Re: Building a friendly AI from a "just do what I tell you" AI

Date: Tue Nov 20 2007 - 18:33:27 MST

On Nov 18, 2007 11:01 PM, Hector Zenil - wrote:
> There is another potential issue concerning questions about models of
> AI, both very likely to happen as I will explain below:
> 1. The problem of OAI deciding if a model (created by itself or not)
> is FAI is undecidable.
> or
> 2. it is irreducible.
> in both cases OAI cannot give a definite answer. Now replace OAI by
> anything else but a hypercomputer.

If you are right, this would also imply that we humans CAN'T prove
that a specific AGI is friendly, correct?

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:00 MDT