From: sl4.20.pris@spamgourmet.com
Date: Tue Nov 20 2007 - 18:33:27 MST
On Nov 18, 2007 11:01 PM, Hector Zenil - hzenilc@gmail.com 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