From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Tue May 21 2002 - 08:10:59 MDT
I don't think any human programmer could possibly defend a network against a
seed AI. That kind of programming ability is simply out of our reach.
Humans do not write *flawless code*. At most they write programs whose
flaws are not easily noticeable even under intense study by their fellow
humans. Settle for defending the Net against human attackers and design
ahead for occasional failures.
-- -- -- -- --
Eliezer S. Yudkowsky http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence
This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:14:14 MST