From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!mcsun!sun4nl!fwi.uva.nl!gene.fwi.uva.nl!pdejong Tue Apr  7 23:23:25 EDT 1992
Article 4839 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!uunet!mcsun!sun4nl!fwi.uva.nl!gene.fwi.uva.nl!pdejong
>From: pdejong@fwi.uva.nl (Paul Gerard de Jong)
Newsgroups: comp.ai.philosophy
Subject: Re: Intelligence Testing
Message-ID: <1992Mar31.102512.23507@fwi.uva.nl>
Date: 31 Mar 92 10:25:12 GMT
References: <1992Feb27.185327.2687@oracorp.com> <6717@pkmab.se> <529@trwacs.fp.trw.com>
Sender: news@fwi.uva.nl
Organization: FWI, University of Amsterdam
Lines: 16
Nntp-Posting-Host: gene.fwi.uva.nl

I found this in sci.electronics, as a followup on a thread about Commercial
Killers for TV programs. It gave me a good :-]

------------ Alex Freed's stuff ----------------------------

After reading this thread for a while I came to a conclusion that an
_unattended_  Commercial Killer is a nice test to put a claimed AI system to.
Even a moderately intelligent human can tell a commercial from the rest.
Should'n a 'smart' machine be able to. I don't mind if it has to watch TV for
a while first -).
--
 _______________________________________________________
| -Alex Freed (The opinions expressed are my own.       |
|               However everyone is entitled to them.)  |
| freed%adobe.com@uucp-gw-1.pa.dec.com                  |
 -------------------------------------------------------


