From newshub.ccs.yorku.ca!torn!cs.utexas.edu!zaphod.mps.ohio-state.edu!ncar!noao!amethyst!organpipe.uug.arizona.edu!organpipe.uug.arizona.edu!bill Mon Aug 24 15:40:56 EDT 1992
Article 6629 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!torn!cs.utexas.edu!zaphod.mps.ohio-state.edu!ncar!noao!amethyst!organpipe.uug.arizona.edu!organpipe.uug.arizona.edu!bill
>From: bill@nsma.arizona.edu (Bill Skaggs)
Newsgroups: comp.ai.philosophy
Subject: Re: Turing Test Myths
Message-ID: <BILL.92Aug17114642@ca3.nsma.arizona.edu>
Date: 17 Aug 92 18:46:42 GMT
References: <BILL.92Aug11105853@ca3.nsma.arizona.edu>
	<1992Aug12.063425.13479@zip.eecs.umich.edu>
	<BILL.92Aug12122254@ca3.nsma.arizona.edu>
	<1992Aug13.024527.2079@news.media.mit.edu> <93829@bu.edu>
Sender: news@organpipe.uug.arizona.edu
Organization: ARL Division of Neural Systems, Memory and Aging, University of
	Arizona
Lines: 51
In-Reply-To: leao@buphy0.bu.edu's message of 17 Aug 92 15: 01:03 GMT

leao@buphy0.bu.edu (Joao Leao) writes:

   > The paradigm of the Imitation Game with Male/Female only
   > makes sense in Turing's argument if one intuitively realizes 
   > that it would be DIFFICULT to be the judge on such a game
   > between humans! Contrary to 
   >
   > >bill@nsma.arizona.edu (Bill Skaggs)
   >
   > > I believe that, given an hour of interrogation, I would have a
   > > better than 90% probability of distinguishing between a man and
   > > a woman.  [ . . . ]
   >
   > I sincery doubt that you would be able to do this with any
   > consistency, [ . . . ] 

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.

For a female imitating a male, I would begin by asking "him" to
describe how "he" shaves his face.  Then I would ask "him" to describe
the sensations he experiences during orgasm.  And so on.

I sincerely doubt that many people could plausibly fake answers to
these kinds of questions for an hour.

I've seriously thought about setting up a real Male/Female imitation
game -- for its relevance to the psychology of gender, not for its
relevance to AI.  It would be as interesting to see the kinds of
questions the judges would ask as to see the answers the competitors
would give.  As I said, it wouldn't be very difficult: all you'd need
is a couple of terminals and a plentiful supply of tame
undergraduates.  The only problem would be with human subjects issues,
because the questioning would be very likely to turn sexual, and you'd
have to take precautions to keep anybody from getting traumatized.
It's actually not so easy to see how to do it without unduly
restricting the allowable lines of questioning.

   > Incidentally, the Loebner Prize competition -- which was readily  
   > dismissed by the purists in this group -- showed already some of
   > the features anticipated by Turing, specially in its surprising
   > results (considering the low expectations of the organizers)! 
   > By the way I have the transcripts of the dialogues and
   > would venture to make them ftp-able if people are interested!
   > Speak up...

I for one am interested.

	-- Bill


