From: justin corwin (outlawpoet@gmail.com)
Date: Mon Sep 19 2005 - 22:31:04 MDT
On 9/19/05, Michael Vassar <michaelvassar@hotmail.com> wrote:
> I have been considering devoting a substantial amount of time to examining
> the question of how the SIAI Guidelines on Friendly AI could be implemented
> by GAI research projects other than that undertaken by SIAI. How feasible
> and how worth-while do people here consider that task to be?
I don't think anyone is currently capable of writing a sufficiently
complete, and sufficiently generic set of FAI Guidelines that would
apply to the class of AGI projects that people are attempting or might
attempt.
I would be very interested in a discussion involving major theorists
as to how FAI safety theory affects the primary categories of AI
architectures, and goal systems. A set of living documentation which
details 'best known, or best projected practices' recommended for
current AI researchers would be a very useful centrepoint for
discussing FAI in general as well.
Concreteness can only help us in at least defining the major problems
and concerns.
-- Justin Corwin outlawpoet@hell.com http://outlawpoet.blogspot.com http://www.adaptiveai.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT