From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!csd.unb.ca!morgan.ucs.mun.ca!nstn.ns.ca!news.cs.indiana.edu!mips!zaphod.mps.ohio-state.edu!uwm.edu!linac!att!att!fang!tarpit!cs.ucf.edu!news Thu Apr 30 15:23:14 EDT 1992
Article 5315 of comp.ai.philosophy:
Newsgroups: comp.ai.philosophy
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!csd.unb.ca!morgan.ucs.mun.ca!nstn.ns.ca!news.cs.indiana.edu!mips!zaphod.mps.ohio-state.edu!uwm.edu!linac!att!att!fang!tarpit!cs.ucf.edu!news
>From: clarke@acme.ucf.edu (Thomas Clarke)
Subject: Test for Intelligence
Message-ID: <1992Apr28.181701.11774@cs.ucf.edu>
Sender: news@cs.ucf.edu (News system)
Organization: University of Central Florida
Date: Tue, 28 Apr 1992 18:17:01 GMT

Much discussion of late has dealt with the good and the bad of the Turing test.   
It seems evident that some sort of test for intelligence needs to be  
established so decisions can be made concerning the intelligence of artificial  
systems.

The only test in view is the Turing test.  I take the Turing test as a broadly  
defined test wherein a putative artificial system is interrogated by humans in  
a blind fashion [For rigor double blind testing could be used].  The means in  
which the blindness is implemented will change with available technology.  Now  
the media are graphics workstations.  In a few years, the means may include  
voice synthesis and recognition.  The main idea is that the artificiality of  
the system under test can only be discovered from the content of the  
communications.

Off hand, I don't think any other test is possible.   Plato (Theaetetus) quotes  
Protagoras "Man is the measure of all things"; this is especially true of  
intelligence.  I think any formal/automatic/mechanical test will have the same  
problem as differentiating man from a "featherless biped."

Anyone else have any other suggestions for a test for intelligence?


