Re: Geddes's 'Moral Perturbation Theory'

From: Marc Geddes (
Date: Thu Jun 17 2004 - 23:35:54 MDT

--- Eliezer Yudkowsky <> wrote: >
Marc Geddes wrote:
> >
> > To approximate the collective volition of humanity
> we
> > don't need to look at the brains of 6 billion
> people
> > at all. In fact I think that the brains of only a
> few
> > hundred should suffice as a very good
> approximation!
> Possibly.
> > Further if we wanted to calculate the approximate
> > extrapolated volition of any particular
> individual,
> > we'd simply take the CV as a generic first order
> > approximation , then add the 'moral
> perturbations'
> > caused by the more specific mental characteristics
> of
> > the individual under consideration.
> This doesn't follow. It's like saying that to
> compute the position of an
> arbitrary solar object, you take the average
> position of the nine planets,
> and then add the specific characteristics of the
> body in question. There
> is a sense in which it is efficient to start with
> the Sun's extrapolated
> position, to get the position of Asteroid #whatever
> in the galaxy and the
> universe, and then add corrections. But this is not
> analogous to starting
> with the collective volition as the generic first
> order approximation; it
> is analogous to starting with the fact of your
> humanity (possibly,
> masculinity or feminity) as the generic first order
> approximation. What
> part of a collective volition is universal in
> individual volitions with
> high probability (say, P > 95%) is a different
> problem from extrapolating a
> collective volition as such.

Um.. you're right. I made a mistake there. But a bit
later I said:

"To increase the accuracy of the extrapolation for
that particular individual we don't need to look at
all their mental characteristics, we just start by
factoring in the ones exerting the most 'moral
influence' on their psyche. As more mental
characteristics are considered, the 'moral
perturbation' caused by the remaining characteristics
would be growing smaller and smaller aka the astronomy
analogy. A database of 'human mental characteristics'
would be consulted, moving from a small number of
generic characteristics exerting large 'moral
influence' on the psyche, to a larger number of more
specific characteristics exerting smaller 'moral
perturbations' on the earlier approximations."

We start with characteristics which are are universal
in individual volitions to a high probability for a
first order approximation, then add the corrections
for each progressively less universal human
characteristic. Do you think that would work to
produce reasonable approximations?

> PS: Geddes, can you please choose less excitable
> subject lines?
> --
> Eliezer S. Yudkowsky
> Research Fellow, Singularity Institute for
> Artificial Intelligence

Um what's wrong with excitable subject lines? Ah..
*Marc holds out his hand lamely* ...oh..sorry.

"Live Free or Die, Death is not the Worst of Evils."
                                      - Gen. John Stark

"The Universe...or nothing!"

Please visit my web-sites.

Science-Fiction and Fantasy:
Science, A.I, Maths :

Find local movie times and trailers on Yahoo! Movies.

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:47 MDT