Newsgroups: sci.skeptic,alt.consciousness,comp.ai.philosophy,sci.philosophy.meta,rec.arts.books
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!gatech!rutgers!argos.montclair.edu!hubey
From: hubey@pegasus.montclair.edu (H. M. Hubey)
Subject: Re: Penrose and Searle (was Re: Roger Penrose's fixed ideas)
Message-ID: <hubey.786306282@pegasus.montclair.edu>
Sender: root@argos.montclair.edu (Operator)
Organization: SCInet @ Montclair State
References: <38tqh6$5qk@percy.cs.bham.ac.uk> <3b5d05$d2o@news-rocq.inria.fr> <Czzrvs.A1u@gpu.utcc.utoronto.ca> <3bfphr$6sj@news-rocq.inria.fr> <D03Lp9.L4H@gpu.utcc.utoronto.ca>
Distribution: inet
Date: Thu, 1 Dec 1994 18:24:42 GMT
Lines: 56
Xref: glinda.oz.cs.cmu.edu sci.skeptic:96801 comp.ai.philosophy:22979 sci.philosophy.meta:15194

pindor@gpu.utcc.utoronto.ca (Andrzej Pindor) writes:

>In article <3bfphr$6sj@news-rocq.inria.fr>,
>Mikal Ziane (Univ. Paris 5 and INRIA)  <ziane@monica.inria.fr> wrote:
>...........
>>This is what I understood of CR so far. I have not looked at it deeply
>>but there are two things which seemed rather clear.
>>1. it certainly does not prove that machine cannot be intelligent

>True. It does not prove or disprove anything. 
>>2. it suggests (to me) that passing TT is not a perfect def. of intelligence.
>>
>Really? How does it do it? When you judge other people's intelligence, don't
>you do it on the basis of some sort ot TT? Sure, this is not perfect, one
>makes mistakes (someone you think at first intelligent turns out to be a fool,
>who is only able to jugle a scientific jargon, without a clue what it means).

Maybe those who are anti-TT [in a manner of speaking] are trying to
question the relativity of TT. I don't see much of a problem here
that statistical testing could not solve.

for example, in statistical testing of a hypothesis you can have
four outcomes [could apply to humans too, stretching the idea].


11	We call it True(1) when it is in fact True(1)
10	We call it True when it is False  (Error)
01	We call it False when it is TRue  (Error)
00	We call it False when it is False

The errors are called Type I and II errors in statistical hypothesis
testing. The other two are correct. When this kind of possibility is
appplied to the TT (or humans passing judgements about each other)
then it's possible that some people could erroneously judge the
computer to be human when it isn't or judge a human to be a computer.

WE can have the same problems with humans. Someone talking gibberish
could fool some people but not the specialists in the field. 

But that is exactly the strength of the Turing test. It's a statistical
test. If a machine can pass for human, then how could we say it isn't
intelligent. The loopholes have been plugged by the TT. So far no one
has even come up with a better alternative. What would be really 
interesting is if some one wrote a program that takes those standardizes
IQ tests that pschologists seem to be fond of giving to humans :-)..

Since the ETS is already field testing ways of giving the SAT's
and GRE's using the network, maybe one day the IQ tests will also
become machine readable, and then it would be even more fun to
see computers get the highest scores on IQ tests, while the AI
folks watch the psychologists squirm :-)...

--
						-- Mark---
....we must realize that the infinite in the sense of an infinite totality, 
where we still find it used in deductive methods, is an illusion. Hilbert,1925
