Re: Why would AI want to be friendly? (Was: Congratulations to Eli, Brian ...)

From: D. den Otter (neosapient@yahoo.com)
Date: Tue Sep 05 2000 - 17:10:53 MDT


At 13:47 5-09-00 -0400, "Michael S. Lorrey" wrote:

>Socio/psychopathic minds are sick/malfunctioning minds.

"Socio/psychopathic" as in "not feeling bad about killing or otherwise
harming someone"? If so, you're "dead" wrong; it can be a perfectly
rational, logical choice to lie, cheat, steal, kill etc. under certain
circumstances. It is blind altruism, honesty and pacificism that's
"abnormal" and "dysfunctional". One could expect a "healthy" SI to be
extremely ruthless and opportunistic, and that's exactly our problem.

>Proper oversight systems
>should quickly put any sociopathic/psychopathic SI down. Such control
>mechanisms
>would be a primary area of research by the Singularity Institute I would
>imagine.

Even if you could somehow thoroughly screen the seed for "undesirable
characteristics", it could still *evolve* into something profoundly
unpleasant, from the human pov.

Upload or die; no flesh shall be spared!
-- Mark 13, 21st century Bible.

_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com



This archive was generated by hypermail 2b29 : Mon Oct 02 2000 - 17:37:14 MDT