From: pdugan (pdugan@vt.edu)
Date: Sat Jul 16 2005 - 02:26:16 MDT
Hell, the "Self" is the most anthropomorphic term there is, I confess what I'm
getting at is somewhat difficult to define in the western positivist sense of
consistency. I guess I'm suggesting inclusive identity is a way to get around
the Godel problem of recursive self-improvement, if the desired values to keep
are inclusive, there are no values to lose amidst change. I am aware theres
significantly more to it to get inclusive identity from including a dominant
phase space populated by little tiles, its just a nice idea which I hope could
be useful to someone's FAI designs, the whole notion is really an intended
intuition for the AGI to be guided by. Of course, if the Penrose hypothesis
proves tenable this might just prove elegant.
>===== Original Message From Peter de Blanc <peter.deblanc@verizon.net> =====
>On Fri, 2005-07-15 at 16:44 -0400, pdugan wrote:
>> I think you miss my point though, what I'm advocating is
>> an inclusion of all information held by the AGI into what functionally
>> might
>> be seen by humans as identity, the AGI treats everything as it would
>> treat
>> itself if it had a tangible individuated self-concept as we do;
>> functional
>> selflessness.
>
>This is anthropomorphic thinking. You're suggesting we take an AGI with
>an observer-centric goal system, and convince it that everything is part
>of the observer. In fact an observer-centric goal system is something
>you would have to add, so all you're accomplishing, at best, is
>implementing the goal system you had originally intended in a more
>roundabout fashion. Please look at CFAI, especially section 2.2, which
>covers this topic. Here's a link if you need it:
>
>http://www.intelligence.org/CFAI/anthro.html#selfishness
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT