Re: Computers that improve themselves

From: Arona Ndiaye (arona1@em8s.com)
Date: Tue Apr 24 2001 - 03:31:06 MDT


Greetings to y'all =)

Samantha Atkins said:

<<<
<< I believe a system could be build to
<< change in such a fashion and to self-test but it would be a far stretch
<< for me to believe that humans are going to know how to test the result
<< in fine-grained function level detail
<<<

Insofar as a Seed AI is concerned, it would seem to me that:

1. Ve shall *wink* should be Friendly (testable/tested/continuously being
tested)

2. That ve should allow and/or help us test vis Friendliness (including in
fine-grained function level detail) and other parts...

3. EC and/or EP might help as one of the tricks needed to improve/self-alter
vis own -fill with appropriate term, relevant part- AFTER Friendliness has
been achieved.

Off course I might be wrong...

Most kind regards,

Arona



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT