Philip Sutton wrote:
A very large number of computer games are based on competition and frequently combat. If we train an AGI on an average selection of current computer games is it possible that a lot of implicit ethical training will happen at the same time (ie. the AGI starts to see the world as revolving around competition and even worse, combat?)I also wondered this, and started trying to work out noncompetitive games an AI could play, to see how far cognition could get before you reached a point where you *had* to start teaching the AI about conflict and combat...
I'm having to deal with this problem in raising two young kids and I wonder why an AGI would not have the same problem.
...you know how Saccheri tried to assume the contrary of Euclid's Fifth Postulate, and then work out propositions of "Saccherian geometry" until he arrived at a contradiction, and yet he never seemed to do so?
I think I caught a glimpse of what non-evolutionary morality would be like. And what our world looks like from there. It's... really very, very, very sad.
I don't think AGIs should play competitive games.
--
Eliezer S. Yudkowsky http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence
-------
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
