From: Tim Freeman (firstname.lastname@example.org)
Date: Sun Dec 09 2007 - 09:38:41 MST
Bah. With one word wrong, it becomes nonsense. I said:
>Similarly, respect coefficients define how much the AI wants to avoid
>hurting people. When someone is harmed, to compute the contribution
>of that to the AI's utility (a negative number) we multiply the
>beneficiary's respect coefficient (a positive number) by the AI's
^^^^^^^^^^^^^ should be "victim's"
>estimate of how much the victim was harmed (a negative number).
-- Tim Freeman http://www.fungible.com email@example.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:01 MDT