From: Marc Geddes (firstname.lastname@example.org)
Date: Wed Apr 07 2004 - 01:45:15 MDT
--- Ben Goertzel <email@example.com> wrote: >
> Thus my oft-repeated statement that the true theory
> of Friendliness will
> be arrived at only:
> A) by experimentation with fairly smart AGI's that
> can modify themselves
> to a limited degree
> B) by the development of a very strong mathematical
> theory of
> self-modifying AGI's and their behavior in uncertain
> My opinion is that we will NOT be able to do B
> within the next few
> decades, because the math is just too hard.
> However, A is obviously pretty dangerous from a
> My best guess of the correct path is a combination
> of A and B, in which
> one builds
> A) a collection of sub-human-level self-modifying
> AI's, with strict
> limits on the ways they can self-modify and careful
> B) a smart non-self-modifying AI which is customized
> for data analysis
> and automated theorem-proving, with a modicum of
> general intelligence as
I agree with you. I think our intellectual fire-power
needs to be directed towards expert systems in maths
to begin with. It's not the case that 'physics always
wins'. More accurate to say that 'Maths always wins'
;) At the end of the day it's going to come down to a
'mathematics of morality' (or at least a 'mathematics
of minds in general'). Since the sort of hard maths
needed is likely well beyond our abilities, we need
dedicated thereom provers. Once we have those, we can
then use them as 'heavy cannons' to 'punch through'
the intellectual maignot line blocking us from AGI.
> One then uses B to help one model A, and obtain a
> high-quality theory of
> the dynamics of AGI's under self-modification. This
> theory then tells
> one how to proceed next.
Right! Time for me to get cracking on those theorem
"Live Free or Die, Death is not the Worst of Evils."
- Gen. John Stark
"The Universe...or nothing!"
Please visit my web-site: http://www.prometheuscrack.com
Find local movie times and trailers on Yahoo! Movies.
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:46 MDT