From: Rick Smith (email@example.com)
Date: Sat Jun 28 2008 - 04:15:37 MDT
Your point was stated thus:
"And my point was that you have no way, absolutely no way of knowing if AI has a reason for doing X or not unless you simulated it on faster hardware, and then you’d have no way of predicting if the faster machine had a reason for doing X unless you simulated it on a even faster machine, and then you’d have no way…"
If you'd like to include 'Pinky and the Brain' scenarios, would you like to restate your point?
From: "John K Clark" <firstname.lastname@example.org>
Date: 2008/06/27 Fri PM 06:20:22 BST
To: "sl4 sl4" <email@example.com>
Subject: RE: [sl4] Evolutionary Explanation: Why It Wants Out
On Fri, 27 Jun 2008 firstname.lastname@example.org said:
> If you build a predicting machine, you don't
> need to predict what it's going to do, you
> watch it do its thing and see what happens.
Right, you build the AI and watch it take over the world.
John K Clark
-- John K Clark email@example.com -- http://www.fastmail.fm - And now for something completely different… ----------------------------------------- Email sent from www.virginmedia.com/email Virus-checked using McAfee(R) Software and scanned for spam
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:03 MDT