From newshub.ccs.yorku.ca!torn!cs.utexas.edu!sun-barr!olivea!uunet!caen!umeecs!dip.eecs.umich.edu!marky Wed Aug 12 16:52:46 EDT 1992
Article 6595 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!torn!cs.utexas.edu!sun-barr!olivea!uunet!caen!umeecs!dip.eecs.umich.edu!marky
>From: marky@dip.eecs.umich.edu (Mark Anthony Young)
Newsgroups: comp.ai.philosophy
Subject: Re: Turing Test Myths
Message-ID: <1992Aug11.143819.22170@zip.eecs.umich.edu>
Date: 11 Aug 92 14:38:19 GMT
References: <2838@ucl-cs.uucp>
Sender: news@zip.eecs.umich.edu (Mr. News)
Organization: University of Michigan EECS Dept., Ann Arbor
Lines: 27

%r G.Joly@cs.ucl.ac.uk (Gordon Joly)
>
>> Eliza never passed the Turing Test.  Never, never, never, never, never.  Not
>> even once.  All we have is some anecdotes saying that some people thought they
>> were talking to a person when they were really talking to Eliza.  That hardly
>> counts as science!
>
>It did, with Feigenbaum's secreatry. She ask Feigenbaum to leave the room.
>
>And it definitely passed the "two second" test!!!!! Some people where
>fooled for a very short space of time...
>
The point is that that is _not_ the Turing Test.

The "two second" Turing Test would involve telling her that she might be 
talking to a machine (and providing a human for comparison purposes), and
then comparing Eliza's performance after two seconds with that of men 
immitating women for two seconds (over a teletype interface!).  Any guesses 
as to how well men would do in such a short test?

Besides, the fact that she asked Feigenbaum to leave the room does not mean
that she necessarily thought she was talking to a person.  She might have done
the same if she were putting her diary on-line.  I get really involved in some
computer games as well, to the point of swearing at it when it does something
I don't like, but that doesn't mean I think it's a person.

...mark young


