From: Michael Anissimov (michaelanissimov@gmail.com)
Date: Thu Aug 24 2006 - 15:07:43 MDT
On 8/24/06, Richard Loosemore <rpwl@lightlink.com> wrote:
> This impression would be a mistake. To take just the issue of
> friendliness, for example: there are approaches to this problem that
> are powerful and viable, but because the list core does not agree with
> them, you might think that they are not feasible, or outright dangerous
> and irresponsible. This impression is a result of skewed opinions here,
> not necessarily a reflection of the actual status of those approaches.
I'm sure that many on the list would be interested in seeing you write
up your ideas as web page. A search for "Loosemore friendliness" only
brings up your posts on this list. Don't let the "list core" get you
down.
The problem about designing motivational systems for AIs is that 99.9%
of people who attempt it have such a poor conception of the problem at
hand that they aren't even wrong. For example, see this:
The guy who wrote this probably isn't a kook, and might even come
across as quite intelligent in person. It's just that his ideas for
AI are complete nonsense.
I'm sure your ideas aren't, and I know they've been discussed on this
list before, but it would be nice to see them on a static page.
-- Michael Anissimov Lifeboat Foundation http://lifeboat.com http://acceleratingfuture.com/michael/blog
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:57 MDT