From: Marc Geddes (marc_geddes@yahoo.co.nz)
Date: Mon May 24 2004 - 00:24:08 MDT
I continue to be particularly intrigued by these
recent statements of Eliezer’s:
“The human ability to employ abstract reasoning is a
threshold effect
that *potentially* enables a human to fully understand
some optimization
processes, including, I think, optimization processes
with arbitrarily
large amounts of computing power. That is only *some*
optimization
processes, processes that flow within persistent,
humanly understandable invariants; others will be as
unpredictable as coinflips.”
…
“The essential law of Friendly AI is that you cannot
build an AI to
accomplish any end for which you do not possess a
well-specified *abstract* description. If you want
moral reasoning, or (my current model) a dynamic that
extrapolates human volitions including the
extrapolation of moral reasoning, then you need a
well-specified abstract description of what that looks
like.
In summary: You may not need to know the exact
answer, but you need to
know an exact question. The question may generate
another question,
but you still need an exact original question. And
you need to understand
everything you build well enough to know that it
answers that question”
[Ref http://www.sl4.org/archive/0405/8553.html]
Anyone want to comment on these statements?
This led me to the intruiging idea that *degree of
understanding* is analogous to the *resolution* of a
picture or hologram, with the image itself being
analogous to the *mental concept*. Low IQ sentients
can still ‘see’ (understand) the hologram (concept),
they just see it in very low resolution (their
understanding is very vague and general?). High IQ
sentients see (understand) the hologram (concept) in
high resolution (analogous to a more detailed, sharper
understanding?) This analogy does seem rather odd,
because the model of intelligence would seem to be
backwards from the conventional understanding.
Conventional wisdom is that understanding starts with
specific concrete examples of a concept, and then
moves to a more general abstract understanding
(induction). But my hologram analogy seems to reverse
that! Understanding would start with vague
abstractions and move towards specifics.
Keep these fascinating conversations going! Yes
indeed - fascinating, fascinating.
=====
"Live Free or Die, Death is not the Worst of Evils."
- Gen. John Stark
"The Universe...or nothing!"
-H.G.Wells
Please visit my web-sites.
Science-Fiction and Fantasy: http://www.prometheuscrack.com
Science, A.I, Maths : http://www.riemannai.org
Find local movie times and trailers on Yahoo! Movies.
http://au.movies.yahoo.com
This archive was generated by hypermail 2.1.5 : Tue Feb 21 2006 - 04:22:36 MST