Date: Thu Mar 13 2008 - 09:16:26 MDT
> This is how humans usually act; it is not how most AIs will act. Iterm
> #1,782 on my agenda is to prove that, except for special cases, you
> get a higher expected utility when another agent shares your utility
> function than when the two agents have different utility functions.
> Hence, forced modification of the other agent's utility function also
> has positive utility.
Yes, it does but it is contrary to that other agent's Omohundro drives and therefore not a wise idea.
This archive was generated by hypermail 2.1.5 : Mon May 20 2013 - 04:01:20 MDT