Re: guaranteeing friendliness

From: Jef Allbright (
Date: Sat Dec 03 2005 - 22:29:13 MST

On 12/3/05, Eliezer S. Yudkowsky <> wrote:

> If I play chess against a stronger player, I cannot predict exactly
> where my opponent will move against me - if I could predict that, I
> would necessarily be at least that strong at chess myself. But I can
> predict the end result, which is a win for the other player. When I am
> at my most creative, that is when it is hardest to predict my actions,
> and easiest to predict the consequences of my actions - if you know and
> understand my goals.

Eliezer, I'm glad to see this statement, which is profound in its
implications and shows a higher level of understanding than even a
year ago. I will suggest, as I have approximately annually, that you
will find that there is no guaranteed *solution* to the problem of
friendliness, but that there is an optimum *approach*, involving a
framework for collaborative intelligence among diverse independent
sources (unpredictable in their actions while maximizing creative
potential) guided by converging human values (which are also

- Jef

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:54 MDT