Re: Effective(?) AI Jail

From: James Rogers (jamesr@best.com)
Date: Tue Jun 12 2001 - 22:44:59 MDT


On 6/12/01 6:06 PM, "Eliezer S. Yudkowsky" <sentience@pobox.com> wrote:
>
> I repeat: The probability, and certainly the conservative assumption, is
> that a transhuman can take over a human through a VT100 terminal. Locking
> a human in a room with an UFSI for a week would certainly do the trick.

I'll have to agree with the other poster who found this to be an absurd
proposition. I can think of a couple obvious and non-obvious reasons that
make this very questionable in my mind, particularly when the human knows
the score before they go into the room with the VT100.

-James Rogers
 jamesr@best.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT