From newshub.ccs.yorku.ca!torn!cs.utexas.edu!zaphod.mps.ohio-state.edu!caen!kuhub.cc.ukans.edu!spssig.spss.com!markrose Mon Aug 24 15:40:57 EDT 1992
Article 6630 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!torn!cs.utexas.edu!zaphod.mps.ohio-state.edu!caen!kuhub.cc.ukans.edu!spssig.spss.com!markrose
Newsgroups: comp.ai.philosophy
Subject: Re: Turing Test Myths
Message-ID: <1992Aug17.191457.8645@spss.com>
>From: markrose@spss.com (Mark Rosenfelder)
Date: Mon, 17 Aug 1992 19:14:57 GMT
Sender: news@spss.com (Net News Admin)
References: <1992Aug13.024527.2079@news.media.mit.edu> <93829@bu.edu> <BILL.92Aug17114642@ca3.nsma.arizona.edu>
Organization: SPSS Inc.
Lines: 46

In article <BILL.92Aug17114642@ca3.nsma.arizona.edu> bill@nsma.arizona.edu 
(Bill Skaggs) writes:
>   > > I believe that, given an hour of interrogation, I would have a
>   > > better than 90% probability of distinguishing between a man and
>   > > a woman.  [ . . . ]
>
>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.

Or perhaps you're thinking that a woman will administer this particular
test?  Then my wife would probably fail.  She doesn't use much makeup,
so she probably doesn't know enough about it to satisfy a female
inquisitor.

>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.

These strike me as tests of writing ability rather than of gender.
I wonder how many males would fail this test.

>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.  

Sounds fun.  Go for it.

Actually, in a sense, this test is tried every day: novelists write 
dialogue and even narration from both sexes' point of view.  How successful
do you think are the male characters of Jane Austen, Emily Bronte, 
Dorothy L. Sayers, or Ursula LeGuin?  How successful are the female
characters of Dickens, Dostoevsky, Poul Anderson, or Raymond Chandler?

But on relevance to AI I agree with you (that was you, wasn't it?)--
success in distinguishing the sexes is a very different thing from
success in detecting intelligence.


