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

From: John Mikes <jamikes.domain.name.hidden>
Date: Tue, 26 Jun 2007 15:39:45 -0400

On 6/23/07, David Nyman <david.nyman.domain.name.hidden> wrote:
>
> Hi John....

....(just your Italics par-s quoted in this reply. Then "JM: means present
text)):

*DN: Since we agree to eliminate the 'obsolete noumenon', we can perhaps
re-phrase this as just: 'how do you know x?' And then the answers are of
the type 'I just see x, hear x, feel x' and so forth. IOW, 'knowing x' is
unmediated** - 'objects' like x are just 'embedded' in the structure of the
'knower', and this is recursively related to more inclusive structures
within which the knower and its environment are in turn embedded.
*
JM: You mean a hallucination of x, when you * 'I just see x, hear x, feel
x' and so forth'*.
is included in your knowledge? or even substitutes for it? Maybe yes...
But then can you differentiate? (or this is no reasonable question?)
*


*((to JM: ...know if you are NOT conscious? Well, you wouldn't.))
DN: Agreed. If we 'delete the noumenon' we get: "How would you know if you
are NOT?" or: "How would you know if you did NOT (know)?". To which we
might indeed respond: "You would not know, if you were NOT", or: "You would
not know, if you did NOT (know)". *
JM: The classic question: "Am I? and the classical answer: "Who is
asking?"
*

*DN: I think we need to distinguish between 'computers' and 'machines'. I
can see no reason in principle why an artifact could not 'know', and be
motivated by such knowing to interact with the human world: humans are of
course themselves 'natural artifacts'.* itself embedded.

JM: Are you including 'humans' into the machines or the computers? And dogs?
Amoebas?
The main difference I see here is the 'extract' of the "human world" (or:
"world, as humans can interpret what they learned") downsized to our
choice of necessity which WE liked to design into an artifact. (motors,
cellphones, AI, AL). Yes, we (humans etc.) are artefacts but 'use' a lot of
capabilities (mental etc. gadgets) we either don't know at all, or just
accept them as 'being human' (or an extract of human traits as 'being dog')
with no urge to build such into a microwave oven or an AI.
But then we are SSOO smart when we draw conclusions!!!!!
*
*DN:
Bruno's approach is to postulate the whole 'ball of wax' as computation, so
that any 'event' whether 'inside' or 'outside' the machine is 'computed'*.
JM:
Bruno is right: accepting that 'any machine' is part of its "outside(?)
totality", i.e. embedded into its ambiance, I would be scared to
differentiate myself. There is no hermetic 'skin' - it is transitional
effects transcending back and forth, we just do not observe those outside
the 'topical boundaries' of our actual observation (model, as I call it).

*DN:*
*The drift of my recent posts has been that even in this account, 'worlds'
can emerge 'orthogonally' to each other, such that from their reciprocal
perspectives, 'events' in their respective worlds will be 'imaginary'.*
JM:
I can't say: I have no idea how the world works, except for that little I
interpreted into my 1st person narrative. I accept "maybe"-s.
And I have a way to 'express' myself: I use "I dunno".

Have fun

John



David

>
>
> Dear David.
> > do not expect from me the theoretical level of technicality-talk er get
> > from Bruno: I talk (and think) common sense (my own) and if the
> > theoretical technicalities sound strange, I return to my thinking.
> >
> > That's what I got, that's what I use (plagiarized from the Hungarian
> > commi
> > joke: what is the difference between the peoples' democracy and a wife?
> > Nothing: that's what we got that's what we love)
> >
> > When I read your "questioning" the computer, i realized that you are
> > in the ballpark of the AI people (maybe also AL - sorry, Russell)
> > who select machine-accessible aspects for comparing.
> > You may ask about prejudice, shame (about goofed situations), humor
> > (does a
> > computer laugh?) boredom or preferential topics (you push for an
> > astronomical calculation and the computer says: I rather play some Bach
> > music now)
> > Sexual preference (even disinterestedness is slanted), or laziness.
> > If you add untruthfulness in risky situations, you really have a human
> > machine
> > with consciousness (whatever people say it is - I agree with your
> > evading
> > that unidentified obsolete noumenon as much as possible).
> >
> > I found Bruno's post well fitting - if i have some hint what
> > "...inner personal or self-referential modality..." may mean.
> > I could not 'practicalize' it.
> > I still frown when "abondoning (the meaning of) something but consider
> > items as pertaining to it" - a rough paraphrasing, I admit. To what?.
> > I don't feel comfortable to borrow math-methods for nonmath explanations
> > but that is my deficiency.
> >
> > Now that we arrived at thequestion I replied-added (sort of) to Colin's
> > question I -
> > let me ask it again: how would YOU know if you are conscious?
> > (Conscious is more meaningful than cc-ness). Or rather: How would
> > you know if you are NOT conscious? Well, you wouldn't. If you can,
> > you are conscious. Computers?????
> >
> > Have a good weekend
> >
> > John Mikes
> >
> >
> >
> > On 6/20/07, David Nyman < david.nyman.domain.name.hidden> wrote:
> > >
> > >
> > > On Jun 5, 3:12 pm, Bruno Marchal < marc....domain.name.hidden > wrote:
> > >
> > > > Personally I don' think we can be *personally* mistaken about our
> > > own
> > > > consciousness even if we can be mistaken about anything that
> > > > consciousness could be about.
> > >
> > > I agree with this, but I would prefer to stop using the term
> > > 'consciousness' at all. To make a decision (to whatever degree of
> > > certainty) about whether a machine possessed a 1-person pov analogous
> > > to a human one, we would surely ask it the same sort of questions one
> > > would ask a human. That is: questions about its personal 'world' -
> > > what it sees, hears, tastes (and perhaps extended non-human
> > > modalitiies); what its intentions are, and how it carries them into
> > > practice. From the machine's point-of-view, we would expect it to
> > > report such features of its personal world as being immediately
> > > present (as ours are), and that it be 'blind' to whatever 'rendering
> > > mechanisms' may underlie this (as we are).
> > >
> > > If it passed these tests, it would be making similar claims on a
> > > personal world as we do, and deploying this to achieve similar ends.
> > > Since in this case it could ask itself the same questions that we can,
> > > it would have the same grounds for reaching the same conclusion.
> > >
> > > However, I've argued in the other bit of this thread against the
> > > possibility of a computer in practice being able to instantiate such a
> > > 1-person world merely in virtue of 'soft' behaviour (i.e.
> > > programming). I suppose I would therefore have to conclude that no
> > > machine could actually pass the tests I describe above - whether self-
> > > administered or not - purely in virtue of running some AI program,
> > > however complex. This is an empirical prediction, and will have to
> > > await an empirical outcome.
> > >
> > > David
> > >
> > > On Jun 5, 3:12 pm, Bruno Marchal <marc....domain.name.hidden> wrote:
> > > > Le 03-juin-07, à 21:52, Hal Finney a écrit :
> > > >
> > > >
> > > >
> > > > > Part of what I wanted to get at in my thought experiment is the
> > > > > bafflement and confusion an AI should feel when exposed to human
> > > ideas
> > > > > about consciousness. Various people here have proffered their own
> > > > > ideas, and we might assume that the AI would read these
> > > suggestions,
> > > > > along with many other ideas that contradict the ones offered here.
> > > > > It seems hard to escape the conclusion that the only logical
> > > response
> > > > > is for the AI to figuratively throw up its hands and say that it
> > > is
> > > > > impossible to know if it is conscious, because even humans cannot
> > > agree
> > > > > on what consciousness is.
> > > >
> > > > Augustin said about (subjective) *time* that he knows perfectly what
> > > it
> > > > is, but that if you ask him to say what it is, then he admits being
> > > > unable to say anything. I think that this applies to
> > > "consciousness".
> > > > We know what it is, although only in some personal and
> > > uncommunicable
> > > > way.
> > > > Now this happens to be true also for many mathematical concept.
> > > > Strictly speaking we don't know how to define the natural numbers,
> > > and
> > > > we know today that indeed we cannot define them in a communicable
> > > way,
> > > > that is without assuming the auditor knows already what they are.
> > > >
> > > > So what can we do. We can do what mathematicians do all the time. We
> > > > can abandon the very idea of *defining* what consciousness is, and
> > > try
> > > > instead to focus on principles or statements about which we can
> > > agree
> > > > that they apply to consciousness. Then we can search for
> > > (mathematical)
> > > > object obeying to such or similar principles. This can be made
> > > easier
> > > > by admitting some theory or realm for consciousness like the idea
> > > that
> > > > consciousness could apply to *some* machine or to some
> > > *computational
> > > > events" etc.
> > > >
> > > > We could agree for example that:
> > > > 1) each one of us know what consciousness is, but nobody can prove
> > > > he/she/it is conscious.
> > > > 2) consciousness is related to inner personal or self-referential
> > > > modality
> > > > etc.
> > > >
> > > > This is how I proceed in "Conscience et Mécanisme". ("conscience"
> > > is
> > > > the french for consciousness, "conscience morale" is the french for
> > > the
> > > > english "conscience").
> > > >
> > > >
> > > >
> > > > > In particular I don't think an AI could be expected to claim that
> > > it
> > > > > knows that it is conscious, that consciousness is a deep and
> > > intrinsic
> > > > > part of itself, that whatever else it might be mistaken about it
> > > could
> > > > > not be mistaken about being conscious. I don't see any logical
> > > way it
> > > > > could reach this conclusion by studying the corpus of writings on
> > > the
> > > > > topic. If anyone disagrees, I'd like to hear how it could happen.
> > > >
> > > > As far as a machine is correct, when she introspects herself, she
> > > > cannot not discover a gap between truth (p) and provability (Bp).
> > > The
> > > > machine can discover correctly (but not necessarily in a completely
> > > > communicable way) a gap between provability (which can potentially
> > > > leads to falsities, despite correctness) and the incorrigible
> > > > knowability or knowledgeability (Bp & p), and then the gap between
> > > > those notions and observability (Bp & Dp) and sensibility (Bp & Dp &
> > >
> > > > p). Even without using the conventional name of "consciousness",
> > > > machines can discover semantical fixpoint playing the role of non
> > > > expressible but true statements.
> > > > We can *already* talk with machine about those true unnameable
> > > things,
> > > > as have done Tarski, Godel, Lob, Solovay, Boolos, Goldblatt, etc.
> > > >
> > > >
> > > >
> > > > > And the corollary to this is that perhaps humans also cannot
> > > > > legitimately
> > > > > make such claims, since logically their position is not so
> > > different
> > > > > from that of the AI. In that case the seemingly axiomatic
> > > question of
> > > > > whether we are conscious may after all be something that we could
> > > be
> > > > > mistaken about.
> > > >
> > > > This is an inference from "I cannot express p" to "I can express not
> > >
> > > > p". Or from ~Bp to B~p. Many atheist reason like that about the
> > > > concept of "unameable" reality, but it is a logical error.
> > > > Even for someone who is not willing to take the comp hyp into
> > > > consideration, it is a third person communicable fact that
> > > > self-observing machines can discover and talk about many non
> > > 3-provable
> > > > and sometimes even non 3-definable true "statements" about them.
> > > Some
> > > > true statements can only be interrogated.
> > > > Personally I don' think we can be *personally* mistaken about our
> > > own
> > > > consciousness even if we can be mistaken about anything that
> > > > consciousness could be about.
> > > >
> > > > Bruno
> > > >
> > > > http://iridia.ulb.ac.be/~marchal/
> > >
> > >
> > >
> > >
> > >
> >
> >
> >
>
> >
>

--~--~---------~--~----~------------~-------~--~----~
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 Tue Jun 26 2007 - 15:39:57 PDT

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