Re: How would a computer know if it were conscious?

From: David Nyman <david.nyman.domain.name.hidden>
Date: Sun, 24 Jun 2007 20:20:49 +0100

On 23/06/07, Russell Standish <lists.domain.name.hidden> wrote:

RS: Perhaps you are one of those rare souls with a foot in
each camp. That could be be very productive!

I hope so! Let's see...

RS: This last post is perfectly lucid to me.

Phew!! Well, that's a good start.

RS: I hope I've answered it
adequately.

Your answer is very interesting - not quite what I expected:

RS: In some Platonic sense, all possible observers are already
out there, but by physically instantiating it in our world, we are in
effect opening up a communication channel between ourselves and the
new consciousness.

I think I must be missing something profound in your intended meanings of:

1) 'out there'
2) 'physically instantiating'
3) 'our world'

My current 'picture' of it is as follows. The 'Platonic sense' I assume
equates to the 'bit-string plenitude' (which is differentiable from 'no
information' only by internal observers, like the Library of Babel - a
beautiful idea BTW). But I'm assuming a 'hierarchy' of recursive
computational emergence through bits up through, say, strings, quarks,
atoms, molecules, etc - in other words what is perceived as matter-energy by
observers. I then assume that both 'physical objects' and any correlated
observers emerge from this matter-energy level, and that this co-emergence
accomplishes the 'physical instantiation'. IOW, the observer is the
1-person view, and the physical behaviour the 3-person view, of the same
underlying complex emergent - they're different descriptions of the same
events.

If this is so, then as you say, the opening of the 'communication channel'
would be a matter of establishing the means and modes of interaction with
any new consciousness, because the same seamless underlying causal sequence
unites observer-world and physical-world: again, different descriptions,
same events.

If the above is accepted (but I'm beginning to suspect there's something
deeply wrong with it), then the 'stability' of the world of the observer
should equate to the 'stability' of the physical events to which it is
linked through *identity*. Now here's what puzzles me. ISTM that the
imputation of 'computation' to the physical computer is only through the
systematic correspondence of certain stable aspects of its (principally)
electronic behaviour to computational elements: numbers,
mathematical-logical operators, etc. The problem is in the terms
'imputation' and 'correspondence': this is surely merely a *way of speaking*
about the physical events in the computer, an arbitrary ascription, from an
infinite possible set, of externally-established semantics to the intrinsic
physical syntactics.

Consequently, ISTM that the emergence of observer-worlds has to be
correlated (somehow) - one-to-one, or isomorphically - with corresponding
'physical' events: IOW these events, with their 'dual description',
constitute a single 'distinguished' *causal* sequence. By contrast, *any*
of the myriad 'computational worlds' that could be ascribed to the same
events must remain - to the computer, rather than the programmer - only
arbitrary or 'imaginary' ones. This is why I described them as 'nested' -
perhaps 'orthogonal' or 'imaginary' are better: they may - 'platonically' -
exist somewhere in the plenitude, but causally disconnected from the
physical world in which the computer participates. The computer doesn't
'know' anything about them. Consequently, how could they possess any
'communication channel' to the computer's - and our - world 'out there'?

Of course I'm not claiming by this that machines couldn't be conscious. My
claim is rather that if they are, it couldn't be solely in virtue of any
'imaginary computational worlds' imputed to them, but rather because they
support some unique, distinguished process of *physical* emergence that also
corresponds to a unique observer-world: and of course, mutatis mutandis,
this must also apply to the 'mind-brain' relationship.

If I'm wrong (as no doubt I am), ISTM I must have erred in some step or
other of my logic above. How do I debug it?

David



> On Sat, Jun 23, 2007 at 03:58:39PM +0100, David Nyman wrote:
> > On 23/06/07, Russell Standish <lists.domain.name.hidden> wrote:
> >
> > RS: I don't think I ever really found myself in
> > disagreement with you. Rather, what is happening is symptomatic of us
> > trying to reach across the divide of JP Snow's two cultures. You are
> > obviously comfortable with the world of literary criticism, and your
> > style of writing reflects this. The trouble is that to someone brought
> > up on a diet of scientific and technical writing, the literary paper
> > may as well be written in ancient greek. Gibberish doesn't mean
> > rubbish or nonsense, just unintelligible.
> >
> > DN: It's interesting that you should perceive it in this way: I hadn't
> > thought about it like this, but I suspect you're not wrong. I haven't
> > consumed very much of your 'diet', and I have indeed read quite a lot of
> > stuff in the style you refer to, although I often find it rather
> > indigestible! But on the other hand, much of my professional experience
> has
> > been in the world of computer programming, right back to machine code
> days,
> > so I'm very aware of the difference between 'syntax' and 'semantics',
> and I
> > know too well how consequences can diverge wildly from a difference of a
> > single bit. How often have I heard the beleaguered self-tester wail "I
> > didn't *mean* that!"
>
> Interesting indeed. I wouldn't have guessed you to have been a
> programmer. Perhaps you are one of those rare souls with a foot in
> each camp. That could be be very productive!
>
> ...
>
> >
> > However, in the spirit of the original topic of the thread, I would
> prefer
> > to ask you directly about the plausibility (which, unless I've
> > misunderstood, you support?) of an AI-program being in principle
> > 'conscious'. I take this to entail that instantiating such a program
> > thereby implements an 'observer' that can respond to and share a
> reality, in
> > broadly the same terms, with human 'observers'. (I apologise in advance
> if
> > any paraphrase or short-hand I adopt misrepresents what you say in TON):
> >
>
> It seems plausible, certainly.
>
> > TON, as you comment in the book, takes the 'idealist' stance that
> 'concrete'
> > notions emerge from observation. Our own relative status as observers
> > participating in 'worlds' is then dependent on computational 'emergence'
> > from the plenitude of all possible bit-strings. Let's say that I'm such
> an
> > observer and I observe a 'computer' like the one I'm using now. The
> > 'computer' is a 3-person 'concrete emergent' in my 1-person world, and
> that
> > of the 'plurality' of observers with whom I'm in relation: we can
> 'interact'
> > with it. Now, we collectively *impute* that some aspect of its 3-person
> > behaviour (e.g. EM phenomena in its internal circuitry) is to be
> regarded as
> > 'running an AI program' (i.e. ISTM that this is what happens when we
> > 'compile and run' a program). In what way does such imputation entail
> the
> > evocation - despite the myriad possible 'concrete' instantiations that
> might
> > represent it - of a *stable* observer capable of participating in our
> shared
> > '1-person plural' context? IOW, I'm concerned that two different
> categories
> > are being conflated here: the 'world' at the 'observer level' that
> includes
> > me and the computer, and the 'world' of the program, which is 'nested'
> > inside this. How can this 'nested' world get any purchase on
> 'observables'
> > that are 'external' to it?
> >
>
> It is no different to a conscious being instantiated in a new-born
> baby (or 18 month old, or whenever babies actually become
> conscious). In some Platonic sense, all possible observers are already
> out there, but by physically instantiating it in our world, we are in
> effect opening up a communication channel between ourselves and the
> new consciousness.
>
> > As I re-read this question, I wonder whether I've already willy-nilly
> fallen
> > into the '2-cultures' gap again. But what I've asked seems to be
> directly
> > related to the issues raised by 'Olympia and Klara', and by the
> substitution
> > level dilemma posed by 'yes doctor'. Could you show me where - or if -
> I go
> > wrong, or does the 'language game' make our views forever mutually
> > unintelligible?
> >
> > David
> >
>
> This last post is perfectly lucid to me. I hope I've answered it
> adequately.
>
> Cheers
>
>
> --
>
>
> ----------------------------------------------------------------------------
> A/Prof Russell Standish Phone 0425 253119 (mobile)
> Mathematics
> UNSW SYDNEY 2052 hpcoder.domain.name.hidden
> Australia http://www.hpcoders.com.au
>
> ----------------------------------------------------------------------------
>
> >
>

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups "Everything List" group.
To post to this group, send email to everything-list.domain.name.hidden
To unsubscribe from this group, send email to everything-list-unsubscribe.domain.name.hidden
For more options, visit this group at http://groups.google.com/group/everything-list?hl=en
-~----------~----~----~----~------~----~------~--~---
Received on Sun Jun 24 2007 - 15:20:57 PDT

This archive was generated by hypermail 2.3.0 : Fri Feb 16 2018 - 13:20:14 PST