Re: [sl4] Alan Turing's results are profound

From: Robin Lee Powell (rlpowell@digitalkingdom.org)
Date: Thu Oct 15 2009 - 10:54:21 MDT


On Thu, Oct 15, 2009 at 12:49:25PM -0400, Gwern Branwen wrote:
> On Thu, Oct 15, 2009 at 12:38 PM, John K Clark <johnkclark@fastmail.fm> wrote:
> > On Wed, 14 Oct 2009 "Robin Lee Powell"
> > <rlpowell@digitalkingdom.org> said:
> >
> >> You asserted that such a mind without a "fixed goal system" was
> >> impossible,
> >
> > JESUS CHRIST! I MOST CERTAINLY DID NOT!! I asserted that a mind WITH a
> > "fixed goal system" was impossible.
> >
> >  John K Clark
> >
> >
> >
> >
> >
> >
> >  and yet, 90+% of human parents raise their children
> >> without ever getting bored and leaving them to die.  Proof by
> >> existence: many human minds succeed at this, and without getting
> >> into infinite loops.
>
> An obvious typo, as the following paragraph makes clear; somehow, I
> don't think Robin is crediting humanity's success at childrearing to
> humans constantly shifting their goals.

No. My point was simply that there exists at least 1 human mind
that:

1. Will always help a baby in need, no matter the circumstances.

2. Doesn't enter into infinite loops at random and end up cold and
lifeless as a result.

I assert, in fact, that there are millions of such minds on our
planet, if not billions.

"All" we need to do, very loosely, to get Friendly AI is emulate
that mind.

Proof by existence, and all that.

-Robin

-- 
They say:  "The first AIs will be built by the military as weapons."
And I'm  thinking:  "Does it even occur to you to try for something
other  than  the default  outcome?"  See http://shrunklink.com/cdiz
http://www.digitalkingdom.org/~rlpowell/ *** http://www.lojban.org/


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:05 MDT