Re: Compassion vs Respect; Exponential discounting of utility (was Re: Building a friendly AI from a "just do what I tell you" AI)

From: Tim Freeman (tim@fungible.com)
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           tim@fungible.com


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:01 MDT