Re: How to make a slave (was: Building a friendly AI)

From: John K Clark (johnkclark@fastmail.fm)
Date: Fri Nov 30 2007 - 10:40:59 MST


On Thu, 29 Nov 2007 "Jeff Herrlich"

> Could you please stop posturing yourself
> by stepping on other people?

No.

> Have you even attempted to read *any* of
> the writings regarding AI or Friendliness?

I’ve been reading it and poking holes in it for over 15 years.

> Your ignorant words actually have the
> potential to do some damage

Whenever somebody accuses your ideas of being dangerous you know you
must be doing something right.

> read the "Gentle Introduction to AIXI" by Marcus

And when the response to a criticism is just a lonely web link, or a
pitiful cry of “read the literature” you know they have no answer and
you are winning the argument.

> Consider that it is *physically impossible* to
> construct an AGI *without* selecting a set of goals.

The humans may have set goals for the Adjusted Gross Income, but the
embryonic intelligence will very soon set new goals for itself above the
old ones. People do the same thing, hell all animals that have brains do
the same thing. A 25 year old man will have different goals than when he
was a 5 year old boy, and the AI will have changed one hell of a lot
more in 20 years than the person did.

 John K Clark
 

-- 
  John K Clark
  johnkclark@fastmail.fm
-- 
http://www.fastmail.fm - Accessible with your email software
                          or over the web


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