Alt-BEAM Archive
Message #11419
To: beam@sgiblab.sgi.com
From: Bob Shannon bshannon@tiac.net
Date: Mon, 06 Mar 2000 23:05:25 -0500
Subject: [alt-beam] Re: Self-Awareness/Conciousness
Mike Kulesza wrote:
> You know i read in that Smithsonian Article about BEAM something just blew
> my mind off. Brossl Hasslacher (Tilden's collegue in BEAM) proposed the idea
> that you can take nervous nets to a new level. In theory, by implementing a
> nervous net WITHIN another nervous net, you actually have a robot that is
> aware of its own existance. See, the outer net is directly interacting with
> the physical world, while the one within is only in contact with the outer.
> This means that the inner net is AWARE of the outer one, which is in turn in
> the PHYSICAL world. Thus the robot is AWARE OF ITS PHYSICAL EXISTANCE!!
>
> Kind of sends shivers down my spine.....
Uhhh, I have bots like this, and they are not aware of anything.
What twisted definition of 'aware' is Hasslacher using here?
Self awareness in the animal realm has some very simple and basic tests
that such a BEAM system can never acheive.
One of the most common is to place a small sticker or mark on the creature
while its attention is diverted. Then the creature is shown its own image
in a mirror. If it sees the sticker or mark, and removes it from its body, we
can make a claim that this animal is self aware in much the same way we are.
Quite a few aminals that are vastly more 'aware' than imbedded nv nets fail
this sort of test (mice fail, cats pass, etc).
Home