Multiple Drafts Model Of Consciousness

[Paul C. Anagnostopoulos]

Originally Posted by David

Well you are probably right - but you are rather avoiding the fundamental contradiction:

input+P=>output

is a theorem

This remains true however many lines of code go into P! Also remember that P could be a simulation of the brain and body!

Your conscious program simply checks a theorem which was already true, and always will be.

What is the contradiction? I don't understand the contradiction.

The computer goes through a series of intermediate states while running the program. You ask it questions. You get the same answers as you do from a human. What is the difference?

~~ Paul

[Paul C. Anagnostopoulos]

Originally Posted by David

My point is that Paul accepts that any material system can in principle be simulated on a computer. Therefore, he accepts that a computer program can be conscious.

Not quite. It is possible that human consciousness requires some interaction between the brain and the external world, as Chalmers claims. If that is true, then the computer would need a particular architecture in order to have the same interaction. So not any old computer could be conscious.

However, my point is that a computer program together with its input can be thought of as simply checking some mathematical relationship (albeit perhaps a very complex one) - a theorem if you like. Therefore it is reasonable to ask in the consciousness (together with qualia, of course) is associated with the checking program, or with the theorem itself! The theorem - like all theorems - is true for all time, which seems an odd place for consciousness to reside (remember this is the ultra-materialist model of consciousness).

This is a reasonable question, although I don't see why it's a paradox.

~~ Paul

[David Bailey]

Paul,

The paradox is that consciousness comes with qualia, and it seems unreasonable to associate them with a theorem that is true over all space-time. What, for example, for all the theorems representing things that have never actually happened. Do the qualia only 'activate' if the theorem is checked!

If you choose to associate the qualia with the checking mechanism - I guess that is just weird, but not perhaps paradoxical.

In effect, I would argue that a computer with a special architecture is not really a computer as we know it - so you are potentially agreeing with me. Furthermore, my guess is that the special architecture will take 200 years to specify Whichever way, the standard materialist 'explanation' looks somewhat flakey when you attack it this way.

For example, it could be that the special architecture is something akin to Open Mind's communicator (which he compares with a TV receiver).

David

[Paul C. Anagnostopoulos]

Originally Posted by David

The paradox is that consciousness comes with qualia, and it seems unreasonable to associate them with a theorem that is true over all space-time. What, for example, for all the theorems representing things that have never actually happened. Do the qualia only 'activate' if the theorem is checked!

You're oversimplifying with this theorem thing. First of all, the inputs to a brain simulator are incredibly complex, including interactions with arbitrary parts of the external world. Some of the inputs are clearly random.

Second, a computer program is different from the execution of the program. A computer program that blows up my car will not blow up my car if it is sitting on a shelf. I cannot ask a program questions to see whether it passes the Turing test if it is not running.

Third, a computer program is only a complete statement of a theorem if it has no state. If it collects data as it runs, then only the running program can be said to be the whole story.

In effect, I would argue that a computer with a special architecture is not really a computer as we know it - so you are potentially agreeing with me. Furthermore, my guess is that the special architecture will take 200 years to specify Whichever way, the standard materialist 'explanation' looks somewhat flakey when you attack it this way.

The question is: How close do we have to come to building a human brain in order for it to pass the Turing test? If it's impossible, as I think Ian says, then that's pretty interesting. Otherwise it's just a question of accuracy of simulation.

~~ Paul

[Interesting Ian]

Getting back to the homunculus problem, in the the book Irreducible Mind, the following opinion is expressed:

no homunculus problem is posed by the structure of our conscious experience itself. The efforts of Dennett (1991) and others to claim that there is such a problem, and to use that to ridicule any residue of dualism, rely upon the deeply flawed metaphor of the “Cartesian theater,” a place where mental contents get displayed and I pop in separately to view them. Descartes himself, James, and Searle, among others, all have this right; conscious experience comes to us whole and undivided, with the qualitative feels, phenomenological content, unity, and subjective point of view all built-in, intrinsic features. I and my experience cannot be separated in this way. (IM, p. 44)

Hmmmm . .yes . . . come to think of it I agree with that. Incidentally I got that from an extended review of this book (click PDF).

[David Bailey]

Originally Posted by Paul C. Anagnostopoulos

You're oversimplifying with this theorem thing. First of all, the inputs to a brain simulator are incredibly complex, including interactions with arbitrary parts of the external world. Some of the inputs are clearly random.

Second, a computer program is different from the execution of the program. A computer program that blows up my car will not blow up my car if it is sitting on a shelf. I cannot ask a program questions to see whether it passes the Turing test if it is not running.

Third, a computer program is only a complete statement of a theorem if it has no state. If it collects data as it runs, then only the running program can be said to be the whole story.


The question is: How close do we have to come to building a human brain in order for it to pass the Turing test? If it's impossible, as I think Ian says, then that's pretty interesting. Otherwise it's just a question of accuracy of simulation.

~~ Paul

The complexity of the external world doesn't really matter, because I am taking the input as fixed. Let's say you get out of bed and stub your toe, and yell out. There will be various inputs to your brain (or your whole body simulation, if you prefer), and the simulation will process them in a completely fixed way. Random number generators can be added to the input if required. We are considering one particular instance, with one set of inputs, one set of inputs coming later in the event, one initial brain state. So whatever you felt on the first occasion, should (according to you) replay each time you run the program to check the corresponding theorem!

I am not quite sure what you mean by the program that blows up your car - is this an Al Qaeda type thing, or something that inflates the tyres? However, whatever it is, the point is that the computer program is still a theorem checker, but it is connected to a bomb or a pump, as required. You want your computer to be conscious in itself - not to send signals off to a 'consciousness unit' to experience the qualia because that gets us back to square one!

I also think the Turing test is a red herring. It was devised over 50 years ago when computers were quite primitive, and I am sure that, had he lived, Turing would have revised the test. One problem with the Touring test, is that no thought was given about the issue of cheating. Suppose, for example, that the computer had access to a huge volume of human written discourse. I type it a sentence such as "Hello, how are you?" - let's just call that sentence A. Suppose the computer scans its text looking for conversations that start with A, and simply returns the next sentence B. I reply with a further sentence C, and it looks through its text for a conversation that starts with ABC, and returns the next sentence D. With a very large body of text and good luck, it might pass the test, but in no possible way could it be said to be conscious.

David

[Interesting Ian]

Originally Posted by Paul C. Anagnostopoulos

The question is: How close do we have to come to building a human brain in order for it to pass the Turing test? If it's impossible, as I think Ian says, then that's pretty interesting. Otherwise it's just a question of accuracy of simulation.

~~ Paul

I certainly do not think it is impossible. I've often mentioned that it should be eventually possible to build an android whose behaviour in practice (including everything it says) is indistinguishable from a human being's. Just like we'll be eventually be able to create a chess program where we cannot tell that it is a computer playing (we can tell now, computers play in a particular characteristic way).

[David Bailey]

Originally Posted by Interesting Ian

I certainly do not think it is impossible. I've often mentioned that it should be eventually possible to build an android whose behaviour in practice (including everything it says) is indistinguishable from a human being's. Just like we'll be eventually be able to create a chess program where we cannot tell that it is a computer playing (we can tell now, computers play in a particular characteristic way).

I am very surprised you say that - I think it is a complete theoretical abstraction to imagine an android indistinguishable in behaviour from a human - except not conscious (which is what I assume you mean).

Chess and similar problems are an incredibly narrow subset of human thought, and even there the computer has to use brute force methods to essentially cheat. Artificial Intelligence has been a spectacular failure, I would say. Just because Chalmers classifies certain problems as 'easy', does not mean they are really any easier than the 'hard' problems - just that they are currently not proven to be as hard as the hard problems.

I would guess that making an android behave as you describe, would be equivalent to solving the hard problems of consciousness.

David

[Paul C. Anagnostopoulos]

... conscious experience comes to us whole and undivided, with the qualitative feels, phenomenological content, unity, and subjective point of view all built-in, intrinsic features. I and my experience cannot be separated in this way.

Unless, of course, you have any one of dozens of known brain defects.

~~ Paul

[Paul C. Anagnostopoulos]

Originally Posted by David

The complexity of the external world doesn't really matter, because I am taking the input as fixed. Let's say you get out of bed and stub your toe, and yell out. There will be various inputs to your brain (or your whole body simulation, if you prefer), and the simulation will process them in a completely fixed way. Random number generators can be added to the input if required. We are considering one particular instance, with one set of inputs, one set of inputs coming later in the event, one initial brain state. So whatever you felt on the first occasion, should (according to you) replay each time you run the program to check the corresponding theorem!

Agreed. So let's consider an unborn fetus. Can you describe what he feels the first time he stubs his toe in the uterus? No, you cannot. It's quite likely he feels nothing, because he has not learned to hurt. How long do we have to run the simulator before we expect typical pain feelings?

I am not quite sure what you mean by the program that blows up your car - is this an Al Qaeda type thing, or something that inflates the tyres? However, whatever it is, the point is that the computer program is still a theorem checker, but it is connected to a bomb or a pump, as required. You want your computer to be conscious in itself - not to send signals off to a 'consciousness unit' to experience the qualia because that gets us back to square one!

Please describe how we determine whether the program is "conscious in itself."

I also think the Turing test is a red herring. It was devised over 50 years ago when computers were quite primitive, and I am sure that, had he lived, Turing would have revised the test. One problem with the Touring test, is that no thought was given about the issue of cheating. Suppose, for example, that the computer had access to a huge volume of human written discourse. I type it a sentence such as "Hello, how are you?" - let's just call that sentence A. Suppose the computer scans its text looking for conversations that start with A, and simply returns the next sentence B. I reply with a further sentence C, and it looks through its text for a conversation that starts with ABC, and returns the next sentence D. With a very large body of text and good luck, it might pass the test, but in no possible way could it be said to be conscious.

Why not?

~~ Paul