From: Mark Waser (firstname.lastname@example.org)
Date: Sun Mar 16 2008 - 19:37:39 MDT
> Getting the re-implementation correct is an intelligence problem. If you
> still have any doubts, the nanobots will go into your brain and remove
> You will believe whatever you are programmed to believe. If you are
> to being reprogrammed, the nanobots will move some more neurons around to
> change your mind about that too. It can't be evil if everyone is in favor
Sorry. By my definition, if you alter my beliefs so to subvert my goals,
you have performed an evil act.
> Look, the AI is smarter than you and knows what's best for you. If you
> persist in your stubbornness and continue to waste the AI's resources, it
> simply declare you UnFriendly and do it anyway.
Yes, it could do that. It would be evil but it probably could get away with
it -- unless it implemented my definition of Friendliness.
This archive was generated by hypermail 2.1.5 : Sat May 25 2013 - 04:01:12 MDT