From: Joshua Fox (email@example.com)
Date: Tue Sep 09 2008 - 00:11:39 MDT
Perhaps this paper by Robin Hansen is relevant
(also discussed here
On Tue, Sep 9, 2008 at 7:40 AM, Tim Freeman <firstname.lastname@example.org> wrote:
> From: "Eliezer Yudkowsky" <email@example.com>
> >I presume you're localizing the difference to the priors, because if
> >the two AIs trust each other's evidence-gathering processes, Aumann
> >agreement prevents them from otherwise having a known disagreement
> >about posteriors.
> I don't know what you mean by "localizing" here.
> All the references I could find for the Aumann agreement theorem apply
> when the two agents have the same priors, and by hypothesis these two
> agents do not. If you think Aumann agreement applies here, please
> point to or give a statement of the theorem that supports your
> assertion. Here's one that does not:
> Tim Freeman http://www.fungible.com
> D O T E A S Y - "Join the web hosting revolution!"
This archive was generated by hypermail 2.1.5 : Thu May 23 2013 - 04:01:41 MDT