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

From: Robin Lee Powell (rlpowell@digitalkingdom.org)
Date: Wed Oct 14 2009 - 11:47:45 MDT


On Wed, Oct 14, 2009 at 10:41:00AM -0700, John K Clark wrote:
>
> On Wed, 14 Oct 2009 "Marc Warner" <marc1warner@gmail.com> said:
>
> > John - Why are your arguments about infinite loops limited to
> > fixed goal minds? It seems that within your framework, a
> > non-fixed goal mind would still be a Turing machine and
> > susceptible to the same infinite loops.
>
> In a real mind all goals are ephemeral, real minds have a
> wonderful property that fictional fixed goal minds don't have,
> real minds get board. Your top goal is to try something, nothing
> is happening, you drum your fingers and say to hell with this, so
> now you have a new top goal and try that.

Please show us your proof that getting bored is amazing magic that a
Friendly AI with a fix top-level goal could not possibly have.

Seriously: there's not reason to not include "get bored" code in an
AI, and plent of reasons to do so. "When bored, try something else
to reach your goals."

-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