From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Thu Nov 19 1998 - 21:49:25 MST
Dan Clemmensen wrote:
>
> continuum. We can of course attempt to guess where the SI will be along this
> continuum or how it will evolve along this continuum. First, I think we need
> to decide how likely it is that an SI is restricted to this continuum at all.
> It looks like the typical oversimplified bipolar mapping of a multivarate
> space to me, sort of like Myers-Brigg.
I also think it's an oversimplified bipolar mapping, but of a nonvariate
space, rather than a multivariate. In other words, I am not sure that there
exists a valid distinction between "many" and "one". Functions have inputs
and outputs. Modules of the human brain have inputs and outputs. How is this
distinguishable from "individual" and "environment"? When does a module stop
being a visual cortex and start being a human? That was my question - what
kind of functionality was involved.
For what it's worth, my guess is that there will not be duplicated
calculations or module-based programming, at least if efficiency is being
maximized. If individuals exist, it will be because of moral concerns
overriding efficiency, or because maximal efficiency cannot be achieved due to
constraints on global interprocess communication such as lightspeed limits or
barriers between Universes.
Two things to consider:
1) There's a lot of duplicated processing in the human race. Is it really
necessary to have five billion copies of the walking algorithm?
2) Ideal efficiency requires that there be only one Post-Singularity Entity,
among all the races of all the Universes.
--
sentience@pobox.com Eliezer S. Yudkowsky
http://pobox.com/~sentience/AI_design.temp.html
http://pobox.com/~sentience/sing_analysis.html
Disclaimer: Unless otherwise specified, I'm not telling you
everything I think I know.
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 14:49:48 MST