Re: ESSAY: Program length, Omega and Friendliness

From: Ben Goertzel (ben@goertzel.org)
Date: Wed Feb 22 2006 - 15:06:08 MST


> Your objection rests upon personal conjectures which are not known
> mathematical results and which I do not share.

Eli, I think I was pretty explicit about this in my email, via
prefacing the appropriate parts of my comments with phrases like "I
think..." and "I believe...."

>I think there can be a
> core of bounded algorithmic complexity which decompresses itself into a
> powerful AI in reasonable time. If you think this requires vast amounts
> of additional startout complexity to run in reasonable time, you could
> be right, but I would be surprised.

Then I think you will be surprised ;-)

> Don't forget to identify which parts of your argument are math and which
> parts are your personal intuition;

As I said above, I think I was pretty clear about this distinction in my email.

> I wouldn't want people to think there
> was a known mathematical problem with FAI.

Mathematics places very specific constraints on FAI. Whether there is
a way to make highly intelligent, provably Friendly AI within these
constraints remains unknown; and we have strongly different intuitions
in this regard.

> Please remember that others
> may not trust your intuitions as much as you do.

Right back atcha, my friend ;-)

-- ben



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:55 MDT