Re: Changing the value system of FAI

From: ARGOSYPC@aol.com
Date: Mon May 08 2006 - 06:13:51 MDT


 
In a message dated 07/05/2006 18:29:37 GMT Daylight Time, ben@goertzel.org
writes:

Eliezer wrote:
> The problem I haven't been able to solve is *rigorously* describing how
> a classical Bayesian expected utility maximizer would make changes to
> its own source code, including the source code that changes the code;
> that is, there would be some set of code that modified itself.
> Classical decision theory barfs on this due to an infinite recursion.

No system can be designed which is able to optimise it's own source code.
I would have thought that Godel's Incompleteness Theorem would have made
that abundantly clear.
 
The solution is actually rather simple -
 
You use TWO or more separate systems (with different code structures) to
modify each other.
 
Paul C
 
 
 



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT