From: Robin Lee Powell (rlpowell@digitalkingdom.org)
Date: Tue Dec 13 2005 - 12:36:59 MST
On Tue, Dec 13, 2005 at 01:55:00PM -0500, Eric Rauch wrote:
> Could we engineer an AGI w/ no goals and allow it to set its own
> agenda? What would be the outcome? Maybe a Friendly AGI is
> crippled.
Erm.
How would it set its own agenda if it didn't have "set my own
agenda" as a goal?
-Robin
-- http://www.digitalkingdom.org/~rlpowell/ *** http://www.lojban.org/ Reason #237 To Learn Lojban: "Homonyms: Their Grate!" Proud Supporter of the Singularity Institute - http://intelligence.org/
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:54 MDT