Re: More silly but friendly ideas

From: Matt Mahoney (matmahoney@yahoo.com)
Date: Thu Jun 05 2008 - 19:25:39 MDT


--- On Thu, 6/5/08, Stathis Papaioannou <stathisp@gmail.com> wrote:

> If you argue that the AI is so complex that its goals will change
> unpredictably despite being initially well-defined then you are
> arguing that the AI will inevitably malfunction and behave
> irrationally and unintelligently.

Probability is relative to the observer. If the observer is more intelligent than the AI, then the AI will be predictable. If the observer is less intelligent, then the AI will be unpredictable.

-- Matt Mahoney, matmahoney@yahoo.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:03 MDT