Re: AI in <what?>

From: Justin Corwin (
Date: Sun May 19 2002 - 17:22:38 MDT

I missed this point, in my earlier response to MRA:

>From: "Michael Roy Ames" <>
> > We don't want an AImind we have to relate to
> > using 786432 pixel 2D metaphors. That would be annoying, and may
> > difficulty the AI may have trouble fixing when in the Self-Modification
> > stage.
> >
>I don't understand your point here. What is wrong with 2D metaphors? If
>you can get an AI that far, then that's freakin' great! Tackle 1D first,
>then 2D, then 3 and 4...

I agree that getting to this point would be great, and encouraging. However,
you dont' want an AI that is 'conceptually limited' to representations
containing 786432 pixels and 2 dimensions.

See Eliezer's example of tying an AI's time perception directly to the
system clock, the poor thing is thus unable to think about units of time
smaller than the smallest system-time unit.

that would be badd.....

just a small self-aggrandizing point!

Justin Corwin

"What? bad rabbit! you leave that poor microwave alone"
(actually uttered by me, embarassing, I know)

Get your FREE download of MSN Explorer at

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:38 MDT