Re: Friendliness SOLVED!

From: Rolf Nelson (rolf.h.d.nelson@gmail.com)
Date: Wed Mar 12 2008 - 21:19:42 MDT


> I've been saying a lot of things and four different people have challenged
> the theory but the truth is "NO ONE HAS PROVIDED A DETAILED, SPECIFIC
> UNHANDLED CASE OR A COUNTER-EXAMPLE" other than the paper-clip example
> which

> is an absurd edge case which we can simply outlaw by requiring all AGI to
> have a sufficient number of goals. If you feel that this statement is
> incorrect then I am asking you to provide what you believe is a detailed
> specific unhandled case or a counter-example. This is not an unreasonable
> demand. This is fundamental Bayesian logic. Show me some hard evidence
> that I am wrong. All I've seen thus far is just wild unfounded
> speculation.

The paperclip example sounds fine to me. As for "sufficient number of
goals", trivially amend it yourself to say "tile the galaxy with
paperclips", "tile the galaxy with smiley faces", "tile the galaxy with
Doritos", etc. The fact that you didn't yourself amend it before posting
suggests that you should spend more time thinking of counter-examples
yourself.

If you want a completely orthogonal example: it is never the case that an
action is "absolutely necessary for the fulfillment of a reasonable/rational
personal goal"; there's always a probability that quantum tunnelling will
solve your problems for you.

There are many many other possible counter-examples, but I warn you ahead of
time that if your plan is to just amend your proposal every time someone
proposes a counter-example and then always claim that no other
counter-examples can possibly exist, you're just wasting your own time and
ours.



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT