RE: AI-Box Experiments

From: Colin Hales (colin@versalog.com.au)
Date: Mon Jul 08 2002 - 04:27:10 MDT


Eliezer S. Yudkowsky:
> Colin, I don't think you're getting the point here... I'm one of the
> people on the side *against* having an AI in a box. I just
> think that this makes a more effective demonstration of the concept's
> futility than trying to argue the cognitive science with people who are
> still attached to the concept of boxed AIs as a "safety mechanism".
>

whoosh, 'point' things. There they go. Oh well.

cheers,

Colin



This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 09:15:14 MST