Re: Mind Reading - Approach to Friendliness

From: Ben Goertzel (ben@goertzel.org)
Date: Mon Jun 19 2006 - 20:24:54 MDT


> > Concept is pretty simple. You develop really powerful analytical/debugging
> > applications that can display the entire contents of the AI mind in
> > tractable and useful visual representations and extrapolations into future
> > states of the mind.
> >
> > Strategy:
> > Let the AI 'sleep' (i.e. down-time) long enough to periodically analyze
> > the entire contents of the mind.

This basically means the AI cannot be alllowed to be strongly
superhuman, because if it were, we humans would certainly not be able
to understand its thought processes, let alone extrapolate them...

-- Ben



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT