From: John K Clark (johnkclark@fastmail.fm)
Date: Mon Feb 11 2008 - 13:44:59 MST
On Mon, 11 Feb 2008 20:31:29 +0300, "Vladimir Nesov"
<robotact@gmail.com> said:
> It's not necessarily in itself ridiculous
I think the idea, that we can put in a line of code that is so well
written that it will be imposable for a mind vastly more powerful than
our own to do anything we might find unpleasant until the end of time,
is ridiculous; but that’s just me. Your opinion may vary.
> it might be more feasible to use first AGI
> with ad-hoc motivational structure to
> develop Friendly AI technology.
I have no great confidence that the first true AI will have any interest
in developing “Friendly AI technology”. And even if He did will He feel
the same way in 90 seconds? After all that’s the equivalent of many
millennia for a human?
John K Clark
-- John K Clark johnkclark@fastmail.fm -- http://www.fastmail.fm - Email service worth paying for. Try it for free
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT