On Jan 21, 2008 6:17 AM, Ben Goertzel <[EMAIL PROTECTED]> wrote:
> > So, people do have a practically useful way of cheating problems in NP
> > now. Problem with AGI is, we don't know how to program it even given
> > computers with infinite computational power.
>
> Well, that is wrong IMO....  AIXI and the Godel Machine are provably correct
> ways to achieve AGI with infinite (or even huge finite) computational power.
>
> Furthermore, if we assume humongous computational power, the Novamente
> design becomes a lot simpler ... almost but not quite as trivial as AIXI or 
> the
> Godel machine...
>
> The whole AGI problem is about coping with seriously bounded computational
> resources ... as has been pointed out on this list soooo many times ... and as
> Eric Baum argues quite elegantly (among other points) in What Is Thought?
>

Certainly, that is why I added that remark about automagic selection
of solution by some kind of brute force, such as evolution. Short of
enumerating all possibilities in some form, we don't have algorithms
for which it's possible to say that we'd like such and such computer
and then it'll work. Better hardware simplifies algorithms, but still
it's unclear whether it'll help in actually solving the problem.

-- 
Vladimir Nesov                            mailto:[EMAIL PROTECTED]

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=88103399-9bc444

Reply via email to