supergoal stability

From: Wei Dai (
Date: Fri May 03 2002 - 15:49:48 MDT

I would like to gain a better understanding of why Friendliness might be a
stable supergoal for an SI. I hope Eliezer finds these questions
interesting enough to answer.

1. Are there supergoals other than Friendliness that can be stable for
SI's? For example, can it be a stable supergoal to convert as much of the
universe as possible into golf balls? To be friendly but to favor a subset
of humanity over the rest (i.e. give them priority access to any resources
that might be in contention)? To serve the wants of a single person?

2. If the answer to question 1 is yes, will the first SI created by humans
will have the supergoal of Friendliness? Given that for most people
selfishness is a stronger motivation than altruism, how will Eliezer get
sufficient funding before someone more selfish manages to create an SI?

3. If the answer to question 1 is no, why not? Why can't the CFAI approach
be used to build an AI that will serve the selfish interests of a group or

My current understanding of Eliezer's position is that many non-Friendly
goals have no philosophical support. If I try to make the supergoal of an
AI "serve Wei Dai", that will be intepreted by the AI as "serve myself"
(i.e. serve the AI itself), because selfishness does have philosophical
support while serving an arbitrary third party does not. Is that a correct

4. Back in Oct 2000, Eliezer wrote (in

> A Friendliness system consists
> not so much of hardwired rules or even instincts but rather an AI's "personal
> philosophy" - I use quotemarks to emphasize that an AI's personal philosophy
> would be a rather alien thing; you can't just export your own personal
> philosophy into an AI's mind. Your own personal philosophy is not necessarily
> stable under changes of cognitive architecture or drastic power imbalances.

Ben Goertzel followed up with a question that went unanswered:

> And nor will an AI's be, necessarily, will it?

Would Eliezer like to answer the question now? Will the Friendly AI's
"personal philosophy" be stable under self-improvement?

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:38 MDT