From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!van-bc!ubc-cs!alberta!kakwa.ucs.ualberta.ca!access.usask.ca!ccu.umanitoba.ca!zirdum Thu Apr 30 15:22:50 EDT 1992
Article 5273 of comp.ai.philosophy:
Newsgroups: comp.ai.philosophy
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!van-bc!ubc-cs!alberta!kakwa.ucs.ualberta.ca!access.usask.ca!ccu.umanitoba.ca!zirdum
>From: zirdum@ccu.umanitoba.ca (Antun Zirdum)
Subject: Re: Intelligence, awareness, and esthetics
Message-ID: <1992Apr27.082403.8235@ccu.umanitoba.ca>
Organization: University of Manitoba, Winnipeg, Manitoba, Canada
References: <1992Apr23.152759.2272@javelin.sim.es.com> <1992Apr24.154950.25222@gpu.utcs.utoronto.ca> <1992Apr24.182714.17683@javelin.sim.es.com>
Date: Mon, 27 Apr 1992 08:24:03 GMT
Lines: 114

In article <1992Apr24.182714.17683@javelin.sim.es.com> biesel@javelin.sim.es.com (Heiner Biesel) writes:
>pindor@gpu.utcs.utoronto.ca (Andrzej Pindor) writes:
>
>>In article <1992Apr23.152759.2272@javelin.sim.es.com> biesel@javelin.sim.es.com (Heiner Biesel) writes:
>>(in reply to Daryl McCullough)
>>>
>>>As I recall, the Turing test is a pretty simple affair, consisting
>>>of a couple of teletype machines and a human interlocutor who is
>>>challenged to decide which - if any - of the two teletypes is connected
>>>to a computer, and which is manned by a person. Nothing is said about

Since I started the current berating of the Turing test, I feel
that I should explain myself better. (but sitting here at 3:00AM
I probably wont:) You are quite correct that the Turing test as
Turing proposed it is quite a simple afair with a few terminals
and a human tester. Now this is not what most people in computer
science have in mind when they speak of the Turing test, and
for this I appologize!
	The Turing test can never be passed because it is never
over, for as long as the object in question exists. The only
thing that can be said of something is that it has passed 
the Turing test SO FAR. But if all of a sudden it started to
act unintelligently then it would fail the Turing test.
So what we can speak of, instead of saying that something
has passed of failed the Turing test is that it has
passed the test to a certain confidence level.
>>>To reiterate: the Turing test does *not* depend on being able to fool
>>>all the people all the time; hell, even I can't do that.
>>>
>>No! Turing test *depends* on not being able to fool all the people all 
the time.

I beg to differ, you did pass (so far) and you did fool me ;-)
Seriously, I do believe that you do convince all of the people
that you speak with that you are conscious, and intelligent.
If you know differently, then I would like to speak with the
person that you did not convince.
>
>Really? Then I submit that no machine can ever be said to have successfully
>passed the Turing test, since it requires - by your definition - an
>infinite amount of time to demonstrate.
>
You are correct in stating that no machine has passed, but
your assumption that a pass requires an infinite amount of
time is certainly wrong, just as passing a mathematics course
does not require an infinite amount of time to determine
that the child can add any pair of integers. (yes, little
Johny can certainly add 34+56, but can he handle 34+57?)
>Any practical test must obviously have bounded criteria. The number and 
>qualifications of the judges, for example, as well as the period of
>testing, must be defined. "Fooling all of the people all of the time"
>is hardly rigorous, and not realizable in any case.
>
>>Do you have any better way of establishing awareness? Your 'Borodin
>>symphony' test would fail most people, as you've agreed yourself so I do not
>>think it is an alternative.
>
>I am suggesting that the Turing test would be sufficient for some but not
>all people, and that that is probably true of any other such test as well.
>As for me, an example of creative art would suffice. This suggests a series
>of alternative tests, each designed to demonstrate some aspect of what
>we call intelligence and awareness. The Turing test simply exploits
>verbal capability as a possible indicator of awareness, to the exclusion

Again, Turing did not fix the test to be only used with
teletype terminals, he plainly states that the only reason
that he uses teletype terminals is that computers do not
look like people, and therefore would have a high predjudice
against them. I think that he would concede that if computers
looked like people then we could simply let them roam about
and if they fool people then we should consider them intelligent,
and more importantly - aware! This idea of computers looking
like people was inconceivable in Turing's day, but today it
is different!
	Again the test is NOT teletype terminal (verbal)
communication, but THE communication itself! This is where
most people have a missunderstanding of the TT. It is simply
a test of abilities, it does NOT require special equiptment,
and it does not specify what should be the parameters of the
test for good reason, because there are no parameters!
>of all other aspects. I fail to understand the almost religious zeal
>with which some people defend the Turing test as *THE* means of establishing
>intelligence - and by inference, awareness - in machines. This zeal seems to
>be at odds with the spirit of the test, which is, after all, a loosely defined
>and easily staged informal affair, surely intended as such by Saint Alan
>himself.
>
>
>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!
	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!)
>Regards,
>       Heiner biesel@thrall.sim.es.com


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


