Newsgroups: comp.ai,comp.ai.philosophy,rec.arts.sf.science
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!portc01.blue.aol.com!portc02.blue.aol.com!howland.erols.net!netcom.com!wiml
From: wiml@netcom.com (Wim Lewis)
Subject: Re: AI Heaven
Message-ID: <wimlE1qCEz.631@netcom.com>
Organization: The Seattle Group
References: <329602B6.6829@mortimer.com> <5789j6$91a@dfw-ixnews4.ix.netcom.com> <8jip4SABEBmyEwUc@trenham.demon.co.uk> <jdunson-2811961334100001@ultraman.cc.vt.edu>
Date: Sun, 1 Dec 1996 10:13:46 GMT
Lines: 24
Sender: wiml@netcom4.netcom.com
Xref: glinda.oz.cs.cmu.edu comp.ai:42516 comp.ai.philosophy:49410

In article <jdunson-2811961334100001@ultraman.cc.vt.edu>,
James R Dunson <jdunson@vt.edu> wrote:
>  This is, to put it mildly, not a new idea.  Most large IRC servers
>have a strict "no bots" policy because of such things, and many 
>MUDs/MUSHs/MOOs/etc. are crawling with the darned critters.  Some years
>ago, I had hopes that through what could be considered a form of 
>a large-scale genetic algorithim this would result in some nifty 
>breakthroughs in Turing-test ideas, but most folks seem to have failed
>to get beyond "Heh, I've modified this old Eliza code to talk dirty!"

There's an interesting paper on a synthetic MUD player named Julia
at http://foner.www.media.mit.edu/people/foner/Julia/Julia.html .
(Especially the chapter titled "A sociological look...".) It's from '92;
I don't don't use MUDs much, but I assume the state of the art has
advanced.

Given the female name, lots of players try to pick her up. The paper's
author made a comment abut one such: "Frankly, it's not entirely clear
to me whether Julia passed a Turing test here or Barry failed one."

-- 
             Wim Lewis * wiml@hhhh.org * Seattle, WA, USA
    PGP 0x27F772C1: 0C 0D 10 D5 FC 73 D1 35  26 46 42 9E DC 6E 0A 88
                  USENET: No Fun Anymore since 1987
