[ExI] What might be enough for a friendly AI?

Dave Sill sparge at gmail.com
Fri Nov 19 03:12:55 UTC 2010


On Thu, Nov 18, 2010 at 5:46 PM, spike <spike66 at att.net> wrote:
> Dave Sill is starting to sound like the lone voice in the wilderness crying
> out insistently that there is no danger, all is safe.

Sorry, Spike, but that's not my position, which is that containing an
AI would be relatively easy is the containment is done properly. But I
do think there's plenty of danger, which is why containment would be
desirable.

None of your scenarios so far would escape even the amateurish sandbox
I designed, and I'm sure the real professionals could do *much*
better.

-Dave



More information about the extropy-chat mailing list