From: Eugene Leitl (Eugene.Leitl@lrz.uni-muenchen.de)
Date: Tue Feb 19 2002 - 01:44:14 MST
On Mon, 18 Feb 2002, Zero Powers wrote:
> See Eli's earlier response to this thread. He sites a number of his
> articles claiming that not only will AI be self-aware, it will be
"Self-aware" is a meaningless property. Any system needs to have an
internal self model as a subset of world representation, in order to be
able to plan its future actions. "Self awareness" used in magic mantra
sense is almost as meaningless as "consciousness".
> friendly to your interests, even over its "own."
My interests, your interests, or Alan Grimes' interests? And how is it
supposed to keep catering to all our interests encoded into it as a seed,
as this seed grows in size and complexity into rather mindboggling
proporitions?
How does it supposed to self-enhance, if it is forbidden from use
noise-driven/evolutionary algorithms? If it executes a self enhancement
plan, which impacts manifest a few decades downstream, and are
uncomputable given its current resources?
This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:12:29 MST