From: Matt Mahoney (matmahoney@yahoo.com)
Date: Thu Apr 03 2008 - 20:56:02 MDT
--- Lee Corbin <lcorbin@rawbw.com> wrote:
> Matt writes
> >> > If you define consciousness as a sequence S
> >> > of algorithmically similar states
> >> > (K(S_n+1|S_n) = O(1)) then certainly it exists.
> >>
> >> First, I don't define consciousness as a sequence of states,
> >> similar or not. You could aim your question at Stathis, for
> >> example. Moreover, I don't follow your mathematical
> >> notation at all. Is the O supposed to be Landau's "big-oh"
> >> notation? (I gather that K is Kolmogorov complexity, though.)
> >
> > That is what I meant. But choose your own definition if you prefer.
> > If we could agree on a definition then the rest would be easy.
>
> I'm pretty leery of definitions (Korzybski explained very well
> how easy it is for Aristotelian definitions to be useless or
> even dangerous), but I would say that consciousness is
> the process whereby a program or operating brain reports
> upon its own substates to itself, and is then able to distinguish
> these reports from the substates, (informally, "so that they can
> be 'though about'".) I mean by "substate" a particular sense
> organ's state or a report of a sense organ's state or a recall
> of some memory, all of which is recursive, so that a report
> of a report may be also considered to be a substate.)
>
> This is admittedly pretty rough, but I've heard people say much
> the same thing, and it sounded right to me.
In that case Homer without a hippocampus is conscious, but so are many
computational processes, for example a database that logs read-transactions to
itself.
But consciousness is just a distraction, a futile attempt to extend our ethics
to AI. Which machines have rights? Is teleportation ethical? (Can I kill
you if I just made a copy of you?) Is a nondestructive upload really you?
Forget consciousness. Just do the math.
-- Matt Mahoney, matmahoney@yahoo.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT