From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Wed May 10 2006 - 20:34:15 MDT
Ben Goertzel wrote:
>
> I suspect that there are, however. For instance, I *suspect* (but
> have not proved) that Godel-type restrictions (appealing to Chaitin's
> algorithmic information based variant of Godel's Theorem) can be shown
> to imply that a system with memory capacity M cannot prove or disprove
> the Friendliness of most AI systems with memory capacity > N.
This doesn't necessarily impose important real-world limitations
because, as I remarked earlier with the bridge analogy, an engineer
operates within the subspace of systems that knowably work.
-- Eliezer S. Yudkowsky http://intelligence.org/ Research Fellow, Singularity Institute for Artificial Intelligence
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT