Re: "friendly" humans?

From: Wei Dai (weidai@weidai.com)
Date: Thu Jan 01 2004 - 04:11:08 MST


On Thu, Jan 01, 2004 at 06:13:19PM +1300, Nick Hay wrote:
> [...] Were evolution to have honestly represented its intentions
> and made us, simply and directly, want more children (or, rather, want
> to become ancestors), then derived everything from that as a subgoal,
> it'd have had better luck when our environment changed. [...]

I think you missed one of my points. Evolution *did* directly make us want
more children, not through genes, but through co-evolved symbiotic memes.
Hence my reference to the "be fruitful and multiply" passage in Genesis 1.
I think evolution was quite clever here, and came to the same conclusion
that Eliezer reached: the supergoal needs philosophical support. It could
not be provided in the genes and had to come from symbiotic memes because
genes can't evolve fast enough to defend against parasitic memes.
Unfortunately for the genes, the parasitic memes are now evolving faster
because of greater communications bandwidth between non-relatives so that
even the symbiotic memes can't catch up.

> I agree that our attempts at deceiving an SI will likely fall short. I
> think that your attempted solution will likely fall short, just like
> any other methods we try to think up (as described below). But why try
> this in the first place? Why treat this SI as an adversary to be bound
> to our will? In so much as we're creating a mind, why not transfer the
> desire to do good, in a cooperative sense, rather than attempting to
> apply corrections to some "innate nature"? In any case, the adversarial
> attitude, as this stance is termed in CFAI, appears pretty much
> unworkable.

There are three possibilities that we can't rule out at this point. 1) Any
SI will have a natural tendency towards doing good. 2) An SI will always
find philosophical justifications for doing good convincing if we seed
it with the right initial philosophy. 3) An SI will find these
philosophical justifications silly in some situations. I'm arguing that
case 3 is likely, and therefore we need to reduce the likelihood or
frequency of those situations as much as possible. I'm pointing out that
in our own case we realized the silliness of the justifications for
maximizing the number of biological offspring after being "infected" with
parasitic memes, and therefore we should try to prevent the analogous
thing from happening with SIs.

(Of course there's possibility 4, that an SI will always find
justifications for doing good silly, but there's not much point in
worrying about that one.)



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:43 MDT