Secondly, the content is more like a natural
conversation: you aren't restricted to just objects, but can also talk
about more abstract subjects, like "Hey, Joe, how has work been?" and say
things like "Yeh, I know what you mean".  Do you talk to people by asking
or telling them about objects?  

You really can have a conversation with an NPC which sounds like a
conversation between two real people. 

As for putting words into your mouth, it's supposed to.  As Adam Cadre
said, it's much more suited to games where you play a character rather than
yourself.  

Anyway, IF is full of stuff which "puts words into your mouth".  

Restrictions on content?  What about the restrictions on content with the
ask/tell style? -- they are far worse.

>Besides, with a menu-based system, I never could have experienced my
>favorite unintentional piece of I-F humor, from I-0:
>
>> ASK JOSH ABOUT SEX
>"I like vanilla."
>
Ok. But if you've ever played Monkey Island then you'd know the techinque
opens up many more possiblities for humor.

 ---------------
 James Cole
 jrcole@ozemail.com.au


From jrcole@ozemail.com.au Sun May 18 17:19:08 MET DST 1997
Article: 25353 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!europa.clark.net!news-peer.sprintlink.net!news.sprintlink.net!Sprint!howland.erols.net!spool.mu.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 17 May 1997 11:07:54 GMT
Organization: Netspace Online Systems
Lines: 87
Message-ID: <337d915e.7968824@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au> <337B30AC.7797CF1C@alcyone.com>
NNTP-Posting-Host: dialup-m1-5.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25353

Erik Max Francis <max@alcyone.com> wrote:

>James Cole wrote:
>
>> I prefer Monkey Island style NCP conversations (A while back I uploaded
>> a utility for implementing it onto GMD - plug!).
>
>By this and the reply I would suppose you're referring to menu-style
>conversation choices.

Yes, though I'm not real keen on that term.  I guess it's because that term
is quite general, and I think more associated to other games, like Ultima,
and the other ones that  people have mentioned.  Although Monkey Island and
all these games have NPC conversation using a menu systems, they can be
large differences.

For example, I suspect people tend to associate "menu-syle" more with a set
of keyword questions rather than a set of things to say.  That is:
	1) name
	2) occupation
	3) etc., etc.

>
[...]
>
>There was a discussion on this long, long ago, back when I used to
>contribute to this newsgroup.

Yep.  I've read it in the archives.  

>                              In my opinion, the ASK X ABOUT Y and SHOW X
>TO Y commands are more open-ended than the menu-drive conversations.  

Ok.  

>                                                                      With
>menu-driven conversations, the questions you're supposed to ask are
>obvious and as such it leads you.

>                              Not only are you restricted from
>choices, but it's also clear when you're supposed to say something,
>because it will appear in the menu where it wasn't before:
>
[example snipped cause server wouldn't let me post it with so much quoted
text]

>In this case, it's not only obvious what your choices are, but it's
>obvious what you're supposed to (like setting fire to a house should be
>part of an IF game).

To tell you the truth, I don't really see that as much of a problem.  It is
quite easy to entirely avoid situations like the above.  Also, if you're
playing a character (rather than "yourself") the things that you are can
say are like what's in your character's mind.

On the flip side, it's possible to use the conversation as a puzzle.
Trying to get someone to say something; trying to knock someones price
down; or even swordfighting someone!

It's easy to think that problems like the one you mentioned would occur
when you look purely at the concept, or a poor implementation.  But, as
LucasArts demonstrate, they don't have to exist if the right
techniques/methods are used. Like most things, it depends on the quality of
implementation.

>The alternative seems much cleaner to me -- where a certain well-defined
>set of conversation verbs are used to communicate with the other
>characters in well-defined ways.  Basically the words are more like
>keywords, with TELL MOM ABOUT FIRE being more concise then entering some
>two-way dialog:

[examples snipped]

>These seem to make it much more a game than just picking the right
>multiple choice answer -- or, in the case where a new answer pops up,
>pickign the only obvious answer.

As I said before, if done well it really isn't like picking the right
multiple choice answer or the only obvious one.  I think it's one of those
things you have to experience to appreciate.  

Also, unlike the ask/tell style it has interaction.  Because of this it can
be fun to talk to people and to "explore" the conversation.

 ---------------
 James Cole
 jrcole@ozemail.com.au


From jrcole@ozemail.com.au Sun May 18 17:19:41 MET DST 1997
Article: 25346 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!pumpkin.pangea.ca!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 17 May 1997 11:16:50 GMT
Organization: Netspace Online Systems
Lines: 44
Message-ID: <337d932b.8430519@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au>
NNTP-Posting-Host: dialup-m1-10.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25346


Has anyone considered the fact that  Monkey Island style NPC conversation
can INCLUDE the "ask/tell <x> about <y>" system?  "The best of both
worlds".  Not only can you talk to people, but you can also ask or tell
them specific things about objects.  

I've already had this coded up in my utility, Converse, for a couple of
months, and it'll be in the second release.  (Out of interest...if anyone
has read the documentation for it, it's one of the extra feature's I said
would be added in future releases - the one that had already been coded)

Imagine the following situation: 

You're in a used-car yard looking at some of the cars.  The greasy dealer
has been following you around, making comments, pointing out things.  There
are a few cars in your price-range.  The yellow Volkswagon seems a bit
interesting, so you decide to ask the dealer about it.  

With the "ask <x> about <y>" form, all you could do is "ask salesman about
Volkswagon".

With the Monkey Island style you could "ask salesman about Volkswagon" and
then be presented with a series of questions to ask him.

	1) What can you tell me about the car?
	2) Can I take it for a test drive?
	3) What's red stain in the glove box?

etc.,

The answer to each of these could in turn give you further questions or
things to say.

Of course, for most objects you might only have the general "what can you
tell me about <x>" choice available (which, obviously, is equivalent to the
ask/tell style).

Also, with my new version of Converse you can add a default response for
objects.  So you can give a default answer when a player asks/tells an NPC
about an object you haven't coded a "conversation" for.  

 ---------------
 James Cole
 jrcole@ozemail.com.au


From jrcole@ozemail.com.au Wed May 21 18:14:36 MET DST 1997
Article: 25375 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!howland.erols.net!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sun, 18 May 1997 10:52:18 GMT
Organization: Netspace Online Systems
Lines: 118
Message-ID: <337edefe.11116727@news.netspace.net.au>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com>
NNTP-Posting-Host: dialup-m1-10.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25375

nulldogma@aol.com (Nulldogma) wrote:

>James Cole wrote:
>
>> Firstly, because you say something, the other person replies, you reply
>> to them, and so on.  Secondly, the content is more like a natural
>> conversation: you aren't restricted to just objects, but can also talk
>> about more abstract subjects, like "Hey, Joe, how has work been?" and
>> say things like "Yeh, I know what you mean".  Do you talk to people by
>> asking or telling them about objects?  
>
>The first is easy: ASK JOE ABOUT WORK. Or, if you feel like doing a little
>extra coding, JOE, HOW IS WORK, or even JOE, HOW HAS WORK BEEN can be made
>to get the same response. 

Ah, this is a good example to explain how the bit about "putting words into
your mouth" fits in.   Say Joe happens to be an old friend of yours who you
haven't seen in years.  Playing the game as "yourself", you might have no
reason to ask Joe about his job -- unless it is obvious to do so (e.g.
something in the game text suggests doing this).  But, playing a character
(who may have worked with Joe at the Cannery a while back) it would be a
natural thing for him/her to do.  

With the ask/tell style the basis of communication are things which can
superficially be observed within the gameworld.  This is not the way people
communicate.

This is another facet of why the Monkey Island style adds up to a more
"real" conversation.  

>                          Expanding the different acceptable syntaxes
>isn't really that hard, though you do start to run into the problem where
>the less you restrict the player, the more restrictive the remaining
>restrictions seem. ("Hey, how come I can ask Joe HOW HAS WORK BEEN but not
>HOW ARE YOU LIKING YOUR NEW JOB?")

gee, really. :-)

There's more I want to say about this when I get the chance.  [Mental note,
don't post about provactive subject when having millions of other things to
do.]

>The second isn't that hard, either: AGREE WITH JOE, or JOE, I AGREE, or
>just YES. 

Ok, how about these examples:
	- He really needs to think about what he says.
	- Ok, where do you want to meet?
	- Hi, can you tell me where I can have some fun around here?
	- Who's in charge here?
	- Hey, that's a nice hat.
	- But I told you that the water had to go in _after_ the flour!

Basically, it can be any possible thing which someone could say to you, or
you to someone else.

>            Again, it takes some coding, but *any* serious NPC work takes a
>buttload of coding.
>
>I guess I just disagree about which feels less stilted. If I'm in a room
>with someone and told I have a choice between speaking a simplified
>version of English, or communicating entirely through a set of pre-printed
>cards, I'll use the simplified English anyday.

Yes, but were not talking about real life here.  I'd do the same in 
that situation too.

>
>> You really can have a conversation with an NPC which sounds like a
>> conversation between two real people. 
>>
>> As for putting words into your mouth, it's supposed to.  As Adam Cadre
>> said, it's much more suited to games where you play a character rather
>> than yourself.  
>
>More suited, sure. But I'm still not convinced that it can be made to work
>with feeling overly manipulative (to me, anyway). Of course, I didn't
>really believe in puzzle-free I-F at one point, and Adam proved me wrong
>about that, so I should really withhold judgment until I see what he and
>others come up with.
>
Am I correct in assuming you haven't ever played something like Monkey
Island?  As I said in another reply, I really think this style of
conversation needs to be "experienced" to be fully appreciated.

If it can run on your system, you might want to have a look at one of the
issues of PC Gamer magazine.  I heard something about their being a
"locked" version of it on one of their cover CD's (The "Monkey Island 3"
issue).  You have to pay something like $10 to get a code or something to
"unlock" it.

>>
>> Anyway, IF is full of stuff which "puts words into your mouth".  
>
>Yup, and I tend to hate it. (See my mini-rant against Tapestry last fall.)

I intend to elaborate on this sometime in the future.  

...one thing I would like to add is that I think this problem occurs with
_all_ Infocom style IF (though that doesn't mean it doesn't occur in other
styles).  It's inherent to the way their done.


>> Restrictions on content?  What about the restrictions on content with
>> the ask/tell style? -- they are far worse.
>
>Why? Ask/tell is only limited to the game's vocabulary. Menus are limited
>to what's on the menu. There's no way any menuing system is going to
>provide as many content options as ask/tell -- not without becoming
>incredibly unweildy.
>
I don't have time to answer this now.  I'll reply to it when I get a
chance.


 ---------------
 James Cole
 jrcole@ozemail.com.au


From rossing@iname.com Wed May 21 18:16:14 MET DST 1997
Article: 25394 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!newsfeeds.sol.net!nntp.msen.com!ftl.msen.com!news
From: rossing@iname.com (Eric Rossing)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Mon, 19 May 1997 16:02:54 GMT
Organization: Msen
Lines: 107
Message-ID: <338179a1.13631028@ftl.msen.com>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au>
Reply-To: rossing@iname.com
NNTP-Posting-Host: gr01-d33.gr.msen.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent 1.01/32.397
Xref: news.lth.se rec.arts.int-fiction:25394

On Sun, 18 May 1997 10:52:18 GMT, jrcole@ozemail.com.au (James Cole) wrote:

: nulldogma@aol.com (Nulldogma) wrote:
: 
: >James Cole wrote:
: >
: >> Firstly, because you say something, the other person replies, you reply
: >> to them, and so on.  Secondly, the content is more like a natural
: >> conversation: you aren't restricted to just objects, but can also talk
: >> about more abstract subjects, like "Hey, Joe, how has work been?" and
: >> say things like "Yeh, I know what you mean".  Do you talk to people by
: >> asking or telling them about objects?  
: >
: >The first is easy: ASK JOE ABOUT WORK. Or, if you feel like doing a little
: >extra coding, JOE, HOW IS WORK, or even JOE, HOW HAS WORK BEEN can be made
: >to get the same response. 
: 
: Ah, this is a good example to explain how the bit about "putting words into
: your mouth" fits in.   Say Joe happens to be an old friend of yours who you
: haven't seen in years.  Playing the game as "yourself", you might have no
: reason to ask Joe about his job -- unless it is obvious to do so (e.g.
: something in the game text suggests doing this).  But, playing a character
: (who may have worked with Joe at the Cannery a while back) it would be a
: natural thing for him/her to do.  

Well, any well-written game will, in one way or another, tell the player
that he knew Joe years ago, or drop other hints that Joe's job is
significant.

: With the ask/tell style the basis of communication are things which can
: superficially be observed within the gameworld.  This is not the way people
: communicate.
: 
: This is another facet of why the Monkey Island style adds up to a more
: "real" conversation.  

But it doesn't!  MI's conversations are scripted conversations handed to me
by the authors of the game.  I don't want to find out that Joe knows nothing
about the blue goose because there aren't any menu choices about it.  I want
to be able to ask him and hear him say he knows nothing about it.  But I've
never seen a MI-style interface that allows that.

It's also annoying when you put things together sooner than the writers
allow you to.  I haven't played Monkey Island, but I've been playing Star
Trek:TNG, A Final Unity, which uses the same style of conversation.  There
have been times when I wanted to ask a character about something, but had to
run around to convince the game that I knew to talk about that.  Here's an
example:

On your way to manipulate the life-support systems of a space station, you
run across an injured woman.  After helping her, you talk to her and find
out she is the Chief Medical Officer of the station.  Does it make more
since to:

A) Ask her then and there if there is anything special needed to access the
life support systems, or

B) Go to the life support system, find out that you need an access code, and
then go back to the doctor to get it, and finally return to the system and
fix the problem?

: Ok, how about these examples:
: 	- He really needs to think about what he says.
: 	- Ok, where do you want to meet?
: 	- Hi, can you tell me where I can have some fun around here?
: 	- Who's in charge here?
: 	- Hey, that's a nice hat.
: 	- But I told you that the water had to go in _after_ the flour!
: 
: Basically, it can be any possible thing which someone could say to you, or
: you to someone else.

Yes, but only if the game writers think you ought to be able to say it.
Admittedly, both styles of conversation require the writer to anticipate
everything the player will want to say, but the normal IF way doesn't
broadcast the limitation.

: >I guess I just disagree about which feels less stilted. If I'm in a room
: >with someone and told I have a choice between speaking a simplified
: >version of English, or communicating entirely through a set of pre-printed
: >cards, I'll use the simplified English anyday.
: 
: Yes, but were not talking about real life here.  I'd do the same in 
: that situation too.

And the point here is which conversation style best simulates real life.
One of the big ideas behind good IF (one of the things I look for in a game,
at any rate) is to do as much as possible to draw the player into the game
world by making it seem as natural as possible.

: >> You really can have a conversation with an NPC which sounds like a
: >> conversation between two real people. 

Yes, but I'm one of the people.  Therefore, I want to control what I say...

: >>
: >> As for putting words into your mouth, it's supposed to.  As Adam Cadre
: >> said, it's much more suited to games where you play a character rather
: >> than yourself.  

Personally, I want to be allowed to play the character, and not have the
character played(scripted) for me...

Eric Rossing
rossing@iname.com
http://home.msen.com/~rossing
PGP Public key available on my WWW page


From ats@hubert.wustl.edu Wed May 21 18:16:32 MET DST 1997
Article: 25427 of rec.arts.int-fiction
Path: news.lth.se!solace!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!newsxfer.itd.umich.edu!!newspump.wustl.edu!newsreader.wustl.edu!not-for-mail
From: Alan Shutko <ats@hubert.wustl.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 20 May 1997 12:35:48 -0500
Organization: Washington University in St. Louis
Lines: 25
Message-ID: <m2oha6vyff.fsf@hubert.wustl.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com>
NNTP-Posting-Host: wuh.eliot226.wustl.edu
Mime-Version: 1.0 (generated by tm-edit 7.93)
Content-Type: text/plain; charset=US-ASCII
X-Newsreader: Gnus v5.4.25/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:25427

>>>>> "Eric" == Eric Rossing <rossing@iname.com> writes:

Eric> I haven't played Monkey Island, but I've been playing Star
Eric> Trek:TNG, A Final Unity, which uses the same style of
Eric> conversation.

I think that most people who oppose this probably haven't played
Monkey Island.  The reason MI worked so well was that the game had
brilliant script writers who made the most of the interface.  You also
had a specific character that was being written for.

A lot of the humor of MI couldn't be expressed in a typical ask/tell
interface, because a lot of it was stuff that Guybrush (the
protagonist) said.  MI was probably less a game where you are the main
character than one where you are the a little voice inside the
character's head.  Guybrush talked to himself, occasionally did stuff
on his own (especially in one hilarious scene where the authors made
fun of the interface), and had a well-defined personality.

I think there's definitely room in IF for this type of game.  I'd love
to play a text-based one.

-- 
Alan Shutko <ats@hubert.wustl.edu> - By consent of the corrupted
This unit... must... survive.


From jrcole@ozemail.com.au Wed May 21 18:34:13 MET DST 1997
Article: 25438 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!news-zh.switch.ch!news-ge.switch.ch!news-fra1.dfn.de!news-kar1.dfn.de!newsfeed.nacamar.de!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!swrinde!ihnp4.ucsd.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Wed, 21 May 1997 07:39:30 GMT
Organization: Netspace Online Systems
Lines: 164
Message-ID: <3382a5cd.8663849@news.netspace.net.au>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com>
NNTP-Posting-Host: dialup-m1-11.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25438

rossing@iname.com (Eric Rossing) wrote:

>On Sun, 18 May 1997 10:52:18 GMT, jrcole@ozemail.com.au (James Cole) wrote:
>
>: nulldogma@aol.com (Nulldogma) wrote:
>: 
>: >James Cole wrote:
>: >
>: >> Firstly, because you say something, the other person replies, you reply
>: >> to them, and so on.  Secondly, the content is more like a natural
>: >> conversation: you aren't restricted to just objects, but can also talk
>: >> about more abstract subjects, like "Hey, Joe, how has work been?" and
>: >> say things like "Yeh, I know what you mean".  Do you talk to people by
>: >> asking or telling them about objects?  
>: >
>: >The first is easy: ASK JOE ABOUT WORK. Or, if you feel like doing a little
>: >extra coding, JOE, HOW IS WORK, or even JOE, HOW HAS WORK BEEN can be made
>: >to get the same response. 
>: 
>: Ah, this is a good example to explain how the bit about "putting words into
>: your mouth" fits in.   Say Joe happens to be an old friend of yours who you
>: haven't seen in years.  Playing the game as "yourself", you might have no
>: reason to ask Joe about his job -- unless it is obvious to do so (e.g.
>: something in the game text suggests doing this).  But, playing a character
>: (who may have worked with Joe at the Cannery a while back) it would be a
>: natural thing for him/her to do.  
>
>Well, any well-written game will, in one way or another, tell the player
>that he knew Joe years ago, or drop other hints that Joe's job is
>significant.

There's the problem, hinting would ruin it.  Sure, in some cases it might
fit in well.  But, in most it will seem unnatural, forced, and awkward.  

"How his job's going" may just be something which the character wants to
ask Joe about, there may be no real purpose to it.  Perhaps Joe's answer
only adds a bit of characterisation, or gives an insight to your
character's relation to Joe in the past.  Hinting is too unelegant in doing
this.  Espeically so, if you want to have more "real" conversations, like
you'd have in a book, movie, etc.

>: With the ask/tell style the basis of communication are things which can
>: superficially be observed within the gameworld.  This is not the way people
>: communicate.
>: 
>: This is another facet of why the Monkey Island style adds up to a more
>: "real" conversation.  
>
>But it doesn't!  MI's conversations are scripted conversations handed to me
>by the authors of the game.  I don't want to find out that Joe knows nothing
>about the blue goose because there aren't any menu choices about it.  I want
>to be able to ask him and hear him say he knows nothing about it.  But I've
>never seen a MI-style interface that allows that.

You've totally missed the point.  

>It's also annoying when you put things together sooner than the writers
>allow you to.  I haven't played Monkey Island, but I've been playing Star
>Trek:TNG, A Final Unity, which uses the same style of conversation.  There
>have been times when I wanted to ask a character about something, but had to
>run around to convince the game that I knew to talk about that.  Here's an
>example:
[...example snipped...]

>From the discussion it's been made clear that the Monkey Island style can
have a lot of problems if not implemented well.  Obviously a bad situation
like in you example can occur fairly easily.  

You have to remember though, these types of situations can generally be
avoided.  It is even possible to do it so it's not obvious to the user that
you're trying to avoid the problem.  

Nothing is perfect, problems can and do occur with the Monkey Island
system.  Part of my preference for it stems from it's disadvantages being
far less than the ask/tell style.  As for the advantages of both systems
it's a more subjective affair, you may like one system better than the
other.  This is Ok; but what you can't do is separate the advantages and
disadvantages of a system.  You have to consider something as a whole.

>: Ok, how about these examples:
>: 	- He really needs to think about what he says.
>: 	- Ok, where do you want to meet?
>: 	- Hi, can you tell me where I can have some fun around here?
>: 	- Who's in charge here?
>: 	- Hey, that's a nice hat.
>: 	- But I told you that the water had to go in _after_ the flour!
>: 
>: Basically, it can be any possible thing which someone could say to you, or
>: you to someone else.

>Yes, but only if the game writers think you ought to be able to say it.

You've missed the point.  

>Admittedly, both styles of conversation require the writer to anticipate
>everything the player will want to say, but the normal IF way doesn't
>broadcast the limitation.

more choices <> less limitated.

>: >I guess I just disagree about which feels less stilted. If I'm in a room
>: >with someone and told I have a choice between speaking a simplified
>: >version of English, or communicating entirely through a set of pre-printed
>: >cards, I'll use the simplified English anyday.
>: 
>: Yes, but were not talking about real life here.  I'd do the same in 
>: that situation too.
>
>And the point here is which conversation style best simulates real life.

why?  

>One of the big ideas behind good IF (one of the things I look for in a game,
>at any rate) is to do as much as possible to draw the player into the game
>world by making it seem as natural as possible.

If you truly understood both systems you would know that the Monkey Island
style actually does quite a good job of this.  

In realy life, when you're talking to someone you think of what to say.
Sure, in most cases it's pretty much automatic.  But, at every point in the
conversation when it's "your turn" you DO have a set of choices of what you
can say.  

You DON'T talk to people by asking (or telling) them about a series of
objects.  It's not natural.

Now Monkey Island does give you a limited number of things to say, but,
done right, it can still give you an impression of a conversation.  You are
playing a character, and your choices are the things the character has
"thought" he/she might say.  You are still folloing the same pattern as
real conversations  -- deciding what to say at a particular point.  In this
way, it does "feel" more natural.

>
>: >> You really can have a conversation with an NPC which sounds like a
>: >> conversation between two real people. 
>
>Yes, but I'm one of the people.  Therefore, I want to control what I say...
>
You can.  The choices are limited **at each point in the conversation** but
this is not that far away from real conversation anyway.  

What **real** control do you have in the ask/tell style??  Sure, you can
ask/tell about any object, but there's no control apart from that.  Do you
really have any control over the meaning of your question.  

Think about if you had to talk to someone but could only ask them an
initial question.  Then questions about the "objects" mentioned/raised in
their reply.  You'd find there were many things you'd like to ask them
about which you couldn't.

>: >> As for putting words into your mouth, it's supposed to.  As Adam Cadre
>: >> said, it's much more suited to games where you play a character rather
>: >> than yourself.  
>
>Personally, I want to be allowed to play the character, and not have the
>character played(scripted) for me...
>
Look, that's just not how it works.  Simple as that.

 ---------------
 James Cole
 jrcole@ozemail.com.au


From carl@earthweb.com Wed May 21 18:45:28 MET DST 1997
Article: 25379 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!news.silcom.com!news.genuity.net!not-for-mail
From: Carl Muckenhoupt <carl@earthweb.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Fri, 16 May 1997 16:34:04 -0400
Organization: EarthWeb
Lines: 64
Message-ID: <337CC4BC.2AF@earthweb.com>
References: <3379b653.10392540@news.netspace.net.au> <337C204E.3DA5@i3d.es>
Reply-To: carl@earthweb.com
NNTP-Posting-Host: ben.earthweb.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25379

Daniel Cardenas wrote:
 Most of the Spanish games are not based in the '[ask|tell] him about
 topic'. They use the 'tell "free_text:_put_here_what_you_want"'. It is
 supposed that the programmer use keywords to implement possible
 responses:
 
 _>tell "hello, what a beutiful day"
   The NPC tells you "Hi if fans!"
 
 Here the keyword was HELLO, but it's not necessary we have only one. We
 can detect one (HELLO) and use some others (MIKE/GLORIA) to help
getting
 the meaning of the sentence:
 
 _>tell "hello Mike"
   The NPC tells you "Hi Daniel"
 
 _>tell "hello Gloria"  (He is actually Mike)
   The NPC says "Gloria? My name's Mike!"
 
 Ok, this was a stupid example, here you have another...
 
 Tom ask you "Have you seen Gloria?"
 
 1. >say "yes"
     Tom asks you "where have you seen her?"
 
    >reply "in the living room, he is expecting you."
     Tom says "Nice. Good bye" and goes down.
 
 2. >say "yes, he is in the living room"
     Tom says "Thanks" and goes down.
 
 3. >say "I'm sorry. No."
    Tom says "Ok. I will continue looking for her."
 
 I think using more than one keyword (like in the ask/tell formula), can
 give more adequate responses, but you have to use it carefully:
 
 _> tell "hello, have you seen Gloria"
    The NPC says "Gloria? My name's Mike!"
 
 Apart from being more difficult to implement, it can help giving a
 feeling of freedom.

I've seen one game that does this.  It was called "Interactive Fiction",
it was published by Adventure International (Scott Adams' company), it
consisted of four small scenarios, and it had no other form of
interactivity.  It didn't work very well, IMHO, and I prefer the Infocom
converstaion mechanism. Why?  For the same reason that I don't like
games to pretend to understand commands that they don't.  "Tell x about
y" - what one might call the single keyword system - has clear and
obvious limitations.  The freeform multiple-keyword system has
limitations as well, but it pretends not to.  The increased feeling of
freedom is an illusion, and the players will realize this and be
disappointed.

This is not to say that the Infocom mechanism is perfect.  But I think
that in any conversation mechanism, the expected input should match the
ability of the program to understand it.

-- 
Carl Muckenhoupt		carl@earthweb.com
EarthWeb			http://www.earthweb.com/


From adamc@acpub.duke.edu Wed May 21 18:46:24 MET DST 1997
Article: 25374 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!news.uni-c.dk!hunter.premier.net!feed1.news.erols.com!howland.erols.net!newsfeed.internetmci.com!portal.gmu.edu!solaris.cc.vt.edu!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sun, 18 May 1997 14:38:40 -0400
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 31
Message-ID: <337F4CB0.52EC@acpub.duke.edu>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25374

Jame Cole wrote:
> With the Monkey Island style you could "ask salesman about Volkswagen"
> and then be presented with a series of questions to ask him.
> 
>          1) What can you tell me about the car?
>          2) Can I take it for a test drive?
>          3) What's red stain in the glove box?

Erik Max Francis replied:
> This seems to me to be more of a situation where the player is merely
> forced to find which option the author wanted him to pick.
> 
> Would there really be a good puzzle where subtlety is important in
> this way?

See, there's the problem.  You're still thinking in terms of puzzles.
It's true that a menu-based conversation interface can turn a puzzle
into a multiple-choice question complete with everything but a Scantron
and a #2 pencil -- but if the NPC interaction in the game in question
is based not on picking the right answer to get the NPC to open the
door or drink the poison, but rather based around more open-ended
consequences (the NPC you're talking to likes you a little less, while
someone else in the room overhears and likes you more, which may be
a benefit later on, or may be a disadvantage, depending on the plot
threads you follow in the meantime), then the problem vanishes in a
puff of green smoke.

  -----
 Adam Cadre, Durham, NC
 obscure Captain America villain
 http://www.duke.edu/~adamc


From erkyrath@netcom.com Wed May 21 19:00:45 MET DST 1997
Article: 25384 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Message-ID: <erkyrathEAErIx.IF2@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <337F4CB0.52EC@acpub.duke.edu>
Date: Mon, 19 May 1997 03:11:21 GMT
Lines: 105
Sender: erkyrath@netcom2.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25384

Adam Cadre (adamc@acpub.duke.edu) wrote:
> Jame Cole wrote:
> > With the Monkey Island style you could "ask salesman about Volkswagen"
> > and then be presented with a series of questions to ask him.
> > 
> >          1) What can you tell me about the car?
> >          2) Can I take it for a test drive?
> >          3) What's red stain in the glove box?

> Erik Max Francis replied:
> > This seems to me to be more of a situation where the player is merely
> > forced to find which option the author wanted him to pick.
> > 
> > Would there really be a good puzzle where subtlety is important in
> > this way?

> See, there's the problem.  You're still thinking in terms of puzzles.

The word "puzzle" can be arbitrarily broad, up to any situation where the 
player wants to influence "what happens next."

> It's true that a menu-based conversation interface can turn a puzzle
> into a multiple-choice question complete with everything but a Scantron
> and a #2 pencil -- but if the NPC interaction in the game in question
> is based not on picking the right answer to get the NPC to open the
> door or drink the poison, but rather based around more open-ended
> consequences (the NPC you're talking to likes you a little less, while
> someone else in the room overhears and likes you more, which may be
> a benefit later on, or may be a disadvantage, depending on the plot
> threads you follow in the meantime), then the problem vanishes in a
> puff of green smoke.

I don't think so. First, do you really mean "open-ended?" Open-*middled* 
is a better description, since you're talking about a broader range of 
consequences of the player's *current* statement, rather than any 
attribute of the *end*-goal.

(Aside one: Why do I pick this nit? Because whether it's a "puzzle" or 
not is irrelevant. Maybe you *do* want the NPC to open the door, but 
it's not going to happen for another three scenes, in which four more 
NPCs are going to interact with you and each other using a full 
emotion-based simulation engine and true natural language parsing. Or 
whatever. The game may ultimately be either a find-the-right-actions 
puzzle or an open-ended branching storyline about character interplay; 
but neither of these is more or less suited to one kind of interface or 
another.)

(Rephrasing of aside one: An "open-ended" scene can be one puzzle in a 
puzzle game; a "puzzle" scene can be one interaction in an open-ended 
consequences story. Repeat recursively. Therefore, it's obvious that an 
interface style can't be suited for just one of these.)

Main point: Well, actually the aside sums it up. If you're interacting 
with story, which is presumably the point, you may *want* the NPC to like 
you a little less, or whatever. There may not be a single option that the 
author wants you to pick; but there will be options that the author wants 
you to pick *in order to go a particular direction*. (Unless all the 
options lead to the same results, which, again, is presumably not the 
point.)

Mmm, let me think of this another way: In any game (not necessarily a
computer game) there is a balance between (A) the number of things you can
do, (B) the number of interesting results, (C) the designer's effort in
inventing results, and (D) the player not getting bored. A choose-your-
own-adventure book, for example, drastically cuts down on (A), and further
cuts down (B) by having plotlines merge up again wherever possible. The
result is almost always dull. 

Colossal Cave managed (by some combination of genius and sheer damn luck)
to invent a brilliant balance where (A) is huge, but (B) is vastly trimmed
down, because 98% of the possible commands have boilerplate responses, and
90% of the remaining 2% merge back into each other in a predictable way.
("GET KEYS. GET LAMP" winds up the same as "GET LAMP. GET KEYS.") And yet 
somehow we focus on the 2% and are most interested in the 0.2%. And 
therefore the game works.

It's all somehow different for conversation. We expect (at least, I 
expect) every act of conversation to be interesting and relevant to the 
plot -- even though we're perfectly happy with a game where 75% of the 
commands are "N", "N", "E", "I", "L", ... etc. I think that's what the 
"ask X about Y" hack is for; it's a syntax where the author can deal with 
every conceivable value of X and Y, and even though 98% of the responses 
will still be boilerplate, they'll all be plausible boilerplate. 

In a menu system -- as opposed to a keyword system -- you're backing up
and giving the player three or four options at a time, instead of
hundreds. This is not unworkable, but it does jar against the IF model
that we're all used to. I think that's why people react badly to the
suggestion. 

As to the two level-system that we started with -- "ask salesman about 
Volkswagen" followed by three options -- it seems unnecessarily 
complicated. Well, I should say, just plain complicated. Any hybrid 
system runs the risk of combining the flaws of both parts; I'd be afraid 
that the result would feel vague and nonspecific *and* forced and 
putting-options-in-my-mouth.

But then I haven't tried it.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From nulldogma@aol.com Wed May 21 19:01:06 MET DST 1997
Article: 25405 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.apfel.de!eerie.fr!news.radio.cz!mr.net!europa.clark.net!newsxfer3.itd.umich.edu!portc01.blue.aol.com!audrey02.news.aol.com!not-for-mail
From: nulldogma@aol.com (Nulldogma)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 19 May 1997 13:01:41 GMT
Lines: 17
Message-ID: <19970519170101.NAA08946@ladder02.news.aol.com>
NNTP-Posting-Host: ladder02.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
References: <337FD9FF.5BE5@acpub.duke.edu>
Xref: news.lth.se rec.arts.int-fiction:25405

Andrew Plotkin wrote:

>It's all somehow different for conversation. We expect (at least, I 
>expect) every act of conversation to be interesting and relevant to the 
>plot -- even though we're perfectly happy with a game where 75% of the 
>commands are "N", "N", "E", "I", "L", ... etc.

You know, it's bad enough that half the people on this newsgroup seem to
have the same name as me, but now even the *commands* are spelling it
out...

Neil

---------------------------------------------------------
Neil deMause                            neild@echonyc.com
                  http://www.echonyc.com/~wham/neild.html
---------------------------------------------------------


From jrcole@ozemail.com.au Wed May 21 19:24:49 MET DST 1997
Article: 25391 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!newsfeed.nacamar.de!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Mon, 19 May 1997 08:45:36 GMT
Organization: Netspace Online Systems
Lines: 105
Message-ID: <3380124d.6822459@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <337F4CB0.52EC@acpub.duke.edu> <erkyrathEAErIx.IF2@netcom.com>
NNTP-Posting-Host: dialup-m1-14.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25391

erkyrath@netcom.com (Andrew Plotkin) wrote:

[...]
>
>Main point: Well, actually the aside sums it up. If you're interacting 
>with story, which is presumably the point, you may *want* the NPC to like 
>you a little less, or whatever. There may not be a single option that the 
>author wants you to pick; but there will be options that the author wants 
>you to pick *in order to go a particular direction*. (Unless all the 
>options lead to the same results, which, again, is presumably not the 
>point.)

...but isn't this supportive of what Adam was saying?


>Mmm, let me think of this another way: In any game (not necessarily a
>computer game) there is a balance between (A) the number of things you can
>do, (B) the number of interesting results, (C) the designer's effort in
>inventing results, and (D) the player not getting bored. A choose-your-
>own-adventure book, for example, drastically cuts down on (A), and further
>cuts down (B) by having plotlines merge up again wherever possible. The
>result is almost always dull. 

>Colossal Cave managed (by some combination of genius and sheer damn luck)
>to invent a brilliant balance where (A) is huge, but (B) is vastly trimmed
>down, because 98% of the possible commands have boilerplate responses, and
>90% of the remaining 2% merge back into each other in a predictable way.

>("GET KEYS. GET LAMP" winds up the same as "GET LAMP. GET KEYS.")

  what's the point of this example?  It doesn't seem to fit in with what
you're saying.

>                                                                   And yet 
>somehow we focus on the 2% and are most interested in the 0.2%. And 
>therefore the game works.

I disagree a bit with this.  Why? The explanation is long, and I couldn't
be bothered explaining at the moment.

>It's all somehow different for conversation. We expect (at least, I 
>expect) every act of conversation to be interesting and relevant to the 
>plot -- even though we're perfectly happy with a game where 75% of the 
>commands are "N", "N", "E", "I", "L", ... etc.

I'm not.

>                                                I think that's what the 
>"ask X about Y" hack is for; it's a syntax where the author can deal with 
>every conceivable value of X and Y, and even though 98% of the responses 
>will still be boilerplate, they'll all be plausible boilerplate. 

Rubbish.  In _every_ Infocom style game I've ever played suspension of
disbelief was destroyed (to some extent) by not providing adequate (and in
most cases, obvious) responses.  This really does put people off IF (even
when they understand the systems limitations).  (In fact this adds to
another, and far greater, problem).

I'm sure Infocom IF fans out there will probably think I'm just an anomaly
with this sort of opinion.  But that's not the case -- they're the
exception in the vast majority of people out there.  

I intend to elaborate on this subject matter in the future.

>In a menu system -- as opposed to a keyword system -- you're backing up
>and giving the player three or four options at a time, instead of
>hundreds. 

I see this as an advantage.  Because there are a clearly defined number of
choices you can't get the situation of a default response destroying
suspension of disbelief.

Note that this doesn't mean that the Monkey Island technique is just a more
fool-proof "mass-market" solution.

I'm interested in knowing exactly why you think hundreds are better?

>            This is not unworkable, but it does jar against the IF model
>that we're all used to. I think that's why people react badly to the
>suggestion. 

Actually, I doubt that.  I suspect it's because most haven't actually used
the Monkey Island style (at least in a decent implementation).  I get this
impression from the responses I've gotten, where people seem to be thinking
about the concept in the context of the functions/uses, etc., of the
ask/tell style.

>As to the two level-system that we started with -- "ask salesman about 
>Volkswagen" followed by three options -- it seems unnecessarily 
>complicated. Well, I should say, just plain complicated. 

Why does it seem complicated?  Have a look at my second example of this in
my reply to Eric.  

>                                                         Any hybrid 
>system runs the risk of combining the flaws of both parts; I'd be afraid 
>that the result would feel vague and nonspecific *and* forced and 
>putting-options-in-my-mouth.

How come?


 ---------------
 James Cole
 jrcole@ozemail.com.au


From erkyrath@netcom.com Wed May 21 19:26:05 MET DST 1997
Article: 25397 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!newsfeed.nacamar.de!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Message-ID: <erkyrathEAFw8A.68F@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <337F4CB0.52EC@acpub.duke.edu> <erkyrathEAErIx.IF2@netcom.com> <3380124d.6822459@news.netspace.net.au>
Date: Mon, 19 May 1997 17:50:34 GMT
Sender: erkyrath@netcom.netcom.com
Lines: 123
Xref: news.lth.se rec.arts.int-fiction:25397

James Cole (jrcole@ozemail.com.au) wrote:
> erkyrath@netcom.com (Andrew Plotkin) wrote:

> [...]
> >
> >Main point: Well, actually the aside sums it up. If you're interacting 
> >with story, which is presumably the point, you may *want* the NPC to like 
> >you a little less, or whatever. There may not be a single option that the 
> >author wants you to pick; but there will be options that the author wants 
> >you to pick *in order to go a particular direction*. (Unless all the 
> >options lead to the same results, which, again, is presumably not the 
> >point.)

> ...but isn't this supportive of what Adam was saying?

Do I remember what the heck Adam was saying? :)

> >Mmm, let me think of this another way: In any game (not necessarily a
> >computer game) there is a balance between (A) the number of things you can
> >do, (B) the number of interesting results, (C) the designer's effort in
> >inventing results, and (D) the player not getting bored. A choose-your-
> >own-adventure book, for example, drastically cuts down on (A), and further
> >cuts down (B) by having plotlines merge up again wherever possible. The
> >result is almost always dull. 

> >Colossal Cave managed (by some combination of genius and sheer damn luck)
> >to invent a brilliant balance where (A) is huge, but (B) is vastly trimmed
> >down, because 98% of the possible commands have boilerplate responses, and
> >90% of the remaining 2% merge back into each other in a predictable way.

> >("GET KEYS. GET LAMP" winds up the same as "GET LAMP. GET KEYS.")

>   what's the point of this example?  It doesn't seem to fit in with what
> you're saying.

It's an example of a trivial branch in the storyline which doesn't take
exponential effort to design. Most commands in a game are orthogonal and
independent of each other; only a tiny fraction have broader effects.
Nonetheless, it's that small fraction which the players focus on. Nobody
ever complains that "GET KEYS" has a predictable boilerplate effect. 

> >It's all somehow different for conversation. We expect (at least, I 
> >expect) every act of conversation to be interesting and relevant to the 
> >plot -- even though we're perfectly happy with a game where 75% of the 
> >commands are "N", "N", "E", "I", "L", ... etc.

> I'm not.

I was describing all existing text IF, is the point...

> >                                                I think that's what the 
> >"ask X about Y" hack is for; it's a syntax where the author can deal with 
> >every conceivable value of X and Y, and even though 98% of the responses 
> >will still be boilerplate, they'll all be plausible boilerplate. 

> Rubbish.  In _every_ Infocom style game I've ever played suspension of
> disbelief was destroyed (to some extent) by not providing adequate (and in
> most cases, obvious) responses.  This really does put people off IF (even
> when they understand the systems limitations).  (In fact this adds to
> another, and far greater, problem).

> I'm sure Infocom IF fans out there will probably think I'm just an anomaly
> with this sort of opinion.  But that's not the case -- they're the
> exception in the vast majority of people out there.  

> I intend to elaborate on this subject matter in the future.

Please do; I don't think any of us can really talk about what the vast 
majority of people do. I don't get feedback from Command&Conquer players 
on the subject -- much less monolingual Chinese duck-farmers. :)

> >In a menu system -- as opposed to a keyword system -- you're backing up
> >and giving the player three or four options at a time, instead of
> >hundreds. 

> I see this as an advantage.  Because there are a clearly defined number of
> choices you can't get the situation of a default response destroying
> suspension of disbelief.

It's neither an advantage nor a disadvantage.

> Note that this doesn't mean that the Monkey Island technique is just a more
> fool-proof "mass-market" solution.

> I'm interested in knowing exactly why you think hundreds are better?

Not better; I'm saying that it's an approach which is consistent with the 
rest (non-conversation portions) of existing text IF. Therefore fans of 
existing IF are predisposed to prefer it.

> >            This is not unworkable, but it does jar against the IF model
> >that we're all used to. I think that's why people react badly to the
> >suggestion. 

> Actually, I doubt that.  I suspect it's because most haven't actually used
> the Monkey Island style (at least in a decent implementation).

Only one possible follow-up to that claim. Heh.

> >As to the two level-system that we started with -- "ask salesman about 
> >Volkswagen" followed by three options -- it seems unnecessarily 
> >complicated. Well, I should say, just plain complicated. 

> Why does it seem complicated?

Two modes rather than one.

> >  Any hybrid 
> >system runs the risk of combining the flaws of both parts; I'd be afraid 
> >that the result would feel vague and nonspecific *and* forced and 
> >putting-options-in-my-mouth.

> How come?

Because that's always the risk when you combine two different systems, of 
any sort. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From adamc@acpub.duke.edu Wed May 21 19:27:30 MET DST 1997
Article: 25408 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!news.uni-c.dk!hunter.premier.net!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!portal.gmu.edu!solaris.cc.vt.edu!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Mon, 19 May 1997 17:03:09 -0400
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 69
Message-ID: <3380C00D.605@acpub.duke.edu>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <337F4CB0.52EC@acpub.duke.edu> <erkyrathEAErIx.IF2@netcom.com> <3380124d.6822459@news.netspace.net.au> <erkyrathEAFw8A.68F@netcom.com>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25408

Andrew Plotkin wrote:
> Main point: Well, actually the aside sums it up. If you're interacting
> with story, which is presumably the point, you may *want* the NPC to
> like you a little less, or whatever. There may not be a single option
> that the author wants you to pick; but there will be options that the
> author wants you to pick *in order to go a particular direction*.
> (Unless all the options lead to the same results, which, again, is
> presumably not the point.)

James Cole replied:
> ...but isn't this supportive of what Adam was saying?

Andrew Plotkin answered:
> Do I remember what the heck Adam was saying? :)

I sure don't.  Let check the thread for a minute...

...okay.  This is kind of difficult for me since I suspect that what
I'm tentatively pouncing on as your point may well be more like a
"whereas" clause leading up to your point.  Let me respond to just
a couple passages.  The first is a recap:

> Main point: Well, actually the aside sums it up. If you're interacting
> with story, which is presumably the point, you may *want* the NPC to
> like you a little less, or whatever.

Right.  I agree with that.

> There may not be a single option that the author wants you to pick;
> but there will be options that the author wants you to pick *in order
> to go a particular direction*.

I'm having trouble with the word "wants."  I think better in the
concrete than in the abstract, so let me make up an example:

Early on, the PC has a conversation with NPC1, while NPC2 sits in the
corner reading the newspaper.  NPC1 and NPC2 hate each other.  At
several points during the conversation, the PC has the opportunity to
respond warmly or coolly to what NPC1 has said.

Later on in the game, the PC receives a dinner invitation.  If the
conversation with NPC1 has been a friendly one, the invitation is from
NPC1.  If the conversation was a chilly one, the invitation is from
NPC2.  The dinner parties are dramatically different: at NPC1's, a
gang of terrorists breaks in and holds everyone at gunpoint, and your
job is to free the hostages; at NPC2's, you meet a charming stranger
and spend the rest of the game trying to get a romance going.  The
author doesn't "want" you to pick either scenario, since both have been
coded -- either choice is just fine with the author.  The author
doesn't nudge the player in either direction; on the contrary, the
author hopes that in later replayings of the game, the player will
select a different course so that all the beautiful prose in the
originally unchosen path won't go to waste.

This is the kind of thing I had in mind, which makes this second
passage seem off the mark:

> First, do you really mean "open-ended?" Open-*middled* is a better
> description, since you're talking about a broader range of 
> consequences of the player's *current* statement, rather than any 
> attribute of the *end*-goal.

No, I'm not.  Or at least I didn't intend to.  The endpoints =are=
different, as are the eventual goals.

  -----
 Adam Cadre, Durham, NC
 obscure Captain America villain
 http://www.duke.edu/~adamc


From erkyrath@netcom.com Wed May 21 19:28:24 MET DST 1997
Article: 25418 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!solace!news.ecn.uoknor.edu!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Message-ID: <erkyrathEAHu9J.5o7@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <337F4CB0.52EC@acpub.duke.edu> <erkyrathEAErIx.IF2@netcom.com> <3380124d.6822459@news.netspace.net.au> <erkyrathEAFw8A.68F@netcom.com> <3381a399.3763609@news.netspace.net.au>
Date: Tue, 20 May 1997 19:03:18 GMT
Lines: 69
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25418

James Cole (jrcole@ozemail.com.au) wrote:
> >It's an example of a trivial branch in the storyline which doesn't take
> >exponential effort to design. Most commands in a game are orthogonal and
> >independent of each other; only a tiny fraction have broader effects.
> >Nonetheless, it's that small fraction which the players focus on. Nobody
> >ever complains that "GET KEYS" has a predictable boilerplate effect. 

> I understand, but I don't quite get what the point was.

The point is that the illusion of boundlessness, as you described it in
another post, is a lot more resilient than you are claiming. Or, at least, 
it holds up very well for me, and I think for a lot of us. I get the 
impression that it's much more fragile for you; but this is a matter of 
personal preference.

> >> >It's all somehow different for conversation. We expect (at least, I 
> >> >expect) every act of conversation to be interesting and relevant to the 
> >> >plot -- even though we're perfectly happy with a game where 75% of the 
> >> >commands are "N", "N", "E", "I", "L", ... etc.
> >
> >> I'm not.
> >
> >I was describing all existing text IF, is the point...

> I don't get what you mean?  

In all existing text games -- well, Infocom games and the ones built with 
TADS and Inform standard libraries -- 75% of the game is trivial commands. 
Movement, look, inventory, and so on. Maybe you can't stand this, but the 
rest of us seem to have adapted. Furthermore, of the boundless (well, 
huge) set of possible commands, 98% produce a dull result like "You don't 
see any such thing here" or "You can't pull that."

In the NPC-conversation parts of these games, again, most commands produce
a dull result like "I dasn't noo nowt aboot tha'." And this doesn't really
bother me either, largely because it's so parallel to the previous case, 
and therefore I've gotten used to it. But it does tend to bother people 
more, which is what I was saying; we do tend to expect that every act of 
conversation with an NPC will be understood and will produce an 
intelligent response. Because that's how real people behave. 

> You can't just give a statement without any reasoning whatsoever.

Demonstratably false; I do it all the time. :)

> >> >This is not unworkable, but it does jar against the IF model
> >> >that we're all used to. I think that's why people react badly to the
> >> >suggestion. 
> >
> >> Actually, I doubt that.  I suspect it's because most haven't actually used
> >> the Monkey Island style (at least in a decent implementation).
> >
> >Only one possible follow-up to that claim. Heh.

> Out of interest, what's your situation?

I have a day job, and my spare time is all taken up right now with writing
a Mac graphics tool. When I finish that, I have at two well-developed plot
lines that I want to turn into games, and at least one more set of ideas
which I want to develop and then turn into a game. Plus assorted other
projects, some related to IF. Exploring new NPC-interaction modes is so far
down the list that it's got coal veins running through it. :(

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From jrcole@ozemail.com.au Wed May 21 19:29:01 MET DST 1997
Article: 25390 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!news.uni-c.dk!hunter.premier.net!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!news.mel.connect.com.au!news.netspace.net.au!not-for-mail
From: jrcole@ozemail.com.au (James Cole)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Mon, 19 May 1997 08:41:45 GMT
Organization: Netspace Online Systems
Lines: 57
Message-ID: <33801214.6765452@news.netspace.net.au>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com>
NNTP-Posting-Host: dialup-m1-14.brisbane.netspace.net.au
X-Newsreader: Forte Free Agent 1.1/32.230
Xref: news.lth.se rec.arts.int-fiction:25390

Erik Max Francis <max@alcyone.com> wrote:

>James Cole wrote:
>
>> With the "ask <x> about <y>" form, all you could do is "ask salesman
>> about Volkswagon".
>> 
>> With the Monkey Island style you could "ask salesman about Volkswagon"
>> and then be presented with a series of questions to ask him.
>> 
>>         1) What can you tell me about the car?
>>         2) Can I take it for a test drive?
>>         3) What's red stain in the glove box?
>> 
>> etc.,
>> 
>> The answer to each of these could in turn give you further questions or
>> things to say.
>
>This seems to me to be more of a situation where the player is merely
>forced to find which option the author wanted him to pick.
>
>Would there really be a good puzzle where subtlety is important in this
>way?

Your considering this in the wrong way.  Basically, the idea of the extra
things to ask about particular object are just there to give you a richer
level of interaction.  

Consider another example: from a distance you see a man surreptitiously
drop something.  All you can distinguish about him is that he's wearing a
red sweater.  You go over and pick the object up, noting that it's some
sort of engine part.  There is a mechanic in the town and you decide to go
and ask him about the part.  

If you were using the ask/tell style, what would asking the mechanic about
the object mean?  Most likely, it'll mean asking him to identify the part
-- but I also want to ask him about the shady character!  There is no way
you could do this with the ask/tell style.  (and yes, you probably could
find some sort of awkward workaround for this particular situation, but not
for the general case.)

Using a monkey island style of the ask/tell format you ask the questions:
      1) What can you tell me about this object?
      2) I saw a man drop this, he was wearing a red sweater.  
	 Do you know who he could be?


It is important to keep in mind, though, that this would not be the typical
situation.  By this, I mean that for most objects you'd probably only have
the general "what can you tell me about..." question.  Therefore, this
technique should be considerd as an extension of the Infocom ask/tell style
which can handle a wider and subtler range of situations.

 ---------------
 James Cole
 jrcole@ozemail.com.au


From nulldogma@aol.com Wed May 21 19:29:19 MET DST 1997
Article: 25404 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!newsfeed.direct.ca!portc01.blue.aol.com!audrey02.news.aol.com!not-for-mail
From: nulldogma@aol.com (Nulldogma)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 19 May 1997 13:16:36 GMT
Lines: 30
Message-ID: <19970519171601.NAA09973@ladder02.news.aol.com>
NNTP-Posting-Host: ladder02.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
References: <5lpe0j$sov@mercury.dur.ac.uk>
Xref: news.lth.se rec.arts.int-fiction:25404

James Cole wrote:

> Using a monkey island style of the ask/tell format you ask the
questions:
>      1) What can you tell me about this object?
>      2) I saw a man drop this, he was wearing a red sweater.  
>  Do you know who he could be?

To add to all the excellent points that Sam made, in this situation I know
exactly what I would do: type "1," undo, then "2," undo, then "3," etc.,
until I'd run through all the options. Obviously limited options
invariably inspire me to try them all in order, both because it's easy and
because I don't want to miss any possibilities. Whereas with ASK/TELL I
never know when I've exhausted the possibilities, adding to the illusion
of boundlessness.

I suppose this could work if each choice led to an ever-increasing tree of
conversation possibilities -- sort of like SUTWIN does with its keywords.
But this would be a very different kind of game (sort of an elaborate
Choose Your Own Adventure, or possibly something like Hidden Agenda, for
those who are familiar with it), and I imagine in any case it would be
incredibly tedious to write anything much longer than SUTWIN by this
method.

Neil

---------------------------------------------------------
Neil deMause                            neild@echonyc.com
                  http://www.echonyc.com/~wham/neild.html
---------------------------------------------------------


From nulldogma@aol.com Wed May 21 19:30:22 MET DST 1997
Article: 25421 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.apfel.de!newsfeed.nacamar.de!newsfeed.direct.ca!portc01.blue.aol.com!newstf02.news.aol.com!audrey02.news.aol.com!not-for-mail
From: nulldogma@aol.com (Nulldogma)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 19 May 1997 22:51:48 GMT
Lines: 27
Message-ID: <19970520025101.WAA00289@ladder02.news.aol.com>
NNTP-Posting-Host: ladder02.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
References: <3380C1C5.749A@acpub.duke.edu>
Xref: news.lth.se rec.arts.int-fiction:25421

Adam C. wrote:
> Neil deMause wrote:
> > To add to all the excellent points that Sam made, in this situation I
> > know exactly what I would do: type "1," undo, then "2," undo, then
> > "3," etc., until I'd run through all the options. Obviously limited
> > options invariably inspire me to try them all in order, both because
> > it's easy and because I don't want to miss any possibilities.
>
> Ah, but what if 1, 2 and 3 all lead to an enigmatic grunt, but at the
> end of the game, after you've had all kinds of adventures in the
> meantime, your choice turns out to be the factor that determines
> whether the NPC tries to kill you, make a pass at you, or both?

>KILL AUTHOR
Enraged at how a seemingly harmless action in the game winds up killing
you 200 turns later, you fly at the author in a rage, plunging your elvish
sword of great antiquity into his sadistic little heart.

***YOUR SCORE HAS JUST GONE DOWN BY 50 POINTS, BUT YOU DON'T CARE***

Neil

Neil
---------------------------------------------------------
Neil deMause                            neild@echonyc.com
                  http://www.echonyc.com/~wham/neild.html
---------------------------------------------------------


From sb6729@irix.bris.ac.uk Wed May 21 19:32:54 MET DST 1997
Article: 25395 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!rill.news.pipex.net!pipex!server1.netnews.ja.net!warwick!bris.ac.uk!irix.bris.ac.uk!sb6729
From: Samuel DAF Barlow <sb6729@irix.bris.ac.uk>
Subject: Re: ask rec.arts.int-fiction about NPC conversation
In-Reply-To: <5lpe0j$sov@mercury.dur.ac.uk>
X-Nntp-Posting-Host: irix.bris.ac.uk
Content-Type: TEXT/PLAIN; charset=US-ASCII
Message-ID: <Pine.SGI.3.95q.970519145621.17168A-100000@irix.bris.ac.uk>
Sender: usenet@fsa.bris.ac.uk (Usenet)
Organization: University of Bristol, England
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <33801214.6765452@news.netspace.net.au> <5lpe0j$sov@mercury.dur.ac.uk>
Mime-Version: 1.0
Date: Mon, 19 May 1997 14:19:41 GMT
Lines: 110
Xref: news.lth.se rec.arts.int-fiction:25395

On 19 May 1997, Big Mad Drongo wrote:

> James Cole (jrcole@ozemail.com.au) wrote:
> : Using a monkey island style of the ask/tell format you ask the questions:
> :       1) What can you tell me about this object?
> 
> SHOW OBJECT TO MECHANIC
OR ASK MECHANIC ABOUT OBJECT
> 
> :       2) I saw a man drop this, he was wearing a red sweater.  
> : 	 Do you know who he could be?
> 
> ASK MECHANIC ABOUT MAN IN RED SWEATER
OR TELL MECHANIC ABOUT MAN IN RED SWEATER 

GARAGE
You are in a garage. A greasy mechanic stands here, looking over a car.
>Mechanic, hello
"Hi. How can I help you, young man?"
>ask mechanic about object
He looks it over in his hands. "Hmmm. A variable-valve gasket. Where
d'ya get your hands on this?"
>tell mechanic about man in red sweater
~Oh...Bob! He's a shifty fella.~
>ask mechanic about bob
etc., etc.

I strongly disagree with the statements about the Monkey-Island style
conversations. I have never found these to work (and, yes, I have
"experienced" them). The humour that Mr. Cole refers to is the same type
of humour we see in sitcoms. It is very obvious in MI when we are about
to see a humourous response, just as in a sitcom when it is obvious a
joke is being set-up. In Ask/Tell I-F, the player can be suprised by
an answer. I find it strange that Adam Cadre supports the MI style as a
way of putting the player in character when his own game, I-0, is a
brilliant example of how to do this outside of MI menus; like when I
asked to "open boot" and was told that my character would call it a
trunk. The large number of humorous responses to my commands also help
tell the player who he/she is without hitting them over the head. 

The Ask/Tell system does have the problem of sustaining a conversation;
many games rely on the player firing lots of ASK's at an NPC to simulate
a conversation. This failed miserably in Corruption in the meal with
David's wife, where her responses were one-liners and the number of
topics was small. However if the NPC's response contains several other
threads to ASK then the flow&feel of the conversation becomes much more
life-like:

PIRATE PUB
You are standing at the bar of a sleezy drinking establishment. Next to
you, perched on a stool, is Pirate Pete.
>Pete,Hi
~Hello, Are yee new in these here parts?~
>Pete,yes
Pete smiles. ~At what be yee doing?~
>tell pete about treasure
Pete's smile widens. ~I used to be a treasure hunter myself but gave up
after my wife died. Now I'm just a fisherman.~
>ask Pete about himself
~I'm just Pete.~
>ask Pete about wife
~She was killed in an awful pirating adventure. Got her head chopped
clean off.~
>ask Pete about adventure
~Oh just some treasure off of Barnacle cove. Never found it.~
>ask Pete about fishing
~I run a tourist service. I take newbies like yerself out fur fishing
trips,~ he pauses, ~would yee like to go on a fishin' trip?~
>> etc. etc.

With simple ASK, TELL and single nouns we have manged to have a
reasonable natural conversation.

The problem with menus is that they run against the rest of the game,
they are an artifice which destroys the suspension-of-willing-disbelief.
If the whole game were menu-driven it would be OK. Whereas the ASk,TELL
convention is part of the parser which we use in the other parts of the
game. I-F's main strength is the fact that its input, the parser is
textual as is the output. Menu's take this away; the player no-longer
types his actions, but is read them. Now we are back to fiction, minus
the interactivity. 

One last thing, as regards MI, etc. from my "experience." Although
Cadre, et al, claim that MI menu's are interactive I have found that of
the, say, 4 options only 1 is neccessary to the game. As such the player
is allowed to click through the other options, always returning to the 4
initial choices until he picks the "right" one. So, the only thing he is
choosing is the order in which to say his funny lines. 

Sorry if I have rambled or been incoherent, but this posting is an
attempt to put of much-needed exam revision.

>s
You leave the computer room and head to the library..
>get books
You take the mountain of Physics and Maths textbooks.
>read books
Zzzzzz.

Sam.
                    ____________________________________
        # \ # #### /...       The One and Only       ...\ #### # / #
        # / # #### \... S A M U E L -x- B A R L O W  .../ #### # \ #
        # \ # ##### |..                              ..| ##### # / #
        # / # #### /..       sb6729@bris.ac.uk        ..\ #### # \ #
        # \ # ### /... http://irix.bris.ac.uk/~sb6729 ...\ ### # / #
        # / # ### \______________________________________/ ### # \ #





From adamc@acpub.duke.edu Wed May 21 19:33:18 MET DST 1997
Article: 25402 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!europa.clark.net!newsfeed.internetmci.com!portal.gmu.edu!solaris.cc.vt.edu!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Mon, 19 May 1997 18:16:43 -0400
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 57
Message-ID: <3380D14B.7BE3@acpub.duke.edu>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <33801214.6765452@news.netspace.net.au> <5lpe0j$sov@mercury.dur.ac.uk> <Pine.SGI.3.95q.970519145621.17168A-100000@irix.bris.ac.uk>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25402

Samuel DAF Barlow wrote:
> I strongly disagree with the statements about the Monkey-Island style
> conversations. I have never found these to work (and, yes, I have
> "experienced" them). The humour that Mr. Cole refers to is the same
> type of humour we see in sitcoms. It is very obvious in MI when we are
> about to see a humourous response, just as in a sitcom when it is
> obvious a joke is being set-up.

This is often true, but I don't think it's necessarily that damning a
criticism -- after all, there =are= funny sitcoms.

> I find it strange that Adam Cadre supports the MI style as a
> way of putting the player in character when his own game, I-0, is a
> brilliant example of how to do this outside of MI menus; like when I
> asked to "open boot" and was told that my character would call it a
> trunk. The large number of humorous responses to my commands also help
> tell the player who he/she is without hitting them over the head.

Thanks for the praise, though you may have hit upon one of my
motivations for trying the menus -- having done one menu-free game,
I want to try other things.  I'm not entirely pleased with the ask/tell
interface, and apparently neither are quite a few others; I tried an
alternative type of conversation in I-0 (with Larry in the truck) but
wasn't completely satisfied with it.  I plan to try a bunch of different
approaches till I find the one I like the best.  This just happens to
be the one I'm currently working on. 

> The problem with menus is that they run against the rest of the game,
> they are an artifice which destroys the suspension-of-willing-
> disbelief.

I'm not convinced this is necessarily true.  It's certainly a danger,
and if I can't find a way to integrate them well I'll jettison them.
Never know till you try, though.

> One last thing, as regards MI, etc. from my "experience." Although
> Cadre, et al, claim that MI menu's are interactive I have found that
> of the, say, 4 options only 1 is neccessary to the game. As such the
> player is allowed to click through the other options, always returning
> to the 4 initial choices until he picks the "right" one. So, the only
> thing he is choosing is the order in which to say his funny lines.

Two things.  First, this is often true, and I suspect is motivated
by the authors' fear that their games are only going to be played
once, and that they'd better make sure that none of their dazzling wit
goes to waste.  But it doesn't have to be that way.  I certainly don't
plan to do it that way, at least.

Second -- please, call me Adam.  Even AdamC is okay, if you want to
distinguish me from the other 150 Adams that frequent this newsgroup.
But when people call me by just my last name I can't help but feel that
they're really mad at me and I'm in big, big trouble.

  -----
 Adam Cadre, Durham, NC
 obscure Captain America villain
 http://www.duke.edu/~adamc


From A.G.Jackson@durham.ac.uk Wed May 21 19:33:34 MET DST 1997
Article: 25417 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newscore.univie.ac.at!newsfeed.Austria.EU.net!EU.net!howland.erols.net!newsxfer3.itd.umich.edu!azure.xara.net!xara.net!server6.netnews.ja.net!str-ccsun!strath-cs!nntphost.dur.ac.uk!housman.dur.ac.uk!d3099u
From: Big Mad Drongo <A.G.Jackson@durham.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 20 May 1997 17:58:55 GMT
Organization: University of Durham, Durham, UK.
Lines: 17
Message-ID: <5lsoov$oq6@mercury.dur.ac.uk>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <33801214.6765452@news.netspace.net.au> <5lpe0j$sov@mercury.dur.ac.uk> <Pine.SGI.3.95q.970519145621.17168A-100000@irix.bris.ac.uk>
NNTP-Posting-Host: housman.dur.ac.uk
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25417

Samuel DAF Barlow (sb6729@irix.bris.ac.uk) wrote:
: The problem with menus is that they run against the rest of the game,
: they are an artifice which destroys the suspension-of-willing-disbelief.
: If the whole game were menu-driven it would be OK.

Indeed - I think you've hit the nail right on the head there. The
menu-driven system is fine (and even preferable) in games like Monkey
Island because it fits in with the point-and-click interface of the game
as a whole. But when we're talking about interactive fiction such as games
produced in Inform then it really does stand out like a sore thumb. Any
game that offers me a menu as part of the main game had better have a good
reason for doing so, or I'll just stop playing it - it just doesn't feel
right in context. The only place I've found menus to work in text
adventures is for the help system provided by Infocom (and similar) games.

Adrian



From robbj95@octarine.cc.adfa.oz.au Wed May 21 19:33:59 MET DST 1997
Article: 25435 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!news-zh.switch.ch!news-ge.switch.ch!news-fra1.dfn.de!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!harbinger.cc.monash.edu.au!newshost.carno.net.au!euryale.cc.adfa.oz.au!octarine!robbj95
From: Barbara Robson <robbj95@octarine.cc.adfa.oz.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 20 May 97 07:26:32 GMT
Organization: ADFA News Service
Lines: 52
Message-ID: <robbj95.864113192@octarine>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <33801214.6765452@news.netspace.net.au>
NNTP-Posting-Host: 131.236.1.1
X-No-Archive: yes
Originator: robbj95@octarine
Xref: news.lth.se rec.arts.int-fiction:25435

jrcole@ozemail.com.au (James Cole) writes:

|Your considering this in the wrong way.  Basically, the idea of the extra
|things to ask about particular object are just there to give you a richer
|level of interaction.  

|Consider another example: from a distance you see a man surreptitiously
|drop something.  All you can distinguish about him is that he's wearing a
|red sweater.  You go over and pick the object up, noting that it's some
|sort of engine part.  There is a mechanic in the town and you decide to go
|and ask him about the part.  

|If you were using the ask/tell style, what would asking the mechanic about
|the object mean?  Most likely, it'll mean asking him to identify the part
|-- but I also want to ask him about the shady character!  There is no way
|you could do this with the ask/tell style.  (and yes, you probably could
|find some sort of awkward workaround for this particular situation, but not
|for the general case.)

Actually, it's not at all difficult to do this for the general case.
Simply set the possible conversation topics up as objects and give them
names that reflect what is likely to be asked about.  Then you could
have, for example:

InfoObj Part "purpose of the engine part"
  with name "part" "object" "purpose" "of" "the" "engine",
  description "~Ah yes, it's a mark I technobabble.~";

InfoObj Crook "shady character who dropped the engine part",
  with name "part" "man" "red" "wearing" "sweater" "engine" "object" 
    "shady" "character" "who" "dropped" "the",
  description "The mechanic looks a little afraid.  ~Nope.  Don't
    know anything about him.  Never saw him.~";

If the player types "Ask the mechanic about the engine part", the
parser will then seek clarification ("Which do you mean, the purpose
of the engine part, or the shady character who dropped the engine 
part?"), and the player can respond, just as in the case of a menu-
based system.  Alternatively, they can be more explicit in the original
question ("Ask him about the man who dropped the part") and it will go
directly to the relevant response, without needing extra coding or 
forcing the player to fiddle with menus.  This will work for the general
case.  

Menus-vs-simplified natural language is a matter of preference.  
Personally, I feel much less restrained when playing using the ask/tell 
about system.  I have played Monkey Island and enjoyed it, but I
just wasn't able to forget that the menu was sitting between me and
the NPCs as I am able to forget about the parser in IF.

Barbara
 


From gdj1@oak21.doc.ic.ac.uk Thu May 22 10:21:01 MET DST 1997
Article: 25434 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!news-zh.switch.ch!news-ge.switch.ch!news-fra1.dfn.de!news-ber1.dfn.de!fu-berlin.de!newsfeed.nacamar.de!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!agate!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!penguin.doc.ic.ac.uk!not-for-mail
From: Gareth Jones <gdj1@oak21.doc.ic.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 20 May 1997 09:32:19 +0100
Organization: Dept. of Computing, Imperial College, University of London, UK
Lines: 122
Message-ID: <beyb9ah7cc.fsf@oak21.doc.ic.ac.uk>
References: <5lq2v8$mkp$2@netty.york.ac.uk>
NNTP-Posting-Host: oak21.doc.ic.ac.uk
X-Newsreader: Gnus v5.3/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:25434

rgc2@york.ac.uk (Richard G Clegg) writes:

[snip]
> 
>   Hmm... the problem is Neil, I don't know about you, but I hardly ever
> actually ASK/TELL characters in IF unless I've had a really strong hint
> that I need to.  Conversation in IF is, generally, pretty limited simply
> because the author can only cover such a small portion of the possible
> choices.  That's why, I find, a game like Monkey Island has far more
> complete and satisfying dialogue than even the top IF games simply
> because, unless you really persevere, you can't find much to say to IF
> characters that they can sensibly respond to.

True, but if IF is written well, then I tend not to want to break
the flow of the story so I don't ask about irrelevant things.  Partly
this is a subconscious acceptance of the limitations but also why
should I want to ask a character about something irrelevant?

As an aside, would it improve IF if the NPCs could discuss events
outside the game - either in the real world, or background events in
the game?  One reason to constrain an NPC's responses and knowledge is
to prevent plot developments that the author doesn't want.  Suppose I
wrote a game about 'The Big Sleep'.  No NPC should know about the
chauffeur's murderer or the player might try to solve this murder when
I want them to follow the original plot.  Would Christminster be a
better game if you could discuss the Moorish conquest of Spain with Edward?
 
>   Can anyone post an extract from an IF game that's anything even like a
> conversation which didn't take them ages poking around in the game to
> find which words were responded to?

I found Dr. Perelman and Jill in AMFV to be quite good.  The only
problem was the Jill couldn't talk about the plan or the BCF but other
than that both characters gave me the impression that the
conversations were unbounded.  I don't think I would have felt this if
there had been a menu:
1) Ask Doctor about plan
2) Ask Doctor about Ryder
3) Ask Doctor about himself

>3
........

1) Ask Doctor about plan
2) Ask Doctor about Ryder
3) Ask Doctor about Leah
4) Ask Doctor about Esther

(I think I've got some of the names wrong, but you get the idea.)

I find the main problem with NPC interaction is that TELL X ABOUT Y
doesn't work very often.  I suppose that for this to work in the
general case the NPCs need to be able to learn, eg.

> Examine car

It is a blue Ford.

> S

You see Tom

> Ask Tom about blue car

Tom says "I havn't seen any cars."

> Tell Tom about blue car

Tom listens

> Ask Tom about blue car

Tom says "It is a blue Ford, according to you."

> Tell Tom that blue car is red
???????

Apart from the last command the general case of the conversation could
be programmed quite easily but other than by making a special case how
do you get Tom to act on this knowledge?  Allowing the player to make
unconstrained statements poses a bigger problem (IMO) than allowing
her to ask unbounded questions.

> Ask Tom about Fermat's last theorum
Tom says "I don't know anything about that."

is fine.  But

> Tell Tom about murderer behind him
Tom ignores you
The murderer kills Tom

doesn't work as well (unless you've cried wolf previously).  Tell X
about Y, or tell X that Y is Z are very difficult to deal with because
even after the NLP stage and the knowledge representation problem
(neither of which are insurmountable or trivial) the problem is then
to get the character to act on his/her/its/their knowledge.  Other
than constraining the plot and using special cases, I don't think that
this can be solved, at least not yet.
 
>   IMHO dialogue is one of the places where Lucas-arts style graphics
> adventures win hands down against IF.  In IF it's much more of a
> struggle simply because of the zillions of things you could ask a
> character, even the most dilligent programmer will only have covered a
> few hundred and most of them scantily.

I prefer to be able to choose my own questions, even if I do get "I
don't know anything about that." a lot of the time.  I suppose it just
comes down to personal taste.
 
>   This is not to say that I prefer point'n'click - just that I think it
> really does win out in this respect.
> 
> --
> Richard G. Clegg     Only the mind is waving
> Dept. of Mathematics (Network Control group) Uni. of York.
> email: richard@manor.york.ac.uk   
> www: http://manor.york.ac.uk/top.html


-- 
Gareth Jones (gdj1@doc.ic.ac.uk)


From mkkuhner@phylo.genetics.washington.edu Thu May 22 14:03:38 MET DST 1997
Article: 25459 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!howland.erols.net!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 20 May 1997 13:32:34 GMT
Organization: University of Washington, Seattle
Lines: 34
Message-ID: <5ls95i$hg9@nntp5.u.washington.edu>
References: <5lpe0j$sov@mercury.dur.ac.uk> <19970519171601.NAA09973@ladder02.news.aol.com> <3380C1C5.749A@acpub.duke.edu>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:25459

adamc@acpub.duke.edu writes:

>Neil deMause wrote:
>> To add to all the excellent points that Sam made, in this situation I
>> know exactly what I would do: type "1," undo, then "2," undo, then
>> "3," etc., until I'd run through all the options. Obviously limited
>> options invariably inspire me to try them all in order, both because
>> it's easy and because I don't want to miss any possibilities.

>Ah, but what if 1, 2 and 3 all lead to an enigmatic grunt, but at the
>end of the game, after you've had all kinds of adventures in the
>meantime, your choice turns out to be the factor that determines
>whether the NPC tries to kill you, make a pass at you, or both?

Without some immediate feedback, I'm pretty darned unlikely to connect
the dialog early in the game with the outcome at the end, unless I
deliberately go back and try all the other options.  After all, in any
reasonably rich game other actions of mine will have impacted the NPC
in some way, if only indirectly.  Since I am not a big replayer, I
may never even *realize* that the NPC might have done different things,
unless his dialog at the end makes that clear.  "You insulted me, scurvy
dog!  Walk the plank!"

One problem I personally have had with games that try to use a real
model of NPC personality (so that, for example, the more you compliment
someone the better he likes you) is that the most successful strategy
is to *think* of the NPCs that way, as bundles of compliment-counters
and aggression-counters and so forth.  The best game implementing this
idea I've ever seen is _Trust and Betrayal_, which had neat NPC
conversations (via a very limited iconic language).  But even that one
had stretches where you didn't feel like you were talking to someone,
just trying to pump up one counter or another.

Mary Kuhner mkkuhner@genetics.washington.edu


From cardinalt@earthlink.net Thu May 22 18:06:20 MET DST 1997
Article: 25465 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!uab.ericsson.se!news.algonet.se!news-xfer.cybernet.dk!cam-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!news.bbnplanet.com!feeder.chicago.cic.net!chi-news.cic.net!nntp.earthlink.net!usenet
From: cardinalt@earthlink.net (Cardinal Teulbachs)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 02:19:53 GMT
Organization: EarthLink Network, Inc.
Lines: 76
Message-ID: <5m0akc$c2@ecuador.earthlink.net>
References: <3379b653.10392540@news.netspace.net.au>
NNTP-Posting-Host: max1-sc-ca-08.earthlink.net
X-Newsreader: Forte Free Agent 1.0.82
Xref: news.lth.se rec.arts.int-fiction:25465

(I can't post news myself atm, so my lacke... good friend Cardinal T
is doing it for me.)

Whew!  This conversation thread is a bit popular, isn't it?  Well,
I've only been skimming through the contributions of the last few
days, so someone else may have already suggested what I suggest below.

I was going to implement a "Monkey Island"-style menu system of
conversation in a game I've not been working on.  However, I
eventually became less than satisfied with the concept, and thought
about how it might be improved.  My idea is to merge the menu system
with the "ask x about y" system.  So, there is only one conversational
verb, "talk." You can either "talk to npc" or you can "talk to npc
about <subject>." If you "talk to npc" a list of topics pops up, with
certain keywords highlighted in each topic.  You can then "talk to npc
about <subject>," where <subject> is one of these keywords (or a
reasonable synonym, of course).  For example:
  >talk to vampire
  What do you want to say to the vampire?
    "So... er... you like *blood* then?"
    "I hear you have a thing about *virgins*."
    "Ever heard of *Max Schreck*, bub?"
    "Hey, nice *fangs*! Who's your *dentist*?"
  
  >talk to vampire about blood
  "So... er... you like blood then?" you venture.
  
  "Why yes," he says, "And I believe I know where I might get some."
He takes a step closer.
  
  >talk to vampire about grace kelly [or anything not in the list]
  You strike up a conversation with the vampire. He makes small talk
  politely enough, but he's taken another step towards you.
Unsettling.
  
  >talk to vampire about fangs
  "Hey, nice fangs! Who's your dentist?" you say nervously.
  
  "Yes," he says, opening his mouth and massaging the back of one
sharp fang with a long, pointed tongue, "They *are* rather impressive,
  aren't they?" You notice he's evaded your question about his
dentist.
  
  >talk to vampire
  What do you want to say to the vampire?
    "So... er... you like *blood* then?"
    "I hear you have a thing about *virgins*."
    "Ever heard of *Max Schreck*, bub?"
    "But seriously, who is your *dentist*?"
  
  >talk to vampire about his dentist
  "But seriously, who is your dentist?" you ask.
  
  "That information is private!" bellows the vampire, as he launches
  himself across the room, and buries those fine fangs into your neck.
  
  ** You have died rather horribly **

This system combines the two traditional systems, but can optionally
be used as either.  To use it in the same way as you would use the
"ask x about y" system, just don't "talk to npc" without a subject (or
a game could have a "talk menu off" command which would turn the lists
of topics off).  And as Cardinal T points out, the "talk to npc"
command also acts as a mild hint system.  Obviously "talk to npc"
would be a system-meta-x command, while "talk to npc about <subject>"
would be a normal one.

Jools
-- 
"For small erections may be finished by their first architects; grand
ones, true ones, ever leave the copestone to posterity.  God keep me
>from ever completing anything." -- Herman Melville, "Moby Dick"






From daly@crestone.uucp Thu May 22 21:56:06 MET DST 1997
Article: 25467 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!nntp.uio.no!news.apfel.de!news.maxwell.syr.edu!feeder.chicago.cic.net!news.altair.com!thetimes.pixel.kodak.com!news.kodak.com!newsserver.rdcs.Kodak.COM!crestone!daly
From: daly@crestone.uucp (Matthew Daly; x67754)
Newsgroups: rec.arts.int-fiction
Subject: Re: New Posssible Magic System
Date: 21 May 1997 15:30:40 GMT
Organization: Eastman Kodak Company, Rochester
Lines: 33
Message-ID: <5lv4f0$rlb$1@kodak.rdcs.Kodak.COM>
References: <19970520200101.QAA02375@ladder02.news.aol.com>
Reply-To: daly@crestone.uucp (Matthew Daly; x67754)
NNTP-Posting-Host: 129.126.74.4
Xref: news.lth.se rec.arts.int-fiction:25467

In article <19970520200101.QAA02375@ladder02.news.aol.com> lfrench106@aol.com (LFrench106) writes:
>I grow weary of the Enchanter magic system, so I'm going to suggest a new
>system of magic in IF. Namely, stones. At the begining of the game you get
>a belt buckle with one slot and one stone (that corrisponds to one element
>- for our example, lets say Air). You put the stone in the buckle to
>"create" a spell. You can cast a spell with this combination; eventually
>you would get more stones and a belt buckle with more then one slot.
>Different combinations would lead to different spells. For example, earth
>and water would lead to a Mud spell. (You could find more belt buckles
>with more slots).
>
>(I'll admit to approapriating this idea from somewhere else, but I can't
>remember where!)

Sounds a lot like Ultima Underworld's scheme.  There, for instance, the
spell for fireball was called "Big Fire Hurt" and required that you find
the Big rune, the Fire rune, and the Hurt rune.  Plus, you needed
to be a high enough level spellcaster that you could cast that spell
(perhaps analogous to your having a belt with enough slots).

The neat thing about that system is that you don't have to describe
all the available spells, just enough that people know what effects
the different runes have (since they weren't actually called the
"Fire" ruin in the game).  For instance, if late in the game you came
across a "Very" rune, the player character ought to have enough sense
to experiment with the Very Big Fire Hurt spell.

The challenge from an author's perspective is coming up with a set
of "words" to chain together, and to have as many different combinations
of words form actual spells as possible, although some might be
humorous or dangerous.

-Matthew


From daryl@cogentex.com Fri May 23 13:48:46 MET DST 1997
Article: 25471 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!pumpkin.pangea.ca!news.mira.net.au!news.netspace.net.au!news.mel.connect.com.au!munnari.OZ.AU!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsfeeds.sol.net!feed1.news.erols.com!news.maxwell.syr.edu!news.emi.com!usenet
From: Daryl McCullough <daryl@cogentex.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 11:06:09 -0400
Organization: CoGenTex
Lines: 40
Message-ID: <338460E1.7600@cogentex.com>
References: <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1kd7$76p@nntp5.u.washington.edu>
NNTP-Posting-Host: mali.cogentex.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (WinNT; U)
Xref: news.lth.se rec.arts.int-fiction:25471

Mary K. Kuhner wrote:

> The ask/tell system puts a low value on "sounding like a real
> converation" compared to the menu system; the things the speaker says
> are *very* flat and dull.  You can jazz them up a little:
> 
> >ASK SALESMAN ABOUT SPOT
> 
> "How about that spot, huh?  You trying to hide something from me?"
> you say accusingly.
> 
> but this kind of hybrid risks inheriting the problems of the menu
> system without its virtues, since you're not allowing the player
> any choice about the flavor-text at all.  (The player may have had
> no idea that just asking about the spot would produce such a rude,
> accusatory statement.)

Here's an idea for a gimmick that would make this kind of unintended
outburst a part of the game:

The player is travelling in a foreign land, Foobia, in which
he/she doesn't speak the language. But the player picks up
two objects that help him/her to communicate with the populace:
One is a telepathic device that allows him/her to understand
the foreign language in a direct sense, but does *not* allow
the player to *speak* the language. The second is a very *bad*
translation device (or perhaps a partially-bilingual parrot).

Then miscommunications like the one you give above would become
part of the story (to be blamed on the stupid translation device).
The player would still be frustrated, but he/she would be frustrated
*in* *character* rather than frustrated out-of-character. Maybe
that's an improvement.

Just a stupid idea. Not a general approach, but a gimmick that might
work for one (humorous) game.

Daryl McCullough
CoGenTex, Inc.
Ithaca, NY


From ldaly@bu.edu Fri May 23 13:50:18 MET DST 1997
Article: 25486 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!uab.ericsson.se!news.algonet.se!news-xfer.cybernet.dk!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!howland.erols.net!newshub2.home.com!newshub1.home.com!news.home.com!nick.arc.nasa.gov!purdue!news.bu.edu!cgl!ldaly
From: ldaly@bu.edu (Liza Daly)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fict
Date: 22 May 1997 14:25:15 GMT
Organization: Your Mom
Lines: 62
Distribution: world
Message-ID: <5m1l0b$iqe@news.bu.edu>
References: <5lpe0j$sov@mercury.dur.ac.uk> <66.9168.1727@tabb.com>
NNTP-Posting-Host: cgl.bu.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25486

Joe Mason (joe.mason@tabb.com) wrote:

: BM>ASK MECHANIC ABOUT MAN IN RED SWEATER

: "Oh you mean old Dan. You should maybe give that back to him - he hates 
: to lose stuff."

:   1) Do you know where I can find him?
:   2) Hates to lose stuff? Why?
:   3) What do you think he'll do if I don't give this back to him?
:   4) Hey, is this the same Dan who owes $100 to the bartender at Jake's?
:   5) Is Dan a member of this mysterious cult I've been hearing about?
:   6) Are YOU a member of this mysterious cult I've been hearing about?

: Implement all these as keyword style questions.

If I were going to do a dialogue-rich game (which I'm not, for the
moment), I'd simply hack the library to include more types of
questions, and put this information in the "First-time players should
type ABOUT" message. 

These don't perfectly correspond, but they greatly expand the type of
questions available.

	WHERE IS [name]?
	WHY?
	HOW IS [name] RELATED TO [object]? 

Or you can implement a Bureaucracy-style conversation subroutine,
where the game behaves more like TSUTW. (I included other possible
responses in parentheses.)

  "Oh you mean old Dan. You should maybe give that back to him - he
  hates to lose stuff."

>> STUFF? (or DAN)

  "He's always losing things, ever since he joined that cult."

>> CULT? (or JOINED, or WHEN)

  "Yeah, the Order of NPC Dialogians. They've got lots of members."

>> YOU? (or MEMBERS, or ORDER)
 
  He gulps nervously.  "No, I'm not a member. Now, get out of here!"

> 

In the trade-off between natural sentences and what Andrew referred to
as the "feeling of boundlessness," I much prefer the boundlessness.
That's just my opinion as a player, of course.

--Liza

--
gecko@retina.net                 "By the way, I've visited Mr. Joffe's site,
. . . . . . . .                   and find it quite garish and unappealing."
Iguanas Mailing List:            - The House of Erotic Massage (May edition)
http://iml.retina.net/                      http://fovea.retina.net/~gecko/




From rglasser@penning.lanl.gov Fri May 23 13:53:04 MET DST 1997
Article: 25488 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!uab.ericsson.se!news.algonet.se!news.maxwell.syr.edu!ix.netcom.com!news
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 07:49:19 -0700
Organization: UCSD
Lines: 47
Message-ID: <33845CEF.1725@penning.lanl.gov>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <5lu4rf$s5v$1@goanna.cs.rmit.edu.au>
NNTP-Posting-Host: sdx-ca11-08.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Thu May 22  9:51:38 AM CDT 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25488

Paul Francis Gilbert wrote:
> 
> Another good example was Simon the Sorcerer. One of favorate moments in the
> game: Wizards: "What makes you think we're wizards". One of simons responses:
> "Because when I move the mouse cursor on you it says wizards."
> 
> Well, that and Doctor von Jones trying to find the missing link between man
> and vegetable. Simon response: "You mean Dan Quale?"
> 
> >I think there's definitely room in IF for this type of game.  I'd love
> >to play a text-based one.
> 

	And let's not forget some of the gems in Legend's "Deathgate."

	Haplo (you): Who are you?
	Zifnab: I already told you, I'm James Bond!
	Haplo: No you're not, those kids told me you were called Zifnab.  
Although I'm not sure what kind of a name Zifnab is.
	Zifnab: Oh yeah?  Well what kind of a name is Haplo?
	Haplo: Hey!  How did you know my name was Haplo?
	Zifnab: Your name is Haplo?  Pleased to meet you, I'm Zifnab!
	Haplo: You didn't answer my question, how did you know my name was 
Haplo?
	Zifnab: Well, you just told me your name was Haplo when you introduced 
yourself!  You'd better start paying attention to the conversation, my boy, if 
you want to learn anything.

	Balthazar: I've never seen you around before, where did you say you 
were from?
	Haplo: Oh, I'm from, you know... Kairn Klosteria.
	Balthazar: Klosteria?  Hmmm.  Strange, that's not on any of my maps.
	Haplo: Gee, did I say Kairn Klosteria?  I meant Flort... wrmpth... 
sinj -- er, ah -- thim.  Surely THAT'S on your maps?
	Balthazar (pregnant pause): Oh yes, of course.

	(Note to purists: no, those WEREN'T the only conversation options 
available, there were plenty of other branches along the way.  Those were just 
some of my favorites.)
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From joe.mason@tabb.com Fri May 23 17:45:37 MET DST 1997
Article: 25491 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!uab.ericsson.se!news.algonet.se!news.maxwell.syr.edu!howland.erols.net!torn!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fict
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.9159.1727@tabb.com>
References: <337B30AC.7797CF1C@alcyone.com>
Date: Tue, 20 May 1997 17:54:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 80
Xref: news.lth.se rec.arts.int-fiction:25491

"Re: ask rec.arts.int-fict", declared Erik Max from the Vogon ship:

EM>The alternative seems much cleaner to me -- where a certain
EM>well-defined set of conversation verbs are used to communicate with
EM>the other characters in well-defined ways.  Basically the words are
EM>more like keywords, with TELL MOM ABOUT FIRE being more concise then
EM>entering some two-way dialog:

EM>    > TELL MOM ABOUT FIRE
EM>    "What the!  Who did it?  Who did it?" she yipes, while running
EM>    around  looking for towels, as if that will help.

EM>    > SAY [or ANSWER] JOHNNY
EM>    "Oh, that little boy is going to get it! . . ."

EM>There can be a host of these verbs, such as ASK PRINCIPAL ABOUT
EM>PADDLE, SHOW GUN TO TROLL, SAY HALLELUJAH, ANSWER NO, etc.

EM>These seem to make it much more a game than just picking the right
EM>multiple choice answer -- or, in the case where a new answer pops up,
EM>pickign the only obvious answer.

This works for simple things like your example, but if you actually want 
two-way conversation it gets harder.  For example, implement this using 
keywords:


Urabi stares at you. Flames burn in his eyes. His voice is a narrow 
hiss.

"You have heard the voice. I can see it in your eyes! She speaks to you, 
too. What has she told you?"

Your response:

  (1) "What voice? I don't know what you're talking about!"
  (2) "She didn't tell me anything."
  (3) "She told me not to trust you."
  (4) "The voice speaks to you? I thought I was the only one!"
  (5) "She told me I could take you by surprise - she betrayed me!"
  (6) Say nothing.

> 1

Urabi draws back his hand and strikes you across the face. The blow is 
only slightly softened by the bandage on his hand. "Answer me!"

Your response:

  (1) "I'm trying! I don't know anything!"
  (2) "She didn't tell me anything."
  (3) "She told me not to trust you."
  (4) "The voice speaks to you? I thought I was the only one!"
  (5) "She told me I could take you by surprise - she betrayed me!"
  (6) Say nothing.

> 5

Urabi smiles, and some of the tension drains from his face. "I was 
worried," he whispers. "She promised me that I would be the victor. When 
I realized she spoke to you as well, I thought that I was the one who 
was betrayed." He chuckles. "Soon... Soon I will be with her."

He strides to the door and leaves. For the first time, he has neglected 
to check the tightness of your bonds.


As you can see, it's NOT obvious what to pick.  You can eventually find 
the right one by trying all of them in turn, of course, but in a game of 
this type the storyline would branch according to which you pick, so if 
you find something that seems to work you still wouldn't know if its the 
best.

The problem with doing this using keywords is finding keywords for 
complex topics.  Even if you can find a way to do it, the player may not 
think of the same keywords as you and get a guess-the-word problem.

Joe

 CMPQwk 1.42 9550 When in doubt, duck. - Malcolm Forbes


From icallaci@csupomona.edu Sun May 25 13:52:55 MET DST 1997
Article: 25531 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!paladin.american.edu!zombie.ncsc.mil!news.gmi.edu!msunews!agate!spool.mu.edu!uwm.edu!chi-news.cic.net!feeder.chicago.cic.net!usc!newshub.csu.net!news.csupomona.edu!news
From: Irene Callaci <icallaci@csupomona.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 10:25:28 -0700
Organization: Cal Poly University
Lines: 36
Message-ID: <33848100.7E30@csupomona.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu>
NNTP-Posting-Host: 134.71.3.152
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25531

OK, let me try this one more time:

With the Monkey Island multiple-choice system, the computer
tells ME what I can say or ask. This is not fun, IMHO.

With the type-it-in-yourself system, I tell the computer
what I want to say. Now I am the one who must be creative,
who must think.

Even though the NPC might not understand what I am trying
to say, it *feels* like I am trying to talk to someone on
his or her own level. If the NPC doesn't understand, I can
rephrase it, just as I would in real life.

The multiple-choice method *feels* like I'm being censored
or guided away from certain areas of inquiry. As soon as I
want to say or ask something that has not been pre-
programmed, I am thwarted. I no longer feel that I have
the slightest chance of communicating with someone who is
also trying to communicate with me. Rather, I feel as if
someone (the programmer? the NPC? the government?) has
decided that certain areas of conversation are taboo,
and that I will NOT be allowed even to ask. It's almost
like a press conference where the questions and answers
are already scripted. Even though it looks like a free
and open exchange is taking place, it's NOT.

There. This thread is a perfectly good example of what
I'm talking about. If we were all using the Monkey
Island system to discuss this, we wouldn't be allowed
to say anything other than what the original author
wanted us to say. No matter how open-minded someone
is, I don't want them putting words in my mouth.
Period. Even if it is "just a game."

irene


From kfischer@x_greenhouse.llnl.gov Sun May 25 13:55:39 MET DST 1997
Article: 25499 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.uoregon.edu!tezcat!cam-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!vixen.cso.uiuc.edu!uwm.edu!lll-winken.llnl.gov!not-for-mail
From: Kathleen Fischer <kfischer@x_greenhouse.llnl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 16:59:08 -0700
Organization: Lawrence Livermore National Laboratory
Lines: 36
Message-ID: <3384DDCC.167E@x_greenhouse.llnl.gov>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu> <3384D153.43CF@acpub.duke.edu>
NNTP-Posting-Host: greenhouse.llnl.gov
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (X11; I; IRIX 5.3 IP22)
Xref: news.lth.se rec.arts.int-fiction:25499

Adam Cadre wrote:
> There's a bit in the ZORK I hintfile that goes something like this.
> "Q: It says I need a machete to get through a certain part of the
> forest.  Where do I get a machete?  A: You can't.  For the same reason,
> you can't expect to walk to the airport and take a plane to London in
> this game.  There have to be limits."  Is ZORK I "censoring" you from
> flying to London?  You're certainly being guided away from it.

Yes, but you are still left with a glimmer of hope that a machete
*might* turn up and you can then go into the forest.  With a menu system
you know all the possibilities right at the start. It's like hanging a
sign on the forest saying "Decoration only"... kinda takes the fun out
out if it (for me, at least).  Of course, I also hate the "That is only
scenery." message for the very same reason.

> Seriously, though, I don't see much virtue in the "freedom" to type
> things the parser has no chance of understanding...

I suppose it depends on whether you are playing for the journey or the
destination.  I enjoy the journey - taking time to look at the scenery
and type weird things in just to see what happens. It doesn't really
matter to me if I make it to the end, so long as the journey is
pleasant. By giving me an up front listing of what my options are, I
think it detracts from the journey, no matter how cleverly worded they
may be. Would XYZZY be as "famous" if it was just another phrase in a
menu?

Just my $0.02(US)

Kathleen

-- 
*******************************************************************
*  Kathleen M. Fischer                                            *
*  kfischer@x_greenhouse.llnl.gov  (Remove 'x_' before replying)  *
** "Don't stop to stomp ants while the elephants are stampeding" **


From icallaci@csupomona.edu Sun May 25 13:56:06 MET DST 1997
Article: 25529 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!hunter.premier.net!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!in3.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: Irene Callaci <icallaci@csupomona.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 24 May 1997 08:59:45 -0700
Organization: Cal Poly Pomona
Lines: 33
Message-ID: <33871071.55EA@csupomona.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu> <3384D153.43CF@acpub.duke.edu>
Reply-To: icallaci@csupomona.edu
NNTP-Posting-Host: max2-ot-ca-12.earthlink.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25529

That's absolutely true (that some people prefer close identification
with the PC, while others prefer to think of the PC as more of a
puppet). Actually, it's not the PC I identify with; it's the 
protagonist of the game. It's one of the reasons I shy away from
RPG-style games. I just don't enjoy controlling an external
character. I want to *become* the character, and even though
the ask/tell style of NPC interaction is limited, it feels more
like "free will" than the multiple-choice style of Monkey Island.

irene

Adam Cadre wrote:
> 
> Elsewhere on this thread, Mary Kuhner posted a great article in which
> she wrote: "In my experience, there are several different virtues which
> a game can have.  Often they are partly mutually incompatible, and one
> must choose which to prioritize. [...] If you value sounding like a real
> conversation, you'll dislike ask/tell. On the other hand, the menu
> system puts a low value on the illusion of free choices."  Your post
> highlights yet another point of difference: some people prefer close
> identification with the PC, while others (and I'm one of these others)
> prefer to think of the PC as more of a puppet that I'm maneuvering
> through an ultimately artificial world.  (There's nothing intrinsically
> wrong with artifice, after all.)  As such, I don't mind menu
> conversation in that I have no problem with the notion that while =I=
> may have lots of things I want to say, my =character= may only be able
> to come up with four or five things to say at any given time.
> Especially if they're as funny as the lines in Monkey Island or
> Star Control 2.
> 
>   -----
>  Adam Cadre, Durham, NC
>  http://www.duke.edu/~adamc


From adamc@acpub.duke.edu Thu May 29 12:37:16 MET DST 1997
Article: 25543 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!jupiter.nic.dtag.de!news-peer.gsl.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!205.160.231.5!fozzie.mercury.net!zombie.ncsc.mil!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Thu, 22 May 1997 19:05:55 -0400
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 89
Message-ID: <3384D153.43CF@acpub.duke.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25543

Irene Callaci wrote:
> With the Monkey Island multiple-choice system, the computer
> tells ME what I can say or ask.

Not exactly.  It tells you what the PLAYER CHARACTER can say or ask.
YOU are free to say or ask anything you want, to anyone within earshot.

> With the type-it-in-yourself system, I tell the computer what I want
> to say.

No, you don't.  You tell it what you want the PC to talk about, or ask
about, but rarely what you want the PC to say (unless all you want the
PC to say is "hello" or "give me the halibut" or some such.)

> Even though the NPC might not understand what I am trying
> to say, it *feels* like I am trying to talk to someone on
> his or her own level. If the NPC doesn't understand, I can
> rephrase it, just as I would in real life.

But you're not rephrasing what the PC has said, you're rephrasing the
command given to the parser in hopes of getting a satisfactory response.
Big difference.
 
> The multiple-choice method *feels* like I'm being censored
> or guided away from certain areas of inquiry. As soon as I
> want to say or ask something that has not been pre-
> programmed, I am thwarted.

There's a bit in the ZORK I hintfile that goes something like this.
"Q: It says I need a machete to get through a certain part of the
forest.  Where do I get a machete?  A: You can't.  For the same reason,
you can't expect to walk to the airport and take a plane to London in
this game.  There have to be limits."  Is ZORK I "censoring" you from
flying to London?  You're certainly being guided away from it.

> Rather, I feel as if someone (the programmer? the NPC? the
> government?) has decided that certain areas of conversation
> are taboo, and that I will NOT be allowed even to ask.

Crossposted to alt.conspiracy.black.helicopters.

Seriously, though, I don't see much virtue in the "freedom" to type
things the parser has no chance of understanding... and someone (Joe
Mason?) has provided a number of examples of questions that simply
cannot be adequately dealt with by the ask/tell interface.

> It's almost like a press conference where the questions and answers
> are already scripted. Even though it looks like a free and open
> exchange is taking place, it's NOT.

Absolutely every single response in every piece of IF ever written
has been "already scripted."

> There. This thread is a perfectly good example of what
> I'm talking about. If we were all using the Monkey
> Island system to discuss this, we wouldn't be allowed
> to say anything other than what the original author
> wanted us to say.

And if we were using the ask/tell interface, you wouldn't be able
to say anything more complex than >TELL NEWSGROUP ABOUT CONVERSATION.

> No matter how open-minded someone is, I don't want them putting words
> in my mouth.

It's not your mouth.  It's the PC's mouth.

> Period. Even if it is "just a game."

Elsewhere on this thread, Mary Kuhner posted a great article in which
she wrote: "In my experience, there are several different virtues which
a game can have.  Often they are partly mutually incompatible, and one
must choose which to prioritize. [...] If you value sounding like a real
conversation, you'll dislike ask/tell. On the other hand, the menu
system puts a low value on the illusion of free choices."  Your post
highlights yet another point of difference: some people prefer close
identification with the PC, while others (and I'm one of these others)
prefer to think of the PC as more of a puppet that I'm maneuvering
through an ultimately artificial world.  (There's nothing intrinsically
wrong with artifice, after all.)  As such, I don't mind menu
conversation in that I have no problem with the notion that while =I=
may have lots of things I want to say, my =character= may only be able
to come up with four or five things to say at any given time.
Especially if they're as funny as the lines in Monkey Island or
Star Control 2.

  -----
 Adam Cadre, Durham, NC
 http://www.duke.edu/~adamc


From mkkuhner@phylo.genetics.washington.edu Thu May 29 12:38:21 MET DST 1997
Article: 25567 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!newsgate.cistron.nl!het.net!btnet-feed3!btnet!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news-feed1.tiac.net!uunet!in2.uu.net!140.142.64.3!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 23 May 1997 14:20:33 GMT
Organization: University of Washington, Seattle
Message-ID: <5m493h$1pd@nntp5.u.washington.edu>
References: <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu> <3384D153.43CF@acpub.duke.edu>
NNTP-Posting-Host: phylo.genetics.washington.edu
Lines: 71
Xref: news.lth.se rec.arts.int-fiction:25567

In article <3384D153.43CF@acpub.duke.edu> adamc@acpub.duke.edu writes:

>Your post
>highlights yet another point of difference: some people prefer close
>identification with the PC, while others (and I'm one of these others)
>prefer to think of the PC as more of a puppet that I'm maneuvering
>through an ultimately artificial world.  (There's nothing intrinsically
>wrong with artifice, after all.)  As such, I don't mind menu
>conversation in that I have no problem with the notion that while =I=
>may have lots of things I want to say, my =character= may only be able
>to come up with four or five things to say at any given time.

And, conversely, someone who prefers strong PC identification should
prefer ask/tell, no?  Because for them monkey style has a huge
drawback....

It's actually a bit more complex than this.  The same issue (degree of
identification with PC) comes up regularly in roleplaying games, and a
good deal of thought's been put into it.  James Wallis, in the journal
_Interactive Fantasy_, describes four modes of relating to character:

--as a playing piece being manuvered through challenges
--as a projection of the player into the game situation
--as an independent personality who behaves according to his own
  personality
--as an independent personality who in a sense possesses the player,
  so that the player imaginatively becomes the other person

(The fourth is difficult to explain.  Wallis compared it to Mask
acting.)

Generally speaking, it would seem that either A/T or monkey are suited
for the first mode:  A/T might be a bit better as it allows the
appearance of more possible "moves" and discourages certain kinds of
"cheating" like backing up to try all possible paths.  A/T is
almost surely, as you say, better for the second mode, where the player
imagines himself as being the PC:  having the game put words into
your mouth is distracting.  Monkey has some serious advantages for the
third mode, because it gives the PC lots of chance to express his
author-determined personality.  One might compare to the way that
Christabel, in _Christminster_, occasionally refuses to do things
because they're gender- or station-inappropriate.  This is easy to
do non-obtrusively with menus, harder with free conversation.

I don't think we know much about the fourth mode in IF.  I suspect it's
not achieved very often (it's not exactly common in roleplaying).  In
the one example I know of, the Mask illusion was quite fragile.  Having
the author suggest actions or dialog for the PC worked beautifully just
as long as the author was in *perfect* accord with the player's
conception of the character, and was horrendously annoying as soon as
any discrepancy occured.  This sets the game a challenge that is
unlikely to be tractable in practice.

So the main choices for IF would seem to be PC as game piece, PC as
surrogate for self, PC as independent character.  The author may
prefer to priviledge one view; in that case s/he should choose tools
accordingly.  _Christminster_ is a nice example of priviledging PC
as independent character.  You might try rewriting some of
Christminster's dialog as monkey-style and see how it looks.
However, a game with different priorities should very sensibly
use other tools.

By the way, saying "People who learn A/T first are prejudiced because
it's their first system; people who learn monkey first aren't
prejudiced, they're just truthfully seeing the flaws of A/T" just
makes you look silly.  What's sauce for the goose is sauce for the
gander.  You're essentially arguing that the other side is blinded
by their first experiences, but somehow your side is immune to this
effect.  Sensible people are unlikely to buy this claim.

Mary Kuhner mkkuhner@genetics.washington.edu


From joe.mason@tabb.com Thu May 29 13:16:47 MET DST 1997
Article: 25571 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!europa.clark.net!newsfeed.direct.ca!torn!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fict
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.9271.1727@tabb.com>
References: <5m493h$1pd@nntp5.u.washington.edu>
Date: Sun, 25 May 1997 23:57:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 70
Xref: news.lth.se rec.arts.int-fiction:25571

"Re: ask rec.arts.int-fict", declared Mary K. from the Vogon ship:

MK>--as a playing piece being manuvered through challenges
MK>--as a projection of the player into the game situation
MK>--as an independent personality who behaves according to his own
MK>  personality
MK>--as an independent personality who in a sense possesses the player,
MK>  so that the player imaginatively becomes the other person

MK>(The fourth is difficult to explain.  Wallis compared it to Mask
MK>acting.)

<snip>

MK>I don't think we know much about the fourth mode in IF.  I suspect
MK>it's not achieved very often (it's not exactly common in
MK>the roleplaying).  In one example I know of, the Mask illusion was

By "roleplaying" you mean pencil-and-paper RPG's, Dungeons & Dragons 
type?  If I understand you right, this is EXACTLY how I role-play, and 
most of the better role-players I know as well.  Of course, we've never 
actually sat down and discussed it, I'm just guessing their mental state 
>from the way they play.  I think it may be more common then you think.

MK>the quite fragile.  Having author suggest actions or dialog for the
MK>PC worked beautifully just as long as the author was in *perfect*
MK>accord with the player's conception of the character, and was
MK>horrendously annoying as soon as any discrepancy occured.  This sets
MK>the game a challenge that is unlikely to be tractable in practice.

This is also what I'm trying to do with the game I'm writing.  One one 
example are you talking about?  I'd like to take a look at it.

But as far as IF goes, it seems to me that the third and fourth options 
are different only in the matter of degree.  If the player achieves 
identification with the character, the game proceeds in the fourth 
state.  If not, it proceeds in the third state.  (This is assuming the 
game makes it obvious that the character has an independent 
personality.)  So I don't think the "fragility" is really that much of 
an issue, since the third mode would work perfectly well.

Your point about the author's and player's conceptions of the character 
being slightly different is a telling one, though.  It's true that the 
more general the game is about the character, the easier it is to keep 
the player's identification with the character.  In this case, menuing 
would have to be done much more carefully then ASK/TELL.

So I'd have to say this:

When the character has to talk about abstracts, ASK/TELL seems to me to 
be a harder technical problem, since it requires recognition of more 
ways to phrase the same request.  Menuing is easier to program, but 
would be much harder to balance right.

MK>accordingly.  _Christminster_ is a nice example of priviledging PC
MK>as independent character.  You might try rewriting some of
MK>Christminster's dialog as monkey-style and see how it looks.
MK>However, a game with different priorities should very sensibly
MK>use other tools.

I also toyed with the idea of converting something like Gabriel Knight 
to a text style.  That would be another way to see if a menu-style 
dialog would work.  (Gabriel Knight is a bad choice for this, though, 
because Gabriel's personality came from Tim Curry's delivery, not from 
his actual lines.  Even Tim Curry sounded unconvincing with some of his 
lines.)

Joe

 CMPQwk 1.42 9550 When in doubt, duck. - Malcolm Forbes


From mkkuhner@phylo.genetics.washington.edu Thu May 29 13:55:07 MET DST 1997
Article: 25580 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!news.seinf.abb.se!inquo!nntp.uio.no!newsfeeds.sol.net!worldnet.att.net!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fict
Date: 26 May 1997 22:33:31 GMT
Organization: University of Washington, Seattle
Lines: 66
Distribution: world
Message-ID: <5md33r$7gs@nntp5.u.washington.edu>
References: <5m493h$1pd@nntp5.u.washington.edu> <66.9271.1727@tabb.com>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:25580

In article <66.9271.1727@tabb.com> joe.mason@tabb.com (Joe Mason) writes:
>"Re: ask rec.arts.int-fict", declared Mary K. from the Vogon ship:

>MK>Having author suggest actions or dialog for the
>MK>PC worked beautifully just as long as the author was in *perfect*
>MK>accord with the player's conception of the character, and was
>MK>horrendously annoying as soon as any discrepancy occured.  This sets
>MK>the game a challenge that is unlikely to be tractable in practice.

>This is also what I'm trying to do with the game I'm writing.  One one 
>example are you talking about?  I'd like to take a look at it.

_Jigsaw_.  Not the whole game, but bits of it involving the interaction
with Black gave me a distinct sense that I was actually roleplaying
White as I would a developed character of my own.  The sensation was a
lot like a baby bird learning to fly--short periods of blissful soaring
followed immediately by clumsy crashes as soon as the game's concept
of White diverged from my own.  Damn near spoiled the ending, it did,
and I'm not sure getting that degree of identification actually made
the overall experience better, but the bits that worked that way were
excellent.

>But as far as IF goes, it seems to me that the third and fourth options 
>are different only in the matter of degree.  If the player achieves 
>identification with the character, the game proceeds in the fourth 
>state.  If not, it proceeds in the third state.  (This is assuming the 
>game makes it obvious that the character has an independent 
>personality.)  So I don't think the "fragility" is really that much of 
>an issue, since the third mode would work perfectly well.

I don't think it's that simple.  In the experience of rgf.advocacy,
where this is discussed a lot, there is a real though hard to describe
difference between character-play and mask-play (third and fourth
states) and mask play also has some similarities with character-as-
surrogate-for-self.  It's interesting that Graham says his intention
with Jigsaw was specifically character-as-surrogate; White is supposed
to be a kind of Everyperson.  I never got close to identifying with
Christabel in _Christminster_ the way I did with White; it was always
clear that the game was *her* experience, facilitated by me but not
experienced directly by me.  On the other hand, I never got close to
it with the pure surrogate PC in _Zork_ either; there was no mask there
to be worn, just me manuvering around in the game world.

The problem here may be that "identify with the character" is not
altogether a clear concept.  Some people use it to mean "root for
the character, enjoy her triumphs, suffer her defeats."  We can
identify in that sense with a movie hero--we want him to win, feel
badly if he loses, root for him to achieve his goals even if they
are not goals we normally share.  (If the hero is a jewel thief,
despite being law-abiding we may find ourselves hoping he gets
away with the loot.)  I certainly cared about Christabel and
wanted her to save her brother.

However, there is also the sense that one is able to think the
character's thoughts, feel her feelings, and have the sense of really
being in the situation.  This is a lot harder to get.  I never
really knew from the inside what Christabel was feeling except
when the game told me.  I was surprised and gratified to discover
that White had fallen in love with Black from my own reactions,
well before the game acknowledged it.

Is this any clearer?  It's a notoriously murky area.  I really recommend
James Wallis' article if you can find it (alas, the magazine has
since folded).

Mary Kuhner mkkuhner@genetics.washington.edu


From joe.mason@tabb.com Thu May 29 13:57:50 MET DST 1997
Article: 25572 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!01-newsfeed.univie.ac.at!news.radio.cz!europa.clark.net!newsfeed.direct.ca!torn!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fict
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.9269.1727@tabb.com>
References: <3384D153.43CF@acpub.duke.edu>
Date: Sun, 25 May 1997 23:57:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 52
Xref: news.lth.se rec.arts.int-fiction:25572

"Re: ask rec.arts.int-fict", declared adamc@acpub.duke.edu  from the 
Vogon ship:

a>Your post highlights yet another point of difference: some people
a>prefer close identification with the PC, while others (and I'm one of
a>these others) prefer to think of the PC as more of a puppet that I'm
a>maneuvering through an ultimately artificial world.  (There's nothing
a>intrinsically wrong with artifice, after all.)  As such, I don't mind
a>menu conversation in that I have no problem with the notion that while
a>=I= may have lots of things I want to say, my =character= may only be
a>able to come up with four or five things to say at any given time.

Now, that's kind of interesting - I'm trying out menu-based 
conversations right now, but in the same game I'm also pushing 
identification with the character.

Pretty much all the descriptive text in the game is heavily "in-
character": it describes not only what the character sees, but how he 
feels about it.  There's a lot of history behind the character, and 
things he sees keep calling up associations. (Not flashbacks, but 

For instance, your character is a general and an experienced fighter.  
So every time you look at a weapon or a combat situation, the 
description contains an evaluation of it:


> EXAMINE THE GUARD'S SWORD
A short, broad-bladed stabbing weapon. The hilt is wider then most, 
which could make for a somewhat awkward grip, but otherwise it seems to 
be nicely balanced.

> EXAMINE BORS' SWORD
A functional blade, in perfect condition. Bors was always careful with 
his weapons.

> EXAMINE BODIES OF THE GUARDS
The guards were backed against the wall when they died. Two have been 
hacked to death, the work of inexperienced swordsmen, but the other two 
bodies bear the marks of precision sword-strokes. If the bodies were the 
only clue you had, you would guess this to be the work of either Bors 
LeBrun or Gilles d'Arton.


The result is that the player is constantly immersed in this character, 
and should after a very short time begin to think like the character. 
Switching to the menu system shouldn't break the flow too much, because 
the responses would all be in the same tone as the "pseudo-interior 
monologue" which the rest of the game is presented as.

Joe

 CMPQwk 1.42 9550 My toughest fight was with my first wife. - Ali


From icallaci@csupomona.edu Thu May 29 14:27:38 MET DST 1997
Article: 25500 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newscore.univie.ac.at!news-ge.switch.ch!in2p3.fr!oleane!jussieu.fr!univ-angers.fr!ciril.fr!cnusc.fr!eerie.fr!news.apfel.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!feed1.news.erols.com!zdc!super.zippo.com!newshub.csu.net!news.csupomona.edu!news
From: Irene Callaci <icallaci@csupomona.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Fri, 23 May 1997 09:25:08 -0700
Organization: Cal Poly University
Lines: 64
Message-ID: <3385C4E4.2F2@csupomona.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu> <33851462.11691357@news.netspace.net.au>
NNTP-Posting-Host: 134.71.3.152
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25500

James Cole wrote:
> I think you need to read my post again.
> How about answering my question?

Sure, I'll try. I assume you mean your original question, which was:

>I prefer Monkey Island style NCP conversations (A while back I uploaded a
>utility for implementing it onto GMD - plug!).  Without saying why I think
>this form is better than the 'ask <x> about <y>' form, I'd be interested in
>the what you think about each of the two forms.  What do you think is
>better/worse about either of them?

I must have misunderstood your question. I THOUGHT you were asking for
our opinions about which style we preferred. Several of us have
expressed
our opinions, and you have proceded to tell us all that we are wrong.

Actually, since I enjoy seeing new developments in the interactive
fiction field, I'm very interested in trying out the Monkey Island
multiple-choice method you've developed to see if it works for me.
However, since I have not particularly enjoyed that type of NPC
interaction in the past (yes, I have played Monkey Island), I am
suspending judgment until I can play a text adventure that
incorporates it.

Until then, I hope that none of us will get stuck blindly defending
a position that is based on personal preference.

As a game developer, you are free to implement whichever style of
NPC conversation you choose. But when you ask for opinions, don't
be surprised when you get ones that differ from your own. I, for
one, am glad that not everyone sees things my way.

> >If we were all using the Monkey
> >Island system to discuss this, we wouldn't be allowed
> >to say anything other than what the original author
> >wanted us to say. No matter how open-minded someone
> >is, I don't want them putting words in my mouth.
> >Period. Even if it is "just a game."
> 
> Simple answer: And how about if we were using the ask/tell system.

If we were using the ask/tell system, I could ASK anything I
want. You wouldn't have to answer, just as an NPC doesn't have
to answer. But I am not an NPC when I play a game. The Monkey
Island style of conversation treats me as if I were a character
inside the game instead of ME.

> Besides all that, a discussion on a newsgroup can't be *simply* 
> compared with a discussion between the player and an NPC.

Aaahhhh....but the illusion of being able to type in anything I
want and have it answered (or not answered, as the case may be)
is certainly common to both the newsgroup discussion and the 
ask/tell method of NPC conversation. It is definitely NOT the
illusion conveyed by the Monkey Island multiple-choice system.

In a way, I think that the ask/tell style of i-f is a reasonably
good example of the Turing test, even if the implementation is
not convincing - yet. I can't see how the Monkey Island method
would ever evoke the sense that I was "talking" to another human
being, no matter how well it was implemented.

irene


From icallaci@csupomona.edu Thu May 29 14:28:03 MET DST 1997
Article: 25519 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!surfnet.nl!sun4nl!fido.news.demon.net!demon!dispatch.news.demon.net!demon!europa.clark.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!in1.uu.net!206.250.118.17!nntp.earthlink.net!usenet
From: Irene Callaci <icallaci@csupomona.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 24 May 1997 11:34:50 -0700
Organization: Cal Poly Pomona
Message-ID: <338734CA.592D@csupomona.edu>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7E30@csupomona.edu> <33851462.11691357@news.netspace.net.au> <3385C4E4.2F2@csupomona.edu> <338720da.29307940@news.netspace.net.au>
Reply-To: icallaci@csupomona.edu
NNTP-Posting-Host: max2-ot-ca-41.earthlink.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (Win95; I)
Lines: 34
Xref: news.lth.se rec.arts.int-fiction:25519

My very first computer game was Dungeon on a PDP-11 at work, for which
I was constantly in trouble:

Boss: Where's Irene?

Staff: She's in the computer room again.

But I could never get past the maze, and so I pretty much dropped the
game. After that (several years, I think), I went out and bought a
Commodore 64. I played several different kinds of games, some with
primitive graphics, some text adventures.

The more I played, the more I gravitated towards the text adventures.
I still prefer them to the graphical adventures. I'm not sure why;
I think it has something to do with my love for reading vs watching
TV or a movie. When I'm watching, I'm external to the action. When
I'm reading, I'm inside the action. I have the same subjective
experience when I compare the ask/tell system vs the multiple-choice
system. I don't want to see the choices presented to me; I want to
discover them myself.

I wish I could be more explicit, but it really is just a personal
preference, probably due to some long-forgotten childhood trauma or
something. 

irene

>I'd be interested in knowing why you used the system like you say.  Did you
>have a fair bit of experience with the ask/tell style before using the
>Monkey Island style?

>  ---------------
>  James Cole
>  jrcole@ozemail.com.au


From rglasser@penning.lanl.gov Thu May 29 15:25:48 MET DST 1997
Article: 25533 of rec.arts.int-fiction
From: Russell Glasser <rglasser@penning.lanl.gov>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: Sat, 24 May 1997 20:47:34 -0700
Organization: UCSD
Lines: 67
Message-ID: <3387B656.3FB0@penning.lanl.gov>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.raa26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <5m7o1t$r0a@newssvr01-int.news.prodigy.com>
NNTP-Posting-Host: sdx-ca12-17.ix.netcom.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-NETCOM-Date: Sat May 24 10:50:00 PM CDT 1997
X-Mailer: Mozilla 2.0 (Win95; I)
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!seunet!news2.swip.net!news.sbbs.se!newsfeed.tip.net!sn.no!nntp.uio.no!newsfeeds.sol.net!ix.netcom.com!news
Xref: news.lth.se rec.arts.int-fiction:25533

Chris Lang wrote:
> 
> Right now, I strongly prefer the Infocom style (which includes more
> >commands than ASK/TELL, btw).  Show me a good implementation of a
> >menu-based system, and I might change my mind.  But I doubt it.
> >
>    Yes. In some cases, you can ask a character WHERE IS (something) in
> addition to giving them instructions like MR. MCNABB, SHOW ME THE ROSES,
> or FLOYD, FOLLOW ME (of course, usually Floyd will follow you even if you
> don't tell him to, but this is just an example anyway).

	Easy for you to say, but I found Deadline (and other games where 
"nonconventional" conversational options were used) extremely bothersome.  I 
had to use the hints every single time that kind of input was required of me. 
I tried "ASK MCNABB ABOUT THE ROSES" and that do anything useful, so I 
naturally assumed that the roses weren't really important after all.
	The problem is, most of the time you wouldn't expect that kind of 
input to work.  Do you go around asking every character in the game to show 
you the things they're talking about?  You'd get a bunch of default responses 
and ultimately give up.  Be honest... did YOU figure out that you were 
supposed to tell McNabb to show you the roses without a hint book?

>    Overall, I prefer the the Infocom style (also used in every Legend
> game prior to Eric the Unready) over the 'menu' style

	Yeah, but in the Legend games it was a lot easier because the menu on 
the left could tell you what each character knows about.  I found that easier 
and much less worrisome.  In "TimeQuest" the old man had dozens of keywords 
you could ask about, and most of them changed depending on the time that you 
were in.  I didn't sit there and ask him about every single one of them.  
(Well, okay, eventually I did.  But that was after I'd already finished the 
game, just for some laughs.)
	To my memory, Spellcasting 101 was the only early Legend game that 
didn't give you menu choices for conversation topics.  And guess what?  I 
didn't spend any time at all talking to other characters in S101, except to 
say "greet" everybody.  When I asked a few people about things they should 
have understood, and I didn't get any responses, I stopped asking questions 
altogether.  In the other Legend games, I actually spent a lot more time 
deciding what to say to people (based on the large number of choices I was 
given).

> which basically
> has you reading lines from a script. If I wanted to do that, I'd go
> audition for a play.

	So what's wrong with being in a play?  Especially a branching play?  
It sounds like it would fun.

>    As for 'default' responses, I like it best when each character has
> his/her own default responses that are more clever than 'I can't tell you
> much about that'. Gives characters more individuality and personality.
> (for example, the hacker's default response to ASK HACKER about
> [something] in The Lurking Horror gives some added insight to his
> character).

	I certainly agree with that.  As long as I have to play "guess the 
noun" to hold down a conversation, it's important that characters have 
interesting and varied default responses.  That doesn't mean I'd prefer that 
over menus, though.
-- 
"The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself.  Therefore all
progress depends on the unreasonable man."
                                -- George Bernard Shaw

Russell can be heckled at
        http://sdcc8.ucsd.edu/~rglasser


From MKST21C@prodigy.com Thu May 29 15:30:49 MET DST 1997
Article: 25560 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!news-peer.sprintlink.net!news.sprintlink.net!Sprint!howland.erols.net!newsfeed.internetmci.com!in2.uu.net!192.207.105.50!prodigy.com!usenet
From: MKST21C@prodigy.com (Chris Lang)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 24 May 1997 22:31:34 GMT
Organization: Prodigy Services Company  1-800-PRODIGY
Lines: 43
Distribution: world
Message-ID: <5m7q86$s22@newssvr01-int.news.prodigy.com>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.raa26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1k5i$iqe@news.bu.edu> <33848100.7e30@csupomona.edu> <3384d153.43cf@acpub.duke.edu> <33871071.55ea@csupomona.edu>
X-Newsreader: Version 1.2
Xref: news.lth.se rec.arts.int-fiction:25560

Irene Callaci <icallaci@csupomona.edu> wrote:
>
>That's absolutely true (that some people prefer close identification
>with the PC, while others prefer to think of the PC as more of a
>puppet). Actually, it's not the PC I identify with; it's the 
>protagonist of the game. It's one of the reasons I shy away from
>RPG-style games. I just don't enjoy controlling an external
>character. I want to *become* the character, and even though
>the ask/tell style of NPC interaction is limited, it feels more
>like "free will" than the multiple-choice style of Monkey Island.
>
>irene
  
    I guess you can count me as one of the people who prefers 'close 
identification' with the PC. I've always liked the Infocom games better 
than any of Sierra's, even before Sierra switched to an all-icon 
interface. Infocom always has that 'first-person' feel that you ARE the 
main character of the story, even in its games with a defined central 
character (where you're someone specific rather than just 'the 
adventurer', 'the detective', and so forth), such as Hitchhiker's, AMFV, 
and Plundered Hearts. 
   The 'menu' interface (called the 'Monkey Island' interface elsewhere 
because it's most common in games such as that) really detracts from the 
illusion that you are the main character in the game, and it detracts 
>from the 'freedom of action' bit as well. You get pre-scripted dialogue 
in this approach, whereas in the Infocom style of conversation, you're 
sort of 'improvising', and you can ask characters about all sorts of 
things and get interesting answers. One of my favorite examples of this 
is the village idiot in 'Arthur: The Quest for Excalibur'. Not only can 
you ask him about things, people, and places in the game, you can also 
ask him about things that aren't in the game. ASK IDIOT ABOUT ZORK. ASK 
IDIOT ABOUT PLANETFALL. ASK IDIOT ABOUT BATES. And so forth. 
   The village idiot also, at one point, says 'Go ahead. Ask me about 
anything'. And then you can try ASK IDIOT ABOUT ANYTHING and get a 
response. This proves that you don't need a menu-style conversation to do 
a good joke with a setup.
    I don't know. As others have stated, it's basically a matter of 
personal preference. And I prefer to 'get into' the main character 
instead of the character just being a puppet, and I prefer the general 
'ASK/TELL' bit over the scripted menu approach. But to each his/her own.

                                           Chris Lang



From mkkuhner@phylo.genetics.washington.edu Thu May 29 15:31:51 MET DST 1997
Article: 25523 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newsfeed.de.ibm.net!ibm.net!jupiter.nic.dtag.de!news-peer.gsl.net!news-peer.sprintlink.net!news.sprintlink.net!Sprint!howland.erols.net!newsfeed.internetmci.com!in3.uu.net!140.142.64.3!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 22 May 1997 14:15:03 GMT
Organization: University of Washington, Seattle
Lines: 49
Message-ID: <5m1kd7$76p@nntp5.u.washington.edu>
References: <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:25523

jrcole@ozemail.com.au (James Cole) writes:

>There is a lot of personal opinion and subjectivity in this discussion, but
>there's a lot more to it than just that.  It is not just a matter of
>subjective personal opinion.

I strongly disagree.

In my experience, there are several different virtues which a game
can have.  Often they are partly mutually incompatible, and one must
choose which to prioritize.  One's priorities are, precisely, subjective
personal opinion.

The ask/tell system puts a low value on "sounding like a real
converation" compared to the menu system; the things the speaker says
are *very* flat and dull.  You can jazz them up a little:

>ASK SALESMAN ABOUT SPOT

"How about that spot, huh?  You trying to hide something from me?"
you say accusingly.

but this kind of hybrid risks inheriting the problems of the menu 
system without its virtues, since you're not allowing the player
any choice about the flavor-text at all.  (The player may have had 
no idea that just asking about the spot would produce such a rude, 
accusatory statement.)

If you value sounding like a real conversation, you'll dislike ask/tell.

On the other hand, the menu system puts a low value on the illusion of
free choices.  As you've argued, this is always an illusion; but
much of IF is an illusion, and how the illusions are handled is
important.  A player who prioritizes the sense of free choice over the
sense of real conversation will therefore tend to prefer ask/tell.  (I
believe this is what Zarf has been trying to say.)

Both very sensible opinions, but there is no way to objectively choose
one, because the core issue--which is more important to me, the illusion
of real conversation or the illusion of free action?--is subjective
and different players will have different answers.

The field would be richer for the presence of games that worked both
ways, so please do pursue this.  But not, I beg you, with the mindset
that there is some objective rule that will prove one set of priorities
correct and the other somehow not.  All that accomplishes is blinding
you to other peoples' experiences, never a useful thing.

Mary Kuhner mkkuhner@genetics.washington.edu


From robbj95@octarine.cc.adfa.oz.au Thu May 29 15:46:35 MET DST 1997
Article: 25513 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!uab.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!sn.no!uninett.no!Norway.EU.net!EU.net!howland.erols.net!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!harbinger.cc.monash.edu.au!newshost.carno.net.au!euryale.cc.adfa.oz.au!octarine!robbj95
From: Barbara Robson <robbj95@octarine.cc.adfa.oz.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 24 May 97 01:18:42 GMT
Organization: ADFA News Service
Lines: 75
Message-ID: <robbj95.864436722@octarine>
References: <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499@news.netspace.net.au> <5m1kd7$76p@nntp5.u.washington.edu> <3385156f.11960793@news.netspace.net.au>
NNTP-Posting-Host: 131.236.1.1
X-No-Archive: yes
Originator: robbj95@octarine
Xref: news.lth.se rec.arts.int-fiction:25513

jrcole@ozemail.com.au (James Cole) writes:

|mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner) wrote:

|>jrcole@ozemail.com.au (James Cole) writes:
|>
|>>There is a lot of personal opinion and subjectivity in this discussion, but
|>>there's a lot more to it than just that.  It is not just a matter of
|						  ^^^^^^^^
|>>subjective personal opinion.
|>
|>I strongly disagree.

|I'm sorry, but you're just plain wrong.  Have a look through the
|discussion.  There have been *many* arguments and points raised which have
|nothing to do with personal opinion. 

Nonsense.  There have been many points raised.  All have come down to
personal preferences.

|Another thing to consider are the disadvantages.  Disadvantages are more
|important.  If something is good and another thing is better, then you may
|choose one over the other for some personal perference.  However, if one
|something has bad flaws and another thing has minor flaws, you're more
|likely to choose the one with the minor flaws.

Of course.  What you appear to be refusing to accept, though, is which
flaws one considers minor and which one considers major will depend on
your personal preferences and which qualities are, in your personal
opinion, most important to enjoyment of the game.

|True.  But does this statement really mean much concerning the two systems?
|No.  The MI style doesn't give you the illusion that you can *ask about
|anything*.  However, it doesn't give you the impression that it's really
|narrow and confined either.  Despite only giving you a set of choices at
|each point in the conversation, it can give a real impression of not being
|narrow or limited.

I did not find that to be the case, at least with Monkey Island.  The
impression was of a severely limited range of topics.

|You may like having illusiong of free choices, but with it come many
|problems.  

Yes.  These are mainly problems for the if-author rather than the player
(they only become the player's problem if the author does a bad job).
With enough effort, most of these problems can be overcome and I prefer
to put up with the remaining few than to put up with the inherent 
problems of a menu system.

|But with all that said, yes, _ultimately it does come down to personal
|opinion_.  It's just I don't think people fully understand the Monkey
|Island system, or their opinions of it are clouded by their experience with
|the ask/tell system.  The opinions expressed in this thread have more to do
|with misunderstanding than with true personal preference.

I disagree.  And I have to admit, I have played more games all the way
through which use menu-based conversation than traditional IF games,
though I enjoy well-written IF games more than well-crafted graphical
adventures.

|>Both very sensible opinions, but there is no way to objectively choose
|>one, because the core issue--which is more important to me, the illusion
|>of real conversation or the illusion of free action?--is subjective
|>and different players will have different answers.

|It's not as simple as you suggest, there is so much more to it.

Repeated statements of this kind do nothing to further the discussion.
If you feel that Mary has missed something, kindly explain what that
might be.

(Sorry for interfering in this part of the thread, Mary).

Barbara


From A.G.Jackson@durham.ac.uk Thu May 29 15:49:54 MET DST 1997
Article: 25578 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeed.nacamar.de!su-news-hub1.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!rill.news.pipex.net!pipex!server1.netnews.ja.net!server6.netnews.ja.net!str-ccsun!strath-cs!nntphost.dur.ac.uk!altair.dur.ac.uk!d3099u
From: Big Mad Drongo <A.G.Jackson@durham.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 22 May 1997 11:47:09 GMT
Organization: University of Durham, Durham, UK.
Lines: 155
Message-ID: <5m1bnt$r76@mercury.dur.ac.uk>
References: <3379b653.10392540@news.netspace.net.au> <337d932b.8430519@news.netspace.net.au> <337F39A8.4B054615@alcyone.com> <33801214.6765452@news.netspace.net.au> <5lpe0j$sov@mercury.dur.ac.uk> <Pine.SGI.3.95q.970519145621.17168A-100000@irix.bris.ac.uk>
 <3381b39b.7862287@news.netspace.net.au>
NNTP-Posting-Host: altair.dur.ac.uk
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25578

James Cole (jrcole@ozemail.com.au) wrote:
: My example wasn't the best to illustrate what I was talking about.

: That aside, the simple fact is, there are many obvious, simple, and valid
: questions which the ask/tell style can't handle.  *At least not in a
: general way*.  It is very important that they do handle them in a general
: way.

: Am I going to bother explaining this or giving examples?  No, not at the
: moment.  Think about it.

Sort of suggests to me you can't think of any. Not that it's particularly
important - you can work your way round most of the problems you encounter
with the ASK ABOUT, TELL ABOUT system more easily than with the MI system,
simply because it's a lot more flexible.

: >                       In Ask/Tell I-F, the player can be suprised by
: >an answer.

: And please, do tell me why this can't happen in Monkey Island style.  
: You can't.

It can, of course, but it's a lot easier in ASK/TELL, because you don't
know that the author expects you to ask the question. Some of the best
lines in ASK/TELL can be where you ask a character about something you
don't expect them to know about, or say something odd to them and you
actually get a response. You just can't have this in MI style, because you
can *only* follow the conversation path that the author has laid out for
you.

: >            I find it strange that Adam Cadre supports the MI style as a
: >way of putting the player in character when his own game, I-0, is a
: >brilliant example of how to do this outside of MI menus; 

: perhaps he's a little more open minded?

Perhaps he's just ready to experiment and be wrong once in a while... :-)

: >                                                          like when I
: >asked to "open boot" and was told that my character would call it a
: >trunk. The large number of humorous responses to my commands also help
: >tell the player who he/she is without hitting them over the head. 

: Relevance to you point?

: and are you implying that the monkey island style really forces it upon
: you?  

Yes. Of course it does. Because with the monkey island style I have a very
limited number of choices at all points in the game. In command line IF I
can type absolutely anything I want, and provided the author has second
guessed me I will get a response out of it. It gives a feeling of far
greater freedom. The point above wasn't quite as relevant as it might have
been, but had it been an ASK situation...

> ASK NEIL ABOUT BOOT
Neil's brow furrows for a moment as he tries to work out what you mean.
Then it dawns upon him. "Oh, you mean the trunk," he says with a smile. "I
always lock it when I leave the car, ever since that time someone stole my
laptop and the insurance company refused to pay up because it wasn't
locked. Here, take the keys..."

> UNDO
[last move undone]

> ASK NEIL ABOUT TRUNK
"I always lock it when I leave the car," Neil explains, "ever since that
time someone stole my laptop and the insurance company refused to pay up
because it wasn't locked. Here, take the keys..."

Maybe rather a subtle difference, but it's the subtleties that really make
IF great most of the time.

[Pirate Pete snipped]
: By itself, this example looks quite convincing.  Step back and consider it
: within the context of a real game and things change.   It doesn't work like
: this.

Whyever not? I've played games even back on the 8-bit BBC Micro that had
this sort of ASK/TELL interface. Hey, I even wrote a couple of them...

: >The problem with menus is that they run against the rest of the game,
: >they are an artifice which destroys the suspension-of-willing-disbelief.

: exaplain exactly how and why they do this?

They break the flow of the game. You have to change the way you're
thinking about the input, from a "What do I do now?" to a "Which option do
I choose?". You have to change the way your hands hover over the keyboard.
Little things, but it does break the flow. And as a lot of people says, it
gives the impression of constraint. What if I want to ask Pirate Pete
about something that isn't on the list? At least if I was using ASK/TELL I
could do, even though the response would probably be a stock one.

: >If the whole game were menu-driven it would be OK. 

: why exactly?

See above. He's wrong, of course. :-) I've played entirely menu-driven
adventure games, and without exception they were dire. The menu-driven
conversation system works quite well in a point-and-click adventure,
though, such as Simon the Sorceror. In fact a command-line interface here
would be seen as out of place. Horses for courses, and all that.

: >                                                    Whereas the ASk,TELL
: >convention is part of the parser which we use in the other parts of the
: >game. 

: Your drawing simplistic conclusions.

Pot. Kettle. Black. Also he's right. Are you denying that the ASK/TELL
convention uses the parser we use in other parts of the game?

: >One last thing, as regards MI, etc. from my "experience." Although
: >Cadre, et al, claim that MI menu's are interactive I have found that of
: >the, say, 4 options only 1 is neccessary to the game. 

: That is wrong.  Simple observation or usage can disprove that.

It tends to be the case, though. Of four options, one will get you out of
the conversation, one will get the information you need (or move the
conversation on a bit) and the other two are just there to set up bad
jokes. Of course it's an exaggeration, but there is a kernel of truth to
it.

Of course, somebody's about to point out that the same holds true for
ASK/TELL - only one or two combinations will be necessary to complete the
game, and the others are just filler (or set things up for bad jokes). Of
course that's true, and until we have fully intelligent NPC's we're going
to have to live with that. (When we do have fully intelligent NPC's we may
have to ask ourselves if it's murder to type QUIT, of course. :-)

: >                                                      As such the player
: >is allowed to click through the other options, always returning to the 4
: >initial choices until he picks the "right" one.

: Untrue.

But again, it tends to be the case, even in very high quality
point-and-click games.

: Throughout your post you've given simplistic reasons.  You've given
: statements, not reasons.  If you want to prove anything you've got to do
: more than that.

Throughout your post you've not given reasons at all. You've just accused 
people of giving simplistic reasons. The obvious thing for you to do would
be to stop criticising other people's views on this, but to sit down and
write a game in Inform or TADS with menu-driven conversation, which makes
use of all the subtleties you seem to think menu-driven conversation can
provide. Then if it turns out to be really good we can all admit we were
wrong, and everyone will abandon the ASK/TELL convention and a new age of
interactive fiction will dawn.

Adrian


From svanegmo@undergrad.math.uwaterloo.ca Thu May 29 16:06:08 MET DST 1997
Article: 25585 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newscore.univie.ac.at!newsfeed.Austria.EU.net!EU.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!199.60.229.3!newsfeed.direct.ca!torn!kwon!watserv3.uwaterloo.ca!undergrad.math.uwaterloo.ca!svanegmo
From: svanegmo@undergrad.math.uwaterloo.ca (Stephen van Egmond)
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Sender: news@undergrad.math.uwaterloo.ca (news spool owner)
Message-ID: <EApEoG.Mr1@undergrad.math.uwaterloo.ca>
Date: Sat, 24 May 1997 21:07:26 GMT
References: <5m494f$886$1@netty.york.ac.uk>
Nntp-Posting-Host: cantor.math.uwaterloo.ca
Organization: University of Waterloo
Lines: 59
Xref: news.lth.se rec.arts.int-fiction:25585

Richard G Clegg <richard@manor.york.ac.uk> wrote:
>>examine busker
>He's a tall gangling man, with long and nimble fingers. He is carrying a black
>rod, and wearing a purple cape.
>
>"Now," says the busker, "to demonstrate that I'm not using any prepared
>equipment, I'd like to do this trick with an object from the audience."
>
>>ask busker about rod
>The busker doesn't quite understand what you want.
>
>>ask busker about cape
>The busker doesn't quite understand what you want.
>
>[Hmm.... they were described as something he had.]

This type of complaint is a common one about text adventures in general: 
the game doesn't know about everything it talks mentions.

I think that is because players who try the above line of inquiry 
originally got started on early games -- Scott Adams', let's say -- where 
just about every thing, every sentence, every single thing that catches 
your avatar's eye is important and essential to completing the game.

As people have tried to make the text adventure into Works Of Interactive 
Fiction, they are adding things -- characterization, atmosphere -- which 
result in the game talking about a great number of things many of which 
are of no consequence to the plot's development (which is what the above 
questions are trying to accomplish; maybe he'll give you the rod?).

The simple fact is that modern IF can't be expected to know about every 
noun it mentions.  Let's say:

> ASK BUSKER ABOUT ROD

"Aye, a fine piece that has seen me to many places.  I found it on a trek 
through the Highlands of Scotland to visit my syster Anne-Marie."

> ASK BUSKER ABOUT ANNE-MARIE
 or
> BUSKER, WHAT ABOUT SCOTLAND?
 or
> ASK BUSKER ABOUT OTHER PLACES

You end up with an exploding tree of topics to discuss. This is obviously 
not desirable since the busker is a minor character in the telling of the 
Christminster story.  Gareth Rees could have made him abitrarily 
interesting, but what's the point?

Someone said a few months ago that the trick to IF is making the lack of 
interactivity appear interactive.  Perhaps the busker's "huh?" responses 
broke it for you.

Personally, I accepted the busker's cues; when he suggested I look under 
the cup, I did, and we went on our way.  I found him a great character 
for what he was supposed to do in the story.

/Steve



From richard@manor.york.ac.uk Fri May 30 13:48:24 MET DST 1997
Article: 25643 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!psinntp!news.idt.net!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!baron.netcom.net.uk!netcom.net.uk!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!yama.mcc.ac.uk!news.york.ac.uk!rgc2
From: rgc2@york.ac.uk (Richard G Clegg)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 27 May 1997 16:40:38 GMT
Organization: The University of York, UK
Sender: rgc2@york.ac.uk
Message-ID: <5mf2q6$bpl$1@netty.york.ac.uk>
References: <5m494f$886$1@netty.york.ac.uk> <EApEoG.Mr1@undergrad.math.uwaterloo.ca>
Reply-To: richard@manor.york.ac.uk
NNTP-Posting-Host: tower.york.ac.uk
X-Newsreader: TIN [version 1.2 PL2]
Lines: 84
Xref: news.lth.se rec.arts.int-fiction:25643

Stephen van Egmond (svanegmo@undergrad.math.uwaterloo.ca) wrote:
: Richard G Clegg <richard@manor.york.ac.uk> wrote:
: >>examine busker
: >He's a tall gangling man, with long and nimble fingers. He is carrying a black
: >rod, and wearing a purple cape.
: >
: >"Now," says the busker, "to demonstrate that I'm not using any prepared
: >equipment, I'd like to do this trick with an object from the audience."
: >
: >>ask busker about rod
: >The busker doesn't quite understand what you want.
: >
: >>ask busker about cape
: >The busker doesn't quite understand what you want.
: >
: >[Hmm.... they were described as something he had.]

: This type of complaint is a common one about text adventures in general: 
: the game doesn't know about everything it talks mentions.

  I know, I fully realise this - I was making a point that whoever it
was who said "My characters can say sixty different things therefore
there should be no problem interacting with them convincingly" was
really fooling themselves to some extent.

: I think that is because players who try the above line of inquiry 
: originally got started on early games -- Scott Adams', let's say -- where 
: just about every thing, every sentence, every single thing that catches 
: your avatar's eye is important and essential to completing the game.

  Well, in my experience, few players do try that line of inquiry since
IF games in general don't encourage you to talk to characters.  

: You end up with an exploding tree of topics to discuss. This is obviously 
: not desirable since the busker is a minor character in the telling of the 
: Christminster story.  Gareth Rees could have made him abitrarily 
: interesting, but what's the point?

  I think Gareth could NOT have made him arbitrarily "interesting"
because the "tree of topics" goes out so quickly.  You can easily make a
character that will answer "hello" "how are you" and the mention of any
very obvious objects associated with the character.  Anticipating the
3rd or 4th thing the player will ask about is next to impossible.

: Someone said a few months ago that the trick to IF is making the lack of 
: interactivity appear interactive.  Perhaps the busker's "huh?" responses 
: broke it for you.

  Not at all because in normal play I wouldn't even talk to the busker
unless I was particularly stuck because my experience is that most
characters, even the better developed ones, simply don't have much of
interest to say.

: Personally, I accepted the busker's cues; when he suggested I look under 
: the cup, I did, and we went on our way.  I found him a great character 
: for what he was supposed to do in the story.

  That really wasn't my point.  I was trying to say that, by necessity
we don't have memorable conversations with IF characters in the current
system.  You claim the busker was "a great character" in Christminster -
could you tell me four things you said to the busker the first time you
played Christminster?  

  Don't get me wrong, I'm not trying to say "IF is awful and we should
all rewrite Monkey Island which was cool" - far from it.  I just don't
like the fact that, while I love IF and I love all the characters from
IF games I don't find that I "interact" with them as fully as I interact
with characters in point'n'click style games.  Maybe one way forward for
IF in this area is to "admit" that conversation, by necessity, is
limited and make it a useful feature instead of something that we do our
best to hide.

  Maybe I'm totally wrong and every other player of (say) Jigsaw was
falling over themselves with excitement at the way they could "talk" to
Black and spent ages telling hir/asking hir about various things and got
sane responses.  Whereas I thought Black was a great character I played
the game almost to the end without saying a word to hir.

--
Richard G. Clegg     Only the mind is waving
Dept. of Mathematics (Network Control group) Uni. of York.
email: richard@manor.york.ac.uk   
www: http://manor.york.ac.uk/top.html



From adamc@acpub.duke.edu Sun Jun  1 08:41:39 MET DST 1997
Article: 25673 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!erinews.ericsson.se!erix.ericsson.se!newsfeed2.luth.se!news.luth.se!eru.mt.luth.se!bloom-beacon.mit.edu!howland.erols.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!199.45.255.100!coop.net!cs.umd.edu!zombie.ncsc.mil!newsgate.duke.edu!usenet
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: "Ractives"
Date: Fri, 30 May 1997 19:46:24 -0400
Organization: the fictional NOW chapter at Carnegie Mellon University
Lines: 35
Message-ID: <338F66D0.13C0@acpub.duke.edu>
References: <338B40D9.498B@acpub.duke.edu> <66.9373.1727@tabb.com>
Reply-To: adamc@acpub.duke.edu
NNTP-Posting-Host: res-117-67.dorm.duke.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:25673

I wrote:
> Has anyone here read Neal Stephenson's THE DIAMOND AGE?  Perhaps
> we've reached the point where we can put the word "ractive" to good
> use.

Joe Mason wrote:
> It's been on my reading list for quite a while now, but I've never
> gotten to it.  What's "ractive"?

"Ractives" are what the characters in THE DIAMOND AGE call the
interactive fiction they play; "ractive" can also be used as an
adjective, as in "ractive porn."  From what I remember, ractives
run the spectrum of quality, from simple plot trees where the computer
moves you around to full virtual reality where the computer constructs
an environment for you on the fly to react to what you do.  The NPCs
are played by human "ractors," whose lines are suggested to them by
the program but who are free to ad-lib as they see fit.  I've always
thought that it might be in our interest to co-opt the word, simply
because computer adventure games, whether text or graphical, seem to
me to be a different enough experience from films or novels that
slapping the word "interactive" in front of a pre-existing medium
doesn't do them justice.  Since this particular branch of the thread
had been discussing whether Monkey Island is "real" IF or if it's more
like an "interactive film" or whatnot, I thought a "ractive" might be
a useful thing to call it: "ractive" in this case defined as "those
things like Monkey Island and Star Control 2 that we can't decide
whether to call IF or Interactive Films or whatnot but which we
recognize as belonging to this category when we see 'em."

Incidentally, THE DIAMOND AGE is significantly inferior to SNOW CRASH.

  -----
 Adam Cadre, Durham, NC
 Now you can play I-0, the "jailbait on the interstate" game, online!
 Find it at http://www.duke.edu/~adamc -- still open while I redecorate.


From A.G.Jackson@durham.ac.uk Mon Jun  2 09:52:44 MET DST 1997
Article: 25690 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!newscore.univie.ac.at!newsfeed.Austria.EU.net!EU.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.nacamar.de!rill.news.pipex.net!pipex!server1.netnews.ja.net!server6.netnews.ja.net!str-ccsun!strath-cs!nntphost.dur.ac.uk!altair.dur.ac.uk!d3099u
From: Big Mad Drongo <A.G.Jackson@durham.ac.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 30 May 1997 11:22:22 GMT
Organization: University of Durham, Durham, UK.
Lines: 19
Message-ID: <5mmd9e$kcr@mercury.dur.ac.uk>
References: <337d92b9.8316679@news.netspace.net.au> <19970517211200.RAA26492@ladder02.news.aol.com> <337edefe.11116727@news.netspace.net.au> <338179a1.13631028@ftl.msen.com> <m2oha6vyff.fsf@hubert.wustl.edu> <33831915.7226@csupomona.edu> <3384284a.6238499 <jota.864328463@sunspot>
NNTP-Posting-Host: altair.dur.ac.uk
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25690

Admiral Jota (jota@tiac.net) wrote:
: I've tried to stay out of this thread (I really have!), but I just have to
: make one comment: If this discussion were in the ASK/TELL system, the only
: thing anyone would have been able to do is TELL GROUP ABOUT CONVERSATION.

And if this discussion were in the MI system, the only choices anyone
would have had would be:

  1) I'm not going to give any examples, but the Monkey Island system is
     just better, alright.
  2) I'm not listening to anything you say, so you're wrong and the
     ASK/TELL system is better.
  3) You're all sad. Go away.
  4) Make $$$ fast.

When all along they wanted to say how wonderful a hybrid system they
worked out would be (TELL GROUP ABOUT HYBRID SYSTEM).

Adrian


From kjahds@kjahds.com Tue Jun  3 09:48:22 MET DST 1997
Article: 25705 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news.mira.net.au!news.netspace.net.au!news.mel.connect.com.au!munnari.OZ.AU!spool.mu.edu!howland.erols.net!newsserver.jvnc.net!newsreader.jvnc.net!kjahds.com!not-for-mail
From: kjahds@kjahds.com (Kenneth Albanowski)
Newsgroups: rec.arts.int-fiction
Subject: Re: ask rec.arts.int-fiction about NPC conversation
Date: 1 Jun 1997 22:11:31 -0400
Organization: None
Lines: 78
Message-ID: <5mta4j$2sq@kjahds.com>
References: <3385156f.11960793@news.netspace.net.au> <3385E464.MD-0.181.s590501@tfh-berlin.de> <3386d0c3.8802012@news.netspace.net.au> <ku$deBAO9uhzEw7Y@highmount.demon.co.uk>
NNTP-Posting-Host: prn-ts1-29.jvnc.net
Xref: news.lth.se rec.arts.int-fiction:25705

In article <ku$deBAO9uhzEw7Y@highmount.demon.co.uk>,
Neil Brown  <neil@highmount.demon.co.uk> wrote:
>
>Fair enough. Also, Monkey Island is a graphical adventure, which is
>quite different to interactive fiction. We have yet to see an IF
>production that uses this approach. Maybe we should all reserve
>judgement until then.

Er, actually it _is_ interactive fiction, or at least it is fiction that you
can interact with. It's does have graphics, but it also has text.

Technically speaking, it isn't insanely different from an Infocom game. The
game is broken up into graphic rooms (which can be larger then the screen
and scroll) which have defined areas in which you can walk, with most rooms
having perspective so that the horizon is usally in the middle of the
screen.

You interact with the world by building a simple phrase. This starts with
selecting a verb from either by clicking on the appropriate word (there are
only eight or so) in the on-screen "control panel", or by hitting a hot-key.
Once you've selected a verb, you may select an object, either from your
inventory (again, graphically) or from the scene by moving the mouse cursor
around and clicking on something. You may only select objects in the scene
which are "active", which is represented by a noun appearing in the sentence
being build when the mouse is over the object. Clicking the mouse button on
such an object completes the phrase and executes it.

Conversation is achieved by using the "talk" verb with a person (or animal,
radio, etc.) which (if the entity desires to talk) consists of a list of
numbered statements you may make, such as:

 1. Nice day, isn't it?
 2. It that boat outside for sale?
 3. Is that your nose, or are you eating a banana?
 4. Never mind.

Typing a digit or clicking on the phrase is enough to "speak" it, and
trigger a response from the entity you are talking with. The last entry
usually terminates the conversation peacefully, and there is commonly a
humorous entry in the list which triggers a funny conversation, but does not
damage your standing in the game.

The phrases branch out in a tree, producing the one main down-shot of this
system: if you want to find out everything a person knows, you have to do a
depth search.

On rare occasions there will be an "N. Other..." entry to let you type a
phrase, but this is only used for passwords. I believe LucasArts has dropped
"Other..." entirely, replacing it with a simple "N. The password is
fizzlefazzle" phrase which only shows up if your character has heard the
password.

Why is this interface so liked? Well, it's been around for a _long_ time
(remember _Maniac_Mansion_?), and the LucasArts team is very good at writing
games. None have yet reached the grandeur and sublimity of Trinity (for
example), but they've come close. Their sense of humour is marvelous, best
demonstrated in the Monkey Island games. Perhaps more importantly, if you
play through to the end of Monkey Island II, you'll see they have far more
design coherency then the average Roberta Williams "flick". Put another way,
if Terry Pratchett decided to write about a pirate, he'd probably write
about Guybrush Threepwood.

The interface has a number of serious benefits. By allowing hotkey access to
many options, the games can be played with the keyboard (for some reason,
many modern graphical games refuse to admit the keyboard exists, even if you
are clicking on a keyboard on the screen...) More abstractly, the inability
to select objects that are just "part of the scenery" solves at a single
stroke the guess-the-synonym puzzle, and the what-do-i-click on problem.
(You do quickly get into the habit of running the mouse cursor over the
entire screen to find active objects.)

The most recent LucasArts production, _The_Dig_ (which, while decent SF, is
only movie-SF, not book-SF) loses most of the verbs, switching over to a
more Sierra like icon-based approach both for verbs, and for conversation
paths. Past those changes, the interface is practically unchanged.
-- 
Kenneth Albanowski (kjahds@kjahds.com)



From erkyrath@netcom.com Tue Jun  3 18:34:26 MET DST 1997
Article: 25727 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!news-feed.inet.tele.dk!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [INFORM] Pesky walls
Message-ID: <erkyrathEB7IH5.EGM@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5n0814$nnc@nntp5.u.washington.edu>
Date: Tue, 3 Jun 1997 15:46:17 GMT
Lines: 42
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25727

Mary K. Kuhner (mkkuhner@phylo.genetics.washington.edu) wrote:
> I am trying to program a ball court with two walls, a north wall
> and a south wall.  Inform is strongly of the opinion that there
> are also northeast, east, southeast...etc. walls (the direction
> objects in the compass).  Is there some way to get rid of them just
> for this room, without breaking the player's ability to move in
> those directions?  Also, how can I give a wall a specific description
> in just this room? 

When I want to do this, I put in my wall object, and then use react_before
to redirect all actions on n_obj to my_north_wall. The my_north_wall
shouldn't have any words in common with the compass object; you may wind up
not giving it any name at all. 

Object my_north_wall "the northern wall"
  with 
    react_before [;
      Go: rfalse;
      default: <<(##action) self second>>;
    ],
    before [; 
      ! code...
    ],
  has scenery;

This is from memory and completely untested. You may have to fool with it 
some.

That said -- it may be easier to hack the library to remove the word 'wall'
>from the names of the compass objects. Or even remove those objects from
being in scope in the first place. I've never seen that feature as being
any use in games anyway; the only value it adds is that "examine ceiling"
or "examine north wall" returns a default "nothing special" response (and
that even when you're outdoors.) (To get a specialized description, I have
to use the trick described above. Which is a pain and a source of bugs.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From whizzard@uclink.berkeley.edu Wed Jun  4 09:16:22 MET DST 1997
Article: 25736 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!hunter.premier.net!hammer.uoregon.edu!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: [Contest] Judging for 1997 I-F Contest.
Date: 3 Jun 1997 19:36:12 GMT
Organization: University of California at Berkeley
Lines: 14
Message-ID: <5n1rnc$igk@agate.berkeley.edu>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:25736


Well, once again this year I've been unable to think of a good
alternative.  Therefore, we will remain on last year's honor system.  The
'random sample of games' method might seem attractive to some, but using
the system reduces the validity of the contest to a degree that I am very 
loath to consider. Thus, I will continue to ask everyone to play every
game they possibly can, but if you have severe time constraints, well,
just do what you can.  Hopefully nobody's going to lose out on first place
just because one or two people had a family vacation to go on.



-- 
	"Ha.  Made ya look!"


From erkyrath@netcom.com Wed Jun  4 17:41:24 MET DST 1997
Article: 25762 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!news.seinf.abb.se!inquo!nntp.uio.no!news.radio.cz!europa.clark.net!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Mucking with the "classics"
Message-ID: <erkyrathEB7zFo.8Io@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <3394616E.611F@ucla.edu>
Date: Tue, 3 Jun 1997 21:52:36 GMT
Lines: 37
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25762

Jon Petersen (enoto@ucla.edu) wrote:
> Has anyone ever attempted to rewrite one of the old Infocom games? My
> thinking is that the game "Suspended", while having much to recommend
> it, could be drastically improved with not too many changes. 

Since Suspended is commercial software, still copyrighted, and still in 
print, it would be pretty tacky to release your own version of it. I can't 
speak for Activision, but if I were in their position, I'd sue.

> I'd say
> this isn't as strange as it sounds: look at Adventure, the very first
> game in our "canon", and its long history of additions and revisions. 

Adventure started out as effectively freeware, although Microsoft did 
publish a commercial version (long long ago, but after the freeware 
version was well-known.)

> Putting copyright issues aside for a moment, is it "ok" to alter
> Adventure but not, for example, to add six treasures and ten new rooms
> to Zork I?  What if I thought Curses would be really groovy if I added
> an Ezra Pound adjunct to the TS Eliot scene?

Well, if someone started mucking with _So Far_, I would send a nasty
letter.  If that didn't work, I'd probably start looking for a lawyer. I
don't have the time or resources for a real legal battle, but it doesn't
cost much to get a lawyer to send a letter saying "Look, you're breaking
copyright law, stop it already." 

I don't think anyone would object (legally or morally) if you fooled 
around with Dungeon (the original, freeware version of Zork.) 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From earendil@ Wed Jun  4 18:00:13 MET DST 1997
Article: 25777 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Subject: Re: Mucking with the "classics"
References: <3394616E.611F@ucla.edu> <5n2540$8ft$1@neko.syix.com>
Organization: Gee Library, Texas A&M at Commerce
From: earendil@ (Allen Garvin)
NNTP-Posting-Host: faeryland.tamu-commerce.edu
Message-ID: <33956f9b.0@news.tamu-commerce.edu>
Date: 4 Jun 97 13:37:31 GMT
Lines: 28
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!europa.clark.net!news.msfc.nasa.gov!bcm.tmc.edu!news.tamu.edu!news.tamu-commerce.edu!!earendil
Xref: news.lth.se rec.arts.int-fiction:25777

In article <5n2540$8ft$1@neko.syix.com>,
Patrick Kellum <patrick@syix.com> wrote:
>For some reason, Jon Petersen was chatting and out came these words of greatness:
>
> >Has anyone ever attempted to rewrite one of the old Infocom games?  My
> >	And what about copyright?  Do you think Activision would slay my pasty
> >ass while I was simultaneously flamed by everybody in the newsgroup?
>
>You won't know until you try :-)  I sugest trying something small that
>Activision won't worry much about, like the demos or miniZork, and see
>what happins.  Or better yet, ask Activision how they would feel.

The people that wrote ZorkMUD got written permission from Activision to
rewrite and extend the original zork stuff in a non-commercial environment.
Activision certainly doesn't appear to be the mean nasty company it was when
it dissolved Infocom (boo! hiss!), so you could probably write to them and
get permission.  Especially if you want to improve the esoteric Suspended,
which was never a great seller.  You might want to contact Michael Berlyn
for "moral permission" also.




-- 
Allen Garvin
------------
earendil@faeryland.tamu-commerce.edu
http://faeryland.tamu-commerce.edu/~earendil


From lpsmith@rice.edu Wed Jun  4 18:01:00 MET DST 1997
Article: 25763 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!news.seinf.abb.se!inquo!nntp.uio.no!news.radio.cz!europa.clark.net!news.msfc.nasa.gov!bcm.tmc.edu!rice!ural.owlnet.rice.edu!lpsmith
From: lpsmith@rice.edu (Lucian Paul Smith)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Contest] Judging for 1997 I-F Contest.
Date: 3 Jun 1997 22:03:44 GMT
Organization: Rice University, Houston, Texas
Lines: 62
Message-ID: <5n24c0$t7r$1@joe.rice.edu>
References: <5n1rnc$igk@agate.berkeley.edu>
NNTP-Posting-Host: ural.owlnet.rice.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:25763

Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:

: Well, once again this year I've been unable to think of a good
: alternative.  Therefore, we will remain on last year's honor system.  The
: 'random sample of games' method might seem attractive to some, but using
: the system reduces the validity of the contest to a degree that I am very 
: loath to consider. Thus, I will continue to ask everyone to play every
: game they possibly can, but if you have severe time constraints, well,
: just do what you can.  Hopefully nobody's going to lose out on first place
: just because one or two people had a family vacation to go on.

I don't see the 'play everything you can' and the 'random' schemes as 
being necessarily incompatable, at least not under the scheme I proposed 
in 'Comp96'.

To recap:  In 'Comp96', you put the games you have the capability to play 
in a bin, pull a lever, and are presented with a randomized list of all 
the games available to you.  You are then honor-bound to play through as 
many of the games as you can.  If you manage to play them all, great!  In 
that scenario, 'Comp96' has affected nothing (except possibly the 'first 
game played' bias, or the 'last game played' bias, whatever those biases 
may be.)  Release 0 is available at GMD, in the infocom/games directory, 
for those who want to check it out.

If you _don't_ get through all the games, the power of randomization 
begins to work.  If everyone has their own randomized list, the number of 
people who don't play a particular game should be roughly equal to the 
number of people who don't play one of the other games.

Consider this:  The judging deadline is tomorrow, and you haven't played 
three games.  Two are Inform games, and one is an AGT game.  Which are 
you going to choose?  (Be honest.)

Consider this, further:  The judging deadline is even closer, and you 
have time for only one more game.  One is 'Tapestry', and the other is 
'Wearing the Claw'.  Which one are you going to play?

My point is not to cast aspersions on the authors' choice of titles or 
game systems.  My point is that people _will_ have opinions, and this 
_will_ skew the number of judges who don't rate a particular game--unless 
those options are taken from them.  If half of those people who can't 
rate all the games are told 'You will play Tapestry before you play 
Wearing the Claw', and the other half are told 'You will play Wearing the 
Claw before you play Tapestry', then approximately the same number of 
people will leave these two games unrated.

>From the 'For What It's Worth' Department:  Several people mentioned that 
they would use a 'Comp97' if I wrote it, whether or not it was official.  
Since I don't see a conflict of interest here, I'm planning on releasing 
it when the time comes.  It would just be nice to be 'official', and have 
access to the game titles beforehand, for everyone's benefit.  The rules 
proposed therein do not in any way contradict the rules posted (above) by 
Whizzard, and I would try to make it perfectly clear within the game that 
although the random order reduces the harm of people not playing all the 
games, this doesn't change the fact that if you can judge all the games, 
you should definitely do so.

Comments?

-Lucian "Lucian" Smith




From graham@gnelson.demon.co.uk Wed Jun  4 20:18:01 MET DST 1997
Article: 25787 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: The canon (Was: Re: Mucking with the "classics")
Date: Wed, 04 Jun 1997 10:55:04 +0100 (BST)
Organization: none
Message-ID: <ant040904345M+4%@gnelson.demon.co.uk>
References: <3394616E.611F@ucla.edu> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 91
Xref: news.lth.se rec.arts.int-fiction:25787

In article <3394616E.611F@ucla.edu>, Jon Petersen
<URL:mailto:enoto@ucla.edu> wrote:
> 
> Has anyone ever attempted to rewrite one of the old Infocom games?  My
> thinking is that the game "Suspended", while having much to recommend
> it, could be drastically improved with not too many changes.  I'd say
> this isn't as strange as it sounds: look at Adventure, the very first
> game in our "canon", and its long history of additions and revisions. 
> Putting copyright issues aside for a moment, is it "ok" to alter
> Adventure but not, for example, to add six treasures and ten new rooms
> to Zork I?  What if I thought Curses would be really groovy if I added
> an Ezra Pound adjunct to the TS Eliot scene?

At the risk of swelling my own ego, perhaps (since you have mentioned
"Curses") I can reply on behalf of The Canon.

Let us look, then, at Adventure and "its long history".  Said
history is not an happy one: it was really a simulation rather than
a game in Crowther's version (it had I believe 5 treasures and
a couple of puzzles, but was mainly an exercise in map-making);
Woods made it a real game.  Even so, some of Woods's additions
are out of keeping: still, therein (arguably) lies some of the charm
of the canonical game as we know it today.

There were then a hideous number of extensions, expansions,
elaborations, elephantiasies, etc., which in almost every case
produced size but not quality and diluted, drowned, dismembered,
diverged from, etc., the original.  Not one of these extensions is
regularly played any more.  I'm afraid I hope the same will apply
to the recent "with Enchanter spells" version, which was put together
(not by me) by merging code from "Balances" with code from my port
of "Advent".  If it had used exclusively new caves and puzzles
with only the odd nod to the original, it might have been worth
the endeavour.

The moral of this is: do you really have something to add?  Something
of genuine artistic value, and which is also of the same artistic
value as the original?  Would you try to publish a version of "Pride
and Prejudice" with half a dozen more dances and two extra sisters,
or Constable's painting "The Hay Wain, with another four carts and
some more cows just down the road"?

A sequel to Pride and Prejudice, or a pastiche or parody of Constable
to achieve some other artistic end, would be a different matter
(and merely ill-advised, or rather, to be undertaken at your own risk).

As it happens, I think a Venetian sequence mixed up with Pound's
cantos might be a plausible extension to "Curses", but I didn't write
one and "Curses" is already too large, and it would unbalance the
(already pretty out-of-kilter) game to have another poetry segment.
Plus, it would relate badly to the rest of the game, because one
of the modernist points of "Curses" is that every region is royally
mixed up with every other.  It may look like a shambles, it may in
fact be a shambles, but it has some integrity as an artistic whole
and the putative extension would violate that.  In any event it is
not easy to imitate an author's style convincingly.

It might also be remarked that on the Internet the canon is much more
at risk from such tampering.  If someone did make some kind of
"Curses Plus" then the casual downloader might well think, "aha!
more for my modem time!" -- whereas Jane Austen's books are protected
partly by the fact that no reputable publisher would adulterate them,
so the casual browser won't make any mistake.

> 	For the sake of the argument, let's assume that these are alterations
> which people generally feel add something good to the games.

Mmm... if you say so.  I've already argued that this cannot be so.
But for the sake of argument.

> 	And what about copyright?  Do you think Activision would slay my pasty
> ass while I was simultaneously flamed by everybody in the newsgroup?

No offence, but (although there is a case for arguing that "Dungeon"
is sort-of in the public domain by virtue of custom and practice)
please note that copyright covers almost all the canonical games,
and copyright exists to prevent artistic damage as well as to prevent
unfair commercial use.  This is why I retain copyright on "Curses"
and why I would take active steps to stop people tampering with it.
I hope Activision would take the same view.

> 	(This is all purely theoretical.  I do have a lot of ideas to change
> Suspended, for the better I think, but not knowing a language I am
> unable to act on my unruly impulses.)

In any event, if you have good ideas for games, don't throw them
away on reworking what already exists!  It would be a sad waste.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From robbj95@octarine.cc.adfa.oz.au Thu Jun  5 12:55:18 MET DST 1997
Article: 25821 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!feed1.news.erols.com!news.ecn.uoknor.edu!munnari.OZ.AU!harbinger.cc.monash.edu.au!newshost.carno.net.au!euryale.cc.adfa.oz.au!octarine!robbj95
From: Barbara Robson <robbj95@octarine.cc.adfa.oz.au>
Newsgroups: rec.arts.int-fiction
Subject: Re: Characterization
Date: 3 Jun 97 23:50:47 GMT
Organization: ADFA News Service
Lines: 26
Message-ID: <robbj95.865381847@octarine>
References: <5n1ec7$ige@dfw-ixnews3.ix.netcom.com>
NNTP-Posting-Host: 131.236.1.1
X-No-Archive: yes
Originator: robbj95@octarine
Xref: news.lth.se rec.arts.int-fiction:25821

mordacai@ix.netcom.com(STANTON FINLEY) writes:

|Further, there's not much reality in the means of communication in i-f
|games.  Sure, "TELL CHARACTER A ABOUT MACGUFFIN B" will work to solve a
|puzzle, but it hardly makes for realistic, characterizing dialogue. 
|And yet how can we change this?  I'm not looking for set answers, but
|I'd like to open up the floor to discussion.

Have you played "In the End"?  I feel that the characters in that are
very well done (given what looks like a small amount of coding effort
for them, but I could be wrong, being a newbie still).  Although their 
repertoire is very limited, the topics they do respond to make sense:
they will talk about themselves, react emotionally to talk of death,
and their replies lead to further topics, if the player wants to take
them up.

In general, I find that characters who can react emotionally help,
characters should always be willing to talk about themselves, and
their responses shouldn't usually be dead-ends (even the default
response should, if possible, hint at what the NPC is interested in).
As a player, I find I enjoy games more if I accept the NPCs as what
they are and allow myself to be led, letting the NPCs show me what
they can do rather than pushing them into areas they're not designed
for.

Barbara


From graham@gnelson.demon.co.uk Thu Jun  5 12:55:38 MET DST 1997
Article: 25806 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: "Deja Vu" deja vu
Date: Wed, 04 Jun 1997 22:43:19 +0100 (BST)
Organization: none
Message-ID: <ant042119868M+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 18
Xref: news.lth.se rec.arts.int-fiction:25806 rec.games.int-fiction:23581


As several people have been asking me about this, perhaps I can
clarify the status of "Deja Vu", a 22K version-3 game file
just posted to ftp.gmd.de.  It was compiled on 21st September 1993,
amazingly.

Congratulations to the archaeologist, whoever it was.  But let's
please not call it a game.  It was only ever a pasted-up group
of five or six rooms from Advent (not then in Inform format) and
Dungeon to demonstrate a few Inform 1 features.  File under
"antiquaries", not "art".

In particular, I'd rather it didn't go into ftp.gmd.de's "games"
directory.  But let's archive it somewhere, if people care enough.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From graham@gnelson.demon.co.uk Thu Jun  5 22:27:06 MET DST 1997
Article: 25806 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: "Deja Vu" deja vu
Date: Wed, 04 Jun 1997 22:43:19 +0100 (BST)
Organization: none
Message-ID: <ant042119868M+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 18
Xref: news.lth.se rec.arts.int-fiction:25806 rec.games.int-fiction:23581


As several people have been asking me about this, perhaps I can
clarify the status of "Deja Vu", a 22K version-3 game file
just posted to ftp.gmd.de.  It was compiled on 21st September 1993,
amazingly.

Congratulations to the archaeologist, whoever it was.  But let's
please not call it a game.  It was only ever a pasted-up group
of five or six rooms from Advent (not then in Inform format) and
Dungeon to demonstrate a few Inform 1 features.  File under
"antiquaries", not "art".

In particular, I'd rather it didn't go into ftp.gmd.de's "games"
directory.  But let's archive it somewhere, if people care enough.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From blore@ibm.net Fri Jun  6 15:37:56 MET DST 1997
Article: 25857 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
From: blore@ibm.net    (Steven Howard)
Subject: Re: Characterization -- SPOILERS
Reply-To: blore@ibm.net
References: <5n1ec7$ige@dfw-ixnews3.ix.netcom.com>
X-Newsreader: IBM NewsReader/2 v1.2.5
NNTP-Posting-Host: 129.37.242.155
Message-ID: <3394e800.0@news1.ibm.net>
Date: 4 Jun 97 03:58:56 GMT
Lines: 41
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news-feed.inet.tele.dk!news.maxwell.syr.edu!newsm.ibm.net!ibm.net!news1.ibm.net!129.37.242.155
Xref: news.lth.se rec.arts.int-fiction:25857

In <5n1ec7$ige@dfw-ixnews3.ix.netcom.com>, mordacai@ix.netcom.com(STANTON FINLEY) writes:
> I just finished playing a new computer game, Phantasmagoria 2: A
>Puzzle of Flesh, by Sierra.  I must admit, I rather liked the game, and

Well, it takes all kinds, I suppose.

I'm kidding -- I haven't actually seen this game, but I hear it's just as
bad as its predecessor.

>     What I'm interested in is: How can writers of i-f create
>characters like that, who the play will honestly CARE about, honestly
>feel something regarding them.  This is a hard task I'm sure, but it's
>effects could make an average game a masterpiece.  First, can anyone
>think of any instances where you've actually FELT some emotion
>regarding an i-f character?  The only one that springs to mind is the
>woman with the umbrella at the begining of Trinity and maybe the mother
>in Tapestry.  These were both very small characters that you didn't
>really react with much, but they evoked a little real feeling in me
>(though not to the degree that Trevor did in P2).  Can anyone think of
>any others?

The classic example, and I mean THE classic example, which many,
many people will post, is Floyd from Planetfall and Stationfall.
To paraphrase Dino de Laurentiis, "Everybody cry when Floyd die."*

Floyd's an effective character for a couple of reasons.  First, he's
childlike and funny.  Second, he seems to genuinely like the 
protagonist and go out of his way to help.  Third, although his
responses are limited, they're limited in a way that maintains
his character:  Floyd is a playful robot, with little patience or
capacity for complex conversation.  

*de Laurentiis actually said "Nobody cry when Jaws die" (while talking
about his execrable 1976 remake of "King Kong").
========
Steven Howard
blore@ibm.net

What's a nice word like "euphemism" doing in a sentence like this?




From graham@gnelson.demon.co.uk Fri Jun  6 16:04:08 MET DST 1997
Article: 25860 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!howland.erols.net!europa.clark.net!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: The canon (Was: Re: Mucking with the "classics")
Date: Wed, 04 Jun 1997 22:32:46 +0100 (BST)
Organization: none
Message-ID: <ant0421461cbM+4%@gnelson.demon.co.uk>
References: <3394616E.611F@ucla.edu> <ant040904345M+4%@gnelson.demon.co.uk> <5n4inv$sva@flood.xnet.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 34
Xref: news.lth.se rec.arts.int-fiction:25860

In article <5n4inv$sva@flood.xnet.com>, Jason Compton
<URL:mailto:jcompton@typhoon.xnet.com> wrote:
> 
> Graham Nelson (graham@gnelson.demon.co.uk) wrote:
> : In any event, if you have good ideas for games, don't throw them
> : away on reworking what already exists!  It would be a sad waste.
> 
> I'd have to disgree.  As a big fan of MST3K: Detective, I recognize that
> Forman would never have been able to put together a thoroughly enjoyable
> game if he didn't build on Detective.

Parodies, pastiche and sequels are a slightly different case,
as I said.

> As for all those versions of Adventure you find upsetting, I don't see
> what's wrong with them--and clearly somebody still has an interest in
> playing them, because they keep getting made and they keep getting
> archived.

Perhaps I've already made this point to death, but I don't
think they are played, very much -- only written (because everyone
loves to implement Adventure, and I'm no exception) and archived
because we (rightly) archive almost everything.  In many ways the
most interesting thing about the morass of Adventure derivatives
is the genealogy of their derivation, rather as happens with
corrupt medieval manuscripts.  Adventure is to some extent
a special case, as it is something of an endlessly retold myth,
shaped and improvised a la Levi-Strauss.

Isn't there something vampiric about this whole business?

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From erkyrath@netcom.com Fri Jun  6 16:22:01 MET DST 1997
Article: 25828 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!ais.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] Sigh.  Playing with describe.
Message-ID: <erkyrathEBB9BG.2zI@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5n5jin$p59@agate.berkeley.edu>
Date: Thu, 5 Jun 1997 16:18:52 GMT
Lines: 53
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:25828

Gerry Kevin Wilson (whizzard@uclink.berkeley.edu) wrote:

> Hi Again, yet another annoying question for you guys.

> I'm playing around with describe now (no, I don't waste any time in
> beating hell out of a language.)

> What I want to do is simply override the (which is empty) message that
> follows after a container's describe message.  Changing describe itself
> does that quite well, but then shoves the container up on a line by
> itself, which I do not desire.  I need a way to do this without announcing
> that I have done it.

Ok, I take it that you're talking about seeing the object listed in a room
description, as opposed to in your inventory. (To adjust it in your
inventory you'd add an invent property.) It's coming from the list-writer
package, obviously. 

Let's see... this message is ListMiscellany 4, which is printed in 
WriteAfterEntry when the PART_INV bit is set... (if FULL_INV was set, it 
would be checking the invent property, and you could deal with it that 
way.) Above that the code becomes unreadable (go go gadget Graham), so we 
try working down... LookSub() calls Locale(), which calls WriteListFrom() 
with the PART_INV bit set.

Conclusion: there's no easy, supported way to do it. Sigh.

Obvious hacks: 

Add a line to WriteAfterEntry() that calls a roominvent property, rather
like the invent property. (That is, if that doesn't return 0, skip the 
automatic message-printing in WriteAfterEntry().)

Jigger the container to turn off its container bit when it's empty, or 
during Look actions, or something.

Do a FULL_INV list-write in Locale() instead of PART_INV. Then you could
have an invent property. This would cause substantial changes in Look
behavior, though, and I fear it. 

You may well ask, why isn't this easier to do... I've wanted to do this 
myself, but I've always handled it by putting in a describe property. The
more things are described with hand-written text, the better, I figure. In 
fact I think I put describe properties on *all* my containers; I don't 
like having a potentially large list of contents buried in the same 
paragraph as the rest of the room contents.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From richard@manor.york.ac.uk Sat Jun  7 18:58:43 MET DST 1997
Article: 25880 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!uninett.no!news-feed.inet.tele.dk!news.maxwell.syr.edu!europa.clark.net!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!rill.news.pipex.net!pipex!server1.netnews.ja.net!server5.netnews.ja.net!server3.netnews.ja.net!nntpfeed.doc.ic.ac.uk!sunsite.doc.ic.ac.uk!yama.mcc.ac.uk!news.york.ac.uk!rgc2
From: rgc2@york.ac.uk (Richard G Clegg)
Newsgroups: rec.arts.int-fiction
Subject: Re: "Real time" games
Date: 6 Jun 1997 11:55:58 GMT
Organization: The University of York, UK
Sender: rgc2@york.ac.uk
Message-ID: <5n8tse$731$2@netty.york.ac.uk>
Reply-To: richard@manor.york.ac.uk
NNTP-Posting-Host: tower.york.ac.uk
X-Newsreader: TIN [version 1.2 PL2]
Lines: 22
Xref: news.lth.se rec.arts.int-fiction:25880

Graham Nelson (graham@gnelson.demon.co.uk) wrote:
:  For a much better implementation of dwarves milling
: about in real time, see Melbourne House's "The Hobbit"...

  Sorry, we've got to be totally pedantic here - "The Hobbit" had a 
disappointing paucity of dwarves featuring in fact, just the one (if I
recall correctly).  It tried to compensate with milling goblins which it
certainly managed to excess (the disgusting goblin, the nauseating
goblin, the army surplus goblin etc).  Even if it had more than one
dwarf, I believe it would have then featured "dwarfs" not "dwarves" that
being the correct plural in Tolkein land for dwarf (I am willing to be
corrected on this point but I seem to remember a tedious introductory
note to this point in The Hobbit).  OK - enough pedantry from me.

  Thorin sits down and sings about gold.

--
Richard G. Clegg     Only the mind is waving
Dept. of Mathematics (Network Control group) Uni. of York.
email: richard@manor.york.ac.uk   
www: http://manor.york.ac.uk/top.html



From graham@gnelson.demon.co.uk Wed Jun 11 17:26:35 MET DST 1997
Article: 25990 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!disgorge.news.demon.net!demon!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: "Real time" games
Date: Tue, 10 Jun 1997 23:35:47 +0100 (BST)
Organization: none
Message-ID: <ant102247f7fM+4%@gnelson.demon.co.uk>
References: <5n8tse$731$2@netty.york.ac.uk> <5nc45k$f1h@bartlet.df.lth.se> <339b5fe9.0@news1.ibm.net> <ant092055868c4bn@arnod.demon.co.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 33
Xref: news.lth.se rec.arts.int-fiction:25990

In article <ant092055868c4bn@arnod.demon.co.uk>, Julian Arnold
<URL:mailto:jools@arnod.demon.co.uk> wrote:
> 
> My dictionary (Chambers) lists both "dwarfs" and "dwarves", but the
> latter is noted as rare.  It says nothing about Tolkien though.  Didn't
> Tolkien make the distinction to separate gold-loving, beard-growing,
> all-singing-type dwarves from abnormally small people-type dwarfs?

Tolkien adduced the words "knife" and "knives" in evidence.  But
I think you're right, in a way: he needed to use words like
"dwarvish" as cultural markers (rather as the adjective "Klingon" is
used in Star Trek): "dwarfish knives" would imply unusually small
daggers.  I think his solution rather clever...

Incidentally, Conan Doyle also has a neologism to his credit --
"grimpen", as in "the grimpen mire".  First usage in "The Hound of
the Baskervilles", which established it as a plausible English
word for swampy ground.  It was next used in the 1940s by T. S. Eliot,
in the Four Quartets -- his editor never questioned the word because
it so happened that Eliot and the editor were both devotees of
Holmes, and both thought it was quite genuine.  It's now in the OED.
(Third usage: a Holmes encyclopaedia published in the 1970s, as
I recall.)

There is another story about Thomas Hardy, at the very end of his
life, not being quite sure about a particular Wessex dialect word
and looking it up in the OED.  To his relief, he finds it, with
just the spelling he expected.  Source -- an early novel by Thomas
Hardy...

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From rscherle@gummy.cs.indiana.edu Thu Jun 12 18:26:23 MET DST 1997
Article: 26023 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!erinews.ericsson.se!news.seinf.abb.se!inquo!nntp.uio.no!news.maxwell.syr.edu!chi-news.cic.net!news.indiana.edu!gummy!rscherle
From: rscherle@gummy.cs.indiana.edu (Ryan Scherle)
Newsgroups: rec.arts.int-fiction
Subject: Re: Disambiguation of balls (was re: NPC conversation etc)
Date: 12 Jun 1997 15:41:15 GMT
Organization: Indiana University, Bloomington
Lines: 52
Message-ID: <5np5ar$dr5$1@dismay.ucs.indiana.edu>
References: <1997Jun12.133138@vaxc.cc.monash.edu.au> <5nof39$43m$1@oravannahka.Helsinki.FI>
NNTP-Posting-Host: gummy.cs.indiana.edu
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:26023

Esa A E Peuha (peuha@cc.helsinki.fi) wrote:
> David Dyte <ddyte@vaxc.cc.monash.edu.au> wrote:
> : Mark Tilford wrote:

> : > Which ball do you mean, the large, interesting ball or the ball?

> : Well I would GET ALL then DROP LARGE if I wanted the other one.
> : Not that hard for the imaginative player really...

> What if the large ball is only a trap that kills you immediately if you
> take it, and there is nothing in the game to prevent that.

Better yet, what if the large ball were so large that you couldn't
pick up other objects while holding it?

> GET LARGE

You stretch your arms around the large, interesting ball. With a heave
and your best weightlifter's grunt, you manage to lift it off the
floor.

> GET BALL

You can't possibly pick up something while your arms are doing
everything they can just to keep holding the large, interesting ball.

> N

The large, interesting ball is too wide to fit through the north door.

> DROP LARGE

The large, interesting ball crashes to the floor.

> PUT BLANKET ON LARGE

(taking the blanket out of your backpack)
You cover the large, interesting ball with the warm, fuzzy blanket.

> LOOK

You see a ball and a blanket covering something large and round.

> GET BALL

As you pick up the ball, you wipe some of the dust off. It looks like
the ball is pure gold!


-----------------------------------------
Ryan Scherle      rscherle@cs.indiana.edu



From jfrancis@dungeon.engr.sgi.com Tue Jun 17 00:17:15 MET DST 1997
Article: 26141 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!su-news-hub1.bbnplanet.com!su-news-feed4.bbnplanet.com!news.bbnplanet.com!enews.sgi.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.arts.int-fiction
Subject: Re: A personal opinion:
Date: 16 Jun 1997 20:44:02 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 52
Message-ID: <5o48ii$hdo@fido.asd.sgi.com>
References: <erkyrathEBoGns.708@netcom.com> <66.9670.1727@tabb.com> <m37mfve8em.fsf@loki.lrz-muenchen.de>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.arts.int-fiction:26141

In article <m37mfve8em.fsf@loki.lrz-muenchen.de>,
Florian Beck  <h729ihqu@sun1.cip.fak14.uni-muenchen.de> wrote:
>joe.mason@tabb.com (Joe Mason) writes:
>
>> "Re: A personal opinion:", declared Andrew Plotkin from the Vogon ship:
>> 
>> AP>I try to repeat the following statistic at least one a month: _So
>> AP>Far_  takes under five minutes to re-solve, if you're a fast typer
>> AP>and have a  fast-scrolling window. If you make a mistake and have to
>> AP>start over, it's  under ten minutes. _Christminster_, ok, much longer
>> AP>plot; still under half  an hour to start over from the beginning.
>> 
>> It takes even less time if you copy and paste the commands from a walk-
>> through.  (Wow - a point in favour of simple list-of-command walkthru's.  
>> I didn't think there were any!)  Of course, the only game I've tried 
>> this is is TATCTAE, and it had a few Z commands or something missing, so 
>> it would never quite work right - very annoying.
>
>Cut and paste doesn't work well for games with lots of output; every
>time the interpreter prompts for the next page, a command is lost. And
>Xzip doesn't allow me to cut and past at all.
>
>Inform would allow to write (and read!) the player's commands via
>output_stream/input_steam 4. Now *this* would be nice for the
>player! Sadly in most games "script" puts out a transcript of the
>whole game, which I don't find useful at all.
>
>-- 
>Flo

Aaah - another advantage of the good old days!

When I played Dungeon on the DECSystem-20, I always ran it over a
pseudo-tty (DECSpeak for virtual terminal) running under the control
of the operator terminal multiplexing software.  That way I could use
the full set of logging and scripting commands.  In particular I could
send a whole list of commands from a file.  I had a set of files for
Dungeon (with breaks at all the random decision points such as the
troll room, the round room, etc.) which I could use to go back and
replay the game very fast (relatively speaking :-) - useful when you
only had a very limited amount of disk space available for save files.

When I was mucking around writing my own late unlamented game-playing
system, I had an "OBEY" command which would take input from a file.
This could be either a simple list of commands, or a full game transcipt.
If it was a transcript I looked for lines beginning with the user input
prompt (normally ">"), and ignored any other lines.
-- 
John Francis  jfrancis@sgi.com       Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 43U-991
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From wwwwolf@iki.fi Tue Jun 17 20:48:00 MET DST 1997
Article: 26169 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!EU.net!news.eunet.fi!wwwwolf
From: wwwwolf@iki.fi (Urpo Lankinen)
Newsgroups: rec.arts.int-fiction
Subject: Death message
Date: 17 Jun 1997 15:21:30 GMT
Lines: 27
Message-ID: <slrn5qdat7.e7.wwwwolf@wwwwolf.pp.fi>
NNTP-Posting-Host: wwwwolf.pp.fi
X-Newsreader: slrn (0.9.3.2 UNIX)
Xref: news.lth.se rec.arts.int-fiction:26169

I found this from my fortune database:


You are transported to a room where you are faced by a wizard who
points to you and says, "Them's fighting words!"  You immediately get
attacked by all sorts of denizens of the museum: there is a cobra
chewing on your leg, a troglodyte is bashing your brains out with a
gold nugget, a crocodile is removing large chunks of flesh from you, a
rhinoceros is goring you with his horn, a sabre-tooth cat is busy
trying to disembowel you, you are being trampled by a large mammoth, a
vampire is sucking you dry, a Tyranosaurus Rex is sinking his six inch
long fangs into various parts of your anatomy, a large bear is
dismembering your body, a gargoyle is bouncing up and down on your
head, a burly troll is tearing you limb from limb, several dire wolves
are making mince meat out of your torso, and the wizard is about to
transport you to the corner of Westwood and Broxton.  Oh dear, you seem
to have gotten yourself killed, as well.

You scored 0 out of 250 possible points.
That gives you a ranking of junior beginning adventurer.
To achieve the next higher rating, you need to score 32 more points.


...this isn't from a real game, is it?

-- 
Urpo Lankinen || wwwwolf@iki.fi || http://www.iki.fi/wwwwolf/


From graham@gnelson.demon.co.uk Wed Jun 18 20:56:47 MET DST 1997
Article: 26203 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!newsfeed.direct.ca!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Stupid Question
Date: Wed, 18 Jun 1997 11:11:00 +0100 (BST)
Organization: none
Message-ID: <ant181000f7fM+4%@gnelson.demon.co.uk>
References: <19970618035800.XAA06980@ladder02.news.aol.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 29
Xref: news.lth.se rec.arts.int-fiction:26203

In article <19970618035800.XAA06980@ladder02.news.aol.com>, LFrench106
<URL:mailto:lfrench106@aol.com> wrote:
> 
> What's the cruelest puzzle in all IF, mewonders.
> 
> The Enigma from Jigsaw?
> The Baseball Diamond from Zork 2 (But not the mainframe)?
> The ending of Sherbet?
> The mousehole in Curses?

Just what kind of utter sadist sets these puzzles, eh?  However,
I nominate:

  The bees (Adventureland)
  The freezer banks (Snowball)
  The maze (in any of the early games, but Zork 1 will do)
  The Bank of Zork (Zork 2)
  The wait-and-something-happens events in Zork 3

Of course "cruel" is not the same as "difficult".  The temporal
puzzle in Spellbreaker is far from easy but is so infinitely
satisfying when one works it out, that it justifies its difficulty.
I've cited only early games -- standards have changed, I think.
(As for the Curses mousehole, I think that's as nothing in
trickiness terms to working out the rods.)

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From anson@ici.net Wed Jun 18 22:50:03 MET DST 1997
Article: 26204 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!207.180.0.49!news.ici.net!d-ma-fallriver-16.ici.net!user
From: anson@ici.net (Anson Turner)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Returning textua
Date: Wed, 18 Jun 1997 10:50:07 -0400
Organization: The Internet Connection
Lines: 16
Distribution: world
Message-ID: <anson-1806971050080001@d-ma-fallriver-16.ici.net>
References: <66.9698.1727@tabb.com>
NNTP-Posting-Host: d-ma-fallriver-16.ici.net
X-Newsreader: MT-NewsWatcher 2.3.1
x-no-archive: yes
Xref: news.lth.se rec.arts.int-fiction:26204

In article <66.9698.1727@tabb.com>, joe.mason@tabb.com (Joe Mason) wrote:

:Did we ever figure out a way to get Inform to return an object's textual 
:name?

Well, you could:


Array name_string -> 80;

@output_stream 3 name_string;
print (object) obj;
@output_stream -3;


Anson.


From joe.mason@tabb.com Thu Jun 19 16:30:12 MET DST 1997
Article: 26223 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!newsfeed.direct.ca!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: Speaking of New Z-machines...
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.9739.1727@tabb.com>
References: <erkyrathEBwMJJ.5xJ@netcom.com>
Date: Wed, 18 Jun 1997 21:27:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 15
Xref: news.lth.se rec.arts.int-fiction:26223

-> The question I want to ask is, how many people would want to try
-> writing a V6 game if it was practical?

I was about to pipe up, "Not me!" until I realized that I would,
actually.  Normally I ignore graphics like the plague, since I'm
horrible visually.  But there's one exactly one thing that I WOULD do
with V6 if it was convenient - put a map in.

You know how all the big fantasy trilogies always have a map of the
world in the front?  That's what I'd use it for.  And I guess maybe for
big curling vines and stuff on title pages (I like title pages).

So yeah, come to think of it I would...

Joe


From sreed2@ix.netcom.com Thu Jun 19 17:14:49 MET DST 1997
Article: 26213 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news.mira.net.au!vic.news.telstra.net!act.news.telstra.net!news-out.internetmci.com!newsfeed.internetmci.com!feeder.chicago.cic.net!howland.erols.net!ix.netcom.com!nas-tn6-59.ix.netcom.com!user
From: sreed2@ix.netcom.com (Shawn L. Reed)
Newsgroups: rec.arts.int-fiction
Subject: Re: Stupid Question
Date: Wed, 18 Jun 1997 19:32:58 -0600
Organization: None
Lines: 36
Message-ID: <sreed2-1806971932590001@nas-tn6-59.ix.netcom.com>
References: <19970618035800.XAA06980@ladder02.news.aol.com> <ant181000f7fM+4%@gnelson.demon.co.uk>
NNTP-Posting-Host: nas-tn6-59.ix.netcom.com
X-NETCOM-Date: Wed Jun 18  7:26:42 PM CDT 1997
Xref: news.lth.se rec.arts.int-fiction:26213

In article <ant181000f7fM+4%@gnelson.demon.co.uk>, Graham Nelson
<graham@gnelson.demon.co.uk> wrote:

>> What's the cruelest puzzle in all IF, mewonders.

> Just what kind of utter sadist sets these puzzles, eh?  However,
> I nominate:
> 
>   The bees (Adventureland)


Playing Adventureland in my youth, I never had much trouble with the
bees.  It was that damn bear that plagued me.  Did anyone else have this
problem?  I swear my brain almost overloaded several nights trying to
think a way to get past him without feeding him the *HONEY*.   I believe I
finally hit on the solution (SCREAM)  not out of any brilliant insight
into how to scare the bear, but because I myself felt like screaming. 
Since then,  I have noticed I have a pathological tendency to type scream
whenever I come to a puzzle I cant solve.  This hasnt resulted in much
success to date, but at least many authors have humored me with a
cathartic scream response.  Some of my favorites:

-  Zork :          Aaaarrrrgggghhhh!

- Wearing the Claw:     AAAAAAAAAAAAAAAAAAAARRRRRRRRRRRRRRRGGGGGHHHHHHHHHHHHH

- Path to Fortune:
Ggggrrrrrrraaaaaaaaaaaaaaaaaaaaaaaaarrrrrrrrrgggggggghhhhhhhhhhh!!!!!!!

- MacWesleyan: Rrrrrraaaaaaaaaaaaaaagh

- I/O : Courtney Love youre not.     



-  Shawn


From graham@gnelson.demon.co.uk Mon Jun 23 09:29:10 MET DST 1997
Article: 26267 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!02-newsfeed.univie.ac.at!paladin.american.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: [Z-Machine] Development system
Date: Fri, 20 Jun 1997 19:45:41 +0100 (BST)
Organization: none
Message-ID: <ant201841868M+4%@gnelson.demon.co.uk>
References: <19970614185553594488@[10.0.2.15]> <ant161138868M+4%@gnelson.demon.co.uk> <19970620133207306691@[10.0.2.15]> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 85
Xref: news.lth.se rec.arts.int-fiction:26267

In article <19970620133207306691@[10.0.2.15]>, Christoffer Karlsson
<URL:mailto:c95chrka@und.ida.liu.se> wrote:
>
> [On Mr Karlsson's proposal to rename the Z-machine opcodes and
> rearrange its assembly syntax]
>
> The main differences (as compared to inform) are (the names aside):
>   * instructions taking stores are of the form "op args... -> r'
>     which is useful for the 'call' opcodes where
>       'call sp' is equivalent to 'call_1n' and
>       'call sp -> sp' to 'call_1s sp sp'

This is already done by Inform: the arrow is optional but
encouraged.  So no argument there.

>   * comma separation of operands (purely a matter of taste - doesn't 
>     txd use commas?)

If you like.  Would you mind making the commas optional?  After
all, they have semantic content.

>   * different op names for branch-if-true and branch-if-false forms of
>     branch instructions (eg. "jgt" [jump if greater than] is the same as
>     "jg" and "jle" [jump if less than or equal] is the same as "jg ~")

It seems to me that there are already 115 or so opcode names,
and this will greatly expand the number.  What is the negation
of, e.g., "piracy" to be called?  Or "get_sibling"?  Etc.

>   * for some operands I have changed the order of the operands for
>     improved consistency (this is probably a bad idea). Eg.
>     'pack a, z, n, s' is the same as 'encode_text a, n, s, z'.

I agree -- this is probably a bad idea!  Write a macro assembler
instead?

>   * intelligent assemblation of the call-instruction based on z version,
>     this removes the need of the suffixes to 'call' (although it might 
>     be needed to specify which form to use in some cases I fail to see 
>     why).

So here's why Inform doesn't do this.  Firstly, of course, if you
want an intelligent "call" instruction, you can just write a function
call in high-level code, since you're allowed to mix high and low
level code freely -- of course in a pure assembler this cannot be
true and you might indeed want a macro.

Secondly, some function calls can genuinely be achieved by more than
one opcode.  One of the main uses of Inform assembly language is to
generate test files for interpreters and the like, so it's a cardinal
principle that one should be able to generate any desired opcode,
not merely any desired semantic equivalent.

> Are these names [Infocom's internal opcode names] available somewhere?

I'm afraid not.

> If not would you please make them (if it is possible, of course)?

Sorry, but they're not mine to circulate.

> > _Please_ use the standard names.  Conforming to these agreements
> > always involves a small sacrifice to perfectionists like myself,
> > and I didn't get to call these opcodes exactly what I wanted
> > either -- but there is some gain.
> 
> Is it acceptable to use a proprietary format if the assembler
> understands the standard formats? Is it just the names or the format (~,
> ?, comma-separation issues) I should use? Is it possible to use some of
> the extensions above and in that case which?

There's nothing proprietory, but the whole strength of the Z-machine
is the solidity of the community which agrees about it.  If we didn't
cooperate on interpreters, debuggers, compilers, disassemblers, etc.
then it would be useless as a design.

Bear in mind, also, that everything currently written about the
Z-machine and assembly language uses the existing names.  Where are
your programmers going to find out what "pack" does?  Aren't they
going to be slightly annoyed that "encode_text", which they've
read about, doesn't seem to work?

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From adamc@acpub.duke.edu Mon Jun 23 10:04:38 MET DST 1997
Article: 26294 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!nntp.uio.no!news.maxwell.syr.edu!howland.erols.net!portc02.blue.aol.com!newsfeed.pitt.edu!news.duq.edu!newsgate.duke.edu!godzilla3.acpub.duke.edu!adamc
From: Adam Cadre <adamc@acpub.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Who is the author of an IF?
Date: Sun, 22 Jun 1997 06:55:39 -0400
Organization: Duke University, Durham, NC, USA
Lines: 77
Message-ID: <Pine.SOL.3.91.970622045847.7111A-100000@godzilla3.acpub.duke.edu>
NNTP-Posting-Host: godzilla3.acpub.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <01bc7de2$13035e40$04e2fcce@default> 
Xref: news.lth.se rec.arts.int-fiction:26294

Gnimish wrote:

> For you who write text adventure games--do you feel that you are--at
> some level--solely responsible for the player's experience in your
> fictive world?  Or do you merely act as a sort of designer/architect
> who puts up the framework which survives or fails based on the 
> ability of your player to imagine what you wish to show him or her?

I had to go to traffic school once, and at one point we each had to come
up with our pet peeves about traffic.  We each gave one, and then the
teacher said, "I have two.  I hate it when people dawdle in a crosswalk,
and I hate it when people rush me when I'm trying to cross the street."
The point, of course, is that you can be wonderfully inconsistent.  As
a writer, I hate it when people misinterpret my stuff.  As a reader, I
hate it when people challenge my interpretation -- the author included.

That said, I have to come down on the reader's/player's side here.  An
author can never be "solely responsible" for the reading experience, even
if we're talking about something as non-interactive as a novel.  Everyone
brings a unique life to a work that colors the experience of that work.
And I'd also submit that in the overwhelming majority of cases, what is
characterized here as a failure of the reader to imagine the world of the
work is actually a failure on the part of the =writer=: if you're so
solipsistic as to leave a reasonably intelligent reader hopelessly
confused as to what is going on, you're the one at fault.

> For you who play--do you play to solve puzzles and conquer evil (or good)?

Heavens, no.  I'm no good at puzzles.  I have too many problems in my life
to have any inclination to solve other problems for entertainment.  I
usually play with a walkthrough and deviate from it when it seems like
it'd be fun to do so.

> Or perhaps to live for a short period of time in someone else's mind?

There you go.  Well phrased.  Of course, this is also why I enjoy
conventional fiction.  What I specifically like about interactive
fiction is the ability to tweak the story and see what happens,
and especially to tweak it in different ways at a single point and
see different things happen.  A good story is always appreciated, but
for IF I prefer a palimpsest of stories -- get too linear and the only
advantage to writing a ractive rather than a novel is the player's
sense of actually inhabiting the space.  ("Lost New York" is an example
of this -- the sense of walking around the space of different New
Yorks justifies what might otherwise be a case of one hell of a novel
stuck in the wrong medium.)

> Is it possible to truly enjoy a game whose plotline you are unable to
> further or understand?

The furthering part isn't a problem for me, since I use walkthroughs.
I think I already covered the understanding part.  I think people should
strive to make their work as easy to understand as possible without
unduly sacrificing other virtues.  Sometimes a work is difficult because
the thoughts it's trying to convey are hard to think.  That's fine.  Other
times a work is difficult because the author thinks that difficulty itself
is a virtue.  It ain't.

> I am gathering information to argue which computer-based form of entertain-
> ment comes the closest to "living":  muds, IFs, or huge multiplayer (and 
> graphically interfaced) games such as Ultima On-line.  There has got to be
> something greater for the future of computer games than flashier
> shoot'em-ups and fancy combat/flight emulators.

Here's a data point, if not an answer: as a regular on ifMUD (hell, close
to a constant on ifMUD), I can say that my interest in hanging out and
talking to folks is much much greater than in exploring and solving puzzles.
In IF, I'm more interested in exploring, but mainly because there aren't
any people to talk to (except to the extent that interacting with the game
is a conversation with the author.)  Which is closer to living sorta depends
on whether you're the type of person who wanders around doing things or
the kind that doesn't wander much and doesn't do much but talks and talks
and talks.  This is not an invidious choice.

  -----
 Adam Cadre, Durham, NC
 http://www.duke.edu/~adamc


From erkyrath@netcom.com Mon Jun 23 10:05:03 MET DST 1997
Article: 26308 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!sn.no!uninett.no!stdio!zdc-e!super.zippo.com!feed1.news.erols.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Who is the author of an IF?
Message-ID: <erkyrathEC6sBI.EJy@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <Pine.SOL.3.91.970622045847.7111A-100000@godzilla3.acpub.duke.edu>
Date: Sun, 22 Jun 1997 16:54:53 GMT
Lines: 34
Sender: erkyrath@netcom7.netcom.com
Xref: news.lth.se rec.arts.int-fiction:26308

> Gnimish wrote:

> For you who write text adventure games--do you feel that you are--at
> some level--solely responsible for the player's experience in your
> fictive world?  Or do you merely act as a sort of designer/architect
> who puts up the framework which survives or fails based on the 
> ability of your player to imagine what you wish to show him or her?

The latter. I did everything right, and if it doesn't work, it's the
player's fault, not mine. I can even prove it -- the game worked for
*other* players, didn't it? 

Heh.

Seriously, no work of art works for everybody. The universality of art is
a myth. To "get it" is necessarily going to require particular skills
(gained by experience), some kind of shared background or culture, and
common interest. This is as true of IF as it is of painting or poetry or
science fiction novels. It's nobody's fault when a particular work and a
particular audience don't match. 

(Hm. That said, let me add that your example -- "the ability of the player
to imagine what you wish to show him" -- isn't all that critical. It's a
concern, particularly when the work is in a genre convention (SF or high
fantasy or whatever) but I don't think it's the primary failure mode. The
trick is getting the reader/player to *care*, and to *want* to visualize
the situation.)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From mkkuhner@phylo.genetics.washington.edu Mon Jun 23 10:06:08 MET DST 1997
Article: 26268 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!bloom-beacon.mit.edu!newsfeed.internetmci.com!dciteleport.com!europa.clark.net!news.msfc.nasa.gov!bcm.tmc.edu!rice!uw-beaver!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: "Bringing Characters To Life"
Date: 20 Jun 1997 17:45:28 GMT
Organization: University of Washington, Seattle
Lines: 53
Distribution: world
Message-ID: <5oefjo$ppm@nntp5.u.washington.edu>
References: <qLYOnAAwzrpzEwp9@highmount.demon.co.uk> <cx0jpDAMFRqzEwV4@highmount.demon.co.uk>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:26268

In article <cx0jpDAMFRqzEwV4@highmount.demon.co.uk> Neil Brown <neil@highmount.demon.co.uk> writes:

>I ask all this because I've built the foundations of a game that is
>intended to be heavily NPC-oriented, and now I have to decide whether to
>build in and pre-program all the behaviour (eg move character to room x
>by turn 3, say q and then move to room y) or provide a large number of
>possible behaviours based on certain motivation factors and let the NPCs
>get on with it themselves. The pre-program method seems too much like
>forcing a story to happen rather than letting it progress naturally, but
>it would be the easier of the two to code.

To what extent will the player be able to tell the difference?

NPC behavioral complexity that is opaque to the player is a waste of
coding effort (unless you enjoy coding it for its own sake), so you
need to take a player's-eye look at the game and see where the extra
coding might actually make a difference.  For example, someone earlier
mentioned an NPC who did something different on his birthday.  Unless
the player can find out why the NPC did something different (birthday
card, conversation, seeing him at the party) it's just going to seem
like random behavior, and might as well have been.

You will be in for a horrid testing effort trying to find out if
the game is winnable, if you let NPC motivations bouncing off each
other have much role in the plotline.  You could easily make the
mistake seen in the vidgame "XCOM II" where the game is sometimes 
winnable and sometimes not, depending on a random roll early on.

If your plotline is at all linear, you probably want to pre-program;
behavior models will lend themselves better to a very loose, non-
directional plotline.  You might look at "Trust and Betrayal" if
you can find it; it goes much further in this direction than any
IF I know, and shows strengths and weaknesses of the attempt.
You can spend a *long* time in T&B trying to out-sweettalk the NPCs,
and having your efforts undercut by what's going on among them.
Progress is often frustratingly slow.  And, though the designer tried
to put in specific plot events, they jar with the rest of the game
since it's hard for the player to talk to the NPC about "that alarming
thing that happened last night."

You may have trouble getting decent NPC dialog if it has to link to
NPC mental states you can't predict in advance, since you can't write
a natural-language conversation generator for the game....

In other words, I'm pessimistic that heavy attention to behavioral
models will help.  I'd keep it simple, but try to make your
pre-programming *look* like a behavioral model by catching some of
the appropriate branches and allowing for them explicitly.

Then again, I'm seriously thinking about killing off some NPCs in
my current game; too bloody much code!  So maybe I'm just a wimp.

Mary Kuhner mkkuhner@genetics.washington.edu


From mkkuhner@phylo.genetics.washington.edu Mon Jun 23 10:07:19 MET DST 1997
Article: 26302 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!bloom-beacon.mit.edu!gatech!news.cse.psu.edu!uwm.edu!vixen.cso.uiuc.edu!howland.erols.net!newsfeed.internetmci.com!in1.uu.net!140.142.64.3!news.u.washington.edu!phylo.genetics.washington.edu!mkkuhner
From: mkkuhner@phylo.genetics.washington.edu (Mary K. Kuhner)
Newsgroups: rec.arts.int-fiction
Subject: Re: "Bringing Characters To Life"
Date: 22 Jun 1997 05:40:55 GMT
Organization: University of Washington, Seattle
Lines: 30
Message-ID: <5oidt7$rlq@nntp5.u.washington.edu>
References: <5oefjo$ppm@nntp5.u.washington.edu> <6pZq$EA7i5qzEwxK@highmount.demon.co.uk> <5ohn7j$af0@staff.cs.su.oz.au>
NNTP-Posting-Host: phylo.genetics.washington.edu
Xref: news.lth.se rec.arts.int-fiction:26302

In article <5ohn7j$af0@staff.cs.su.oz.au> srn@fn.com.au writes:
>This discussion brings up an interesting (well, to me) question. How
>much code do NPCs take? I mean someone like the chap with the parrot in
>Christminster.  I've just started playing with inform, and I can well
>imagine having literally thousands of lines of code for an NPC...

>	Stephen

Thousands of lines of code.  More than anything else.  Especially if
they are not limited to just one scene--for example, in the game I'm
currently working with, early on an NPC won't talk about X or Y (she
is keeping them secret from the PC) but will talk about the current
puzzle.  Later, when X and Y have been revealed, she will talk about
them but no longer cares about the first puzzle.  Still later, after
X has been dealt with, she is mainly interested in Y.  It is easy to
end up with five to ten different states for even a simple NPC, each
of which has mostly its own set of responses to actions and questions.

I tried coding a bargaining scene--whoof.

I'm curious myself--in games like Christminster or Jigsaw where an
NPC appears in several distinct scenes, is it usual to code the NPC
as one object or several?  I've tried both and I'm still not sure
which works best.  The single-object approach makes for huge
confusing player-objects.  The multiple-object approach leads to
weird little bugs like "Which Grandmother do you mean?" as
a response to "Who is Grandmother?" (done with scope=All in
Inform) and makes inventory and so forth tricky.

Mary Kuhner mkkuhner@genetics.washington.edu


From s590501@tfh-berlin.de Mon Jun 23 10:07:37 MET DST 1997
Article: 26303 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!feed1.news.erols.com!newsfeed.nacamar.de!fu-berlin.de!zrz.TU-Berlin.DE!tfh-berlin.de!news
From: Miron Schmidt <s590501@tfh-berlin.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: "Bringing Characters To Life" [mild Christminster spoilers]
Date: 22 Jun 97 16:11:33 +0200
Organization: TFH Berlin via PPP
Lines: 26
Message-ID: <33AD4EB4.MD-0.193.s590501@tfh-berlin.de>
References: <5ohn7j$af0@staff.cs.su.oz.au>
NNTP-Posting-Host: dip8085.tfh-berlin.de
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: MicroDot-II/AmigaOS 0.193
Xref: news.lth.se rec.arts.int-fiction:26303

Stephen Robert Norris <srn@psrg.cs.usyd.edu.au> wrote:

> This discussion brings up an interesting (well, to me) question. How
> much code do NPCs take? I mean someone like the chap with the parrot in
> Christminster.

The chap with the parrot takes up around 600 lines, plus a couple of special
routines all NPCs in _Christminster_ use. His name is Edward, by the way.

Also keep in mind that Edward is a very well-develeoped character in a very
large game. A good deal of his code go into situation-dependent actions, such
as being in the same room when one tries to read the bible, etc.

As for well-developed characters in moderate-sized games:

Christopher Robin from _Ralph_ has ~250 lines in the current release (6).
One of the prominent characters in my upcoming competition game has ~100
lines at the moment, with about half his conversational skills, a third of
his general reactions, and none of his puzzle-specific code finished.


--
Miron Schmidt <miron@comports.com>                       PGP key on request

WATCH TV... MARRY AND REPRODUCE... OBEY... PLAY INTERACTIVE FICTION...



From wolf@one.net Wed Jun 25 21:26:01 MET DST 1997
Article: 26348 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!news-lond.gsl.net!news.gsl.net!news-dc.gsl.net!news.gsl.net!news-fw.gsl.net!news.gsl.net!news-peer.gsl.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!newsfeed.one.net!news.one.net!not-for-mail
From: wolf@one.net
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Tue, 24 Jun 1997 12:19:33 GMT
Organization: OneNet Communications, Inc. News Server
Lines: 21
Message-ID: <33b0b98d.10802576@news.one.net>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: port-27-8.access.one.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent 1.0/32.390
Xref: news.lth.se rec.arts.int-fiction:26348


Hi Miron,

Miron Schmidt <s590501@tfh-berlin.de> wrote:

>I have always wondered what the average age of the r.a.i-f community is.
> ...
>From what I've heard, most of us are around my own age, give or take. So may
>I make a start.
>I'm 25: 26 in two weeks (hey, if anyone happens to be in Berlin at the time,

I'm 37, first ran into IF with the granddaddy of them all--the Fortran
version of Advent running on a DEC PDP-11 when the game was still
distributed on paper tape, which was probably back in 1976 - 1977.

The perfect game to play on those nifty new CRT terminals...

Respectfully,

Wolf (starting to grey around the muzzle)



From erkyrath@netcom.com Wed Jun 25 21:26:09 MET DST 1997
Article: 26349 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Age?
Message-ID: <erkyrathECALsK.G57@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <33afff33.6364250@news.u.washington.edu>
Date: Tue, 24 Jun 1997 18:24:20 GMT
Lines: 23
Sender: erkyrath@netcom.netcom.com
Xref: news.lth.se rec.arts.int-fiction:26349

Matthew Amster-Burton (mamster@u.washington.edu) wrote:
> Miron Schmidt <s590501@tfh-berlin.de> wrote:

> >I have always wondered what the average age of the r.a.i-f community is.
> >Now, I understand that most of us have to be old enough to have experienced
> >the old magic when it was still fresh. At this age, it starts to be
> >considered rude to ask for details.
> >Nevertheless, I _have_ wondered.

> As Neil D. put it, I'm far too young to remember Watergate.  In fact,
> I was born over a year after Nixon resigned.

Obfuscation, obfuscation... I'm 27. 

In the spirit of prying, I'll point out that in the "About the Author" 
section of Jigsaw, Graham admitted to having been born in 1968.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From jfrancis@dungeon.engr.sgi.com Wed Jun 25 21:26:22 MET DST 1997
Article: 26333 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!neru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!feeder.chicago.cic.net!chi-news.cic.net!EU.net!enews.sgi.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 24 Jun 1997 18:59:56 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 25
Message-ID: <5op5fc$7rf@fido.asd.sgi.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <33afff33.6364250@news.u.washington.edu> <erkyrathECALsK.G57@netcom.com>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.arts.int-fiction:26333

In article <erkyrathECALsK.G57@netcom.com>,
Andrew Plotkin <erkyrath@netcom.com> wrote:
>Matthew Amster-Burton (mamster@u.washington.edu) wrote:
>> Miron Schmidt <s590501@tfh-berlin.de> wrote:
>
>> >I have always wondered what the average age of the r.a.i-f community is.
>> >Now, I understand that most of us have to be old enough to have experienced
>> >the old magic when it was still fresh. At this age, it starts to be
>> >considered rude to ask for details.
>> >Nevertheless, I _have_ wondered.
>
>> As Neil D. put it, I'm far too young to remember Watergate.  In fact,
>> I was born over a year after Nixon resigned.
>
>Obfuscation, obfuscation... I'm 27. 
>
When I was 27, IF consisted of ADVENT.   In FORTRAN.
The first release of ZORK was a year away.

(To save you time searching the history files, that makes me 48)
-- 
John Francis  jfrancis@sgi.com       Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 43U-991
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From jholder@deimos.frii.com Wed Jun 25 21:27:09 MET DST 1997
Article: 26342 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!psinntp!howland.erols.net!news.maxwell.syr.edu!newsfeed.wli.net!frii.com!deimos.frii.com!jholder
From: jholder@deimos.frii.com (J. Holder)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 24 Jun 1997 19:26:49 GMT
Organization: Front Range Internet, Inc.
Lines: 26
Message-ID: <5op71p$6js$2@europa.frii.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: deimos.frii.com
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:26342

In a fit of lunacy, Miron Schmidt (s590501@tfh-berlin.de) escribed:
: From what I've heard, most of us are around my own age, give or take. So may
: I make a start.
: I'm 25: 26 in two weeks (hey, if anyone happens to be in Berlin at the time,
: you're invited to my birthday party :)).

I'm 26, 27 in August.  Sorry I won't be in Berlin... :(

: WATCH TV... MARRY AND REPRODUCE... OBEY... PLAY INTERACTIVE FICTION...

> WATCH TV

You are watching an inane program called "Married with Children"

> MARRY AND REPRODUCE

After watching that show, you decide against it.

> PLAY INTERACTIVE FICTION

You whip out a copy of I-0, and have some fun!

--
John Holder (jholder@frii.com) /\            http://www.frii.com/~jholder/
UNIX Specialist, Paranet Inc. <--> Raytracing|Fractals|Interactive Fiction
http://www.paranet.com/        \/           Homebrewing|Strange Attractors


From patrick@syix.com Wed Jun 25 21:30:42 MET DST 1997
Article: 26354 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.algonet.se!news.maxwell.syr.edu!syix.com!not-for-mail
From: patrick@syix.com (Patrick Kellum)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 25 Jun 1997 08:54:54 GMT
Organization: Pup-Tek Software International
Lines: 23
Message-ID: <5oqmcu$2ne$1@neko.syix.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: ns1.syix.com
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.arts.int-fiction:26354

[I would quote, but as usual I never recived the orignal post, it'll show
up next month (not kidding)]

Well, I'm an old fart, being 26 I'm the oldest of all my friends which
really makes me feel real old sometimes.

My start in IF was a pirated copy of Zork III for the Apple IIe givin to
me and my classmates by my computer teacher (he also gave us each a copy
of Strip Poker ;-)  Ahhh, I miss being 15.

I didn't really get totally hooked until I started a BBS and found out I
could use text adventures as on-line games.  After playing them for hours
I became hooked. 

Patrick
---

"Every weekday morning the school bell cast its glamour over the
 surounding hills, calling the young to classes.  They came running
 down the slopes and leaping over the streams, out from caves and the
 hollows of trees and suburban tract homes, impelled by powers greater
 then their own to gain an education." 
    "The Iron Dragon's Daughter" by Michael Swanwick


From sgranade@phy.duke.edu Wed Jun 25 21:30:51 MET DST 1997
Article: 26350 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!mn6.swip.net!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!gatech!newsfeed.pitt.edu!news.duq.edu!newsgate.duke.edu!nebula.phy.duke.edu!sgranade
From: Stephen Granade <sgranade@phy.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Wed, 25 Jun 1997 08:46:52 -0400
Organization: Duke University, Durham, NC, USA
Lines: 15
Message-ID: <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: nebula.phy.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <33B00B17.MD-0.193.s590501@tfh-berlin.de> 
Xref: news.lth.se rec.arts.int-fiction:26350

On 24 Jun 1997, Miron Schmidt wrote:

> I have always wondered what the average age of the r.a.i-f community is.

I'm 24. I don't know what the average age is, but I could guess:

73.

Stephen

--
  Stephen Granade                | "It takes character to withstand the
  sgranade@phy.duke.edu          |  rigors of indolence."
  Duke University, Physics Dept  |    -- from _The Madness of King George_



From sgranade@phy.duke.edu Wed Jun 25 21:31:10 MET DST 1997
Article: 26350 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!mn6.swip.net!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!gatech!newsfeed.pitt.edu!news.duq.edu!newsgate.duke.edu!nebula.phy.duke.edu!sgranade
From: Stephen Granade <sgranade@phy.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Wed, 25 Jun 1997 08:46:52 -0400
Organization: Duke University, Durham, NC, USA
Lines: 15
Message-ID: <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: nebula.phy.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <33B00B17.MD-0.193.s590501@tfh-berlin.de> 
Xref: news.lth.se rec.arts.int-fiction:26350

On 24 Jun 1997, Miron Schmidt wrote:

> I have always wondered what the average age of the r.a.i-f community is.

I'm 24. I don't know what the average age is, but I could guess:

73.

Stephen

--
  Stephen Granade                | "It takes character to withstand the
  sgranade@phy.duke.edu          |  rigors of indolence."
  Duke University, Physics Dept  |    -- from _The Madness of King George_



From mordacai@aol.com Wed Jun 25 21:32:33 MET DST 1997
Article: 26355 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!newsfeed.nacamar.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!portc01.blue.aol.com!audrey01.news.aol.com!not-for-mail
From: mordacai@aol.com (Mordacai)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 25 Jun 1997 16:45:33 GMT
Lines: 16
Message-ID: <19970625164501.MAA20256@ladder01.news.aol.com>
NNTP-Posting-Host: ladder01.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
References: <33b04ca9.1254816@hermes.rdrop.com>
Xref: news.lth.se rec.arts.int-fiction:26355

I would appear to be one of the young ones in this group, at 17.  This is
an interesting situation in that, frankly, it's a good age for computer
gamers, so I've played a lot of the current graphic games as well as i-f,
and I've learned from both.  My first connection with i-f was in fifth
grade when my teacher (Mrs. Martinez, who I still claim was the best
teacher I ever had) got a group of us together in the ancient computer lab
and gave us Zork.  We went wild, and, from that day on I've loved i-f and
have wanted to write a piece of my own.  I admit, being one of the
youngest here, I'm a little intimidated; I've sunk about 40 work hours
into my little game so far and am hoping it'll be able to stand on it's
own out there in the cold, harsh world ;)

Ian 
mordacai@ix.netcom.com
     "I'm more of a man than you'll ever be and more of a woman than
you'll ever get." -Angel, RENT


From jmacb@medusa.u-net.com Thu Jun 26 09:36:34 MET DST 1997
Article: 26362 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!news.uni-c.dk!hunter.premier.net!feed1.news.erols.com!newsfeed.internetmci.com!in1.uu.net!194.119.128.129!news.u-net.com!not-for-mail
From: jmacb@medusa.u-net.com (Jim MacBrayne)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Wed, 25 Jun 1997 17:25:40 GMT
Organization: U-NET Ltd
Lines: 23
Message-ID: <33b45469.39991532@news.u-net.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <33b0b98d.10802576@news.one.net>
Reply-To: jmacb@medusa.u-net.com
NNTP-Posting-Host: medusa.u-net.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent 1.0/32.390
Xref: news.lth.se rec.arts.int-fiction:26362

>>I have always wondered what the average age of the r.a.i-f community is.
>> ...
>>From what I've heard, most of us are around my own age, give or take. So may
>>I make a start.
>>I'm 25: 26 in two weeks (hey, if anyone happens to be in Berlin at the time,

Funnily enough, I've often wondered about this as well but didn't have
the brass neck to make the posting. I'm pretty much of an occasional
lurker here only.

Equally funnily enough, most of the ages I've seen tie in pretty well
exactly with what I'd imagined.

I'm 54, so that makes me the grandaddy of you all!

Jim

-----------------------------------------
Jim MacBrayne
jmacb@medusa.u-net.com
http://www.medusa.u-net.com/jmacb.htm
CIS 100411,461
-----------------------------------------


From russotto@wanda.vf.pond.com Thu Jun 26 09:36:48 MET DST 1997
Article: 26373 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!hunter.premier.net!europa.clark.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!198.69.82.4!news.pond.com!wanda.vf.pond.com!not-for-mail
From: russotto@wanda.vf.pond.com (Matthew T. Russotto)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 24 Jun 1997 23:13:34 -0400
Organization: Ghotinet
Lines: 23
Message-ID: <5oq2cu$q3a@wanda.vf.pond.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <33afff33.6364250@news.u.washington.edu>
NNTP-Posting-Host: 198.69.82.2
Xref: news.lth.se rec.arts.int-fiction:26373

In article <33afff33.6364250@news.u.washington.edu>,
Matthew Amster-Burton <mamster@u.washington.edu> wrote:
}Miron Schmidt <s590501@tfh-berlin.de> wrote:
}
}>I have always wondered what the average age of the r.a.i-f community is.
}>Now, I understand that most of us have to be old enough to have experienced
}>the old magic when it was still fresh. At this age, it starts to be
}>considered rude to ask for details.
}>Nevertheless, I _have_ wondered.
}
}As Neil D. put it, I'm far too young to remember Watergate.  In fact,
}I was born over a year after Nixon resigned.

Ack, a young'un!

I'm old enough to remember playing "Star Trek" on a state-of-the-art
printing terminal connected to an acoustic coupler.  I think I saw
"Adventure" on that terminal too, but I didn't really get into it
until I got an Apple ][ with the Microsoft version.
-- 
Matthew T. Russotto                                russotto@pond.com
"Extremism in defense of liberty is no vice, and moderation in pursuit
of justice is no virtue." 


From graham@gnelson.demon.co.uk Thu Jun 26 09:37:10 MET DST 1997
Article: 26365 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!seunet!mn7.swip.net!nys.stupi.se!netnews.com!howland.erols.net!europa.clark.net!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Wed, 25 Jun 1997 18:56:47 +0100 (BST)
Organization: none
Message-ID: <ant2517470b0M+4%@gnelson.demon.co.uk>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <CaxQRAAQQBszEwE2@elvw.demon.co.uk> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=ISO-8859-1
X-Newsreader: ANT RISCOS Marcel [ver 1.09]
Lines: 10
Xref: news.lth.se rec.arts.int-fiction:26365

Miron Schmidt <s590501@tfh-berlin.de> asks
>I have always wondered what the average age of the r.a.i-f community is.

29.  Actually, I just got an award which is only available to
people under 30, with a feeling of being just in the nick of
time.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From ddyte@vaxc.cc.monash.edu.au Thu Jun 26 09:37:24 MET DST 1997
Article: 26374 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!news-penn.gsl.net!news.gsl.net!news-fw.gsl.net!news.gsl.net!news-dc.gsl.net!news.gsl.net!news.belnet.be!skynet.be!news.interpac.be!uunet!in1.uu.net!141.211.144.13!newsxfer3.itd.umich.edu!news.maxwell.syr.edu!pumpkin.pangea.ca!news.mira.net.au!news.netspace.net.au!news.mel.connect.com.au!harbinger.cc.monash.edu.au!vaxc.cc.monash.edu.au!ddyte
From: ddyte@vaxc.cc.monash.edu.au (David Dyte)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 97 08:53:03 +1000
Organization: Computer Centre, Monash University, Australia
Lines: 16
Message-ID: <1997Jun26.085303@vaxc.cc.monash.edu.au>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu>
NNTP-Posting-Host: vaxc.cc.monash.edu.au
Xref: news.lth.se rec.arts.int-fiction:26374

Miron Schmidt wanted to know how old we are:

28. In 1982 I played Dungeon at school on a PDP-11 and was addicted
pretty much immediately. Mind you, I was also addicted to Super Star Trek.

At a new school the next year, a friend of mine (who shall remain
nameless but will read this post) acted as computer while I played
Scott Adams adventures he had memorised, during a stunningly dull
hiking camp.

Once I got my Vic 20, well I already knew how to solve Adventureland,
and things went from there...  

- David Dyte




From rsimpson@access4.digex.net Thu Jun 26 09:37:38 MET DST 1997
Article: 26386 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!mn6.swip.net!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!howland.erols.net!news2.digex.net!access4.digex.net!not-for-mail
From: rsimpson@access4.digex.net (This is a test)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 25 Jun 1997 23:13:20 GMT
Organization: Express Access Online Communications, Greenbelt, MD USA
Lines: 9
Message-ID: <5os8mg$1c4$1@news2.digex.net>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu> <5orbg7$egr$1@europa.frii.com>
NNTP-Posting-Host: access4.digex.net
PSA: Call Crunchland 703-765-6885
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.arts.int-fiction:26386

J. Holder (jholder@deimos.frii.com) wrote:

: My first experience with IF was at a family day at my father's workplace,
: Los Alamos National Labs, in 1978.  I sat down in front of a high-tech
: green screen (next to a few old teletypes) and played Crowther & Woods
: "Adventure" on some old DEC platform.  I was a ripe eight years old.

I remember going to my father's workplace and having to play *Yahtzee*. I
bet your dad could beat up my dad, too. I'm 26.


From jfrancis@dungeon.engr.sgi.com Thu Jun 26 12:07:52 MET DST 1997
Article: 26363 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!howland.erols.net!feeder.chicago.cic.net!EU.net!enews.sgi.com!fido.asd.sgi.com!dungeon.engr.sgi.com!jfrancis
From: jfrancis@dungeon.engr.sgi.com (John Francis)
Newsgroups: rec.arts.int-fiction
Subject: Re: Speaking of New Z-mac
Date: 24 Jun 1997 17:41:22 GMT
Organization: Silicon Graphics, Inc., Mountain View, CA
Lines: 32
Message-ID: <5op0s2$8uh@fido.asd.sgi.com>
References: <5o704v$1d6$2@europa.frii.com> <66.9756.1727@tabb.com> <33AAA777.56B9@earthweb.com>
NNTP-Posting-Host: dungeon.engr.sgi.com
Xref: news.lth.se rec.arts.int-fiction:26363

In article <33AAA777.56B9@earthweb.com>,
Carl Muckenhoupt  <carl@earthweb.com> wrote:
>About TIFF: If my understanding is correct (and I urge the TIFF
>proponents to clarify this matter), TIFF files can store their data raw
>or compressed.  When raw, the same objection applies as to BMP: big
>waste of space.  When compressed, they use LZW compression, and thus we
>get the same legal complications as with GIF: the interpreter writers
>would need to pay a licensing fee to Unisys or face possible lawsuits.

Two points. First, Unisys have stated that they don't intend to go after
viewers, just commercial content providers.  So it wouldn't be the
interpreter writer (or user) that had the problem - it would be the game
author, if anyone. I doubt if Unisys would seek large $$$ amounts from
a freeware game author.  That's just my opinion, of course. And Unisys
could change their policy at any time.  And even if I am right there is
a certain amount of hassle involved in getting official clearance.

Secondly, the currently available freeware TIFF libraries support pkzip-
style compression (just like PNG).  Unfortunately support for this is
even less widely available in commercial image manipulation packages
than is support for PNG.

So for either format, it would often still be necessary to provide a
program to convert from the image manipulation program of choice to
the canonical format supported by the interpreters.

[See my comments on adding images, submitted as a separate posting]
-- 
John Francis  jfrancis@sgi.com       Silicon Graphics, Inc.
(415)933-8295                        2011 N. Shoreline Blvd. MS 43U-991
(415)933-4692 (Fax)                  Mountain View, CA   94043-1389
Unsolicited electronic mail will be subject to a $100 handling fee.


From s590501@tfh-berlin.de Thu Jun 26 15:37:16 MET DST 1997
Article: 26397 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!bloom-beacon.mit.edu!spool.mu.edu!sol.net!spool.mu.edu!newsspool.sol.net!howland.erols.net!newsfeed.nacamar.de!fu-berlin.de!dip8085.tfh-berlin.DE!miron
From: Miron Schmidt <s590501@tfh-berlin.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 97 06:23:43 +0200
Organization: TFH Berlin via PPP
Lines: 40
Message-ID: <33B20AEE.MD-0.193.s590501@tfh-berlin.de>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: dip8085.tfh-berlin.de (141.64.108.85)
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
NNTP-Posting-User: miron
X-Access: 16 1054 1055
X-Newsreader: MicroDot-II/AmigaOS 0.193
Xref: news.lth.se rec.arts.int-fiction:26397

I myself wrote:
> I have always wondered what the average age of the r.a.i-f community is.

Wow. That's far more answers than I would have expected. Lots of lurkers,
too.
I hope it doesn't disappoint anyone too much if I admit that I only really
wanted to test my new news server and didn't know what to write. :)

The average age seems to be a trifle higher than I thought; more thirty-ish
then twenty-five-ish. I'll make a small anonymous statistic when the thread
has died.

OK, so many people also gave a little personal IF history. Here's mine then.

The first adventure I played was Zork I on a C-64 around 1983. I was
instantly hooked, although I didn't quite grasp the concept of solving
puzzles then. It was the atmosphere that had me squirming in my seat.
After that, Zork II, Adventureland, The Count, The Masquerade.

Lots of adventures on the Apple II, which was the time I first actually
_solved_ a game (Back in Time, anyone remember that?).

I started to write my own somewhere around 1987, 88, using AmigaBASIC. My
parser sucked so bad that I soon dropped it, desperately looking for a
programmer to write around my stories.
Those problems got solved when I discovered ADL, and I started lots of games.
Finished only one, though: a birthday-present for a close friend. You may
have noticed that Ralph claims to be my 10th project, and so it is. The other
publically available is Dark Army (project 005), meant solely as a
programming example in ADL, as it is still unfinished.

Anyway, thanks for your enthusiastic responses (I have really seen worse
waste of bandwidth); I'm looking forward for the postings yet to come.


--
Miron Schmidt <miron@comports.com>                       PGP key on request

WATCH TV... MARRY AND REPRODUCE... OBEY... PLAY INTERACTIVE FICTION...



From s590501@tfh-berlin.de Thu Jun 26 15:41:44 MET DST 1997
Article: 26399 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeeds.sol.net!europa.clark.net!newsfeed.nacamar.de!fu-berlin.de!dip8085.tfh-berlin.DE!miron
From: Miron Schmidt <s590501@tfh-berlin.de>
Newsgroups: rec.arts.int-fiction
Subject: Age?
Date: 24 Jun 97 17:59:51 +0200
Organization: TFH Berlin via PPP
Lines: 22
Message-ID: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: dip8085.tfh-berlin.de (141.64.108.85)
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
NNTP-Posting-User: miron
X-Access: 16 1054 1055
X-Newsreader: MicroDot-II/AmigaOS 0.193
Xref: news.lth.se rec.arts.int-fiction:26399

Hi!

I have always wondered what the average age of the r.a.i-f community is.
Now, I understand that most of us have to be old enough to have experienced
the old magic when it was still fresh. At this age, it starts to be
considered rude to ask for details.
Nevertheless, I _have_ wondered.
>From what I've heard, most of us are around my own age, give or take. So may
I make a start.
I'm 25: 26 in two weeks (hey, if anyone happens to be in Berlin at the time,
you're invited to my birthday party :)).

Any volunteers?




--
Miron Schmidt <miron@comports.com>                       PGP key on request

WATCH TV... MARRY AND REPRODUCE... OBEY... PLAY INTERACTIVE FICTION...



From rlanger@tiac.net Thu Jun 26 20:36:12 MET DST 1997
Article: 26411 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!europa.clark.net!howland.erols.net!cpk-news-hub1.bbnplanet.com!cam-news-hub1.bbnplanet.com!news.bbnplanet.com!news-feed1.tiac.net!posterchild!news@tiac.net
From: Rick Langer <rlanger@tiac.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Thu, 26 Jun 1997 13:34:56 -0400
Organization: TCC - Transcontinental Computer Consulting
Lines: 19
Message-ID: <33B2A840.1F65@tiac.net>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <CaxQRAAQQBszEwE2@elvw.demon.co.uk>
NNTP-Posting-Host: p3.gw1.littl.ma.tiac.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.01Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:26411

Miron Schmidt <s590501@tfh-berlin.de> wrote:
>I have always wondered what the average age of the r.a.i-f community is.

I seem to be toward the upper end of the scale at 40.

>Ask old guy about adventure games

The old geezer says, "Well... I remember getting hooked on 'puters in
'77, programming a Cyber 70. Went nuts when I discovered Adventure.
First system I bought was an Apple ][ Plus (black case, marked as Bell &
Howell). Had to settle with Super Star Trek -- in those days we typed in
our own code -- and Wizardry until they wrote Zork. Yeah, Infocom's
heyday ... things were good back then. Glad to see you young 'uns know a
good thing when you see it. Nelson's a wonder for givin' us Inform ..."

He continues to mumble incoherently as you tip-toe away.
-- 
   Rick Langer (rlanger@tiac.net)
   TCC - Transcontinental Computer Consulting


From wsherman@ncsa.uiuc.edu Thu Jun 26 20:36:53 MET DST 1997
Article: 26406 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!news.maxwell.syr.edu!ais.net!vixen.cso.uiuc.edu!wsherman
From: wsherman@ncsa.uiuc.edu (William R Sherman)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 1997 03:51:28 GMT
Organization: National Center for Supercomputing Applications
Lines: 70
Message-ID: <5osp00$fu1$1@vixen.cso.uiuc.edu>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: rodin.ncsa.uiuc.edu
X-newsreader: xrn 7.04-beta-14
Xref: news.lth.se rec.arts.int-fiction:26406

In article <...>, Miron Schmidt <s590501@tfh-berlin.de> writes:
> Hi!
[snip]
> 
> Any volunteers?

Odd that you bring that up now, since it's also a major thread
in another newsgroup that I read -- must be something in the air.

> Miron Schmidt <miron@comports.com>                       PGP key on request

As for me: 33.  Which puts me at the age just before the home
computer revolution took off, so when I went to school, I was
basically the only kid playing with computers, and everyone
was amazed that a kid could understand how to use computers.
When my high-school decided to add a programming class (my
senior year), they didn't want me to take it since I knew more
than the math teacher who would be teaching the course -- and
I'd been working in a computer store for two years by then.
This is all for context btw, I don't consider it bragging, because
I'm sure most in this ng have similar experiences.

Anyway, as far as I-F goes, I'm still a newby.  Despite the fact
that I've been reading r.a.i-f since 1991/2 when I found this cool
program called ITF that allowed people to play infocom games on
their UNIX machines (SGIs, which I used exclusively).  That prompted
me to go out and get LTOI I (later II (much later MOI)).  Now, I
still haven't gone an finished any games, so most of my playing
experience is still limited to two games: Adventure and Dungeon
(ie. the complete Zork).

My fondest memories were as a freshman in college playing Zork
on my terminal (dialed up to a VAX 780 at 300 baud) with my
roommate, and a big 1.5 liter bottle of wine -- on a few Friday
nights that my fraternity didn't have a party.  Often other
guy in the fraternity would stop by to help.  Again, as a sign
of the times, my terminal/modem was the only sign of computer
technology in my house at the time.

Prior to college, I played Adventure on some CPM S-100 bus
machine and loved it.  I had also seen some Adam's games on
TRS-80s (model I), but was fairly unimpressed.  Adventure even
inspired me to begin writing my first "text adventure" -- for
my HP-CV calculator.  I came up with a simple world, and
simpler parser, but never really implemented much.

I hope to enter the (co-ed) fraternity of I-F authors soon,
but I have some other writing that needs to get done first.
(that which I am currently procrastinating from doing.)

Ahhh, how cathartic.


BTW, despite not authoring anything yet, I really love this
newsgroup.  It has probably the lowest S/N ratio of any USENET
group I've ever seen (in 15 years), and by far some of the best
discussions -- from the programming, theory and media points
of view.  Even the off-topic discussions are interesting.

	Bill

/*************************************************************************/
/* Bill Sherman	 (wsherman@ncsa.uiuc.edu)                                */
/* National Center for Supercomputing Applications                       */
/* University of Illinois at Urbana-Champaign                            */
/*     Og - "You want to do mankind a real service?  Tell funnier jokes" */
/*  Spinner - "but facts don't always reveal the truth"                  */
/*      Robin - "Yeah, but I always figure that's the writers' fault"    */
/*************************************************************************/



From whizzard@uclink.berkeley.edu Thu Jun 26 20:36:57 MET DST 1997
Article: 26405 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!news-feed.inet.tele.dk!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!howland.erols.net!agate!uclink.berkeley.edu!whizzard
From: whizzard@uclink.berkeley.edu (Gerry Kevin Wilson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 1997 02:38:39 GMT
Organization: University of California at Berkeley
Lines: 5
Message-ID: <5osknf$1ph@agate.berkeley.edu>
References: <867210152.31691@dejanews.com> <5os455$fi3@fido.asd.sgi.com>
NNTP-Posting-Host: uclink.berkeley.edu
Xref: news.lth.se rec.arts.int-fiction:26405


22.  But I swear, I'm really 84 at heart.
-- 
	My new email address is: whizzard@pobox.com.
	If that's too long for you, try gkw@pobox.com.


From Volker.Blasius@gmd.de Thu Jun 26 22:46:27 MET DST 1997
Article: 26414 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.algonet.se!news.maxwell.syr.edu!newsfeed.nacamar.de!fu-berlin.de!cs.tu-berlin.de!uni-duisburg.de!RRZ.Uni-Koeln.DE!nntp.gmd.de!newsmaster
From: Volker Blasius <Volker.Blasius@gmd.de>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Thu, 26 Jun 1997 13:51:37 +0200
Organization: GMD - German National Research Center for Information Technology
Lines: 7
Message-ID: <33B257C9.323@gmd.de>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <33b0b98d.10802576@news.one.net> <33b45469.39991532@news.u-net.com>
NNTP-Posting-Host: xyzzy.gmd.de
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0Gold (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:26414

Jim MacBrayne wrote:
>
> I'm 54, so that makes me the grandaddy of you all!

But not by much; in 6 weeks I'll have caught up. :)

Volker


From jholder@deimos.frii.com Fri Jun 27 08:12:41 MET DST 1997
Article: 26419 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!howland.erols.net!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!199.45.255.100!coop.net!frii.com!deimos.frii.com!jholder
From: jholder@deimos.frii.com (J. Holder)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 25 Jun 1997 14:55:03 GMT
Organization: Front Range Internet, Inc.
Lines: 33
Message-ID: <5orbg7$egr$1@europa.frii.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu>
NNTP-Posting-Host: deimos.frii.com
X-Newsreader: TIN [version 1.2 PL2]
Xref: news.lth.se rec.arts.int-fiction:26419

In a fit of lunacy, Stephen Granade (sgranade@phy.duke.edu) escribed:
: On 24 Jun 1997, Miron Schmidt wrote:

: > I have always wondered what the average age of the r.a.i-f community is.

: I'm 24. I don't know what the average age is, but I could guess:

: 73.

You're just saying that because we all act like old farts, constatntly
bitching about this and that, and "the good (bad?) old days"...

Hmmmph!

<ALERT=NOSTALGIA>
My first experience with IF was at a family day at my father's workplace,
Los Alamos National Labs, in 1978.  I sat down in front of a high-tech
green screen (next to a few old teletypes) and played Crowther & Woods
"Adventure" on some old DEC platform.  I was a ripe eight years old.
In 1980 I enrolled in a BASIC programming class at the High School
(it was a summer school course, and I got special dispensation to
enroll) where I learned my first programming chops on a PDP11/780. 
Late that year I got my first PeeCee, an Atari 800 w/ 16Kb RAM and a
screaming tape drive.  For almost $800.00.   ->SIGH<-  Ah, how fun
it was, Zorking about (after a RAM upgrade and a floppy drive).

Okay, I'm making myself sick.  I hate to think about everyone else...
</ALERT>

--
John Holder (jholder@frii.com) /\            http://www.frii.com/~jholder/
UNIX Specialist, Paranet Inc. <--> Raytracing|Fractals|Interactive Fiction
http://www.paranet.com/        \/           Homebrewing|Strange Attractors


From staffan.friberg@swipnet.se Fri Jun 27 08:13:21 MET DST 1997
Article: 26418 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!news-paris.gsl.net!news.gsl.net!rain.fr!jussieu.fr!pasteur.fr!univ-lyon1.fr!news.ujf-grenoble.fr!ciril.fr!cnusc.fr!eerie.fr!news.maxwell.syr.edu!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!129.240.148.41!nntp.uio.no!mn6.swip.net!mn5.swip.net!news
From: Staffan Friberg <staffan.friberg@swipnet.se>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 97 18:56:10 +0100
Organization: Rabbit's Den
Lines: 16
Message-ID: <33B2BB4A.MD-0.193.staffan.friberg@swipnet.se>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: mn8.swip.net
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: MicroDot-II/AmigaOS 0.193
Cache-Post-Path: mn8!s-257051@dialup117-6-3.swipnet.se
Xref: news.lth.se rec.arts.int-fiction:26418

Miron Schmidt writes:

> Nevertheless, I _have_ wondered.
> From what I've heard, most of us are around my own age, give or take. So may
> I make a start.
> I'm 25: 26 in two weeks (hey, if anyone happens to be in Berlin at the time,
> you're invited to my birthday party :)).
> 
> Any volunteers?

Going to your party or revealing our age? :-)

I'm 28.

     /Staffan



From boutel1g@wcc.govt.nz Fri Jun 27 08:13:23 MET DST 1997
Article: 26423 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!europa.clark.net!howland.erols.net!newspump.sol.net!sol.net!spool.mu.edu!newsspool.sol.net!munnari.OZ.AU!comp.vuw.ac.nz!wcc.govt.nz!wcc.govt.nz!nntp
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Message-ID: <01bc8285$1a855c20$171e0a0a@prod1001>
From: "Giles Boutel" <boutel1g@wcc.govt.nz>
Date: 27 Jun 97 11:03:44 NZST
References: <867210152.31691@dejanews.com> <5os455$fi3@fido.asd.sgi.com> <5osknf$1ph@agate.berkeley.edu>
Organization: Wellington City Council
Nntp-Posting-Host: 10.10.30.23
X-Newsreader: Microsoft Internet News 4.70.1161
Lines: 12
Xref: news.lth.se rec.arts.int-fiction:26423



Gerry Kevin Wilson <whizzard@uclink.berkeley.edu> wrote in article
<5osknf$1ph@agate.berkeley.edu>...
> 22.  But I swear, I'm really 84 at heart.
> -- 
Ah - you're just a young fogey :)

26 as of this sunday, first played IF in '78 (advent - what else?). Wrote
my first complete game 18 years later.

-Giles 


From mulveyr@frontiernet.net Fri Jun 27 13:47:58 MET DST 1997
Article: 26440 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!newsfeed.internetmci.com!news-peer.sprintlink.net!news-pull.sprintlink.net!news-in-east.sprintlink.net!news.sprintlink.net!Sprint!205.232.174.12!node2.frontiernet.net!node17.frontiernet.net!katy
From: katy@katy.aa2ys.ampr.org (Katy Mulvey)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 1997 22:53:32 GMT
Organization: Complete and Utter Chaos
Lines: 44
Message-ID: <5ourtc$1gbe$2@node17.cwnet.frontiernet.net>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu> <5orbg7$egr$1@europa.frii.com> <5os8mg$1c4$1@news2.digex.net>
Reply-To: mulveyr@frontiernet.net
NNTP-Posting-Host: usr22-218.dial.roc.frontiernet.net
X-Trace: 867365612 49518 (none) 205.232.174.25
X-Newsreader: slrn (0.9.2.0 BETA UNIX)
Xref: news.lth.se rec.arts.int-fiction:26440

On 25 Jun 1997 23:13:20 GMT, This is a test <rsimpson@access4.digex.net> wrote:
>J. Holder (jholder@deimos.frii.com) wrote:
>
>: My first experience with IF was at a family day at my father's workplace,
>: Los Alamos National Labs, in 1978.  I sat down in front of a high-tech
>: green screen (next to a few old teletypes) and played Crowther & Woods
>: "Adventure" on some old DEC platform.  I was a ripe eight years old.
>
>I remember going to my father's workplace and having to play *Yahtzee*. I
>bet your dad could beat up my dad, too. I'm 26.

Hmm. I got to play Dungeon. (I'm 27). I remember Dad taking me in to
work (Computer Consoles, Inc., later bought by Northern Telecom) and
showing me the secret commands I needed to enter to play Dungeon.
(Something along the lines of 'cd /usr/_games; dungeon')

My fondest Dungeon memory, though, is getting Dad to print out the
"instructions" section on computer paper, and using it as a prop in
a school play when I was 11. The play was a musical called "The Gigo
Effect", and I got to be a singing, dancing, computer Glitch.

Let's see, other gaming memories:
+ I remember playing Planetfall with a friend on a Macintosh, and
  figuring out how to retrieve the key.

+ Solving the Royal Puzzle in Zork III, on our Atari 800. In 
  retrospect, I probably wasn't as close to solving it as I 
  thought I was -- I had all 7 points, and got to the end game
  area, and even with clues from a BBS, I could never make the
  Implementor follow my instructions.

+ Typing in innumerable games (in BASIC) of all sorts (including adventure
  games) from Antic magazine. Wonder if those are still around
  anywhere, or if Mom got rid of them when they moved...

I've never written an adventure game, although I've thought about
it plenty of times. I never seem to keep my enthusiasm up past
the very beginning of the planning stages.

  Katy

-- 
Katy Mulvey
Home: mulveyr@frontiernet.net  http://www.frontiernet.net/~mulveyr/Katy


From cinnamon@shell.one.net Fri Jun 27 17:39:58 MET DST 1997
Article: 26448 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!thor.atcon.com!pumpkin.pangea.ca!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!howland.erols.net!newsfeed.internetmci.com!newsfeed.one.net!news.one.net!not-for-mail
From: cinnamon@shell.one.net (athol-brose)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 26 Jun 1997 19:50:17 GMT
Organization: standing on a hill
Lines: 58
Message-ID: <5ouh5p$4sj$1@news.one.net>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <5otbog$fqg$3@neko.syix.com>
NNTP-Posting-Host: shell.one.net
Xref: news.lth.se rec.arts.int-fiction:26448

In article <5otbog$fqg$3@neko.syix.com>,
Patrick Kellum <patrick@syix.com> said (among other things):
>Sonic The Hedgehog as a text adventure

You are on a strip of lush, green lawn. To the west is a rope-and-log
bridge over a waterfall. To the east, the ground slopes sharply upward, as
if it were half of a skateboarder's half-pipe. The top of the quarter-pipe
is roughly eight feet up.

There is a ring here. There is a ring here. There is a ring here. There is
a ring here.

A nervous mechanical porcupine paces back and forth.

>examine porcupine

A red shell with yellow spikes? That's not the proper color for a
porcupine! It must be one of Robotnik's robot helpers!

>jump

Whee!

The porcupine is getting agitated!

>land on porcupine

Splat!
[Your score has gone up by 100.]

>take ring.g.g.g

Ring!
[Your score has gone up by 10.]

Ring!
[Your score has gone up by 10.]

Ring!
[Your score has gone up by 10.]

Ring!
[Your score has gone up by 10.]

>go east

Unable to build up enough speed, you fall backward, ending up where you
started out.

---------------------------

Nah. I just can't see it. :)

--r.

-- 
r. n. dominick -- cinnamon@one.net -- http://w3.one.net/~cinnamon
 some things are just pictures - they're scenes before your eyes


From carl@earthweb.com Sat Jun 28 21:05:52 MET DST 1997
Article: 26488 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!howland.erols.net!newsfeed.internetmci.com!news.silcom.com!news.genuity.net!not-for-mail
From: Carl Muckenhoupt <carl@earthweb.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Wed, 25 Jun 1997 16:52:55 -0400
Organization: EarthWeb
Lines: 9
Message-ID: <33B18527.6BE@earthweb.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu>
Reply-To: carl@earthweb.com
NNTP-Posting-Host: ben.earthweb.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (Win95; I)
Xref: news.lth.se rec.arts.int-fiction:26488

27, if you must know. And my first adventure, at the age of eight, was
Scott Adams' Adventureland. The original version, in TRS-80 BASIC, not
the later form with the game engine in assembly language and the
standardized data file format. (You actually had to wait several seconds
for your commands to be processed...)

-- 
Carl Muckenhoupt		carl@earthweb.com
EarthWeb			http://www.earthweb.com/


From femaledeer@aol.com Sun Jun 29 00:31:21 MET DST 1997
Article: 659 of rec.arts.int-fiction
From: femaledeer@aol.com (FemaleDeer)
Newsgroups: rec.arts.int-fiction
Subject: Inform Library 6/5 bug found re: add_to_scope
Date: 28 Jun 1997 22:07:17 GMT
Lines: 29
Message-ID: <19970628220701.SAA26923@ladder02.news.aol.com>
NNTP-Posting-Host: ladder02.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
Path: klump.df.lth.se!news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!portc02.blue.aol.com!audrey02.news.aol.com!not-for-mail

I just mention this for your enlightment. I am not totally sure what is
causing the bug, but I think it has to do with the backward ancestoring of
objects in Library 6/5 (i.e. used in ObjectIsUntouchable and other
places).

If you use add_to_scope and have a container as one of those parts added
to scope, anything IN the container will be unavailable. That seems to be
because the library go back through ancestors and discovers the
"grandparent" is a transparent object, ergo, its parts are not takeable,
not available. Note: add_to_scope did not behave this way in any of the
previous libraries.

Example (simplified code):

Object remote "remote-control"
  has transparent
  add to scope power_button scanner battery_compartment;

Object battery_compartment;

Object -> -> battery "battery";  OR   Object battery "battery"
compartment;

The battery will not be available because the parent of the battery
compartment is transparent.

FemaleDeer@aol.com

"If builders built buildings the way most programmers program, civilization would fall apart with the first peck of a woodpecker."


From jkennedy@himail.hcc.com Sun Jun 29 14:03:37 MET DST 1997
Article: 26494 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!newsfeed2.luth.se!news.luth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!nntp.uio.no!news.uoregon.edu!news-feed.newscorp.com!uunet!in3.uu.net!148.163.20.117!hcc.com!usenet
From: jkennedy@himail.hcc.com
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 27 Jun 1997 21:51:05 GMT
Organization: Hoechst Celanese
Lines: 8
Message-ID: <5p1ck9$k15@decgate.bridgewater.ne.hcc.com>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de>
Reply-To: jkennedy@himail.hcc.com
NNTP-Posting-Host: kennedy.bridgewater.ne.hcc.com
X-Newsreader: IBM NewsReader/2 2.0
Xref: news.lth.se rec.arts.int-fiction:26494

In <33B00B17.MD-0.193.s590501@tfh-berlin.de>, Miron Schmidt <s590501@tfh-berlin.de> writes:
>I have always wondered what the average age of the r.a.i-f community is.

I'm 48; my wife is 38.  I started with Microsoft Adventure and Zork I and II on
my new IBM PC in '82; she started about a year later with a no-save-feature
Adventure for Wang word processors, and actually managed to finish it.
After we married in 1984, we were regular Infocom beta testers.  (The
first betas of AMFV [but it was PRISM, then] and Journey were -- interesting.)


From pk@cordoba6.ns.itd.umich.edu Sun Jun 29 22:28:56 MET DST 1997
Article: 26511 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!newsfeed.nacamar.de!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsfeed.internetmci.com!jump.net!grunt.dejanews.com!not-for-mail
Date: Fri, 27 Jun 1997 15:42:32 -0600
From: pk@cordoba6.ns.itd.umich.edu
Subject: Re: Who is the author of an IF?
Newsgroups: rec.arts.int-fiction
Message-ID: <867442657.620@dejanews.com>
Organization: Deja News Usenet Posting Service
References: <Pine.SOL.3.91.970622045847.7111A-100000@godzilla3.acpub.duke.edu> <5omf7p$gj$10@news2.xs4all.nl> <ant240038c72M+4%@gnelson.demon.co.uk>
X-Article-Creation-Date: Fri Jun 27 20:17:38 1997 GMT
X-Originating-IP-Addr: 198.133.30.28 (sb-fw1-ny.i11.advantis.net)
X-Http-User-Agent: Mozilla/3.0 (Win95; I; 16bit)
X-Authenticated-Sender: pk@cordoba6.ns.itd.umich.edu
Lines: 40
Xref: news.lth.se rec.arts.int-fiction:26511

Graham Nelson <graham@gnelson.demon.co.uk> wrote:
> Branko Collin <URL:mailto:collin@xs4all.nl> wrote:
> >
> > You give me an idea. I don't know if this has been suggested before,
> > but what about a text adventure like Lemmings, where you have to
> > follow one or more NPCs around (like some kind of spirit) and make
> > sure the NPC(s) can fullfil his/her/their goals? The player doesn't
> > exist in the gameworld, but can influence it. The better the player
> > is at influencing the world, the longer the NPC stays on track and
> > the longer the player can enjoy the story.
>
> Good lord.  Like playing a version of "Quantum Leap" as the
> slightly uglier, slightly more irritating one who is actually
> a hologram from back home...

Actually, this was the plot of a novel by Andrew Greeley (or possibly
Greely - it's been a while) called _God Game.  The general plot is
that the narrator is beta-testing a new text parser game for his friend,
which test goes awry as the computer (through electrical accident) makes
contact with another world, one oddly similar to the model used by the
game.  Sure enough, the narrator can influence this world by typing
commands, which the various characters in this world interpret as
communications from their deity.  The often fail to pay attention,
interestingly, except when it suits them.

Anyway, it's a curious book.  I believe Greeley mostly writes religious
murder-thrillers, though I've not read any of them.  It's not badly
executed, and has taken the IF concept in a direction rather different
than the genre has progressed.  Might be some good inspiration there for
someone who wanted to attempt this sort of thing.  Or perhaps not.

Plant Kingdom (pk@cordoba6.ns.itd.umich.edu)
--
"You, Sir, talk like a Rosicrucian whole will love
nothing but a sylph, who does not believe in a sylph,
and who yet quarrels with the universe for not containing
a sylph."  --Thomas Love Peacock, _Nightmare Abbey_

-------------------==== Posted via Deja News ====-----------------------
      http://www.dejanews.com/     Search, Read, Post to Usenet


From jcompton@typhoon.xnet.com Mon Jun 30 08:20:56 MET DST 1997
Article: 26522 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!feed1.news.erols.com!newsfeed.internetmci.com!news.xnet.com!typhoon.xnet.com!not-for-mail
From: jcompton@typhoon.xnet.com (Jason Compton)
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Subject: Re: Difficulty level of "best" IF games
Followup-To: rec.games.int-fiction,rec.arts.int-fiction
Date: 29 Jun 1997 14:31:54 GMT
Organization: XNet - Chicagoland's Regional ISP (630) 983-6064
Lines: 68
Message-ID: <5p5rkq$ljl@flood.xnet.com>
References: <19970623055001.BAA18602@ladder02.news.aol.com> <5ot77p$onb@flood.xnet.com> <5p4350$m9h$1@bartlet.df.lth.se>
NNTP-Posting-Host: typhoon.xnet.com
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.games.int-fiction:24100 rec.arts.int-fiction:26522

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
: jcompton@typhoon.xnet.com (Jason Compton) wrote:
: >
: >No, you're right, most modern offerings have a steeper introduction, and I
: >think part of that can be chalked up to a lack of game package materials.
: >Infocom immersed us in the game through typically excellent boxes,
: >manuals, and toys.  The modern offerings, being freely available and
: >coming to us as data files only, don't have the ability to flesh out the
: >world before the fact for us, and many have no or very little introductory
: >material for the player.  We're just dropped into the gaming universe with
: >very little insight into what we're supposed to be doing.
: 
: I don't think this is the primary cause of the problem. Sure, the
: "package material" is excellent for immersing the player in the world
: of the game, but I've seldom had much help from it to actually solve
: the puzzles in the game (apart from those needing references from the
: packaging as a means of copy protection).

You're right, they didn't much help except to fill out the early "You'll
find that information in your game package" and later "Enter the codewheel
number" blanks, but I still feel that the sense of atmosphere they
provided was one of the things that really hooked you into playing the
game for an extended period.  That, and spending the money on them...:)

: And why did the Infocom authors pay so much attention to such issues?
: Because they were professionals. They knew that their living depended
: on their ability to attract players, and keep them hooked. Of course,
: being a professional also involves having the resources to test these
: aspects of the games before releasing them. And that is something we
: amateurs lack, even those of us who are perfectly aware of the issues
: involved. 

Right.  And that part isn't anybody's fault.

: >This has caused me a lot of trouble.  I don't think I would have been as
: >interested in solving the case in Witness, or in the setting of the piece,
: >without the cheesy detective journal and the matchbook and the note and
: >telegram.  I don't think Wishbringer would have been nearly as engrossing
: >if not for the library book and the "stone."
: 
: Well, to each his own, I suppose. I must confess that I first played
: "Wishbringer" with a pirated copy and without any of the props. I was
: still instantly absorbed into the story. The stone would probably just
: have distracted me - I was a bit too old to be impressed
: by glowing pieces of plastic at the time.

I wasn't.  Touche. :)

: Incidentally, this is a shame, since "TME" is very well written in
: other ways, and I found it hauntingly intense and graphic (in the
: metaphorical sense, of course) despite its shortcomings.

Yes, there were parts which I found effective and well-written, but
usually just after the fact, as you said.

: I'd like to add another competition game as an example of how an
: author can immerse the player in his world by providing background
: material: "Sherbet". Graham Nelson's notes to the game serve much the
: same function as Infocom's enclosed "extras".

Sherbet is an excellent example of filling in the exact sort of blanks I'm
talking about, yes.

-- 
Jason Compton                                jcompton@xnet.com
Editor-in-Chief, Amiga Report Magazine       Anchor, Amiga Legacy
http://www.cucug.org/ar/                     http://www.xnet.com/~jcompton/
     ...Sharp...Distance...how can the wind with so many around me...


From erkyrath@netcom.com Sun Jul  6 19:00:43 MET DST 1997
Article: 26638 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!online.no!Norway.EU.net!EU.net!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Are the following true?
Message-ID: <erkyrathECszBC.GCt@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <5phlla$m4@dmorin.tiac.net>
Date: Fri, 4 Jul 1997 16:33:12 GMT
Lines: 56
Sender: erkyrath@netcom3.netcom.com
Xref: news.lth.se rec.arts.int-fiction:26638

Generic News Posting Account (newsaccount@dmorin.tiac.net) wrote:

> Somebody want to give me their opinion on the following generalizations?

No generalization is *always* true. (And don't nobody get meta on my ass 
for saying that.)

> 1) All conversation between PC and NPC can be placed into one of the following
> three categories:
> 	commands  (i.e. troll, kill rabbit)
> 	requests for information  (i.e. troll, where is food)
> 	statements of information (i.e. troll, food is on table)

> Though the first two are the most common uses of NPC conversation, I think
> some value could be gained from the third in varying the behavior of the NPC.

Existing games generally use the first two. We just had a large 
discussion about the possibilities of choice-based systems (where the 
game gives you a short list of options of things to say.) The conclusion, 
predictably, was that some people would be more comfortable with that, 
some less, and it really depends on what the game does with it.

> 2) All objects within a game can be considered as being contained within other
> objects.  Inventory is a simple example where objects are contained by an 
> actor, but this would also extend to room-2 being "contained" by room-1
> in room-1's container called "north".  Most things would have multiple
> containers, for instance an actor might have a container "holding" to refer
> to things currently in hand, or "pack" to refer stuff that is being carried
> in your pack (as a stretch, one could consider the container "inside" an actor
> as where things go after they're eaten).

Usually true. The raw containment-structre doesn't have to be used 
naively; you could have a book of spells "containing" individual spells, 
or you could just have an array of spells elsewhere in the game.

It's sometimes convenient to break the rules. Inform allows a way to do
this; I don't know about TADS. 

> 3) (Given the previous assumption...), all actions performed on objects can 
> be considered as either a change of state for the object (break table) or
> a transition from one container to another (get stick, put stick on table,
> eat food).  

If you make the categories broad enough, you can categorize anything. It 
doesn't seem to be very useful. You could consider a transition to be a 
change of state (the "position" state.) Then there's only one kind of 
action. Some actions are both motion and state-change. Some actions 
involve many objects, and are hard to break down into operations on 
individual objects.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From femaledeer@aol.com Sun Jul  6 19:57:41 MET DST 1997
Article: 26562 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!uninett.no!news-feed.inet.tele.dk!newsfeed.direct.ca!portc01.blue.aol.com!audrey02.news.aol.com!not-for-mail
From: femaledeer@aol.com (FemaleDeer)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 30 Jun 1997 20:15:20 GMT
Lines: 25
Message-ID: <19970630201501.QAA02277@ladder02.news.aol.com>
NNTP-Posting-Host: ladder02.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
References: <m3u3im6x8w.fsf@loki.lrz-muenchen.de>
Xref: news.lth.se rec.arts.int-fiction:26562

>From: Florian Beck <h729ihqu@sun1.cip.fak14.uni-muenchen.de>
>Date: 26 Jun 1997 02:09:22 +0200

>Question to IF authors: Is it normal to have started about ten games,
>discarded them all and therefore having zero lines of code after one
>year of writing?

I would say it is not abnormal. I started another game before the one I am
currently writing. I finished about 1/4 of that one so far.  I think I
will finish this game (fairly soon), then get back to the original one,
which will be the first of a trilogy. The game I am working on now has
turned out to be too big, too involved and too much work, now I know
better, the next one will be simplier. Oh well. It helps to be a
programmer (which I am), it helps to like solving tricky programming tasks
(which I do), it helps to be able to think up puzzles (which I have
difficulty with) and it helps to be able to write (which I am not sure I
can). Other than that, it helps to be slightly obsessed (or crazy,
whichever comes first). 

P.S. (I am, gasp, almost 50. The reference to Watergate and apple IIc may
not have dated me enough. I might as well be honest, I earned dem darn
years.)

FemaleDeer@aol.com 
"If builders built buildings the way most programmers program, civilization would fall apart with the first peck of a woodpecker."


From mamster@u.washington.edu Sun Jul  6 19:57:49 MET DST 1997
Article: 26542 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!nntp.primenet.com!news.sgi.com!howland.erols.net!newsfeed.internetmci.com!in1.uu.net!140.142.64.3!news.u.washington.edu!root
From: mamster@u.washington.edu (Matthew Amster-Burton)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Mon, 30 Jun 1997 15:37:12 GMT
Organization: University of Washington
Lines: 26
Message-ID: <33b8d264.2561081@news.u.washington.edu>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu> <5orbg7$egr$1@europa.frii.com> <5os8mg$1c4$1@news2.digex.net> <5ourtc$1gbe$2@node17.cwnet.frontiernet.net> <5p14g0$39s$1@news10.gte.net>
NNTP-Posting-Host: mamster.cdmrc.washington.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Newsreader: Forte Agent 1.0/32.390
Xref: news.lth.se rec.arts.int-fiction:26542

34ram@gte.net (Jason Melancon) wrote:

>On 26 Jun 1997, Katy Mulvey wrote:
>
>> My fondest Dungeon memory, though, is getting Dad to print out the
>> "instructions" section on computer paper, and using it as a prop in
>> a school play when I was 11. The play was a musical called "The Gigo
>> Effect", and I got to be a singing, dancing, computer Glitch.
>
>Let's see, now . . .
>
>  We are the Glitches and we're here to say
>  We're gonna cause distortion every day.
>  We're gonna bring computers to a halt,
>  And when the systems fail it's gonna be our fault.
>
>  We're gonna do whatever disconcerts,
>  Destroying kilowatts and megahertz.
>  We're gonna wipe out all your memory--
>  Wait and see!

Omigod!  I was in this play when I was 11, too!  I don't think I was a
glitch, though.  I was one of the people who panic when the glitches
arrive.  Katy Mulvey, you are my long-lost sista!

Matthew


From kaleid@ftoomsh.socs.uts.edu.au Sun Jul  6 19:58:07 MET DST 1997
Article: 26575 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!sn.no!nntp.uio.no!news.maxwell.syr.edu!newsfeed.direct.ca!news.wildstar.net!news.ecn.uoknor.edu!munnari.OZ.AU!metro!metro!news.uow.edu.au!socs.uts.edu.au!not-for-mail
From: kaleid@ftoomsh.socs.uts.edu.au (Piers Johnson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: 3 Jul 1997 05:55:39 GMT
Organization: School of Computing Sciences, UTS
Lines: 25
Message-ID: <5pfesr$q2q$1@woodstock.socs.uts.EDU.AU>
References: <33B00B17.MD-0.193.s590501@tfh-berlin.de> <Pine.SUN.3.91.970625084513.22666E-100000@nebula.phy.duke.edu> <33B18527.6BE@earthweb.com>
NNTP-Posting-Host: ftoomsh.progsoc.uts.edu.au
X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
Xref: news.lth.se rec.arts.int-fiction:26575

Carl Muckenhoupt (carl@earthweb.com) wrote:
: 27, if you must know. And my first adventure, at the age of eight, was
: Scott Adams' Adventureland. The original version, in TRS-80 BASIC, not
: the later form with the game engine in assembly language and the
: standardized data file format. (You actually had to wait several seconds
: for your commands to be processed...)

Close to me, I guess.. I'm 29 a few weeks back. My first adventure would have
been .. Pyramid Adventure on a TRS-80, you know, the one with the dwarf that
said "you be weird, cut that out" if you typed GET/TOUCH/GRAB DWARF. :)

I quickly discovered Infocom and stuck to them. My brother probably still
has the original HHGTTG packaging somewhere.. I remember playing a version of
Adventure on the mainframe of Qantas Airlines here in Sydney in 1983.
I played Scott Adams games later on, when I got PC version of them.
Must have been around '86, when I finally got a PC.
I wrote a DooM take-off, called FooM, in TADS a couple of years ago - more
as an exercise in concept than a serious game, although some of my testers
complained about it only being one level. I wasn't going to do *that* much
work. I'm still marvelling at the quality of Curses. I regularly play it
again, just to enjoy the prose. I think it's even better than Infocom ever
were. 
-- 
piers@socs.uts.edu.au             kaleid@ftoomsh.progsoc.uts.edu.au
   http://ftoomsh.progsoc.uts.edu.au/~kaleid/ (WWW home page)


From bnewell@gobblernet.dyndns.com Sun Jul  6 19:59:04 MET DST 1997
Article: 26634 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!cpk-news-hub1.bbnplanet.com!cam-news-feed2.bbnplanet.com!news.bbnplanet.com!republic.btigate.com!gobblernet.dyndns.com!bnewell
From: bnewell@gobblernet.dyndns.com (Uncle Bob)
Newsgroups: rec.arts.int-fiction
Subject: Re: Age?
Date: Thu, 3 Jul 1997 12:16:44 GMT
Organization: GobblerNet BBS 701 222 0429
Lines: 17
Message-ID: <ECqsrw.107.0.GobblerNet@gobblernet.dyndns.com>
References: <867210152.31691@dejanews.com> <5os455$fi3@fido.asd.sgi.com> <5osknf$1ph@agate.berkeley.edu> <33B929A5.F9FD791C@msn.com> <33bc95d0.9675171@news.demon.co.uk>
NNTP-Posting-Host: bti5200-4-a32.btigate.com
X-Newsreader: TIN [UNIX 1.3 BETA-950824-color PL0]
Xref: news.lth.se rec.arts.int-fiction:26634

Well, I'm close to being the oldest on this list, but I'm not...I know 
for sure Volker is older!  (But not much).  Let's just say that I'm 
nearly twice as old as many of you.

My intro to I-F came in 1979 when, in the course of buying a minicomputer 
for my company, I came across Adventure and Dungeon.  I begged a copy of 
the source for Adventure, took it home, and ported it to our Honeywell 
mainframe.  (I am not joking, I really did.  This was the start of my 
career as an I-F porter of sorts.)

After rediscovering I-F in 1990 or so, I've been threatening to write 
some games "as soon as I have time."  Heh.  Those of you younger 
correspondents who think you'll have more time when you get a little 
older: it doesn't quite work out that way.

"Uncle" Bob Newell



From erkyrath@netcom.com Sun Jul  6 20:10:00 MET DST 1997
Article: 26524 of rec.arts.int-fiction
Newsgroups: rec.games.int-fiction,rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Difficulty level of "best" IF games
Message-ID: <erkyrathECK5qr.9KB@netcom.com>
Followup-To: rec.games.int-fiction,rec.arts.int-fiction
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <19970623055001.BAA18602@ladder02.news.aol.com> <5ot77p$onb@flood.xnet.com> <5p4350$m9h$1@bartlet.df.lth.se>
Date: Sun, 29 Jun 1997 22:13:39 GMT
Lines: 21
Sender: erkyrath@netcom12.netcom.com
Xref: news.lth.se rec.games.int-fiction:24104 rec.arts.int-fiction:26524

Magnus Olsson (mol@bartlet.df.lth.se) wrote:
> > I don't think Wishbringer would have been nearly as engrossing
> >if not for the library book and the "stone."

> Well, to each his own, I suppose. I must confess that I first played
> "Wishbringer" with a pirated copy and without any of the props. I was
> still instantly absorbed into the story. The stone would probably just
> have distracted me - I was a bit too old to be impressed
> by glowing pieces of plastic at the time.

Now, wait. I take exception to this. I still have that glowing bit of 
plastic, in with my collection of glowing things, and it *still* 
impresses me. It's such a great color. It really stands out amid all the 
standard green glowing things.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From s590501@tfh-berlin.de Sun Jul  6 20:14:44 MET DST 1997
Article: 26547 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!pumpkin.pangea.ca!news.mira.net.au!news.netspace.net.au!news.mel.connect.com.au!munnari.OZ.AU!uunet!in1.uu.net!160.45.4.4!fu-berlin.de!dip8085.tfh-berlin.DE!miron
From: Miron Schmidt <s590501@tfh-berlin.de>
Newsgroups: rec.arts.int-fiction
Subject: Age: Results
Date: 30 Jun 97 09:45:14 +0200
Organization: TFH Berlin via PPP
Lines: 24
Message-ID: <33B78029.MD-0.193.s590501@tfh-berlin.de>
NNTP-Posting-Host: dip8085.tfh-berlin.de (141.64.108.85)
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
NNTP-Posting-User: miron
X-Access: 16 1054 1055
X-Newsreader: MicroDot-II/AmigaOS 0.193
Xref: news.lth.se rec.arts.int-fiction:26547

"Age?" thread, I declare you officially dead now.

As I stated earlier, I've made a little statistic of all the posts.

50 non-anonymous people who stated an age or gave enough information for me
to find out (Jools, I don't have your old post, sorry. I'm too lazy to check
Dejanews right now. It's not _that_ important, anyway) answered.

Their average age is 28.3 (with a total age of 1415!)

Also counting those who didn't appear on this thread, but on the similar
one on r.g.i-f: 28.07
(Speaking of granddaddies: Audrey De Lisle beats everyone at 69!)

Also counting three additional persons whose ages I happen to know (and who
are at least moderately active on r.a.i-f or r.g.i-f): 27.90

Altogether, 62 ages were counted.

--
Miron Schmidt <miron@comports.com>                       PGP key on request

WATCH TV... MARRY AND REPRODUCE... OBEY... PLAY INTERACTIVE FICTION...



From erkyrath@netcom.com Sun Jul  6 20:32:08 MET DST 1997
Article: 26606 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news.maxwell.syr.edu!newsfeed.internetmci.com!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: TADS daemon problem
Message-ID: <erkyrathECsyys.G4w@netcom.com>
Followup-To: rec.arts.int-fiction,rec.games.int-fiction
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <19970701192200.PAA11531@ladder02.news.aol.com> <erkyrathECnyy4.CKq@netcom.com> <Pine.A41.3.95.970702085707.27388B-100000@login4.isis.unc.edu> <5ph354$jv5@wnnews1.netlink.net.nz> <33bd90eb.3863754@news.softcom.net>
Date: Fri, 4 Jul 1997 16:25:40 GMT
Lines: 36
Sender: erkyrath@netcom3.netcom.com
Xref: news.lth.se rec.arts.int-fiction:26606 rec.games.int-fiction:24208

Nathan Thompson (apothegm@no.spam.net) wrote:
> On 3 Jul 1997 20:47:32 GMT, Stephen Griffiths <stevgrif@moc.govt.nz>
> wrote:

> >5) if you aren't able to quit a tads game, try this recent tip posted by 
> >Andrew Plotkin before trying a different interpreter ....
> >Disappearing footnotes in Legend, and inability to quit, are symptoms of 
> >the TADS heap being too small. Different interpreters have different 
> >default sizes, but you should always be able to find an option to increase 
> >it. (-mh 65535 in Unix TADS.)

> Just for reference, the -mh 65535 also works on DOS machines.  65535
> is probably overkill, though; it's well over ten times the default
> heap size (default=2048).  I was the guy who recently had trouble with
> The Legend Lives and go32 TADS, and a 16,000 byte heap worked just
> fine for me, although I can't comment on the daemon bug -- I haven't
> experienced it yet.

That's 65535 *bytes*. If you're working on a desktop machine with 8 megs 
of memory, I can't see any reason not to give it the maximum; it's one 
more reduced uncertainty. 

I sweated a lot over how to determine the optimum heap size for MaxZip,
until I realized, duh, the maximum is 65535! Now it always sets it that
high. Ditto for undo size and stack size (well, there's a note somewhere
that the undo allocation should stay a little shy of 65535.)

If you'r writing an interpreter for a memory-limited palmtop or an old 
machine, that's different. Fortunately I'm not. :)

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From max@alcyone.com Sun Jul 13 18:13:56 MET DST 1997
Article: 26664 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.algonet.se!news-feed.inet.tele.dk!europa.clark.net!howland.erols.net!newshub2.home.com!newshub1.home.com!news.home.com!enews.sgi.com!news.sgi.com!newsfeed.netscape.com!nixon.area.com!not-for-mail
From: Erik Max Francis <max@alcyone.com>
Newsgroups: rec.arts.int-fiction
Subject: Re: Are the following true?
Date: Sun, 06 Jul 1997 14:39:52 -0700
Organization: Alcyone Systems
Lines: 67
Message-ID: <33C010A8.2865F7C6@alcyone.com>
References: <5phlla$m4@dmorin.tiac.net>
NNTP-Posting-Host: newton.alcyone.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 2.02 (X11; I; Linux 2.0.29 i686)
Xref: news.lth.se rec.arts.int-fiction:26664

Generic News Posting Account wrote:

> Somebody want to give me their opinion on the following generalizations?
> 
> 1) All conversation between PC and NPC can be placed into one of the
> following
> three categories:
>         commands  (i.e. troll, kill rabbit)
>         requests for information  (i.e. troll, where is food)
>         statements of information (i.e. troll, food is on table)
> 
> Though the first two are the most common uses of NPC conversation, I
> think
> some value could be gained from the third in varying the behavior of the
> NPC.

There's also a "zeroth" category (which I put before the rest because it is
less important than the rest), which is just small talk.  For instance,
TROLL, HELLO would be part of this zeroth category -- it's not a command,
no information is being requested, and no information is being delivered.
(You could classify it, of course, in terms of the programming needed as a
first-category statement, because it's something the player says which the
NPC has to respond to.)

> 2) All objects within a game can be considered as being contained within
> other
> objects.  Inventory is a simple example where objects are contained by an
> actor, but this would also extend to room-2 being "contained" by room-1
> in room-1's container called "north".  Most things would have multiple
> containers, for instance an actor might have a container "holding" to
> refer
> to things currently in hand, or "pack" to refer stuff that is being
> carried
> in your pack (as a stretch, one could consider the container "inside" an
> actor
> as where things go after they're eaten).

This is a common approach, and is one I used in an adventure authoring
system I was designing until I realized how many there were out there
already (you can actually see me briefly talking about this very aspect of
it in archived IF lists).  Note that if you want to get fancy, you're going
to have to include a prepositional tag with that property of
"includedness," for cases where two things are associated but not in a
direct "inside" (even taken abstractly, as in the player's possessions are
considered "inside" the player object) relationship.  For instance,
distinguishing between two objects that are next to each other, or on top
of each other, or one is behind the other, or to the left of the other,
etc.  (Whether you'd want to do these in an actual game is another
question, but I'm talking in the general, abstract case of object
interaction simulation.)

> 3) (Given the previous assumption...), all actions performed on objects
> can
> be considered as either a change of state for the object (break table) or
> a transition from one container to another (get stick, put stick on
> table,
> eat food).

I'd agree with that.

-- 
       Erik Max Francis, &tSftDotIotE / email / max@alcyone.com
                     Alcyone Systems /   web / http://www.alcyone.com/max/
San Jose, California, United States /  icbm / 37 20 07 N  121 53 38 W
                                   \
           "All the gods are dead / except the god of war."
                                 / Eldridge Cleaver


From masenten@hans.math.upenn.edu Fri Jul 25 15:30:21 MET DST 1997
Article: 26948 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!uninett.no!news-feed.inet.tele.dk!europa.clark.net!howland.erols.net!gatech!newsfeed.pitt.edu!dsinc!netnews.upenn.edu!hans.math.upenn.edu!masenten
From: masenten@hans.math.upenn.edu (Robert Masenten)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: AGiliTy 0.7
Date: 15 Jul 1997 16:27:48 GMT
Organization: Univ. of Pennsylvania Dept. of Mathematics
Lines: 24
Message-ID: <5qg8e4$usk@netnews.upenn.edu>
NNTP-Posting-Host: hans.math.upenn.edu
Xref: news.lth.se rec.arts.int-fiction:26948 rec.games.int-fiction:24453

  I've uploaded version 0.7 of AGiliTy, the (Mostly) Universal AGT
Interpreter, to ftp.gmd.de.  There are three files,
   agil07src.zip -- the (ANSI C) source code
   agil07linux.tgz -- The Linux executables
   agil07dos.zip -- the MS-DOS executables

The new version  includes a lot of small bug fixes and adds command
history to the Linux and DOS ports. 


  AGiliTy was written with two major goals:
 
   i) To be portable across a wide range of platforms. At this time,
I know of ports to the Amiga, various flavors of Unix, and MS-DOS.

  ii) To run all AGT games with a single interpreter (rather than
needing a different interpreter for each game).

  In addition, it has a better parser than the original interpreters and
supports RESTART and UNDO.


Robert Masenten



From mamster@u.washington.edu Sun Aug  3 14:33:17 MET DST 1997
Article: 27183 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-stkh.gsl.net!news.gsl.net!news-lond.gsl.net!news.gsl.net!news-peer.gsl.net!news.gsl.net!europa.clark.net!mis1!worldnet.att.net!news.u.washington.edu!saul9.u.washington.edu!mamster
From: Matthew Amster-Burton <mamster@u.washington.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Help with TADS bug? Please?
Date: Mon, 21 Jul 1997 21:47:45 -0700
Organization: University of Washington
Lines: 24
Message-ID: <Pine.OSF.3.96.970721214616.29152A-100000@saul9.u.washington.edu>
References: <sandifer-2007972155050001@sci-dial-2-mac2.sdsu.edu>
NNTP-Posting-Host: saul9.u.washington.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
NNTP-Posting-User: mamster
To: cody sandifer <sandifer@crmse.sdsu.edu>
In-Reply-To: <sandifer-2007972155050001@sci-dial-2-mac2.sdsu.edu>
Xref: news.lth.se rec.arts.int-fiction:27183

On 21 Jul 1997, cody sandifer wrote:

> I've run across a pesky bug in TADS; specifically, the bug concerns orders
> directed toward items in the player's inventory (where item.location = Me,
> in other words).  Here is a sample transcript from Shelby: 
> 
> > >antenna, hello  [antenna in player's inventory]
> > Have you gone the way of Barclay and truly lost your mind?
> > 
> > >antenna, get chickenfeed   [chickenfeed in another room]
> > I don't see any chickenfeed here.
> > 
> > >antenna, get fog   [fog in the same room]
> > 
> > [TADS-1023: invalid type for built-in function]

Congratulations!  Looks like you've found a bug in adv.t.  I can promise
you that the bug is there and not, say, in the TADS source code (shudder),
but I don't have time to sift through it.  Hey, adv.t isn't so long--have
at it!

Matthew




From mamster@u.washington.edu Sun Aug  3 14:33:28 MET DST 1997
Article: 27184 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!europa.clark.net!mis2!worldnet.att.net!news.u.washington.edu!saul9.u.washington.edu!mamster
From: Matthew Amster-Burton <mamster@u.washington.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: Help with TADS bug? Please?
Date: Mon, 21 Jul 1997 22:30:43 -0700
Organization: University of Washington
Lines: 27
Message-ID: <Pine.OSF.3.96.970721222427.26483A-100000@saul9.u.washington.edu>
References: <sandifer-2007972155050001@sci-dial-2-mac2.sdsu.edu> <Pine.OSF.3.96.970721214616.29152A-100000@saul9.u.washington.edu>
NNTP-Posting-Host: saul9.u.washington.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
NNTP-Posting-User: mamster
To: cody sandifer <sandifer@crmse.sdsu.edu>
In-Reply-To: <Pine.OSF.3.96.970721214616.29152A-100000@saul9.u.washington.edu>
Xref: news.lth.se rec.arts.int-fiction:27184

On Mon, 21 Jul 1997, Matthew Amster-Burton wrote:

> Congratulations!  Looks like you've found a bug in adv.t.  I can promise
> you that the bug is there and not, say, in the TADS source code (shudder),
> but I don't have time to sift through it.  Hey, adv.t isn't so long--have
> at it!

Okay, I lied.  I took a look.  The problem is in the thing object, in the
isReachable routine, on this line here:

if( find( actor.location.reachable, self ) <> nil )
  return( true );

Everything works fine until actor.location is an Actor, not a room,
because Actors don't have a reachableList.

I tried the quick workaround of wrapping that if statement with another to
check whether actor.location was an Actor, and it worked except for
producing the nasty message, "You can't reach that from yourself."

Wait...I have an idea.  What about checking
actor.location.location.reachable if actor.location turns out to be an
Actor.  Would this work?  I'm too tired to try it right now...

Matthew




From fake-mail@anti-spam.address Sun Aug  3 14:33:57 MET DST 1997
Article: 27190 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!bloom-beacon.mit.edu!howland.erols.net!infeed1.internetmci.com!newsfeed.internetmci.com!newsfeed.direct.ca!newsgate.direct.ca!van-52-0607.direct.ca!user
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: Help with TADS bug? Please?
Date: Mon, 21 Jul 1997 22:44:40 -0700
Organization: tela design
Lines: 81
Message-ID: <fake-mail-2107972244410001@van-52-0607.direct.ca>
References: <sandifer-2007972155050001@sci-dial-2-mac2.sdsu.edu>
NNTP-Posting-Host: van-52-0607.direct.ca
Xref: news.lth.se rec.arts.int-fiction:27190

In article <sandifer-2007972155050001@sci-dial-2-mac2.sdsu.edu>,
sandifer@crmse.sdsu.edu (cody sandifer) wrote:

> I've run across a pesky bug in TADS; specifically, the bug concerns orders
> directed toward items in the player's inventory (where item.location = Me,
> in other words).  Here is a sample transcript from Shelby: 
> 
> > >antenna, get fog   [fog in the same room]
> > 
> > [TADS-1023: invalid type for built-in function]

> Same thing happens in 4 other TADS games that I downloaded. The bug is a
> real problem in my current project, since the player can pick up and speak
> to movableActors.  Unfortunately, the result is the same.  (The error also
> occurs under MaxTADS, by the way.)

 Weeelll, that's an interesting one! It looks to me like you've discovered
a bug that's lain dormant for many a year. I certainly hadn't heard of it,
anyway. I guess most people don't try to order around inanimate objects.
:) Anyway, some light spelunking with the TADS debugger (have I mentioned
lately how much I like that program?) reveals the problem is with the
following code in adv.t:

    isReachable( actor ) =
    {
        local loc;

        /* if the object is in the room's 'reachable' list, it's reachable */
        if (find( actor.location.reachable, self ) <> nil )
            return( true );

 In the event that the "actor" is actually an inanimate thing, the bug
occurs because the return value of actor.location.reachable is nil. And
thus finding self in nil results in a runtime error. One way around the
problem would be to stick in a couple checks thusly:

      if ( actor.location and actor.location.reachable and ( find(
actor.location.reachable, self ) <> nil ) )

 That fix actually needs to be put in twice in the isReachable code -
should be obvious where. That will prevent the actual runtime error.

 However, note that it doesn't prevent spurious and wacky error messages
that crop up in other ways. The three cases I can think of are as follows,
in the event of the player commanding an inanimate object:

 1) If the item that the inanimate object is being asked to verb is not
present, it'll call the usual "there's no xyz here", which is also
parseError case 9.

 2) If the item that the inanimate object is being asked to verb *is*
present but unreachable in some way, it'll issue the cantReach( actor )
error message - "the <inanimate object> can't reach that from <the
inanimate object's location>." or whatever. To avoid this messy and
incomprehensible error message I've amended the cantReach code in my copy
of adv.t to have this as the first line:

         if ( not isclass( actor, movableActor ) )
         {
            "There's no point trying to talk to inanimate objects! ";
         }

 This is followed by two else ifs as usual. That way any attempts by the
player to order a non-actor around simply result in an admonishing
message.

 3) Only if the xyz is both present and accessible will it give you the
standard actorAction message. In adv.t that message is "You have lost your
mind," but I've changed it in my adv.t file to read "You can't talk to
inanimate objects," reckoning that the latter is both less impolite and
more informative.

 Hope that makes a little sense. I'm not sure how you're planning on
handling the interaction with non-actor objects, though, so it may or may
not help you.

 - Neil K.

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From erkyrath@netcom.com Mon Aug  4 16:03:43 MET DST 1997
Article: 27424 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news.kth.se!nntp.uio.no!sn.no!Norway.EU.net!EU.net!howland.erols.net!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: [Inform] Newbie problem with "my"--please lend a hand!
Message-ID: <erkyrathEE63B1.2I6@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <33DFC453.C5E1DE7A@uiuc.edu>
Date: Thu, 31 Jul 1997 05:01:49 GMT
Lines: 30
Sender: erkyrath@netcom19.netcom.com
Xref: news.lth.se rec.arts.int-fiction:27424

Will Grzanich (grzanich@uiuc.edu) wrote:

> My question is:  can I get Inform to view the word "my" as
> a simple, everyday word that I can stick into a name property, etc.
> without hacking the Parser library 

No. ...um, maybe. :)

> and likely making things much worse?

I never understood what the Inform library thought it was doing with 
"my", anyhow.

...no, I take that back. I never understood it with the 5/... libraries. 
With the 6/5 libraries it seems to make sense ('my' applies to anything 
in your possession). This is useful if there are several identical items 
in scope and you're holding exactly one of them.

To make it stop doing that, go into the English header file. Find where 
the word 'my' is -- it's about line 119, in the LanguageDescriptors 
array. Change 'my' to 'mogleschnitzer'. Now the library thinks 
'mogleschnitzer' is a pronoun which applies to anything in your 
possession, and it's never heard of 'my', so you can use it as you like.

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From fake-mail@anti-spam.address Tue Aug  5 09:09:13 MET DST 1997
Article: 27435 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news01.sunet.se!sunic!mn6.swip.net!nntp.uio.no!nntp.se.dataphone.net!zdc-e!super.zippo.com!lotsanews.com!howland.erols.net!infeed1.internetmci.com!newsfeed.internetmci.com!newsfeed.direct.ca!newsgate.direct.ca!van-as-13a14.direct.ca!user
From: fake-mail@anti-spam.address (Neil K.)
Newsgroups: rec.arts.int-fiction
Subject: Re: [TADS] Question?
Date: Sat, 02 Aug 1997 04:24:18 -0700
Organization: tela design
Lines: 54
Message-ID: <fake-mail-0208970424190001@van-as-13a14.direct.ca>
References: <5rs514$3q5@ob1.uws.EDU.AU>
NNTP-Posting-Host: van-as-13a14.direct.ca
X-Newsreader: MT-NewsWatcher 2.3.1
Xref: news.lth.se rec.arts.int-fiction:27435

In article <5rs514$3q5@ob1.uws.EDU.AU>, n9707022@scholar.nepean.uws.edu.au
(Jeff Walters) wrote:

> Is there any limitations to the size of a TADs game?

 There are limits, but they are sufficiently high that the likelihood of
you running up against them are fairly low. I know I've discussed these
limits with Mike Roberts in the past, but I can't recall specific numbers.
So I won't go into details because I'll surely be wrong, but suffice to
say that the biggest TADS games out there, such as Legend and Lost New
York, have binary files in the high hundreds of kilobytes and work
swimmingly. At risk of boring r.a.i-f regulars, my own TADS bloatware in
progress has a game file of over a megabyte, and it works fine. And now
that the GO32 problem has been happily fixed, even PC users can play TADS
games unencumbered by the 640K limit.

 I have encountered three problems over the years that could be described
as limits issues. The first two problems were caused by arbitrary fixed
limits in the TADS runtime. Earlier versions of my game ran into problems
with too many pending notifiers and too many ambiguous objects with the
same vocabulary accessible to the player. To fix these problems Mike just
upped the limits to 200 notifiers and 100 objects, respectively, back with
TADS 2.2. He also increased the number of pending daemons and fuses to 100
each. I understand that these are just arbitrary runtime limits, not
limits in the internal TADS architecture itself. That means you could, if
you wanted to, recompile the TADS runtime with higher limits if necessary.
The drawback, of course, would be that players would need your customized
runtime to play your game without runtime errors.

 The third problem concerned the compiler. Its internal code parser isn't
able to swallow really large object definitions. I forget the limit - it's
less than 64K, I think - but if I increase the size of my heavily modified
"thing" object class to anything longer than its current 1800 or so lines
of code, problems ensue. The solution was simply to split the object into
two objects; one inheriting from the other. The way the "item" object
inherits from the "thing" object, actually. Again, this is a limitation of
the implementation of the compiler parser, not of the internal TADS file
structure for objects.

 At this point, game size is one of the remaining areas where TADS has
something of an edge over Inform. Since Inform has to be backwards
compatible with the original constraints of the Z-machine in many ways,
you can bump up against immutable limits. There have been ingenious fixes
for some of the more troubling ones, but at this time you can't have a .z8
game bigger than half a megabyte, if memory serves. There are also limits
to the number of global variables you can have, I think. I'm sure that
these ceilings will be raised when the Z-machine cabal comes up with a .z9
format or something, but it's a potential issue for the present.

 - Neil K.

-- 
 t e l a  computer consulting + design   *   Vancouver, BC, Canada
      web: http://www.tela.bc.ca/tela/   *   email: tela @ tela.bc.ca


From mol@bartlet.df.lth.se Wed Aug  6 16:57:31 MET DST 1997
Article: 27463 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Inventiveness of Infocom (was: Zork I on the C64 - how?)
Date: 6 Aug 1997 16:47:51 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 41
Message-ID: <5sa2qn$5ud$1@bartlet.df.lth.se>
References: <slrn5toqtm.5h.jhawkins@tardis.apana.org.au> <erkyrathEE1MFz.Az6@netcom.com> <slrn5uajkp.6j1.jhawkins@tardis.apana.org.au> <lynnjEEG2qt.7Cn@netcom.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27463

In article <lynnjEEG2qt.7Cn@netcom.com>,
Lynn Johannesen <lynnj@netcom.com> wrote:
>Justin Hawkins (jhawkins@tardis.apana.org.au) wrote:
>: On Mon, 28 Jul 1997 19:07:11 GMT, Andrew Plotkin <erkyrath@netcom.com> wrote:
>: >> I seem to remember the drive being accessed a lot - was it some kind
>: >> of virtual memory type scheme? I can't imagine anything that advanced
>: >> on my old commie :)
>: >
>: >Surprise! Virtual memory was exactly what it was. The C64 interpreter
>: >(like the Apple II interpreter, and all the others that ran on 64K
>: >machines) kept a subset of the game file in memory, and swapped in 
>: >various bits as needed.
>
>That's it.  Whether this scheme should be called "virtual memory" is
>debatable; that term usually refers to what an OS does, not an
>application program, and frequently involves hardware support these
>days.

Well, it's of course amatter of definition. But if you view the Z-code
program as running on a (virtual) Z-machine, comprised of the
computer/OS/interpreter combination, then the Z-machine certainly has
a kind of virtual memory.

>  Somebody else referred to Infocom's use of this technique
>as "innovative".  It wasn't; several more sophisticated paging
>algorithms are described in Knuth's _Fundamental Algorithms_ (1968),
>and they weren't new then either.  I personally used
>least-recently-used paging in some commercial application
>programs (unrelated to games) in 1979, and I certainly didn't invent it.

Oh, come on, nobody has ever claimed that the Infocom people invented
either virtual memory or virtual machines. The inventive part was
applying those techniques to lowly microcomputer games. "Inventive"
can mean either that you invent something totally new, or that you
apply a known technology to a new field.


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From scythe@u.washington.edu Wed Aug  6 21:13:23 MET DST 1997
Article: 27470 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!howland.erols.net!infeed1.internetmci.com!newsfeed.internetmci.com!in1.uu.net!140.142.64.3!news.u.washington.edu!scythe
From: scythe@u.washington.edu (Dan Shiovitz)
Newsgroups: rec.arts.int-fiction
Subject: Re: TADS is freeware.  WAS: Macintosh problems with Inform 6
Date: 6 Aug 1997 18:55:17 GMT
Organization: University of Washington, Seattle
Lines: 42
Message-ID: <5sahal$n62@nntp5.u.washington.edu>
References: <B00CE70E9668124272@206.20.145.20> <5s81bb$rag@agate.berkeley.edu> <33e99a1c.590539@news.u.washington.edu> <5saefb$8je$1@bartlet.df.lth.se>
NNTP-Posting-Host: saul7.u.washington.edu
NNTP-Posting-User: scythe
Xref: news.lth.se rec.arts.int-fiction:27470

In article <5saefb$8je$1@bartlet.df.lth.se>,
Magnus Olsson <mol@bartlet.df.lth.se> wrote:
>In article <33e99a1c.590539@news.u.washington.edu>,
>Matthew Amster-Burton <mamster@u.washington.edu> wrote:
>>whizzard@uclink.berkeley.edu (Gerry Kevin Wilson) wrote:
>>
>>>Just to dispel the fallacy that TADS is still shareware, I thought I'd
>>>point out that it has been released as freeware for quite some time now.  
>>>TADS gets enough bad press without the whole shareware fee being dredged
>>>up again.  It is simply a different tool designed for a different type of
>>>user.
>>
>>An incomparably attractive and self-assured type, one might add.
>
>:-)
>
>But, seriously speaking, in what sense do you think TADS caters to a
>different type of user than Inform?

I don't think there's any really radical difference between the syntax
of the two languages.  But of the two, TADS seems to me to be the more
welcoming to people who have some programming background already;
instead of mucking around with all this "foo has light" and "give bar
proper" and for statements punctuated by colons instead of
semi-colons, TADS is pretty darn close to C (except for := vs =, and
there's some sort of #define to change that).  Contrariwise, Inform is
probably more welcoming to novices, though this is more due to the
additional documentation and userbase than actual language features.

Of course, they're more like each other than either is like AGT :)

>Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
>------    http://www.pobox.com/~zebulon   ------
--
Dan Shiovitz :: scythe@u.washington.edu :: shiov@cs.washington.edu
..................................................................
"Alas, I do not rule the world and that, I am afraid, is the story
of my life: always a godmother, never a God."     -- Fran Lebowitz
...http://weber.u.washington.edu/~scythe/home.html................





From gleemoth@aol.com Fri Aug  8 09:58:54 MET DST 1997
Article: 27484 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news00.sunet.se!sunic!mn6.swip.net!nntp.uio.no!news-feed.inet.tele.dk!europa.clark.net!205.252.116.205!howland.erols.net!infeed1.internetmci.com!newsfeed.internetmci.com!portc03.blue.aol.com!newstf02.news.aol.com!audrey01.news.aol.com!not-for-mail
From: gleemoth@aol.com (GLEEMOTH)
Newsgroups: rec.arts.int-fiction
Subject: The Well-Dressed Adventurer
Date: 2 Aug 1997 21:16:34 GMT
Lines: 103
Message-ID: <19970802211601.RAA06638@ladder01.news.aol.com>
NNTP-Posting-Host: ladder01.news.aol.com
X-Admin: news@aol.com
Organization: AOL http://www.aol.com
Xref: news.lth.se rec.arts.int-fiction:27484

*warning- long post ahead*
I was looking through old posts I saved on my hard drive and I noticed
this little gem of a thread: "The Well-Dressed Adventurer". Here's my
compiled list of the best (in my opinion) required attributes and items.
Enjoy!

* A light source. There are dark rooms out there, after all, and the
Well-Dressed Adventurer's night vision is notoriously poor. Preferably the
source can be refueled, or doesn't require fuel. In the olden days,
Adventurers were always running out of lamp oil right when they needed it
most...

* An amazing sense of the cardinal directions. The Well-Dressed Adventurer
can tell you which way is north after being stripped naked and teleported
to a pitch-black room on a different planet. While he understands the
basic concept of doors (often as obstacles to further progress), he
doesn't think of rooms in the same way as you or I, namely, the
connections between rooms. (Quiz yourself. Do *you* know which way north
is from your house?) Imagine trying to give the Well-Dressed Adventurer
directions: "Bathroom? Yeah. Go through that door, on the end of the hall,
on your left." "Pardon?" "South twice, than east." "Ah."

* Map-making tools. The Well-Dressed Adventurer never relies on his memory
to navigate around even such a theoretically familiar place as his own
home digs. Paper, a writing utensil (preferably a pencil), and a surface
are a must. Many modern Adventurers, though, just take notes in the field
and render a map on their computer when they get back to home base.

* A major case of kleptomania. While the Well-Dressed Adventurer would
never *steal* from you, he is always on the lookout for items he can
borrow until his adventure is done. To prevent unfortunate property
damage, I recommend against attempting to secure your valuables in a safe,
by nailing them down, by hiding them under the bed, etcetera. The more
difficult an item is to obtain, the more obsessed he becomes with getting
it. Lay in a supply of sticky labels instead, and label anything you don't
want him fiddling with 'scenery'. This magic incantation wards the
Well-Dressed Adventurer more often than not. It also helps if you give all
of your possessions really obscure names or describe them in odd nouns.
Instead of 'computer', make sure your 386 can only be referred to by the
name 'Torgo'. Always call your mouse a pointer, and call the phone an
audicom. More often than not, this will make an Adventurer simply give up.

* A rucksack, backpack, or other pack capable of holding all the things
he's err.. borrowed. Of course, this is an idea the Well-Dressed
Adventurer got from a certain lean and hungry gentleman. The Well-Dressed
Adventurer likes to carry everything around with him at all times, for he
never knows when he might need it. Unless, of course, the Adventurer has
found the object's 'true home', the idyllic location or situation which
Adventurers know every inanimate object tries to reach, the one that truly
fits best- and so Adventurers continue their crusade to put such objects
in their rightful place...

* Pocketless clothes. Many a Well-Dressed Adventurer spurns pockets, even
when it -would- make it easier to carry that rubber duck (which the
Well-Dressed Adventurer needs to be able to get Foucault's Pendulum away
>from the Sword of Damocles). Others, however, just don't know what to do
with them. Even when they have pockets, all they do is search them-- it
just rarely occurs to them that they might benefit from putting an object
they've worked so hard to find into something not in immediate view...
They -will-, however, look for any objects that they can put their stuff
in. On a related subject, the Well-Dressed Adventurer either walks around
stark naked most of the time, or is completely unaware of most of his/her
clothes.

* A bad memory. I forget why.

* A funny little voice inside their heads which tells them what to do.

* A good case of deja vu. The Well-Dressed Adventurer will often know that
pulling that lever will propell them into certain death at the teeth of a
six-foot razor worm at the bottom of a pit, in spite of the fact that the
only way such information could be gained would be by actually pulling the
lever. Odd, that.

* The Well-Dressed Adventurer is always gender unspecified, yet at the
same time always male.

* The Well-Dressed Adventurer either is unable to hold more than, oh, say
10 objects, even if the items are just 10 pebbles, or can hold every item
he sees and still be able to push buttons, open doors, and pull levers.

* The Well-Dressed Adventurer is also never surprised by a lack of people
milling about and thinks everyone he encounters is going to help or
hinder.

* The Well-Dressed Adventurer insists on *carrying* his sword, when most
people would *wear* it in some way thus leaving their hands free.

These attributes of the Well-Dressed Adventurer came directly from the
keyboards of these people:
Fred "Clyde" Sloniker (puma@u.washington.edu)
Matthew T. Russotto (russotto@wanda.vf.pond.com)
George Caswell (timbuktu@adamant.res.wpi.edu)
Bruce Alan Greenwood (RDQW@music.macarthur.uws.EDU.AU)
Nicholas Daley (daleys@ihug.co.nz)
Andrew Plotkin (erkyrath@netcom.com)
Dan Shiovitz (scythe@u.washington.edu)
Eli The Bearded (eli@alpha.netusa.net)
Bill Hoggett (mas.supplies@easynet.co.uk)
The above E-mail addresses and names are those shown on the posts I got
these from. They are dated around 11/96, so be warned.
Also, please be sure to follow-up with more ideas. :-)
            Shay Caron (gleemoth@aol.com)


From mol@bartlet.df.lth.se Sat Aug  9 15:38:43 MET DST 1997
Article: 27528 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Dead ends and needed objects
Date: 9 Aug 1997 15:36:49 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 69
Message-ID: <5shrph$pqc$1@bartlet.df.lth.se>
References: <B010B76A96683CB8F@slip14.worldaxes.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27528

In article <B010B76A96683CB8F@slip14.worldaxes.com>,
Morgan Wajda-Levie <mpwl@locke.ccil.org> wrote:
>I was mowing the lawn (my usual thinking time) when I thought of a great
>way to deal with puzzles that require objects from places a player can not
>reach.
>
>You have a command which allows the player to teleport any object to
>himself, but of course, this would come with a price. 

(...)

>Please, give me comments on the quality of this idea, and maybe
>even give me the exact code I would need to write in.  Thanks!

I think it depends on how puzzles and plot depend on each other in
your game. What you are suggesting can be seen as a way of bypassing
puzzles: "I can't solve the puzzle of finding the trifoliate
thingummybob, so I'll just try teleporting it to me so I can go on
with the game". But what if solving that puzzle not only gives you
access to the object, but also was crucial for the plot? In that case,
teleporting it would not only bypass the puzzle, it would bypass a
part of the plot as well. 

The idea might work best in a "traditional" puzzle game, where puzzles
don't contribute to the plot. A similar situation would be a classic
locked-door puzzle: if the puzzle you have to solve to obtain the key
to the door isn't important to the plot, you could give the player the
alternative solution of breaking down the door with brute force. 

Or you could take the opposite approach, and make the teleportation
idea not just a "help for stuck players", but an integral part of the
plot. What if, for example, the protagonist had a magic spell that
allowed him to obtain any tool he might need at the snap of his
fingers? 

And perhaps bypassing puzzles in this way should be penalized not just
by the mimesis-breaking device of reducing the player's score, or the
external-to-the-game-world device of appealing to the player's
curiosity ("But where on earth was the thingummybob really hidden?"),
but by a way internal to the plot? For example, using the spell might
give the protagonist bad karma :-).

I can see a few problems for the author with the idea of a "give me
any object I need" command. None of them are very serious, but they
must be considered:

* How does the player know that he/she really needs a trifoliate
thingummybob to frobnicate the fertsneet? Part of the fun with IF is
when you find the thnigummybob first, without knowing really what to
use it for, and then finding out that by yourself.

* How does the player know what he/she can obtain magically and what
he/she can't? Suppose, for example, that I'm standing in front of a
locked door, and can't find any key. WHat I don't know is that there
is no key in the game; instead I need to use a log from the fireplace
as a battering ram to break it open. Should I be able to "teleport
key" anyway? And, if I am able to do that, should the key really open
the door in  that case?

* How is the player prevented from ruining later parts of the game by
teleporting away objects that really need to be in a certain location
a hundred moves later? 



-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From ivan@texoma.net Sun Aug 17 23:37:14 MET DST 1997
Article: 27681 of rec.arts.int-fiction
From: ivan@texoma.net (Ivan Cockrum)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: Many Spectrum Games Available
Date: Sun, 17 Aug 1997 10:57:22 -0500
Organization: Internet Texoma
Lines: 21
Message-ID: <ivan-1708971057220001@news.texoma.net>
NNTP-Posting-Host: ppp116-072.texoma.net
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
X-Newsreader: Yet Another NewsWatcher 2.2.0b13
Path: news.lth.se!genius.dat.hk-r.se!news.ifm.liu.se!news.lejonet.se!newsfeed1.telia.com!masternews.telia.net!news-out.internetmci.com!infeed2.internetmci.com!newsfeed.internetmci.com!199.0.154.56!ais.net!logbridge.uoregon.edu!hammer.uoregon.edu!news.texoma.net!ivan
Xref: news.lth.se rec.arts.int-fiction:27681 rec.games.int-fiction:25081

I don't know if this is common knowledge, but a large collection of
obsolete, commercial Spectrum IF is available at The Spectrum Adventurer
site:

   http://home.virtual-pc.com/isblpx/index.html

Includes all games published by Level 9 and Melbourne House, many of
Adventure International's games, as well as games from a dozen other
commercial and homegrown publishers.  Don't ask me about the legality of
it, I'm just reporting the find.

And you'll likely find a Spectrum emulator for your system at:

   ftp://ftp.nvg.unit.no/pub/sinclair/emulators/spectrum/

-- Ivan

----------------------------------------------------------------------
Ivan Cockrum       http://home.texoma.net/~ivan/       ivan@texoma.net
----------------------------------------------------------------------
       Visit historic downtown CockrumVille, home of Hellacious Eats!


From jota@tiac.net Mon Aug 18 17:21:47 MET DST 1997
Article: 27660 of rec.arts.int-fiction
Path: news.lth.se!newsfeed.sunet.se!news99.sunet.se!news99.sunet.se!newsfeed2.luth.se!news.luth.se!erix.ericsson.se!uab.ericsson.se!news.algonet.se!newsfeed.direct.ca!news-feed1.tiac.net!posterchild!jota
From: jota@tiac.net (Admiral Jota)
Newsgroups: rec.arts.int-fiction,rec.games.int-fiction
Subject: ABCs of Adventuring
Date: 16 Aug 97 10:07:34 GMT
Organization: The Internet Access Company, Inc.
Lines: 41
Message-ID: <jota.871726054@sunspot>
NNTP-Posting-Host: sunspot.tiac.net
X-Newsreader: NN version 6.5.0 #2 (NOV)
Xref: news.lth.se rec.arts.int-fiction:27660 rec.games.int-fiction:25067

This was composed on ifMUD (fovea.retina.net 4000), by Whizzard, Psmith,
inky, and Jota. We hope you enjoy it.


The ABCs of Adventuring

by Admiral Jota, Dylan O'Donnell, 
G. Kevin Wilson, and Dan Shiovitz.

A is for Adventure, the first of them all;
B is for Brass lantern, so you don't take a fall.
C is for Compass, an unseen one you keep
D is for Drinking, eating and sleep.
E is for Everything you can carry along;
F is for language that's sometimes too <<strong>>.
G is for Grues, who slaver and bite;
H is for Hints, when it's been a long night.
I is for Infocom, the kings of the game;
J is for Jewels, money and fame.
K is for Klepto, whatever's not nailed down;
L is for Locomotion: N S E W U D.
M is for Mazes, that we all love to hate;
N is for NPCs, to duel or to date.
O is for Ordering, mice or mouse-holes;
P is for Puzzles, obstructing your goals.
Q is for Questions: >ASK FROG ABOUT KISS.
R is for Replies. "I don't know about this."
S is for Save, when the going gets tough;
T is for Thief, who'll steal all of your stuff
U is for Undo, to take a move back;
V is for Verbose, to help you keep track.
W is for Wait, if things happen too slow;
X is for XYZZY, the quick way to go.
Y is for You, whenever you play.
Z is for Zork; now go back to A.


--
Support the anti-Spam amendment!      /<-= Admiral  Jota =->\
Join at http://www.cauce.org/       -< <-= jota@tiac.net =-> >-
                                      \<-=- -=  -=-  =- -=->/


From mol@bartlet.df.lth.se Thu Aug 21 16:31:53 MET DST 1997
Article: 27787 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: [Inform] Removing entire player inventory
Date: 21 Aug 1997 16:16:16 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 58
Message-ID: <5thijg$aot$1@bartlet.df.lth.se>
References: <01bcacf2$c417f9e0$190da8c0@andrew.daikin.com.au> <erkyrathEF76wu.Ft6@netcom.com> <5tecsf$npm@mercury.king.ac.uk>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27787

In article <5tecsf$npm@mercury.king.ac.uk>,
Adrian Preston <te_s343@kingston.ac.uk> wrote:
>Andrew Plotkin (erkyrath@netcom.com) wrote:
>: Do *not* do
>
>: objectloop (i in obj) {
>:   remove i;          ! this will fail!
>: }
>
>: This makes perfect sense if you know how linked lists work. :-(
>
>Interesting, but why? Given that a container is the parent and contained
>objects the children: For an OO system, there should
>be no particular relationships between the children. 

On the contrary, there *must* be some sort of ordering of the
children; otherwise, how could you iterate over them?

>I would have thought that in an OO hierarchy, the third example would and
>should work.

This has nothing to do with OO. Similar things occur all over the C++
Standard Template Library, for example: removing the element of a container
pointed to by an iterator invalidates that iterator. Which is actually exactly
the thing that happens in

objectloop (i in foo)
    remove i;

Here the variable i is the iterator, and the statement remove i; makes the
iterator invalid, which means that the next iteration of the loop will do
something unexpected.

>If the programmer needs to know storage mechanisms for objects, in this
>case a linked list, is this not a deficiency of the Inform system?

The programmer doesn't have to know anything about the storage
mechanism. It does help to know about the "eldest sibling"
representation used in the object tree (to be precise, this is *not*
the storage mechanism, but a relation between objects; objects are
statically allocated, not stored as dynamically-allocated linked
lists), but it is by no means necessary.

The semantics of objectloop can be stated without any reference to linked
lists or siblings, however: the simple rule

"When the object loop is of the form objectloop (i in foo), the statements
remove i; and move i to bar; are illegal within the body of the loop"

would in principle be sufficient.

Perhaps the deficiency in the Inform system is that the compiler allows
this? It would be (moderately) simple to have the compiler disallow
it.
-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From graham@gnelson.demon.co.uk Thu Aug 21 20:24:48 MET DST 1997
Article: 27795 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-ge.switch.ch!news-zh.switch.ch!news-hh.maz.net!news-muc.maz.net!news-fra.maz.net!news.seicom.net!newsfeed.nacamar.de!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: The Z Machine?
Date: Thu, 21 Aug 1997 11:49:08 +0100 (BST)
Organization: none
Message-ID: <ant2110080b0M+4%@gnelson.demon.co.uk>
References: <5t97oo$tmu@polaris.aye.net> <19970821005201.UAA17094@ladder01.news.aol.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII
X-Newsreader: ANT RISCOS Marcel [ver 1.26]
Lines: 46
Xref: news.lth.se rec.arts.int-fiction:27795

In article <19970821005201.UAA17094@ladder01.news.aol.com>, LFrench106
<URL:mailto:lfrench106@aol.com> wrote:
> >Hi.  I have a question, and it's just out of curiosity.  Why is the
> imaginary
> >machine in which all Infocom and Inform games are executed 
> >called "The Z Machine?"  I know that the Inform files have extentions
> like
> >".Z5", ".Z8", etc, but where did the name come from?
> 
> Z stands for Zork. That's why the language Infocom used was called ZIL
> (Zork Implimentation Langauge).

It's actually a good question.  Infocom didn't call the object-code
format "the Z-machine": they had an assembler called ZAP which took
the assembly-language output from the compiler, ZILCH, and converted
it to ZIP.

Unfortunately they used the term ZIP to mean both the architecture
of the virtual machine and its interpreter (the "Zork Implementation
Program"), and even sometimes to mean story files.  This carried on
through EZIP, YZIP, etc., which we would now call Version 4
interpreters or the V4 virtual machine, and so on.

The problem was complicated for us, meaning Infocom hackers in the
early 1990s, by Mark Howell's ground-breaking interpreter Zip -- which
came to include ZIP, EZIP, etc. -- and the fact that there was a
file-compression format called ".zip", leading to confusion with
filenames at ftp.gmd.de.

The useful term "Z-Machine", meaning the architecture of the virtual
machine only, was (I'm pretty sure) not in circulation when I began
Inform in 1993 -- although people had written programs related to the
Z-Machine, they hadn't really written documents about it, with the
exception of some scraps by Mike Threepoint and a few others (mostly
listing the header format).  So the term had not then been needed.
I think the earliest document trying to specify the whole thing,
collating a lot of work by other people, was by me, but I was still
calling it "the ZIP".

I have a feeling that Marnix Klooster may have coined the term, but
there are numerous other suspects -- Stefan Jokisch?  Dave Doherty?
Mark Howell?  At any rate, it wasn't me.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From sgranade@phy.duke.edu Fri Aug 22 17:47:35 MET DST 1997
Article: 27822 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!news-peer.sprintlink.net!news.sprintlink.net!Sprint!newsxfer3.itd.umich.edu!agate!newsgate.duke.edu!nebula.phy.duke.edu!sgranade
From: Stephen Granade <sgranade@phy.duke.edu>
Newsgroups: rec.arts.int-fiction
Subject: Re: [TADS] HELP--URGENT: Disabling "x all"
Date: Fri, 22 Aug 1997 08:23:36 -0400
Organization: Duke University, Durham, NC, USA
Lines: 24
Message-ID: <Pine.SUN.3.91.970822081912.27167C-100000@nebula.phy.duke.edu>
References: <19970820030201.XAA13411@ladder02.news.aol.com> <leonlin-1908972313130001@ala-ca26-45.ix.netcom.com> <5tilg5$skg$1@goanna.cs.rmit.edu.au> <fake-mail-2108972131110001@van-52-0828.direct.ca>
NNTP-Posting-Host: nebula.phy.duke.edu
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
In-Reply-To: <fake-mail-2108972131110001@van-52-0828.direct.ca> 
Xref: news.lth.se rec.arts.int-fiction:27822

On Thu, 21 Aug 1997, Neil K. wrote:

>  I must agree with this. I'm not going to play a game that annoys me, and
> one in which the author sanctimoniously decides to remove 'verb all' in
> order to make things more tedious (and thus difficult) for me is likely to
> annoy me. Increasing the difficulty level of a game by making it more
> tedious is, in my opinion, counter-productive and a splendid example of
> poor design. It's like putting in a 5000-room maze or something.

Speaking only for myself, I sanctimoniously disable 'verb all' to lower
the number of brute-force solutions which are possible. At some point
_anything_ in IF can be considered tedium; there's a fine line between
making the players' task harder to help them experience the game and
making the players' task harder just because. It's the designer's job to
decide where to draw that line and then hope that many people agree with
their decision.

Stephen

--
  Stephen Granade                | Interested in adventure games?
  sgranade@phy.duke.edu          | Check out
  Duke University, Physics Dept  |   http://interactfiction.miningco.com



From joe.mason@tabb.com Sat Aug 23 01:44:15 MET DST 1997
Article: 27818 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!newsfeed.direct.ca!news.uunet.ca!tabb!joe.mason
Distribution: world
Newsgroups: rec.arts.int-fiction
Subject: [Inform] A Case of Identi
From: joe.mason@tabb.com (Joe Mason)
Message-ID: <66.10547.1727@tabb.com>
References: <01bcacf5$ff72a640$190da8c0@andrew.daikin.com.au>
Date: Thu, 21 Aug 1997 20:44:00 -0500
Organization: Timmins Area BBS (705)268-0801
Lines: 82
Xref: news.lth.se rec.arts.int-fiction:27818

"[Inform] A Case of Identi", declared andreww  from the Vogon ship:

a>In a "standard" game, most objects are described - locations and items
a>- but the player is not, except for a token response to "examine me".

a>How can the player be better defined - is there actually a "me"
a>object?  (There must be for the player to be able to refer to it - so
a>where is it kept?)

Personally, I like to create a custom "me" object and change to it in 
the Initialize routine:

Object Start_Room "Start Room"
  with
    description...

Object -> The_Player
  with
    description...

[ Initialize;
  ChangePlayer(The_Player);
  location==Start_Room;
];

You can probably also edit the default player; I've never actually 
bothered to check on that since this system works well for me 
(especially when I'm planning to change players throughout the game).

a>And how can more than one identity be set up, such as in HHG, where
a>the player is not always Arthur, but sometimes Zaphod, Trillian, &
a>Ford?

Ah.  You want the ChangePlayer command in Chapter 19.  (You want the 
rest of the chapter, too, but ChangePlayer is perhaps my all-time 
favourite Inform routine...)

a>I would also be interested in peoples opinions how the player can be
a>"better defined" generally, as well as technically (through the
a>mechanics of Inform).

The player is mostly defined through their reactions to the world.  I 
think *all* the descriptions in the game have to be written in the 
player's voice, ie. very subjectively.

For example, here's a segment of a game I was writing.  I've got the 
prologue written, but I wasn't going to release it until I wrote more of 
it; then I started on other projects.  (You all know the story...)


>get all
Bors' sword: Taken.
body: Though Bors does not deserve to lie here in the stronghold of your 
enemy, his weight would slow you down too much. Much as it grieves you, 
you must leave him behind.

>x bors' sword
A functional blade, in perfect condition. Bors was always careful with 
his weapons.

>x guard's sword
A short, broad-bladed stabbing weapon. The hilt is wider then most, 
which could make for a somewhat awkward grip, but otherwise it seems to 
be nicely balanced.


In this transcript, you're playing a professional soldier.  I wrote the 
description of the guard's sword to be very analytical: you're 
evaluating it for practical use.  I use the technique again later, when 
the command "x pile of bodies" gives a brief tactical analysis of the 
last stand of the battle.  This shows that matters of war are second 
nature to the player.

Later on, I plan to change to a different point of view, which would see 
the same things completely differently.  I hadn't decided on a voice for 
that character yet, but I hope my example is clear: by including the 
character's associations and feelings in descriptions, you make the 
player see the world through their eyes.

Joe

 CMPQwk 1.42 9550 Vultures only fly with carrion luggage.


From mol@bartlet.df.lth.se Sat Aug 23 15:03:37 MET DST 1997
Article: 27843 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: [TADS] Disallowing "all" selectively - one solution
Date: 23 Aug 1997 15:00:51 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 47
Message-ID: <5tmmu3$e7h$1@bartlet.df.lth.se>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27843

I'm worried. Here I am in the middle of a rather heated discussion about
how (and whether) to disallow things like "examine all" in a TADS game,
and I totally forget that I've made some attempts to solve the problem
myself. Must be the onset of premature senility, I suppose.

Anyway, when I wrote "Uncle Zebulon's Will", I modified the TADS
library so that each object in scope could ask to be excluded from
"all". For example, when the player types "take all", a hidden object
wouldn't be taken, unless the player had already discovered it. This
particular problem can of course also be solved by not putting the
object into scope until it's found, but in some situations that's not
enough, or inconvenient - you want the object to be in scope, so you
can refer to it explicitly, but you don't want it included by default
in any action.

Another example: if you have in your possession a number of (edible)
mushrooms and one (deadly) toadstool, it would be reasonable to have
"taste all" skip the toadstool, but you'd still want to be able to taste
it by explicitly typing "taste toadstool".

Anyway, my code gives each item in the game a method no_all(verb,
prep, io) that you can override to return true if you want the object
to be excluded from "all" with that perticular verb (and preposition +
indirect object, when applicable). By default it always returns nil
which means "include me in 'all'". 

So for the toadstool, you could give it the method

    no_all(verb, prep, io) = {
	return (verb = eatVerb or verb = tasteVerb);
    }

to exclude it from "eat all" and "taste all".


The code is in the file z_std.t, included in the Zebulon source
distribution:
ftp://ftp.gmd.de/if-archive/games/source/tads/zeb2_src.zip.

To see examples of how it is used, grep the other .t files in the 
distribution for the string "no_all".


-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From mol@bartlet.df.lth.se Sun Aug 24 16:47:53 MET DST 1997
Article: 27869 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: Nonlinearity
Date: 24 Aug 1997 16:41:42 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 141
Message-ID: <5tph76$nvi$1@bartlet.df.lth.se>
References: <01bcb083$e874bbe0$539f72ce@hammurabi.blarg.net>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27869

In article <01bcb083$e874bbe0$539f72ce@hammurabi.blarg.net>,
Brandon Van Every <vanevery@blarg.net> wrote:
>Howdy folks, my name's Brandon and I just read a host of DejaNews
>back-posts on the keywords "nonlinear."  (And also "non-linear," just for
>pedantry. :-)  I noticed a recurring theme in the threads.  Generally
>speaking, IF works are deemed to have a beginning, a middle, and an end,
>and if the middle can be traversed in many different ways, the game is
>called "nonlinear."  I'd like to offer a perception on this, based on many
>years of playing text adventures, graphics adventures, etc.:
>
>	If the beginning and end are perceptible, then the game is linear.

IMAO, what you're offering is not just a "perception", but you're
trying to re-define the term "non-linear" as applied to games. While I
can see your point, and think that the distinction you are making
between what you call "linear" and "non-linear" is important, I think
that re-defining the terminology is a really bad idea, for several
reasons:

1) Re-defining established terminology always leads to
confusion. "Let's see, he was criticizing my game for being too
linear. Did he mean lienar in the old sense, or in Brandon's sense?" 

2) The "traditional" distinction between "linear" and "non-linear"
games really is quite important from a game-play point of view. I'll
try to explain why below.

3) From what I understand of your article, "linearity" really isn't a
very good metaphor for what you're aiming at. The terms "linear"
suggests something that looks like a line, and if you draw a decision
graph for a "traditionally linear" game, then it will indeed *look*
linear (essentially, a straight line with little dead-end branches for
all the wrong decisions you can make).


>What I'm saying is that if you want to walk through the alphabet from A to
>Z, and you know about A and you know about Z, then it is really of no
>consequence if you do
>
>ABCDEFGHIJKLMNOPQRSTUVWXYZ
>or
>AIUKBLVGNMWCTHXYOSFPIQERJDZ

The point you're misssing is that it's of *great* consequence from the
game-playing, as well as the artistic, point of view whether the game
*forces* you to do things in a certain order or not. 

Linear games (in the traditional sense) are easier to write, because
the the author can be sure that when the player gets to scene D, he's
already experienced scenes A, B and C. From this point of view, a
highly non-linear game is like a play where the audience can choose to
see the acts in any order they like. Imagine what "Hamlet" would be
like if the audience had the option of seeing the final scene before
knowing about the ghost?

On the other hand, the player of a linear game (still in the
traditional sense) often feels "trapped" and constrained by being
forced to do things in a certain order. This is especially true if
he's stuck on some problem, say, getting the key to unlock the
wizard's castle. It makes a great difference to the player if he is
stuck at that point, or if he has the choice of going away and
exploring another part of the world while pondering the problem of the
key.

>The result is that you've still covered all the letters A..Z.  Players are
>quite capable of remembering how many sub-problems they've dealt with. 
>They routinely employ a breadth-searching algorithm, asking themselves "how
>many areas have I explored?"  "Have I opened up all the doorways, walked
>down all the passages?"  More abstractly, "have I taken all the branches
>yet?"  Or more concretely, "have I gotten all the objects/keys yet?"

This, of course, rests on the entirely unwarranted assumption that the
player knows of all the sub-problems beforehand.  You seem to be
thinking that in a linear game (again, in the traditional sense), the
player knows the entire plot of the game as soon as it starts, that he
is given, as it were a list of problems B, C, D, ..., Y and is told
that he has to solve them in that order, whereas in a non-linear game
he is given the same list and told that he can solve them in any
order.

Of course, things aren't like that in very many games. In most IF,
linear or non-linear, the player starts out with zero knowledge, and
only gradually learns of the problems he has to solve (or the plot
twists he will go through, in less puzzle-oriented IF). The crucial
difference is that in a linear game, the player is at first handed B,
then, once he's past it, he's handed C, once he's past that he's
handed D, and so on. In a non-linear game, he's perhaps handed B, C, D
and E at a time.

>The
>archetypical example of this narrative structure was Zork I.  Collect the
>20 treasures of Zork, then you get to exit the game.  So I ask what is the
>point of calling such plot devices "nonlinear."  Gaining B..Y is all just
>an unordered or semi-ordered easter egg hunt, so why should we fool
>ourselves into thinking we've achieved more than a moderate tweak of a pure
>linear plotline?

You're taking a bird's eye's view of a piece of IF, viz. the view of
somebody who's already solved it and knows all the problems and plot
twists. This view is appropriate if you're talking about
re-playability (and you are entirely right in that re-playing Zork,
solving the puzzles in a different order, doesn't add very much to the
experience). But it doesn't mean that the difference between linear
and non-linear in the traditional sense isn't important.

>Often people say the game is more nonlinear if the middle is "wide."  As
>the middle gets larger and larger, the illusion of flexibility can become
>greater.

In the following you are taking a slightly different tack, arguing for
expanding the possibilities in the "middle" part of the game towards
an infinite array of possibilities. I'll jump right to the conclusion:

>Simply put, get rid of your linear assumptions about what the story is, and
>what the goals are, and then you'll have a nonlinear narrative.  Call it
>"character development."  *Your* character development, as you play the
>game.

...which seems to be advocating the kind of IF championed by the
"simulationist" school. These ideas have great merit. They also offer
immense practical difficulties of implementation. My own opinion is
that we're talking about a different medium than today's plot-driven
adventure games (where the journey from A to Z is the important
thing). Of course, this medium has just as much a right to be called
"IF" as the Infocom-school of IF has.

I will not try to argue the relative merits of these two media. I
think that both have a right to exist, that both *should* exist, and
that they are sufficiently different that one shouldn't try to fit
them both into the same procrustean bed. 

The purpose of this article is simply to counter your position that the
traditional distinction between "linear" and "non-linear" plots within
the medium of plot-driven IF is of no importance, and to argue that
you really should try to find some other terminology to avoid
confusing people. 

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From erkyrath@netcom.com Mon Aug 25 10:02:44 MET DST 1997
Article: 27884 of rec.arts.int-fiction
Newsgroups: rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!globalcenter1!news.primenet.com!nntp.primenet.com!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!ix.netcom.com!erkyrath
From: erkyrath@netcom.com (Andrew Plotkin)
Subject: Re: Nonlinearity
Message-ID: <erkyrathEFG5Kv.6Dv@netcom.com>
Organization: Netcom On-Line Services
X-Newsreader: TIN [version 1.2 PL2]
References: <01bcb083$e874bbe0$539f72ce@hammurabi.blarg.net>
Date: Mon, 25 Aug 1997 02:00:31 GMT
Lines: 72
Sender: erkyrath@netcom19.netcom.com
Xref: news.lth.se rec.arts.int-fiction:27884

Brandon Van Every (vanevery@blarg.net) wrote:
>  I noticed a recurring theme in the threads.  Generally
> speaking, IF works are deemed to have a beginning, a middle, and an end,
> and if the middle can be traversed in many different ways, the game is
> called "nonlinear."  I'd like to offer a perception on this, based on many
> years of playing text adventures, graphics adventures, etc.:

> 	If the beginning and end are perceptible, then the game is linear.
>
> What I'm saying is that if you want to walk through the alphabet from A to
> Z, and you know about A and you know about Z, then it is really of no
> consequence if you do
>
> ABCDEFGHIJKLMNOPQRSTUVWXYZ
> or
> AIUKBLVGNMWCTHXYOSFPIQERJDZ

{"I" twice? :-)}

Mmm. First of all, I agree with what Magnus said: the current meaning of 
"linear" is well-known and useful, and not likely to change.

On to your actual point: 

There are a couple of ways a story can be nonlinear, while still having a 
fixed beginning and end.

One is the trivial one you mention -- a bunch of unrelated events, like
getting the treasures in Zork. Neither the player nor the author really
cares what order they happen in. 

However, matters can go a little deeper. There may be different paths of
events that lead to a single conclusion: ABCZ or ABDZ or AEFZ, in your
analogy. These do in fact lead to different stories, even if all the
stories end the same way. The different paths can be *significantly*
different -- in terms of the story, even if not the game mechanics.  They
may lend very different implications to the ending, or just leave the
player with different things to think about. I'm thinking of "I-0" here; 
there are lots of different ways to "win", and in addition to the 
different places you go to and the different people you meet, the 
protagonist's character can develop somewhat differently.

Or: The *events* in the plotline may not be the same as the puzzles in the
game. I guess this is my basic objection to your POV; there can be a lot 
going on in a game which *is* different depending on how you scramble it 
around. It's not just a matter of getting the crystal skull or the 
trident first. Where you go along the way can be significant.

> Simply put, get rid of your linear assumptions about what the story is, and
> what the goals are, and then you'll have a nonlinear narrative.  Call it
> "character development."  *Your* character development, as you play the
> game.

This is one kind of game. I'm generally interested in writing the more 
traditional kind -- I have a linear story and I want to tell it. A 
"nonlinear story", in the sense that you're using the word, is just 
something I've never wanted to create. Well, except for the "Window" 
experiment.

Of course, they're not completely separate categories either. I'm
currently working on an idea where there's an overall linear story, which
is also a pretty linear game. However, one particular side matter can
develop and end in a few different ways -- within certain limits,
admittedly. It doesn't affect the denoument of the plot; but players may
find it important anyway. 

--Z

-- 

"And Aholibamah bare Jeush, and Jaalam, and Korah: these were the
borogoves..."


From martin.jerabek@siemens.at Mon Aug 25 11:01:48 MET DST 1997
Article: 27890 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!news-ge.switch.ch!news-fra1.dfn.de!news-was.dfn.de!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!EU.net!newsfeed.Austria.EU.net!siemens.at!news.sie.siemens.at!not-for-mail
From: Martin Jerabek <martin.jerabek@siemens.at>
Newsgroups: rec.arts.int-fiction
Subject: Inform 6 16-bit MSDOS port failed
Date: 25 Aug 1997 08:22:14 GMT
Organization: Siemens AG Austria
Lines: 26
Sender: Hr.Martin Jerabek <jerabek@mx5217.gud.siemens.at>
Message-ID: <5trfbm$daf@scesie10.sie.siemens.at>
NNTP-Posting-Host: mx5217.gud.siemens.co.at
X-Newsreader: TIN [UNIX 1.3 unoff BETA 970516; MX500I SINIX-M 5.41]
Xref: news.lth.se rec.arts.int-fiction:27890

Just in case somebody's waiting for it: I aborted the attempt of porting
Inform 6.13 to real mode MSDOS because it's much to slow. I had to put
nearly everything into overlays to get enough free memory and this
causes excessive thrashing, of course. On my hardware (8088 7.15 MHz,
ZIP drive) compiling the library 6/5 takes nearly 3.5 hours and even
the first version of "ruins" from the Designer's Manual takes more than
18 minutes using the precompiled libraries. The produced Z-files are not
entirely correct but I won't try to find the reason for it since it is
too slow for me and I'm currently out of altruism. :-) (My guess is that
there are assumptions in the source code that ints are 32 bit although
the int32 type should be used in such cases; at least I found one such
case in BPATCH.C.)

Well, I'll check out the other languages or finally learn to put up with
the noisy fans and harddisks in my other computers...

ObInfocom: Is the G in GNUSTO silent?

Jerry,
who is currently reading the LToI manuals

-- 
Martin "Jerry" Jerabek in /earth/europe/austria/vienna
mailto:martin.jerabek@siemens.at
Disclaimer: That is my opinion, it is mine and belongs to me and I own
it, and what it is too. (paraphrasing Anne Elk (Miss))


From mol@bartlet.df.lth.se Tue Aug 26 10:37:29 MET DST 1997
Article: 27908 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: language question
Date: 26 Aug 1997 10:35:17 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 97
Message-ID: <5tu4g5$nsq$1@bartlet.df.lth.se>
References: <33FF1444.4714@erols.com> <340286A6.6D53@juno.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27908

In article <340286A6.6D53@juno.com>, Ron Hatch  <ronhatch@ix.netcom.com> wrote:
>Billy wrote:
>> 
>> Hey there.
>> Thanks for your time.
>> I find that Inform is too 'codey' for me.
>> Are there any good higher-level text adv. languages
>> out there?
>
>I assume you're using the normal definition of a "higher-level"
>language.  To most programmers, the epitome of a "low-level" language is
>assembly language,

That's true.

> and a good example of a "high-level" language is
>Basic. 

But that's *not* true. Basic is a relatively high-level language, but
there are languages that are much higher-level than that.

The "level" of a language refers to its level of _abstraction_: how
far away it takes you from the nitty-gritty details of the
machine. Basic is high-level because you don't have to worry about
things like machine addresses, internal representations and so on, but
it's low-level in the sense that most operations are still fairly
basic (pardon the pun). 

> So when you're asking for a "higher-level" language you want
>something designed for beginners.

That's a rather strange way of putting it. High-levle languages are
usually not designed specifically for beginners, but to make things
easier for programmers at all levels.

In the case of IF languages, a high-level language (compared to
Inform) would be one where you work exclusively with high-level
concepts such as rooms, chairs, NPC's, etc, without having to worry
about the low-level details of how to implement their
behaviour. Inform is low-level in the sense that you have to do rather
a lot of coding at a level much lower than this (though still at a
much higher level than if you were writing Z-code directly).

TADS and Hugo both are on about the same level as Inform in this
respect: you'll have to do a lot of coding in a C-like language, as soon
as you want to override the default behaviour of things.

>Alas, the consensus seems to be that the high-level IF languages are
>low-quality.

At first, we must define whether there are any high-level IF
languages.  Most attempts at such languages fail because they choose
the easy way out: avoid low-level coding by disallowing it! That is,
you can build a world using high-level objects, but you can't change
their behaviour in the flexible way that you can with Inform.

AGT seems to be high-level up to a limit: you can write working, but
fairly primitive, games without delving into low-level details, but
when you want to do something advanced, things get very low-level
indeed.

The only working (in the sense that people actually write real games
with it) higher-level system that has gained any wider following yet
seems to be Alan. However, there still are things you can't do with
Alan (such as talk to NPC's about things that you can't see). I
haven't used it myself, but people keep saying nice things about it.



Oh, finally, my own theory about why it's so hard to design a
higher-level IF language:

IF programming to a large extent deals with high-level concepts that
are relatively easy to express at a high level of
abstraction. However, these objects also exhibit very complex
behaviour, and modelling this behaviour calls for a very flexible
language. The easiest way of making a language flexible is to allow
access to the details behind the abstractions, but this also makes the
language more low-level.

I'm not saying that it *has* to be that way, only that it's hard to be
abstract and flexible at the same time. The resources devoted to IF
language design are very limited indeed (maybe ten people worldwide
are doing this, *as a hobby*). Advances in other areas (such as world
modeling in AI) may lead to better IF languages. Or perhaps the
commercial designers of graphic IF will start emphasizing flexible,
complicated behaviour over flashy graphics and video clips, and in
that case they will need to develop better tools for describing it -
high-level languages, for example.




-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From graham@gnelson.demon.co.uk Tue Aug 26 15:00:31 MET DST 1997
Article: 27915 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform 6 16-bit MSDOS port failed
Date: Tue, 26 Aug 1997 12:37:49 +0100 (BST)
Organization: none
Message-ID: <ant261149e61M+4%@gnelson.demon.co.uk>
References: <5trfbm$daf@scesie10.sie.siemens.at> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII
X-Newsreader: ANT RISCOS Marcel [ver 1.26]
Lines: 34
Xref: news.lth.se rec.arts.int-fiction:27915

In article <5trfbm$daf@scesie10.sie.siemens.at>, Martin Jerabek
<URL:mailto:martin.jerabek@siemens.at> wrote:
> Just in case somebody's waiting for it: I aborted the attempt of porting
> Inform 6.13 to real mode MSDOS because it's much to slow. I had to put
> nearly everything into overlays to get enough free memory and this
> causes excessive thrashing, of course. On my hardware (8088 7.15 MHz,
> ZIP drive) compiling the library 6/5 takes nearly 3.5 hours and even
> the first version of "ruins" from the Designer's Manual takes more than
> 18 minutes using the precompiled libraries. The produced Z-files are not
> entirely correct but I won't try to find the reason for it since it is
> too slow for me and I'm currently out of altruism. :-) (My guess is that
> there are assumptions in the source code that ints are 32 bit although
> the int32 type should be used in such cases; at least I found one such
> case in BPATCH.C.)

Please email me about this!  I can fix that one, anyway.  I have
tried to avoid such assumptions, but you're the only 16-bit porter
left, I think.
 
> Well, I'll check out the other languages or finally learn to put up with
> the noisy fans and harddisks in my other computers...

Yes, in a way I miss my old Acorn A310.  It was so silent that I could
use it as an alarm clock.  Sitting at my present behemoth is like
talking to an expensive vacuum cleaner.

> ObInfocom: Is the G in GNUSTO silent?

Umm... it's like the "g" in "gnostic", rather than the "g" in "gnome"?
Heaven knows.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From mol@bartlet.df.lth.se Wed Aug 27 11:07:47 MET DST 1997
Article: 27950 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Re: language question
Date: 27 Aug 1997 11:04:49 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 96
Message-ID: <5u0qjh$m4$1@bartlet.df.lth.se>
References: <33FF1444.4714@erols.com> <340286A6.6D53@juno.com> <5tu4g5$nsq$1@bartlet.df.lth.se> <3403D9F1.4445@juno.com>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27950

In article <3403D9F1.4445@juno.com>, Jeff Hatch  <jeffhatch@juno.com> wrote:
>Magnus Olsson wrote:
>
>> IF programming to a large extent deals with high-level concepts that
>> are relatively easy to express at a high level of
>> abstraction. However, these objects also exhibit very complex
>> behaviour, and modelling this behaviour calls for a very flexible
>> language. The easiest way of making a language flexible is to allow
>> access to the details behind the abstractions, but this also makes the
>> language more low-level.

>High-level languages are those with complex built-in features that don't
>translate directly into machine code.  For instance, Basic is high-level
>because it has "Print" and "Input" commands.  C doesn't have those
>commands, but it has special character string manipulation rules, so
>it's a higher-level language than assembly language.

When we're discussing specific lnaguge features like this, we come to
the somewhat confusing conclusion that sometimes language A is
higher-level than language B, and sometimes it's the other way round.

>Allowing access to
>details doesn't turn a high-level language into a low-level one.  If it
>did, PC-Basic would be low-level, since "POKE" and "PEEK" allow direct
>memory access!

That's true. What makes language A lower-level than language B is not
that A _allows_ you to do low-level programming, but that it _forces_
you to do that, when language B doesn't.

>But to an experienced programmer, C is much easier to use than Basic. 

Not when it comes to string handling (which I think is a better
example than "print"). All but the most primitive Basics have
high-level string handling primitives - you can concatenate strings
and extract substrings without bothering about how strings are
implemented. C doesn't - the C library has string-handling functions,
but the programmer has to worry very much indeed about how strings are
implemented, or he'll have some very nasty surprises.

On the other hand, C is higher-level than "classic" Basic when it
comes to control constructs: you don't have to bother with line
numbers and goto's in C.  (To be fair, you don't in modern Basics
either).

So comparing languages for "level" is a complex issue.

>That's how you can be abstract and flexible at the same time!  Create a
>language that's extremely low-level.  Don't bother to define Rooms,
>Fuses, Demons, Verbs, or Actors at all.  Make your first priority in
>creating this language flexibility; make ease of use your second
>priority.  Once you've created this language, build a library that can
>handle the "high-level" stuff.

Indeed. Modern languages are extensible, that is, you can write high-level
libraries that hide the language itself from the programmer.

Inform's parser is a good example of this: the language itself knows
zilch about natural language grammar, parsing, and all that (except
for some very low-level primitives used by the parser). By including
Graham's parserm.h, you extend the language to include a high-level
way of describing grammar.

Something similar could no doubt be done for other parts of the Inform
library as well. For example, a special notation could be developed
for describing NPC "scripts", and this would hide the (relatively)
low-level programming needed to get an Inform NPC to work today.

However, my point is that *today* no such thing exists for Inform,
hence you have to delve into low-level (not assembly-language, but
low-level compared to the concepts you're dealing with) programming as
soon as you want an NPC that actually does anything.

>Yes, the resources devoted to IF language design are small, and always
>have been.  But by the same token, it wouldn't take much effort to raise
>the standard.  Inform was primarily the result of one man's work, wasn't
>it?
>
>I believe that one dedicated programmer could create an abstract yet
>flexible IF language in just two years.  Perhaps a year and a half, if
>his talented younger sibling began assisting when the project was 50
>percent complete.  :)

The problem is, of course, where does he get the funding to do this?
The cost of two man-years of experienced programming time is several
hundred thousand dollars.

Of course, he could do it in his spare time, as a hobby, just as
Graham has done with Inform. I've felt the urge to do so several
times. Then I've thought that it's much more fun to spend the time
writing actual games, even with today's limited tools.

-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


From graham@gnelson.demon.co.uk Wed Aug 27 11:08:15 MET DST 1997
Article: 27949 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!dispatch.news.demon.net!demon!gnelson.demon.co.uk!graham
From: Graham Nelson <graham@gnelson.demon.co.uk>
Newsgroups: rec.arts.int-fiction
Subject: Re: Inform 6 16-bit MSDOS port failed
Date: Wed, 27 Aug 1997 00:28:54 +0100 (BST)
Organization: none
Message-ID: <ant262354d07M+4%@gnelson.demon.co.uk>
References: <5trfbm$daf@scesie10.sie.siemens.at> <5tstkm$9i0@hiway1.exit109.com> <5tuavq$ggu$1@bartlet.df.lth.se> <5tuf0j$ph3@scesie10.sie.siemens.at> <erkyrathEFJ1EM.G39@netcom.com> 
NNTP-Posting-Host: gnelson.demon.co.uk
X-NNTP-Posting-Host: gnelson.demon.co.uk [194.222.103.187]
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII
X-Newsreader: ANT RISCOS Marcel [ver 1.26]
Lines: 38
Xref: news.lth.se rec.arts.int-fiction:27949

In article <erkyrathEFJ1EM.G39@netcom.com>, Andrew Plotkin
<URL:mailto:erkyrath@netcom.com> wrote:
> 
> The problem is that Inform 6 is complicated enough that it requires more 
> than 640K of memory. That's all. 
> ...
> Inform 5 is really perfectly viable as an IF language. Many things are 
> messier than in Inform 6, but nothing I've found is an order of magnitude 
> harder to do.

Well, yes.  One of the points of Inform 6, though, was to run
about three times faster; plus, it's a bigger program, and does
more.  Both factors tend to reel in memory.  Inform 5 ran in
two passes to resolve forward references: Inform 6 runs in one,
but making a host of notes of things it must eventually sort out.
Also, Inform 5's speed was often I/O bound on slow media like
floppy-disc drives: Inform 6 buffers input much more heavily,
which is faster, but takes up memory.  Also, again, if you want
to use the linker (new to Inform 6), you have to give up a little
workspace memory for that.  Finally, as you say, Inform 6 itself
is a larger program, consuming more memory simply in its own bulk.

Yet another factor is that Inform 6 makes more memory allocations,
of smaller chunks of memory, compared with Inform 5: so if
"malloc" is implemented badly on your machine, the usage is
exaggerated.

The irony is that it actually uses about 100K less memory than
Inform 5 in the everyday business of compilation, but the above
factors outweigh that...

You can configure Inform 6 back pretty heavily using the memory
settings: its default options are quite greedy because for the
great majority of today's users memory is not a problem.

-- 
Graham Nelson | graham@gnelson.demon.co.uk | Oxford, United Kingdom



From ah56846@uta.fi Wed Aug 27 11:08:22 MET DST 1997
Article: 27931 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!feta.direct.ca!newsfeed.direct.ca!news.algonet.se!news3.funet.fi!news.funet.fi!news.cc.tut.fi!not-for-mail
From: Aapo Haapanen <ah56846@uta.fi>
Newsgroups: rec.arts.int-fiction
Subject: Re: "Porculi Matris" (was: Is this a puzzle?)
Date: 26 Aug 1997 20:01:33 GMT
Organization: University of Tampere, Finland
Lines: 22
Message-ID: <5tvcmt$juj$1@cc.tut.fi>
References: <5tcghd$asr$1@joe.rice.edu> <5tohbe$626$2@news01.micron.net> <5tosh4$kgf$1@bartlet.df.lth.se> <Pine.SGI.3.95L.970826142256.9329A-100000@ebor.york.ac.uk> <5tv634$a47$1@bartlet.df.lth.se>
NNTP-Posting-Host: vuokko.uta.fi
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
X-Newsreader: TIN [UNIX 1.3 unoff BETA 970406; sun4m SunOS 5.5]
Xref: news.lth.se rec.arts.int-fiction:27931

Magnus Olsson <mol@bartlet.df.lth.se> wrote:
-snip-
: Which leads to the translation "We are all mothers' piglets" which
: sounds like total gibberish.

: However, there's a popular Swedish folk song called "Morsgrisar r vi
: allihopa" which has the same literal meaning. The Swedish word
: "morsgris", or "mother's piglet", is a pejorative term for a child (or
: adult!) who is overly dependent on his or her mother. My dictionary
: gives the English translations "Mother's darling" and "milksop".

: Whether this Swedish folk song is widely known in Finland as well is
: of course an open question :-).

Song "Porsaita idin oomme kaikki" is widely known in Finland.  I think
that we are talking about the same song.  The finnish name translates to
"We are all mothers' piglets" too.

This interesting piece of trivia brought to you by:   +--------------+
                                                       aapo  haapanen
                                                       ah56846@uta.fi
                                                      +--------------+


From peuha@cc.helsinki.fi Wed Aug 27 11:08:30 MET DST 1997
Article: 27948 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!feed1.news.erols.com!feta.direct.ca!newsfeed.direct.ca!newshub1.home.com!news.home.com!news1.best.com!uninett.no!news-stkh.gip.net!news.gsl.net!gip.net!news3.funet.fi!news.funet.fi!news.helsinki.fi!not-for-mail
From: Esa A E Peuha <peuha@cc.helsinki.fi>
Newsgroups: rec.arts.int-fiction
Subject: Re: "Porculi Matris" (was: Is this a puzzle?)
Date: 27 Aug 1997 08:48:10 GMT
Organization: University of Helsinki
Lines: 20
Message-ID: <5u0pka$1dl$1@oravannahka.Helsinki.FI>
References: <5tcghd$asr$1@joe.rice.edu> <5tohbe$626$2@news01.micron.net> <5tosh4$kgf$1@bartlet.df.lth.se> <Pine.SGI.3.95L.970826142256.9329A-100000@ebor.york.ac.uk> <5tv634$a47$1@bartlet.df.lth.se>
NNTP-Posting-Host: kruuna.helsinki.fi
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-Trace: oravannahka.Helsinki.FI 872671690 1461 (None) 128.214.205.14
X-Complaints-To: usenet@oravannahka.Helsinki.FI
X-Newsreader: TIN [UNIX 1.3 unoff BETA 970613; sun4m SunOS 5.5]
Xref: news.lth.se rec.arts.int-fiction:27948

On 26 Aug 1997 20:08:36 +0200 in article <5tv634$a47$1@bartlet.df.lth.se>
Magnus Olsson <mol@bartlet.df.lth.se> wrote:
: However, there's a popular Swedish folk song called "Morsgrisar r vi
: allihopa" which has the same literal meaning. The Swedish word
: "morsgris", or "mother's piglet", is a pejorative term for a child (or
: adult!) who is overly dependent on his or her mother. My dictionary
: gives the English translations "Mother's darling" and "milksop".

: Whether this Swedish folk song is widely known in Finland as well is
: of course an open question :-).

Yes, this song (called "Porsaita idin oomme kaikki" in Finnish) is well known
in Finland. However, the implied meaning of "morsgris" is lost in translation
(I didn't know it before, and certainly that doesn't make me an exception
among Finnish people).

-- 
Esa Peuha
student of mathematics at the University of Helsinki
http://www.helsinki.fi/~peuha/


From dfan@thecia.net Wed Aug 27 12:43:57 MET DST 1997
Article: 27944 of rec.arts.int-fiction
Path: news.lth.se!eru.mt.luth.se!www.nntp.primenet.com!globalcenter1!news.primenet.com!nntp.primenet.com!news.maxwell.syr.edu!supernews.com!Supernews69!not-for-mail
From: Dan Schmidt <dfan@thecia.net>
Newsgroups: rec.arts.int-fiction
Subject: Re: Nonlinearity
Date: 26 Aug 1997 22:01:23 -0400
Organization: All USENET -- http://www.Supernews.com
Lines: 50
Sender: dfan@razumovsky.thecia.net
Message-ID: <87pvr0jsek.fsf@razumovsky.thecia.net>
References: <01bcb083$e874bbe0$539f72ce@hammurabi.blarg.net>  <340300A2.489@romulus.sun.csd.unb.ca>  <01bcb24c$bd7ee580$2e9f72ce@hammurabi.blarg.net> <Rc4iJGAY5zA0Iwi7@isla-mia.demon.co.uk>
NNTP-Posting-Host: 18211@206.40.163.3
X-Newsreader: Gnus v5.4.46/Emacs 19.34
Xref: news.lth.se rec.arts.int-fiction:27944

Terence Fergusson <taf@isla-mia.demon.co.uk> writes:

| Also, would anyone like to comment on the Ultima series?  Particularly,
| let's say, "Ultima 7 : The Black Gate" vs. "Ultima 7 : The Serpent
| Isle"?  "The Black Gate" has all manner of subquests, and non-linearity,
| while "The Serpent Isle" restricts your movement, and seems highly
| linear.  Comments?

I wrote a good deal of Ultima Underworld, which is not one of the above
two games but is fairly similar in many ways, being an Ultima.  For
example, here are eight subquests corresponding to the eight virtues,
etc.  Sometimes the quests depend on each other a bit (e.g., you can't
get to part 2 of quest B until you've gotten to part 3 of quest D).  But
there are usually a fair number of things you can do at once.  Then, at
the end, it all gets pretty linear again - in fact, I don't think the
last two levels succeeded that well.  RPG's do have the nice (sometimes)
property of also having the "gain experience and items" quest, which can
run in parallel with all the others but subtly interacts with them.

One of the interesting things about Underworld is that it was a
dungeon game, so there was (physical) level 1, level 2, etc.  We
specifically tried to avoid making the player clear out a level at a
time, but people were so used to playing that way (from games like
Wizardry) that they would refuse to go down a level until they had
cleared the current one out.  There was a monster on level 2 that
was almost impossible to kill when you first found it, which delayed
some people from going to level 3 for weeks...

We were actually very influenced by the Infocom games, and had to dumb
down a lot of puzzles because they were puzzles, and Warren Spector
(our producer) pointed out that in an Ultima, the player is always
told explicitly what to do; they're not supposed to have to infer
anything themselves.  Grrr.

I played around two thirds of Ultima 7, and remember feeling that it
was always pretty obvious what I had to do next, but I imagine the
game was actually designed less linearly than that.

Serpent Isle was a monstrosity; even Warren (the producer of that game
too) agrees.

For what it's worth, my favorite "Ultima" was Savage Empire.  I would
have been happy to see Origin churn out a few more games for the
"U6-machine."

-- 
                 Dan Schmidt -> dfan@alum.mit.edu, dfan@thecia.net
Honest Bob & the                http://www2.thecia.net/users/dfan/
Factory-to-Dealer Incentives -> http://www2.thecia.net/users/dfan/hbob/
          Gamelan Galak Tika -> http://web.mit.edu/galak-tika/www/


From mol@bartlet.df.lth.se Wed Aug 27 18:03:08 MET DST 1997
Article: 27956 of rec.arts.int-fiction
Path: news.lth.se!not-for-mail
From: mol@bartlet.df.lth.se (Magnus Olsson)
Newsgroups: rec.arts.int-fiction
Subject: Disabling "all"
Date: 27 Aug 1997 18:01:52 +0200
Organization: Societas Datori Universitatis Lundensis
Lines: 73
Message-ID: <5u1j1g$emp$1@bartlet.df.lth.se>
References: <19970820030201.XAA13411@ladder02.news.aol.com> <fake-mail-2108972131110001@van-52-0828.direct.ca> <5tjghf$kjb$1@bartlet.df.lth.se> <fake-mail-2208971956300001@van-52-0328.direct.ca>
NNTP-Posting-Host: bartlet.df.lth.se
NNTP-Posting-User: mol
Xref: news.lth.se rec.arts.int-fiction:27956

In article <fake-mail-2208971956300001@van-52-0328.direct.ca>,
Neil K. <fake-mail@anti-spam.address> wrote:
>In article <5tjghf$kjb$1@bartlet.df.lth.se>, mol@bartlet.df.lth.se (Magnus
>Olsson) wrote:
>
>> > I must agree with this. I'm not going to play a game that annoys me, and
>> >one in which the author sanctimoniously decides to remove 'verb all' in
>> >order to make things more tedious (and thus difficult) for me is likely to
>> >annoy me. [...]
>> 
>> You astonish me. If I'm to take your remarks
>> literally, then you're flat out refusing to play basically *any* game
>> written in Inform, and many TADS games as well.
>
> I said "is likely to annoy me". So, reading that literally...

Oh, well, in that case you're _likely_ to refuse to play basically *any*
game written in Inform, and many TADS games as well.

Which means that something is wrong.  Not with you, of course, but
with the authors' assumptions. The reason I reacted a bit strongly was
that we've been through all this several times before, and I thought
we'd reached a consensus that the only *essential* "all" is with
"take" and "drop". That was obviously wrong.

> And yes, actually, a lot of games do get on my nerves when they disallow
>"all" in a context that I'd want.

Could you give any more specific examples, please?

>> And where did you get the extraordinary idea that anybody would disallow
>> "all" to make the game more _tedious_? 
>
> Sure seems like it to me. If I type "examine all" and the game tells me I
>can't do that, that's annoying. 

I can only think of one case where an author in his or her right mind
would deliberately try to make things tedious for the player, and that
is to prevent brute-force solutions of puzzles. It's not a very good
method, of course.

And then there are the authors who aren't in their right minds :-).

>But if I type "examine all" and the game
>describes a list of all carried items plus any notable objects in the room
>that the game author deems interesting, then that makes sense to me.

To me as well, but there are a few pitfalls here. What if an object is
left out, and the player draws the conclusion that it doesn't exist,
or isn't interesting?


Some personal reflections:

As a player, I don't like "x all", because the resulting output tends
to break mimesis: I get a long infodump with maybe up to half a page
of text for each of twenty objects. But of course that's no reason for me
as an author to forbid my players from doing it.

In some games, there are NPC's that have vital information which you
can only get by asking them about a lot of different things. This is
one of the few cases where I really miss "all": it would be nice to be
able to say "ask oracle about all" and get a total braindump in
return. Of course, it's not very practical to implement.

A (hypothetical) example of an extremely "obliging" parser would be
one that accepted the verb "use" as a catch-all (some people have
proposed this, to avoid guess-the-verb problems), coupled with "all".
Such a parser could make the game almost self-solving: "use all on all". :-) 
-- 
Magnus Olsson (mol@df.lth.se, zebulon@pobox.com)
------    http://www.pobox.com/~zebulon   ------
     Not officially connected to LU or LTH.


