Newsgroups: comp.ai.philosophy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!cs.utexas.edu!news.unt.edu!hermes.oc.com!internet.spss.com!markrose
From: markrose@spss.com (Mark Rosenfelder)
Subject: Re: Bag the Turing Test
Message-ID: <D0IoAu.7DA@spss.com>
Sender: news@spss.com
Organization: SPSS Inc
References: <1994Dec8.143144.11787@oracorp.com>
Date: Fri, 9 Dec 1994 00:06:30 GMT
Lines: 25

In article <1994Dec8.143144.11787@oracorp.com>,
Daryl McCullough <daryl@oracorp.com> wrote:
>Here is my candidate for a Turing Test for AI programs which would be
>practically impossible to fool. You need three participants: the
>judge, the AI's Advocate and the Devil's Advocate. The goal of the
>Devil's advocate is to convince the judge that the subject is merely
>an unintelligent computer program, and the goal of the AI's Advocate
>is to convince the judge that the subject possesses genuine
>intelligence.  However, the only means that the two advocates have of
>convincing the judge is by asking the subject questions and letting
>the judge hear the responses. The advocates are able to analyze the
>code (to find out *how* responses are created) in order to come up
>with their questions. But the judge is not allowed to see the code,
>and is not even allowed to know whether the subject is human or
>machine.

Well, this is a step in the right direction.  You've added a good deal of
rigor to the Turing Test, and allowing the advocates to examine a machine's
mechanism is a nice touch.

I'd still not be willing to *define* intelligence using this test, and
I would still want to be able to investigate non-verbal behavior.

It's curious that you've pretty much come up with the same method to test 
"intelligence" as the Catholic Church uses to test "sainthood".  :)
