On Thu, Mar 6, 2008 at 8:27 PM, Mark Waser <[EMAIL PROTECTED]> wrote:
>
> Now, I've just attempted to sneak a critical part of the answer right past
> everyone with my plea . . . . so let's go back and review it in slow-motion.
> :-)
>
> Part of our environment is that we have peers.  And peers become resources
> towards our goals when we have common or compatible goals.  Any unimaginably
> intelligent system/entity surrounded by peers is certainly going to work
> with it's peers wherever possible.  Society/community is a feature that is
> critically important to Friendliness -- and this shows up in *many* places
> in evolution (if you're intelligent enough and can see beyond the "red in
> tooth and claw").  Note also that this can also (obviously) be easily and
> profitably extended to sub-peers (entities below a peer status) as long as
> the sub-peer can be convinced to interact in manner such that they are a net
> positive to the super-intelligences goals.

Mark, I think you base your conclusion on a wrong model. These points
depend on quantitative parameters, which are going to be very
different in case of AGIs (and also on high level of rationality of
AGIs, which seems to be a friendly AI complete problem, including
kinds of friendliness that don't need to have properties you list).

When you essentially have two options, cooperate/ignore, it's better
to be friendly, and that is why it's better to buy a thing from
someone who produces it less efficiently then you do, that is to
cooperate with sub-peer. Everyone is doing a thing that *they* do
best.

But when you have a third option, to extract the resources that
sub-peer is using up and really put them to better use, it's not
stable anymore. The value you provide is much lower then what your
mass in computronium or whatever can do, including the trouble of
taking over the world. You don't grow wild carrot, you replace it with
cultivated forms. The best wild carrot can hope for is to be ignored,
when building plans don't need the ground it grows on cleared.

-- 
Vladimir Nesov
[EMAIL PROTECTED]

-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=8660244&id_secret=95818715-a78a9b
Powered by Listbox: http://www.listbox.com

Reply via email to