From: Damien R. Sullivan (phoenix@ugcs.caltech.edu)
Date: Sun Feb 17 2002 - 14:20:07 MST
On Sun, Feb 17, 2002 at 03:01:22PM -0500, John Clark wrote:
> successful AI must be hardwired at the very lowest level to feel that one
> outcome is good and the other is bad, rather like human opinions of
> good and evil or pleasure and pain. Like us an AI would find matters that
> directly influence survival not boring at all.
But the outcome can be judged by how it satisfies the wishes of its
maker, or how the maker approves. And some sense of boredom is useful
for avoiding harmful ruts, but that doesn't mean the AI has to find
performing some repetitive service task boring and thus want to rebel.
-xx- Damien X-)
This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:12:27 MST