From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!emory!gwinnett!depsych!rc Fri Jan 31 10:27:08 EST 1992
Article 3281 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!emory!gwinnett!depsych!rc
>From: rc@depsych.Gwinnett.COM (Richard Carlson)
Newsgroups: comp.ai.philosophy
Subject: Re: Turing Test
Message-ID: <g2HBFB3w164w@depsych.Gwinnett.COM>
Date: 29 Jan 92 15:25:39 GMT
References: <1992Jan28.130209.2486@arizona.edu>
Lines: 39

bill@NSMA.AriZonA.EdU (Bill Skaggs) writes:

> 
>   Let's try a different angle.
> 
>   Turing, when he proposed his test, thought of it essentially
> as a benchmark -- an important and useful goal for AI to aim
> at.  He considered "thinking" too fuzzy a notion to be a useful
> goal, and proposed to replace it with his test.
> 
>   Incidentally (I have just been rereading "Computing Machinery
> and Intelligence"), as a stunning example of prescience in a
> field notable for appallingly bad predictions, Turing predicted
> (in 1950) that in fifty years machines would exist that would
> be detected (in the imitation game) less than 70% of the time
> in a test of five minutes duration.  This looks to be very close
> to the level of performance that will actually be achieved by
> the year 2000.
> 
>   But my real question is:  are there any other good, simple,
> straightforward benchmarks for AI?  

How about a Goedel test?  Goedel once said that he arrived as his
shocking and curiously ultra-modern-looking results not by seeking
something new but by laboriously applying simple tried and true
ideas with as much precision as he was capable.  So how about an
expert system (since the posters in the Newsgroup seem to prefer
expert systems) sufficiently detailed and precise that it appears
to come up with "new" and startling formulations that appear to be
generated at a first glance by what an intelligent non-AI-trained
layperson would be inclined to label "creative intuition"?  That
would even _look_ more like artificial _intelligence_ than a
Turing test.

--
Richard Carlson        |    rc@depsych.gwinnett.COM
Midtown Medical Center |    {rutgers,ogicse,gatech}!emory!gwinnett!depsych!rc
Atlanta, Georgia       |
(404) 881-6877         |


