Robot consciousness

[Paul C. Anagnostopoulos]

Consider a conscious robot with a brain composed of a computer running sophisticated software. Let's assume that the appropriately organized software is conscious in a sense similar to that of human brains.

Would the robot be conscious if we ran the computer at a significantly reduced clock speed? What if we single-stepped the program? What would this consciousness be like if we hand-executed the code with pencil and paper?

I can't take credit for these questions; they were posted on another forum. The following paper is relevant to this issue:

http://www.biolbull.org/cgi/content/abstract/215/3/216

~~ Paul

 

[Darat]

Oh that's the main idea in an interesting science fiction novel - damn what's it called, let me try and find it.

 

[nathan]

Consider a conscious robot with a brain composed of a computer running sophisticated software. Let's assume that the appropriately organized software is conscious in a sense similar to that of human brains.

Would the robot be conscious if we ran the computer at a significantly reduced clock speed? What if we single-stepped the program? What would this consciousness be like if we hand-executed the code with pencil and paper?

You're making the assumption that such a system has a clock rate.

Bunch of Rocks

 

[Paul C. Anagnostopoulos]

You're making the assumption that such a system has a clock rate.

Yes, and that may be the crux of the matter. Our brain has a clock rate, too, but it is determined by chemistry. Perhaps consciousness arises only within a narrow range of clock rates, due to requirements for ensembles of neurons to form. In order to obtain similar behavior from a programmed consciousness, we might have to emulate the chemical clock and possibly other chemical components.

Even if a CPU doesn't have a central clock, it does have a (possibly variable) running speed. Is that relevant to the robot's consciousness? If not, then is the robot conscious even when the CPU is not running?

~~ Paul

P.S. Excellent cartoon!

 

[athon]

Oh that's the main idea in an interesting science fiction novel - damn what's it called, let me try and find it.

Permutation City by Greg Egan?

Damn good read that one.

Athon

 

[Dancing David]

Um the human brain would be a multiple processor fuzzy cross wired.

No exact clock rate.

 

[Paul C. Anagnostopoulos]

Um the human brain would be a multiple processor fuzzy cross wired.

No exact clock rate.

Certainly no single clock rate, for sure. But what about a robot consciousness implemented on a computer? It has a clock rate, or at least a processing speed. Would we need to emulate the brains various chemical clocks to obtain consciousness? What if we ran the computer faster or slower?

~~ Paul

 

[Aepervius]

I am not sure if I got the question properly. Maybe you can check that by answering me : your conscious robot/human, if you film it taking a decision/being conscious, then AGAIN do the same but reduce the "clock/chemistry metabolism reaction rate & molecule speed" divided speed by 1 billion, and then film it making a similar decision, when you do accelerate it by 1 billion, do you still see the emergent property of consciousness ? Yes ? Then the robot/human/living being is still the same conscious, even if it would be difficult to detect at our speed level.

Consciousness is defined by emergent property , independently of the speed of those same emergent property.

 

[Darat]

Permutation City by Greg Egan?

Damn good read that one.

Athon

That's the one - I knew it was a "Greg", but was looking for a Greg Bear novel.

 

[Darat]

Certainly no single clock rate, for sure. But what about a robot consciousness implemented on a computer? It has a clock rate, or at least a processing speed. Would we need to emulate the brains various chemical clocks to obtain consciousness? What if we ran the computer faster or slower?

~~ Paul

Paul - now that Athon's identified it I really suggest you gab a copy of "Permutation City", it explores this concept in some detail.

 

[athon]

Paul - now that Athon's identified it I really suggest you gab a copy of "Permutation City", it explores this concept in some detail.

I whole-heartedly second that. Get your hands on any of his stuff, actually. It's all good.

Athon

 

[Paul C. Anagnostopoulos]

Paul - now that Athon's identified it I really suggest you gab a copy of "Permutation City", it explores this concept in some detail.

I just 1-clicked it.

~~ Paul

 

[Paul C. Anagnostopoulos]

I am not sure if I got the question properly. Maybe you can check that by answering me : your conscious robot/human, if you film it taking a decision/being conscious, then AGAIN do the same but reduce the "clock/chemistry metabolism reaction rate & molecule speed" divided speed by 1 billion, and then film it making a similar decision, when you do accelerate it by 1 billion, do you still see the emergent property of consciousness ? Yes ? Then the robot/human/living being is still the same conscious, even if it would be difficult to detect at our speed level.

Consciousness is defined by emergent property , independently of the speed of those same emergent property.

I don't think this is obvious. I think it's pretty clear that the human brain is conscious only when certain ensembles of neurons become synchronized in certain timeframes.

Consider the possibility that a robot consciousness algorithm might have to consult a wall clock to work correctly. Then the speed of the computer could make a big difference.

I'm certainly not sure about this, just sayin'.

~~ Paul

 

[nescafe]

Certainly no single clock rate, for sure. But what about a robot consciousness implemented on a computer? It has a clock rate, or at least a processing speed. Would we need to emulate the brains various chemical clocks to obtain consciousness? What if we ran the computer faster or slower?

~~ Paul

There would be no need for a robot consciousness implemented on a computer to have a "clock rate" (either a single global clock rate or a bunch of different systems operating at their own clock rates), either. Asynchronous circuit based digital logic does not require a clock to keep things consistent.
[/nitpick]

 

[Aepervius]

I don't think this is obvious. I think it's pretty clear that the human brain is conscious only when certain ensembles of neurons become synchronized in certain timeframes.

Consider the possibility that a robot consciousness algorithm might have to consult a wall clock to work correctly. Then the speed of the computer could make a big difference.

I'm certainly not sure about this, just sayin'.

~~ Paul

This is a bit of setting up an example destined to fail. If I kill a sheep and burn it, I can prove I can't later shave it. You impose the later failure by imposing precondition which might not be necessary. By ascribing the necessity to use a FIXED time (the second of a clock) then you automatically limit the range where such process is possible to the range to which that time epriod exists. Too long, too short nothing happens.

I do not think this is a necessity. What *might* be a necessity for the emergent property is a proper synchronization of some parallel process. but that this synchronization is within 1 ms or 1 billion time slower within 11 days (1 million seconds) does not matter as long as the synchronization and the follow up resulting state are identical. A AND gate is still a hand gate whether it reacts within 1 ms or within 1 day.

Proof of concept : basically if consciousness is just a calculation how ever horrid and complicated with synchronization of massive parallel process, an emergent property, then there is no reason that making it slower or quicker, as long as *ALL* time period are made quicker or slower. Basically the result would come to the same.

 

[shuttlt]

Consider a conscious robot with a brain composed of a computer running sophisticated software. Let's assume that the appropriately organized software is conscious in a sense similar to that of human brains.

In the sense that it has a subjective experience in the same way that I do, rather than that it just behaves as if it was conscious?

Would the robot be conscious if we ran the computer at a significantly reduced clock speed? What if we single-stepped the program? What would this consciousness be like if we hand-executed the code with pencil and paper?

My view on this is that this is much the same question as asking whether Thompson's Lamp is on, or off at the end of the series. There isn't enough information in your definition of consciousness to answer the question.

If explain how you would know the robot IS conscious I'm sure somebody will be able to tell you whether varying the clock speed will matter.

If all you care about is behavior rather than unknowable subjective nonsense, then of course the robot is conscious in all your examples.

 

[Paul C. Anagnostopoulos]

There would be no need for a robot consciousness implemented on a computer to have a "clock rate" (either a single global clock rate or a bunch of different systems operating at their own clock rates), either. Asynchronous circuit based digital logic does not require a clock to keep things consistent.

But autonomous circuits may not allow consciousness.

We have to distinguish the clock (or lack thereof) of the underlying processor from the clocks (or lack thereof) of the algorithms. The speed of the underlying processor might have an effect on the algorithms (see next post).

~~ Paul

 

[Paul C. Anagnostopoulos]

I do not think this is a necessity. What *might* be a necessity for the emergent property is a proper synchronization of some parallel process. but that this synchronization is within 1 ms or 1 billion time slower within 11 days (1 million seconds) does not matter as long as the synchronization and the follow up resulting state are identical. A AND gate is still a hand gate whether it reacts within 1 ms or within 1 day.

Proof of concept : basically if consciousness is just a calculation how ever horrid and complicated with synchronization of massive parallel process, an emergent property, then there is no reason that making it slower or quicker, as long as *ALL* time period are made quicker or slower. Basically the result would come to the same.

I would tend to agree with you, except that the human brain appears to be an exception. The speed at which ensembles of neurons synchronize and desynchronize seems to dictate whether those processes are conscious or not. Is this a result of the chemical basis of human consciousness, or is it true for robot consciousness, too?

Is it possibly the case that if the computer ran slow enough, the robot would not perceive itself as conscious, because it would be in the equivalent of non-REM sleep?

~~ Paul

 

[Paul C. Anagnostopoulos]

In the sense that it has a subjective experience in the same way that I do, rather than that it just behaves as if it was conscious?

Since we have no way of determining the former, we'll have to go with the latter. We have to use some sort of Turing test.

If explain how you would know the robot IS conscious I'm sure somebody will be able to tell you whether varying the clock speed will matter.

I'm not convinced it's that simple. If the robot can be in non-REM sleep and pass the Turing test for that state, then maybe it's the case that the robot could be in a vegetative state if the processor was running slow enough.

~~ Paul

 

[The Central Scrutinizer]

If the robot is running Windows, the answer is no.