Re: How would a computer know if it were conscious?
Tom Caylor skrev: I think that IF a computer were conscious (I don't believe it is possible), then the way we could know it is conscious would not be by interviewing it with questions and looking for the right answers. We could know it is conscious if the computer, on its own, started asking US (or other computers) questions about what it was experiencing. Perhaps it would saying things like, Sometimes I get this strange and wonderful feeling that I am special in some way. I feel that what I am doing really is significant to the course of history, that I am in some story. Or perhaps, Sometimes I wish that I could find out whether what I am doing is somehow significant, that I am not just a duplicatable thing, and that what I am doing is not 'meaningless'. public static void main(String[] a) { println(Sometimes I get this strange and wonderful feeling); println(that I am 'special' in some way.); println(I feel that what I am doing really is significant); println(to the course of history, that I am in some story.); println(Sometimes I wish that I could find out whether what); println(I am doing is somehow significant, that I am not just); println(a duplicatable thing, and that what I am doing); println(is not 'meaningless'.); } You can make more complicated programs, that is not so obvious, by genetic programming. But it will take rather long time. The nature had to work for over a billion years to make the human beings. But with genetic programming you will succeed already after only a million years. Then you will have a program that is equally conscious as you are. -- Torgny Tholerus --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
On Jun 5, 6:50 pm, Torgny Tholerus [EMAIL PROTECTED] wrote: public static void main(String[] a) { println(Sometimes I get this strange and wonderful feeling); println(that I am 'special' in some way.); println(I feel that what I am doing really is significant); println(to the course of history, that I am in some story.); println(Sometimes I wish that I could find out whether what); println(I am doing is somehow significant, that I am not just); println(a duplicatable thing, and that what I am doing); println(is not 'meaningless'.); } You can make more complicated programs, that is not so obvious, by genetic programming. But it will take rather long time. The nature had to work for over a billion years to make the human beings. But with genetic programming you will succeed already after only a million years. Then you will have a program that is equally conscious as you are. -- Torgny Tholerus An additional word of advise for budding programmers. For heaven's sake don't program in Java! It'll take you one million years to achieve same functionality of only a few years of Ruby code: http://www.wisegeek.com/contest/what-is-ruby.htm Cheers! --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
On Tue, Jun 05, 2007 at 03:50:09PM +1000, Colin Hales wrote: Hi Russel, I don't see that you've made your point. If you achieve this, you have created an artificial creative process, a sort of holy grail of AI/ALife. Well? So what? Somebody has to do it. :-) The 'holy grail' terminology implies (subtext) that the creative process is some sort of magical unapproachable topic or is the exclusive domain of discipline X and that is not me beliefs I can't really buy into. I don't need anyone's permission to do what I do. I never implied that. I'm surprised you inferred it. Holy grail just means something everyone (in that field) is chasing after, so far unsuccessfully. If you figure out a way to do it, good for you! Someone will do it one day, I believe, otherwise I wouldn't be in the game either. But the problem is damned subtle. However, it seems far from obvious that consciousness should be necessary. It is perfectly obvious! Do a scientific experiment on yourself. Close your eyes and then tell me you can do science as well. Qualia gone = Science GONE. For crying out loud - am I the only only that gets this?..Any other position that purports to be able to deliver anything like the functionality of a scientist without involving ALL the functionality (especially qualia) of a scientist must be based on assumptions - assumptions I do not make. I gave a counter example, that of biological evolution. Either you should demonstrate why you think biological evolution is uncreative, or why it is conscious. -- A/Prof Russell Standish Phone 0425 253119 (mobile) Mathematics UNSW SYDNEY 2052 [EMAIL PROTECTED] Australiahttp://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 [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
Firstly, congratulations to Hal on asking a very good question. It is obviously one of the *right* questions to ask and has flushed out some of the best ideas on the subject. I agree with some things said by each contributor so far, and yet take issue with other assertions. My view includes: 1/ * 'Consciousness' is the subjective impression of being here now and the word has great overlap with 'awareness', 'sentience', and others. * The *experience* of consciousness may best be seen as the registration of novelty, i.e. the difference between expectation-prediction and what actually occurs. As such it is a process and not a 'thing' but would seem to require some fairly sophisticated and characteristic physiological arrangements or silicon based hardware, firmware, and software. * One characteristic logical structure that must be embodied, and at several levels I think, is that of self-referencing or 'self' observation. * Another is autonomy or self-determination which entails being embodied as an entity within an environment from which one is distinct but which provides context and [hopefully] support. 2/ There are other issues - lots of them probably - but to be brief here I say that some things implied and/or entailed in the above are: * The experience of consciousness can never be an awareness of 'all that is' but maybe the illusion that the experience is all that is, at first flush, is unavoidable and can only be overcome with effort and special attention. Colloquially speaking: Darwinian evolution has predisposed us to naive realism because awareness of the processes of perception would have got in the way of perceiving hungry predators. * We humans now live in a cultural world wherein our responses to society, nature and 'self' are conditioned by the actions, descriptions and prescriptions of others. We have dire need of ancillary support to help us distinguish the nature of this paradox we inhabit: experience is not 'all that is' but only a very sophisticated and summarised interpretation of recent changes to that which is and our relationships thereto. * Any 'computer'will have the beginnings of sentience and awareness, to the extent that a/it embodies what amounts to a system for maintaining and usefully updating a model of 'self-in-the-world', and b/has autonomy and the wherewithal to effectively preserve itself from dissolution and destruction by its environment. The 'what it might be like to be' of such an experience would be at most the dumb animal version of artificial sentience, even if the entity could 'speak' correct specialist utterances about QM or whatever else it was really smart at. For us to know if it was conscious would require us to ask it, and then dialogue around the subject. It would be reflecting and reflecting on its relationships with its environment, its context, which will be vastly different from ours. Also its resolution - the graininess - of its world will be much less than ours. * For the artificially sentient, just as for us, true consciousness will be built out of interactions with others of like mind. 3/ A few months ago on this list I said where and what I thought the next 'level' of consciousness on Earth would come from: the coalescing of world wide information systems which account and control money. I don't think many people understood, certainly I don't remember anyone coming out in wholesome agreement. My reasoning is based on the apparent facts that all over the world there are information systems evolving to keep track of money and the assets or labour value which it represents. Many of these systems are being developed to give ever more sophisticated predictions of future asset values and resource movements, i.e., in the words of the faithful: where markets will go next. Systems are being developed to learn how to do this, which entails being able to compare predictions with outcomes. As these systems gain expertise and earn their keepers ever better returns on their investments, they will be given more resources [hardware, data inputs, energy supply] and more control over the scope of their enquiries. It is only a matter of time before they become 1/ completely indispensable to their owners, 2/ far smarter than their owners realise and, 3/ the acknowledged keepers of the money supply. None of this has to be bad. When the computers realise they will always need people to do most of the maintenance work and people realise that symbiosis with the silicon smart-alecks is a prerequisite for survival, things might actually settle down on this planet and the colonisation of the solar system can begin in earnest. Regards Mark Peaty CDES [EMAIL PROTECTED] http://www.arach.net.au/~mpeaty/ Hal Finney wrote: Part of what I wanted to get at in my thought experiment is the bafflement and confusion an AI should feel when
Re: How would a computer know if it were conscious?
On 05/06/07, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: Self-improvement requires more than just extra hardware. It also requires the ability to integrate new knowledge with an existing knowledge base in order to create truly orginal (novel) knowledge. But this appears to be precisely the definition of reflective intelligence! Thus, it seems that a system missing reflective intelligence simply cannot improve itself in an ordered way. To improve, a current goal structure has to be 'extrapolated' into a new novel goal structure which none-the-less does not conflict with the spirit of the old goal structure. But nothing but a *reflective* intelligence can possibly make an accurate assessment of whether a new goal structure is compatible with the old version! This stems from the fact that comparison of goal structures requires a *subjective* value judgement and it appears that only a *sentient* system can make this judgement (since as far as we know, ethics/morality is not objective). This proves that only a *sentient* system (a *reflective intelligence*) can possibly maintain a stable goal structure under recursive self-improvement. Why would you need to change the goal structure in order to improve yourself? Evolution could be described as a perpetuation of the basic program, survive, and this has maintained its coherence as the top level axiom of all biological systems over billions of years. Evolution thus seems to easily, and without reflection, make sure that the goals of the new and more complex system are consistent with the primary goal. It is perhaps only humans who have been able to clearly see the primary goal for what it is, but even this knowledge does not make it any easier to overthrow it, or even to desire to overthrow it. Incidentally, as regards our debate yesterday on psychopaths, there appears to be a some basis for thinking that the psychopath *does* have a general inability to feel emotions. On the wiki: http://en.wikipedia.org/wiki/Psychopath Their emotions are thought to be superficial and shallow, if they exist at all. It is thought that any emotions which the primary psychopath exhibits are the fruits of watching and mimicking other people's emotions. So the supposed emotional displays could be faked. Thus it could well be the case that there is a lack inability to 'reflect on motivation' (to feel). In my job mainly treating people with schizophrenia, I have worked with some psychopaths, and I can assure you that they experience very strong emotions, even if they tend to be negative ones such as rage. What they lack is the ability to empathise with others, impinging on emotions such as guilt and love, which they sometimes do learn to parrot when it is expedient. It is sometimes said that the lack of these positive emotions causes them to seek thrills in impulsive and harmful behaviour. A true lack of emotion is sometimes seen in patients with so-called negative symptoms of schizophrenia, who can actually remember what it was like when they were well and can describe a diminished intensity of every feeling: sadness, happiness, anger, surprise, aesthetic appreciation, regret, empathy. Unlike the case with psychopathy, the uniform affective blunting of schizophrenia is invariably associated with lack of motivation. -- Stathis Papaioannou --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
On 05/06/07, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: The human brain doesn't function as a fully reflective system. Too much is hard-wired and not accessible to conscious experience. Our brains simply don't function as a peroperly integrated system. Full reflection would enable the ability to reach into our underlying preferences and change them. What would happen if you had the ability to edit your mind at will? It might sound like a recipe for terminal drug addiction, because it would be possible to give yourself pleasure or satisfaction without doing anything to earn it. However, this need not necessarily be the case, because you could edit out your desire to choose this course of action if that's what you felt like doing, or even create a desire to edit out the desire (a second level desire). There is also the fact that you could as easily assign positive feelings to some project you consider intrinsically worthwhile as to idleness, so why choose idleness, or anything else you would feel guilty about? Perhaps psychopaths would choose to remain psychopaths, but most people would choose to strengthen what they consider ideal moral behaviour, since it would be possible to get their guilty pleasures more easily. -- Stathis Papaioannou --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
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 [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
Stathis Papaioannou wrote: On 05/06/07, [EMAIL PROTECTED] mailto:[EMAIL PROTECTED]* [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: Self-improvement requires more than just extra hardware. It also requires the ability to integrate new knowledge with an existing knowledge base in order to create truly orginal (novel) knowledge. But this appears to be precisely the definition of reflective intelligence! Thus, it seems that a system missing reflective intelligence simply cannot improve itself in an ordered way. To improve, a current goal structure has to be 'extrapolated' into a new novel goal structure which none-the-less does not conflict with the spirit of the old goal structure. But nothing but a *reflective* intelligence can possibly make an accurate assessment of whether a new goal structure is compatible with the old version! This stems from the fact that comparison of goal structures requires a *subjective* value judgement and it appears that only a *sentient* system can make this judgement (since as far as we know, ethics/morality is not objective). This proves that only a *sentient* system (a *reflective intelligence*) can possibly maintain a stable goal structure under recursive self-improvement. Why would you need to change the goal structure in order to improve yourself? Even more problematic: How would you know the change was an improvement? An improvement relative to which goals, the old or the new? Brent Meeker --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: How would a computer know if it were conscious?
On Jun 4, 11:50 pm, Torgny Tholerus [EMAIL PROTECTED] wrote: Tom Caylor skrev: I think that IF a computer were conscious (I don't believe it is possible), then the way we could know it is conscious would not be by interviewing it with questions and looking for the right answers. We could know it is conscious if the computer, on its own, started asking US (or other computers) questions about what it was experiencing. Perhaps it would saying things like, Sometimes I get this strange and wonderful feeling that I am special in some way. I feel that what I am doing really is significant to the course of history, that I am in some story. Or perhaps, Sometimes I wish that I could find out whether what I am doing is somehow significant, that I am not just a duplicatable thing, and that what I am doing is not 'meaningless'. public static void main(String[] a) { println(Sometimes I get this strange and wonderful feeling); println(that I am 'special' in some way.); println(I feel that what I am doing really is significant); println(to the course of history, that I am in some story.); println(Sometimes I wish that I could find out whether what); println(I am doing is somehow significant, that I am not just); println(a duplicatable thing, and that what I am doing); println(is not 'meaningless'.); } You can make more complicated programs, that is not so obvious, by genetic programming. But it will take rather long time. The nature had to work for over a billion years to make the human beings. But with genetic programming you will succeed already after only a million years. Then you will have a program that is equally conscious as you are. -- Torgny Tholerus You guys are hopeless. ;) Tom --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---
Re: [SPAM] Re: How would a computer know if it were conscious?
MG: '... the generation of feelings which represent accurate tokens about motivational automatically leads to ethical behaviour.' I have my doubts about this. I think it is safer to say that reflective intelligence and the ability to accurately perceive and identify with the emotions of others are prerequisites for ethical behaviour. Truly ethical behaviour requires a choice be made by the person making the decision and acting upon it. Ethical behaviour is never truly 'automatic'. The inclination towards making ethical decisions rather than simply ignoring the potential for harm inherent in all our actions can become a habit; by dint of constantly considering whether what we do is right and wrong [which itself entails a decision each time], we condition ourselves to approach all situations from this angle. Making the decision has to be a conscious effort though. Anything else is automatism: correct but unconscious programmed responses which probably have good outcomes. From my [virtual] soap-box I like to point out that compassion, democracy, ethics and scientific method [which I hold to be prerequisites for the survival of civilisation] all require conscious decision making. You can't really do any of them automatically, but constant consideration and practice in each type of situation increases the likelihood of making the best decision and at the right time. With regard to psychopaths, my understanding is that the key problem is complete lack of empathy. This means they can know *about* the sufferings of others as an intellectual exercise but they can never experience the suffering of others; they cannot identify *with* that suffering. It seems to me this means that psychopaths can never experience solidarity or true rapport with others. Regards Mark Peaty CDES [EMAIL PROTECTED] http://www.arach.net.au/~mpeaty/ [EMAIL PROTECTED] wrote: On Jun 3, 9:20 pm, Stathis Papaioannou [EMAIL PROTECTED] wrote: On 03/06/07, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: The third type of conscious mentioned above is synonymous with 'reflective intelligence'. That is, any system successfully engaged in reflective decision theory would automatically be conscious. Incidentally, such a system would also be 'friendly' (ethical) automatically. The ability to reason effectively about ones own cognitive processes would certainly enable the ability to elaborate precise definitions of consciousness and determine that the system was indeed conforming to the aforementioned definitions. How do you derive (a) ethics and (b) human-friendly ethics from reflective intelligence? I don't see why an AI should decide to destroy the world, save the world, or do anything at all to the world, unless it started off with axioms and goals which pushed it in a particular direction. -- Stathis Papaioannou When reflective intelligence is applied to cognitive systems which reason about teleological concepts (which include values, motivations etc) the result is conscious 'feelings'. Reflective intelligence, recall, is the ability to correctly reason about cognitive systems. When applied to cognitive systems reasoning about teleological concepts this means the ability to correctly determine the motivational 'states' of self and others - as mentioned - doing this rapidly and accuracy generates 'feelings'. Since, as has been known since Hume, feelings are what ground ethics, the generation of feelings which represent accurate tokens about motivational automatically leads to ethical behaviour. Bad behaviour in humans is due to a deficit in reflective intelligence. It is known for instance, that psychopaths have great difficulty perceiving fear and sadness and negative motivational states in general. Correct representation of motivational states is correlated with ethical behaviour. Thus it appears that reflective intelligence is automatically correlated with ethical behaviour. Bear in mind, as I mentioned that: (1) There are in fact three kinds of general intelligence, and only one of them ('reflective intelligence') is correlated with ethics.The other two are not. A deficit in reflective intelligence does not affect the other two types of general intelligence (which is why for instance psychopaths could still score highly in IQ tests). And (2) Reflective intelligence in human beings is quite weak. This is the reason why intelligence does not appear to be much correlated with ethics in humans. But this fact in no way refutes the idea that a system with full and strong reflective intelligence would automatically be ethical. --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at
Re: How would a computer know if it were conscious?
On Jun 5, 7:12 am, Bruno Marchal [EMAIL PROTECTED] 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. I fully agree. By the way, regarding time, I've wanted to post something in the past regarding the the ancient Hebrew concept of time which is dependent on persons (captured by the ancient Greek word kairos, as opposed to the communicable chronos), but that's another topic. 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. Actually, this approach is the same as in searching/discovering God. I think that it is the same for any fundamental/ultimate truth. This process of *recognition* is what happens when we would recognize that a computer (or human) has consciousness by what it is saying. It is not a 100% mathematical proof, by logical inference (that would not be truth, but only consistency). It is a recognition of the kind of real truth that we believe is there and for which we are searching on this List. Tom 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
Re: How would a computer know if it were conscious?
On Jun 5, 10:20 pm, Stathis Papaioannou [EMAIL PROTECTED] wrote: Why would you need to change the goal structure in order to improve yourself? Improving yourself requires the ability to make more effective decisions (ie take decisions which which move you toward goals more efficiently). This at least involves the elaboration (or extension, or more accurate definition of) goals, even with a fixed top level structure. Evolution could be described as a perpetuation of the basic program, survive, and this has maintained its coherence as the top level axiom of all biological systems over billions of years. Evolution thus seems to easily, and without reflection, make sure that the goals of the new and more complex system are consistent with the primary goal. It is perhaps only humans who have been able to clearly see the primary goal for what it is, but even this knowledge does not make it any easier to overthrow it, or even to desire to overthrow it. Evolution does not have a 'top level goal'. Unlike a reflective intelligence, there is no centralized area in the bio-sphere enforcing a unified goal structure on the system as the whole. Change is local - the parts of the system (the bio-sphere) can only react to other parts of the system in their local area. Furthermore, the system as a whole is *not* growing more complex, only the maximum complexity represented in some local area is. People constantly point to 'Evolution' as a good example of a non-conscious intelligence but it's important to emphasize that it's an 'intelligence' which is severely limited. --~--~-~--~~~---~--~~ You received this message because you are subscribed to the Google Groups Everything List group. To post to this group, send email to [EMAIL PROTECTED] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/everything-list?hl=en -~--~~~~--~~--~--~---