From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!bonnie.concordia.ca!ccu.umanitoba.ca!zirdum Thu Apr 30 15:23:04 EDT 1992
Article 5295 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!bonnie.concordia.ca!ccu.umanitoba.ca!zirdum
>From: zirdum@ccu.umanitoba.ca (Antun Zirdum)
Newsgroups: comp.ai.philosophy
Subject: Re: Intelligence, awareness, and esthetics
Message-ID: <1992Apr28.054106.29987@ccu.umanitoba.ca>
Date: 28 Apr 92 05:41:06 GMT
References: <1992Apr24.182714.17683@javelin.sim.es.com> <1992Apr27.082403.8235@ccu.umanitoba.ca> <1992Apr27.162558.9544@javelin.sim.es.com>
Organization: University of Manitoba, Winnipeg, Manitoba, Canada
Lines: 78

In article <1992Apr27.162558.9544@javelin.sim.es.com> biesel@javelin.sim.es.com (Heiner Biesel) writes:
>zirdum@ccu.umanitoba.ca (Antun Zirdum) writes:
>
>>>Perhaps you could explain to what the quoted sentence means,
>>>and how I can come to fully appreciate what 'Turing test' means? I am
>>>thus far unaware of any "Turing testing" of any machine intelligence,
>>>the occasional playing with Eliza clones excepted. The programs I know
>>>about are without exception abysmally stupid and totally devoid of anything
>>>approaching awareness. 
>>>
>>I will tell you what I mean!
>>First, how did you determine that the machines that you tested
>>are "abysmally stupid and totally devoid of anything approaching
>>awareness"??? If you did not determine this by the exact methog
>>described by Alan Turing then I will eat my shoes!
>
>Do you like 'em well done, with a Bearnaise Sauce?
>
>I have never applied the Turing test to any subject, human or computer.

First, from what I see I shall be wearing these shoes for a while
longer!

>My opinions of programs so tested are second hand and anecdotal. My direct
>exposure to programs has been limited to the kind of informal doodling
>that I would prefer *not* to call Turing testing, precisely because it
>is so informal and lacking in rigor. Since there are no programs that
>would have even a faint chance of passing a rigorous test of even a few 
>minutes, the whole point is moot.

>From your own admission, there are no programs that are capable
of passing a TT greater than a few minutes - doesn't this tell
you something? Yes - the TT works! Your experience of programs
so tested may be second hand, but that still does not escape
the fact that the Turing test was performed to determine this!
The other thing is, your 'informal doodling' was a TT, do not
be fooled, when you where 'doodling' you where actually testing
the limits of the program - at least that is what you learned!
(There's reason to our madness!)
>
>>	You yourself have used the Turing test, and failed to
>>recognize it! I can say with confidence that there is NO OTHER
>>METHOD OF DETERMINING INTELLIGENCE! (remember that we are
>>not talking of any simple test paper that Turing wrote! We
>>are talking of the method of testing!)
>
>If I understand you correctly, your definition of the Turing test is
>primarily an extended interaction with some entity - human or artificial -
>with a gradually increasing degree of confidence that the entity is, or
>is not, intelligent and aware. That is certainly one way of determining
>intelligence. However, this method fails in determing the intelligence of
>Beethoven, for example. Therefore I am inclined to accept the intelligence 
>and awareness of Beethoven on the strength of any of his symphonies,
>or that of Twain on the evidence of "Huckleberry Finn".
>
This is not my definition of the TT, this is a generally
accepted definition - there is no reason to limit it in
the ways that you would - except to prevent it from working!
	This method does not fail in determining that
Bethoven, Twain, etc.. WAS intelligent (when alive)
There is nothing in Turing's paper that implies that the TT
must be verbal (he simply saw no other way of communicating
with machines in his day!) The TT can, and must be based on
all of the capabilities of the machine, so for instance - if
the machine is capable of producing music/sound it would
be tested on its ability to produce sound in an intelligent
manner. After all is said - Music IS a form of communication!
>I'm still reserving judgement on Mondrian ;-)
>
>Regards,
>       Heiner biesel@thrall.sim.es.com


-- 
*****************************************************************
*   AZ    -- zirdum@ccu.umanitoba.ca                            *
*     " The first hundred years are the hardest! " - W. Mizner  *
*****************************************************************


