From: Ben Houston (ben@exocortex.org)
Date: Tue Jun 18 2002 - 14:17:40 MDT
> Dani Eder [danielravennest@yahoo.com] wrote:
> > It is also my opinion that
> > such a value system could be 'tuned' to be in
> > accord with human values. This would be done
> > by asking humans to make value comparisons, and then
> > adjusting relative values of different types
> > of information (genetic, neuronal, computer-stored)
> > to match the human results.
>
> Ben Houston [ben@exocortex.org] wrote:
> The addition of an undefined and open ended "tuning" procedure to the
> first measure could easily result in a measure that is completely
> different. I would argue then that any initial measure to which such
a
> "tuning" procedure was applied could easily be equal to the one you
are
> proposing.
Actually that is probably too harsh a statement on my part -- sorry
Dani. I guess systems wouldn't be equivalent if only the tuning only
applied to the values of different forms of information rather than
specific instances. I guess I was only thinking about the first part of
that statement that focused on tuning the system "to be in accord with
human values."
Sorry,
Ben Houston
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:39 MDT