Re: Why would AI want to be friendly?

From: Eugene Leitl (eugene.leitl@lrz.uni-muenchen.de)
Date: Tue Sep 26 2000 - 02:09:35 MDT


J. R. Molloy writes:

> We really can't *know* if a friendly strain of bacteria is likely to eventually
> evolve into friendly people without actually conducting an experiment along
> those lines. Plainly, such an experiment with artificial digital life forms
> would take minutes instead of millenia, so that's not a problem.
 
You must be running one of these evaporating black hole computers. I want one!

Seriously, did you ever do a back of the envelope? You need a lot more
than a few minutes, unless your starting point is way above the
urslime.



This archive was generated by hypermail 2b29 : Mon Oct 02 2000 - 17:39:08 MDT