From: Ben Goertzel (ben@goertzel.org)
Date: Fri Jun 28 2002 - 09:35:38 MDT
> I encourage (and I see Ben does too) anyone who reads his AI Morality
> paper or his other messages here to let him know what you think still
> needs to be addressed in his plan.
Certainly. I will say again that the "Thoughts on AI Morality" document
pointed to from www.realai.net's "Novamente AI Engine" page is precisely
that -- a set of thoughts on AI Morality, not a systematic manifesto, nor a
detailed "plan for action."
My position -- probably not stressed strongly enough in that essay -- is
that it's too early to formulate a definitive approach to Friendliness...
that will be possible only after some experimentation with real AGI's.
Nevertheless, it's possible to write a more thorough treatment of my
perspective than I did in that essay.
At the end of my last response to Brian, I made a list of things to add to
the next revision of the essay based on his suggestions those and others on
this list. So yeah, I'm quite open to suggestions here.
If my projections are correct, it will be years, not months, before this
kind of thinking is directly relevant to Novamente work [i.e., until we have
a system that is autonomously generally intelligent on a level where its
Friendliness or not is a worry.] But we'll get there -- we're in this for
the long haul, for sure...
-- Ben G
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:39 MDT