From: Rolf Nelson (rolf.h.d.nelson@gmail.com)
Date: Thu Apr 03 2008 - 00:00:20 MDT
Is there a simple explanation for why you suspect this is so?
Is there anything else, like a technical version of the CEV, that
would provide a more rigorous shared understanding of what type of
thing we're targeting, but would be vastly easier to produce than a
working AGI?
-Rolf
On Wed, Apr 2, 2008 at 9:08 PM, Eliezer S. Yudkowsky
<sentience@pobox.com> wrote:
> Rolf Nelson wrote:
> >
> > 2. Publish a technical document, or better yet a computer program,
> > that would produce a Friendly outcome, given infinite computing
> > resources. Presumably such a program would not significantly help
> > someone to accidentally build a UFAI, but would provide evidence of
> > whether the FAI community has reached some level of convergence as to
> > the desired outcome.
>
> Actually, I suspect this is at least 95% of the way to a
> fully-functioning FAI, or UFAI.
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT