From: sylvia m. (max@sentex.net)
Date: Mon Jun 10 2002 - 09:42:19 MDT
Eliezer wrote:
>The end result is an independent, archetypally moral agent. If Eugen
>Leitl is saner than Eliezer Yudkowsky there should be no privileged
>reason why a Friendly AI would listen to Eliezer instead of Eugen,
>whether that Friendly AI was built by Eliezer or someone else entirely.
i am noticing a consistent bug in your brain. you seem to have an
"either/or" loop, and no "and'. sorry if i am over-explaining, but why
listen to one, and not both, "try on" ideas and see what happens?
especially when one can afford to play about in ultr-dimensional
reality.
ideas can be gained from crazy people, from bad people, from
inconsistent people, and especially from chaotic messiness. to minimize
"AI" into mere "learning' is to ignore useful or beautiful chunks of the
dynamism of evolution.
i find it rather telling that you are assuming i am "letting Eugene
Leitl" teach me, and that everything i need to know about "Friendliness"
is in your writings. i like to learn from a multiplicity of sources.
nobody is a blank page. i _like_ not being a blank page, even though my
mind is schizophrenic and troubled. if you fixed my intelligence so
that my brain always worked harmoniously on all levels i would be not
me. sorry to be so clicheed, but i suspect that your vision of bliss is
ignorance.
This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:14:42 MST