From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!tdatirv!sarima Thu Feb 20 15:20:07 EST 1992
Article 3663 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!tdatirv!sarima
>From: sarima@tdatirv.UUCP (Stanley Friesen)
Newsgroups: comp.ai.philosophy
Subject: Re: Real-life Turing test
Message-ID: <408@tdatirv.UUCP>
Date: 11 Feb 92 21:33:37 GMT
References: <1992Feb10.235221.56220@spss.com>
Reply-To: sarima@tdatirv.UUCP (Stanley Friesen)
Organization: Teradata Corp., Irvine
Lines: 19

In article <1992Feb10.235221.56220@spss.com> markrose@spss.com (Mark Rosenfelder) writes:
|For those who still think the Turing Test is a sufficient test for
|intelligence, there is food for thought in the results of the Loebner Prize 
|Competition in Boston, ...

|The conversations were restricted by topic (to give the programs a fighting
|chance), and PC Therapist's topic was "whimsical conversation."  Some samples:

But that is not the Turing Test!!   It is only *unrestricted* conversation
that is truly discriminating, at least as far as the most important aspects
of consciousness are concerned.


Any half-way decent Expert System can pass a *limited* TT.

-- 
---------------
uunet!tdatirv!sarima				(Stanley Friesen)



