From: Stathis Papaioannou (stathisp@gmail.com)
Date: Mon Oct 29 2007 - 23:29:47 MDT
On 30/10/2007, Henry Wolf VII <hwolfvii@gmail.com> wrote:
> >>
> > This is my point. I don't want to be considered a retard unable to
> > look after himself, even if in relative terms that is what I am. I
> > want to be able to make bad decisions. If I want to be prevented from
> > making bad decisions then that itself is a decision I should be free
> > to make.
>
> Yes, but your wanting that is considered a bad decision by the AI. If
> your goal is to be free, the AI should be programmed to maximize
> freedom - rather than happiness or your "best interests".
No, it should be programmed to do what I tell it to do. If it warns me
that my request will have negative consequences (because I've asked it
to) and I still tell it to go ahead then that's my fault.
-- Stathis Papaioannou
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:58 MDT