Re: Paradox--was Re: Active shields, was Re: Criticism depth, was Re: Homework, Nuke, etc..

From: John Marlow (
Date: Fri Jan 12 2001 - 01:07:52 MST

I suggest to you that the entire effort to create and
empower a nanny AI can end ONLY in disaster. The thing
will have no allegiance to us, no dependence on
us--will no more "relate" to us than we do to insects
or, perhaps more appropriately, to the descendants of
those more primitive life-forms from which many
believe we have evolved.

Tell me--when you turn on the hot-water faucet, do you
think about the bacteria in the drain being scalded to

john marlow

--- "Eliezer S. Yudkowsky" <>
> John Marlow wrote:
> >
> > Well I do confess to a perhaps inordinate fondness
> for
> > James Cameron epics--but "friendly" is of course a
> > human concept which, arguably, is not
> logic-based--or
> > wouldn't be for an entity not dependent upon
> friends
> > for its own well-being.
> I didn't say friendly, I said Friendly. A Friendly
> AI is not an AI with
> anthropomorphic friendship instincts copied from
> humans; a Friendly AI is
> one that exhibits Friendly behavior, from whatever
> source derived.
> Dependence upon humans is certainly not a reliable
> source except for
> human-equivalent AIs operating in the human social
> context, and frankly I
> wouldn't trust it there either. Obviously, a
> Friendship system that makes
> Friendliness conditional upon dependence or even
> reciprocal altruism is
> not well-designed, though there are (sigh) some
> AIfolk who still seem to
> be stuck on that point.
> > I present the following scenario: AI programmed to
> be
> > friendly and oversee humanity, exterminating pesky
> > aggressors. Something goes wrong with AI. Humans
> try
> > to shut it down to avoid catastrophe. AI perceives
> > this as aggression (after all, why would we want
> to
> > harm Mr. Friendly..?), and so on...
> Sounds like a pretty stupid AI to me. One incapable
> of understanding
> humans, or for that matter, its own mission. We
> aren't talking about an
> insect armed with nuclear weapons and a six-line
> definition of
> "aggression"; we're talking about a
> superintelligence who started life as
> a seed AI that spent months if not years chatting
> about Friendliness with
> the programmers, including the part where Friendly
> behavior should not be
> conditional upon the way humans behave toward the
> AI, and the part where
> you don't destroy the village in order to save it.
> I mean, really, this is such an obviously unFriendly
> scenario that it's a
> science-fictional cliche and the first thing you
> thought of; d'you really
> think a transhuman AI won't be able to understand
> that this ain't
> Friendliness?
> -- -- -- --
> --
> Eliezer S. Yudkowsky
> Research Fellow, Singularity Institute for
> Artificial Intelligence

Do You Yahoo!?
Yahoo! Photos - Share your holiday photos online!

This archive was generated by hypermail 2b30 : Mon May 28 2001 - 09:56:18 MDT