Newsgroups: comp.ai.philosophy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!swrinde!sgiblab!uhog.mit.edu!news.mathworks.com!solaris.cc.vt.edu!insosf1.infonet.net!internet.spss.com!markrose
From: markrose@spss.com (Mark Rosenfelder)
Subject: Re: Please outline Turing Test
Message-ID: <CzFGJu.E9L@spss.com>
Sender: news@spss.com
Organization: SPSS Inc
References: <zpc325aAc3pWZf0@pp78hsp.hsp.zer.de>
Date: Thu, 17 Nov 1994 19:52:41 GMT
Lines: 17

In article <zpc325aAc3pWZf0@pp78hsp.hsp.zer.de>,  <T.EICHER@HSP.zer.de> wrote:
>reading several articles in this newsgroup, I stumbled over a "Turing"
>test for AI. I wasn't able to find any explanation in the AI.faq,
>so could someone please outline this test for me ? 

The Turing Test is generally taken to work like this:
Take a human judge and sit her in front of a teletype.  The teletype is
connected either to another human being, or to an AI pretending to be human.  
The judge converses by teletype with the subject, on any topic.  If she
can't tell whether she's talking to a machine or a human being, the
machine can be considered intelligent.

Turing's original article proposing this test, "Computing Machinery and
Intelligence", is readily available in Dennett and Hofstadter's collection
_The Mind's I_.  (From this article it seems apparent that Turing intended
it not as an operational definition of intelligence, but as a thought
experiment designed to accustom people to the idea of machine intelligence.)
