Message-ID: <3BB63AA9.A77D1087@csi.com>
Date: Sat, 29 Sep 2001 17:18:33 -0400
From: John Colagioia <JColagioia@csi.com>
X-Mailer: Mozilla 4.61 [en] (Win98; I)
X-Accept-Language: en
MIME-Version: 1.0
Newsgroups: rec.arts.int-fiction
Subject: Re: If you code an NPC with this good AI in Inform I'll eat my hat!
References: <20010910184059.00307.00000071@mb-bh.aol.com>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
NNTP-Posting-Host: 24.47.51.158
X-Original-NNTP-Posting-Host: 24.47.51.158
X-Trace: excalibur.gbmtech.net 1001797925 24.47.51.158 (29 Sep 2001 17:12:05 EST)
Organization: GBM Technologies Ltd
Lines: 14
X-Authenticated-User: jnc
X-Original-NNTP-Posting-Host: 127.0.0.1
Path: news.duke.edu!newsgate.duke.edu!nntp-out.monmouth.com!newspeer.monmouth.com!diablo.netcom.net.uk!netcom.net.uk!newsfeed.online.be!zur.uu.net!bos.uu.net!nyc.uu.net!excalibur.gbmtech.net
Xref: news.duke.edu rec.arts.int-fiction:93035

Robotboy8 wrote:

> Go to www.leedberg.com/glsoft and download Billy or Daisy.  They're
> chatterbots, a la Eliza, but smart.  Too smart.  Look around, and wonder at how
> much better _these_are than the NPC's in, say, Christminster or Trinity.  I
> will issue the following challenge: make a chatterbot in Tads or Inform that
> performs higher than a much-talked-to Billy or Daisy in a Turing test, and I'll
> send you a picture of me eating my hat.

But...aren't they pretty much just Markov process programs at the (looks like) word
level?  Any language with middling string processing could make that trivial.  It's
a first-order process, no less, from what I can tell.


