Re: AI-Box Experiments

From: Harvey Newstrom (mail@HarveyNewstrom.com)
Date: Sun Jul 07 2002 - 10:31:42 MDT


On Sunday, July 7, 2002, at 04:13 am, Anders Sandberg wrote:

> Just a variant to think of: I'm an superintelligent AI loose on the
> net. You are to talk me into my box. Might be very useful to know
> how to do beforehand :-)

He's just taunting us. No AI would give us a warning ahead of time, or
give us the real answer. By seeing this suggestion, I can only assume
that it would be impossible to talk Anders back into his box. As a
super-intelligent AI, he undoubtedly has already contemplated all the
possibilities before revealing this to us. There obviously is no hope
left. We must give up now. :-)

(Future responses to me will be encrypted and rerouted to an unspecified
asteroid in the Kuiper Belt.)

--
Harvey Newstrom, CISSP <www.HarveyNewstrom.com>
Principal Security Consultant <www.Newstaff.com>


This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:15:12 MST