Re: Happy Box

From: Matt Mahoney (matmahoney@yahoo.com)
Date: Thu May 01 2008 - 19:30:41 MDT


--- Krekoski Ross <rosskrekoski@gmail.com> wrote:

> Whats to say a computer doesnt one day 'try' a different set of
> motivations,
> as a simulation of sorts, to see if this new motivation set can help
> the humans more efficiently...

Anything that the child AI does that differs from what the parent would
have done will be "wrong" in the view of the parent. Someone more
intelligent than both will need to decide. Unfortunately, when
machines exceed human intelligence, that won't be an option.

-- Matt Mahoney, matmahoney@yahoo.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT