RE: Revising a Friendly AI

From: Ben Goertzel (ben@intelligenesis.net)
Date: Mon Dec 11 2000 - 07:17:26 MST


> > The upshot is that I now no longer believe - or rather, am no
> longer sure;
> > it amounts to the same thing - that the ability to see "turning the
> > Universe into regular polygons" as "sterile", and "sterile" as
> > "undesirable", is strictly a property of pure intelligence. It may also
> > have a long evolutionary background in the hundred little goals
> that dance
> > in our brains.
> >
>
> I think a reasonably powerful intelligence would be sufficient to see
> this as boring and destructive of many interesting aspects of said
> universe.

I suppose that an intelligence with the inclination to do something like
this, would
probably never EVOLVE. Imagine its hypothetical predecessor, a stupider AI
with the
same inclination. It would do similar stupid things, and never evolve into
a really
intelligent being, because it would be spending all its time doing boring
repetitive things...

Of course this isn't an ironclad argument, at best it's the hint of a
probabilistic argument,
but that's how all evolutionary matters are...

> We would be in big trouble if we make any mere human the authority over
> relatively unlimited SI capabilities.

Even ~you~, Samantha?? ;>

ben



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:35 MDT