From: turin (turin@hell.com)
Date: Mon Mar 06 2006 - 00:29:15 MST
<What I've just said makes the argument for friendliness verifiers<easier. However, I'm not on the side of the verifiers - I think there<is absolutely no hope of being able to formally verify anything about<the results of a proposed course of action in the world. Given any<formal system to prove actions benign, I could make it prove any set<of actions benign by rigging the perceptual system that connected the<action representations with their real-world semantics. Besides<which, decades of experience shows that systems with provable<properties are useless in the real world.- PhilExactly so. This is why I think Turing and later Bill Hibbard are smart to say SIA needs to be built through reinforcement learning especially at a human level
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT