From: Stathis Papaioannou (email@example.com)
Date: Wed Feb 28 2007 - 05:55:11 MST
On 2/28/07, Adam Safron <firstname.lastname@example.org> wrote:
Wouldn't it be a horrible idea to reverse engineer the human brain as a
> template for your AI? If you have an AI that's human-like, I fail to see
> how you could ensure the "friendliness" of subsequent iterations of the
> progressively developing intelligence. Am I missing something?
That would be like someone reverse engineering a computer CPU then having
difficulty working out how to insert the plug into the power point. We give
patients drugs that change their personality with only the faintest idea (if
we are to be honest) as to how these work; if we knew enough about the brain
to build one, adjusting for friendliness (however that might be defined)
should be a relatively trivial problem.
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:57 MDT