From newshub.ccs.yorku.ca!torn!cs.utexas.edu!uwm.edu!rpi!bu.edu!buphy0.bu.edu!leao Mon Aug 24 15:41:01 EDT 1992
Article 6635 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!torn!cs.utexas.edu!uwm.edu!rpi!bu.edu!buphy0.bu.edu!leao
>From: leao@buphy0.bu.edu (Joao Leao)
Newsgroups: comp.ai.philosophy
Subject: Re: Turing Test Myths
Message-ID: <93944@bu.edu>
Date: 18 Aug 92 14:41:30 GMT
References: <1992Aug13.024527.2079@news.media.mit.edu> <93829@bu.edu> <BILL.92Aug18001050@ca3.nsma.arizona.edu>
Sender: news@bu.edu
Lines: 66

In article <BILL.92Aug18001050@ca3.nsma.arizona.edu>, bill@nsma.arizona.edu (Bill Skaggs) writes:
|> markrose@spss.com (Mark Rosenfelder) writes:
|> 
|>    > > For a male imitating a female, I would begin by asking for an
|>    > > explanation of the system of women's clothing sizes.  (Junior, Misses,
|>    > > etc.)  Then I would ask for an explanation of "her" philosophy for
|>    > > using makeup.  And so on.
|>    >
|>    > Would *you* be able to detect "wrong" answers to these questions?  
|>    > If so, then you know enough about women to pass your own test.
|>    > If not, then males could certainly imitate women well enough to
|>    > pass the test with you.
|> 
|> Not so.  It is often possible to detect a lie (because of internal
|> inconsistency) without knowing the truth.
|> 
|> Anyway, try to imagine how *you* (a man) would respond if asked
|> questions like these.  I know that *I* would be completely befuddled,
|> and anybody with any sense would quickly realize that I didn't know
|> what I was talking about.
|> 
|> 	-- Bill

I think you are missing Mark's point: the beauty of the Imitation Game
is that it is imprevious to any strategy of detection that you may devise
because any of these is ultimately self-defeating in the general context 
of the game. 

Who says that being "a man" or being "a woman" is more of a consistent
proposal that "appearing to be a man" or "appearing to be a woman"?
Turing was well aware that none of these boils down to a finite set 
of questions and answers because none exists that
can unambiguously distinguish between these two. Thus he chose the 
analogy to persuade you that the same goes for Man and Machine
interlocutors. This is what he means by the impossibility of
defining terms like "think" and "machine".

Incidentally you also hit upon the wall which defends Turing from
the charges of "chauvinism" frequently brought up to the 1950 paper.
You seem to believe that you come to the Imitation Game armed with
a knowledge of "how women think" or at least your own personal knowledge
of "how man do not think" only to find that none of those myths bears
much empirical consequence... Part of Turing's intention was of course
combating such form of "human chauvinism" vis-a-vis machines or what 
have you...

On another note: I have had enough encouragement to make available the
Transcripts of the Loebner Prize Competition 1991 so I will do it. To
make things more interesting I propose to post the several dialogues
without indication of which ones are Competitors (machines) or
Confederates (humans). This will make it possible for you guys who 
have not attended the competition to try your own skills if you
want. Not that this was much of a match but even so it will give
you some feeling for the mechanics of the competition...

I will also try and post the relevant rules for the competition as
they were implemented on this first round.



---
Joao Pedro Leao (Artificial Iconoclast and Director of Computer Resources
Artificial Physics Lab * Boston University - Physics Dept. Boston MA 02215)
 	leao@buphy.bu.edu | leao@buphyc.bitnet | BUPHYC::LEAO 
"Well I am sitting here in Tahiti/ I am laying in the sun and sipping a...
...chartreuse tropical drink!/ and I say: I know those Bermuda shorts!..."


