Re: [extropy-chat] Two draft papers: AI and existential risk; heuristics and biases

From: Robin Lee Powell (
Date: Tue Jun 13 2006 - 12:12:03 MDT

On Tue, Jun 13, 2006 at 10:57:11AM -0700, Jef Allbright wrote:
> On 6/13/06, Mikko S?rel? <> wrote:
> >On Tue, 13 Jun 2006, Jef Allbright wrote:
> >> On 6/12/06, Eliezer S. Yudkowsky <> wrote:
> >> > (4) I'm not sure whether AIs of different motives would be
> >> > willing to cooperate, even among the very rare Friendly AIs.
> >> > If it is *possible* to proceed strictly by internal
> >> > self-improvement, there is a *tremendous* expected utility
> >> > bonus to doing so, if it avoids having to share power later.
> >>
> >> Eliezer, most would agree that there are huge efficiencies to
> >> be gained over the evolved biological substrate, but I continue
> >> to have a problem with your idea that a process can recursively
> >> self-improve in isolation. Doesn't your recent emphasis on
> >> perception being the perception of difference (which I strongly
> >> agree with) highlight the contradiction and the enormity of the
> >> "if" in "if it is *possible* to proceed strictly by internal
> >> self-improvement"?
> >
> >Internal workings of a system are also part of the percieved
> >reality. One can test out another algorithm for indexing data and
> >notice that it works better. Completely internally. And still
> >percieving the difference. Or one could prove that a certain
> >algorithm for searching data is more efficient than another. And
> >self-improve. The software and hardware are part of the reality.
> >
> The problem is in the concept of "works better". Where does the
> knowledge defining what is better (necessarily more refined than
> present internal knowledge) come from, if not from some form of
> competition with that which is external to the present system?

I have no doubt that I could refine how my memory works usefully in
totaly isolation if I had access to the source code. The AI will
have to have some concept of "efficiency", but competition in the
broad sense isn't particularily required there.


-- ***
Reason #237 To Learn Lojban: "Homonyms: Their Grate!"
Proud Supporter of the Singularity Institute -

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT