--- Mark Waser <[EMAIL PROTECTED]> wrote:
> And thus, we get back to a specific answer to jk's second question.  "*US*"
> should be assumed to apply to any sufficiently intelligent goal-driven
> intelligence.  We don't need to define "*us*" because I DECLARE that it
> should be assumed to include current day humanity and all of our potential
> descendants (specifically *including* our Friendly AIs and any/all other
> "mind children" and even hybrids).  If we discover alien intelligences, it
> should apply to them as well.

Actually, I like this.  I presume that showing empathy to any intelligent,
goal driven agent means acting in a way that helps the agent achieve its
goals, whatever they are.  This aligns nicely with some common views of
ethics, e.g.

- A starving dog is intelligent and has the goal of eating, so the friendly
action is to feed it.

- Giving a dog a flea bath is friendly because dogs are more intelligent than
fleas.

- Killing a dog to save a human life is friendly because a human is more
intelligent than a dog.

- Killing a human to save two humans is friendly because two humans are more
intelligent than one.

My concern is what happens if a UFAI attacks a FAI.  The UFAI has the goal of
killing the FAI.  Should the FAI show empathy by helping the UFAI achieve its
goal?

I suppose the question could be answered by deciding which AI is more
intelligent.  But how is this done?  A less intelligent agent will not
recognize the superior intelligence of the other.  For example, a dog will not
recognize the superior intelligence of humans.  Also, we have IQ tests for
children to recognize prodigies, but no similar test for adults.  The question
seems fundamental because a Turing machine cannot distinguish a process of
higher algorithmic complexity than itself from a random process.

Or should we not worry about the problem because the more intelligent agent is
more likely to win the fight?  My concern is that evolution could favor
unfriendly behavior, just as it has with humans.


-- Matt Mahoney, [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