Re: [agi] Trouble implementing my AGI Algorithm
they are not the quickest path to AGI. I believe that having a design which has a number of well-thought-through restrictions with designed-in obsolescence (so that the AGI can easily become more generalized after a working foundation is built) is the most effective route to AGI. And before I get hammered -- No, this is *NOT* equivalent to a belief that narrow AI will eventually grow to AGI. Narrow AI applications all have far too many *required*, unremovable restrictions built into them that they will collapse without. This is more equivalent to training wheels on a bicycle or a scaffolding that is used to construct a building. - Original Message - From: Mark Waser [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Saturday, May 05, 2007 12:21 PM Subject: Re: [agi] Trouble implementing my AGI Algorithm I do not believe that the algorithm must be more complex. The more complex the algorithm, the more ad hoc it is. Complex algorithms are not able to perform generalized tasks. I believe the reason that n-digit was a failure was because there is no vision system, NOT because the algorithm is too simple. Fundamentally, there is always a trade-off of flexibility/freedom vs.complexity/control vs. speed. The real question is what trade-off values will work and quickly allow you to get to a system where you can relax some of your initial restrictions. My personal intuition/opinion (which I can't prove) is that many (if not the majority) of people on this list are trying for solutions that are *too* general. I believe that these too general solutions can (probably) work eventually (given enough computing power) but they are not the quickest path to AGI. I believe that having a design which has a number of well-thought-through restrictions with designed-in obsolescence (so that the AGI can easily become more generalized after a working foundation is built) is the most effective route to AGI. Of course, I could also be seriously wrong and find it impossible to remove a restriction that then prevents AGI -- but that's the route I'm taking. :-) I know that the database has to remember pain and pleasure for stimuli. But I have difficulty making a fuzzy database representation, even for some subfields. Fuzziness can mean different things to different people and the best forms of fuzziness are extremely hard to design and most often suffer *seriously* from the unconscious assumptions of the creator. I'm afraid that you're going to have to give far more detail before we'll have a clue of what you're asking. - Original Message - From: a [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Friday, May 04, 2007 6:08 PM Subject: Re: [agi] Trouble implementing my AGI Algorithm I do not believe that the algorithm must be more complex. The more complex the algorithm, the more ad hoc it is. Complex algorithms are not able to perform generalized tasks. I believe the reason that n-digit was a failure was because there is no vision system, NOT because the algorithm is too simple. Because the algorithm searches the database recursively, I believe that my simple algorithm can perform any computation (trained by operant conditioning). The failure for n-digit addition was because there are no eyes that can move to concentrate on each digit. The database is remarkably similar to the human brain. It can learn easily by only remembering the difference between the external stimuli with a similar stimuli remembered in the database. Therefore, the algorithm compress the learned knowledge efficiently. Pattern recognition and abstract reasoning is also easy because of the incremental learning. I am having trouble with the fuzzy database representation. So it's best to test the algorithm in a specific subfield (like n-digit addition) and then generalize it into real-world tasks. In general, my algorithm behaves like the brain of an animal. Animals learn by operant conditioning and are also difficult to teach them multiple digit addition. I believe that the environment must be fuzzy in order for the operant conditioning method to work. I know that the database has to remember pain and pleasure for stimuli. But I have difficulty making a fuzzy database representation, even for some subfields. - Original Message From: Mark Waser [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 3, 2007 5:06:33 PM Subject: Re: [agi] Trouble implementing my AGI Algorithm Interesting e-mail. I agree with most of your philosophy but believe that the algorithm you are requesting is far, far more complex than you realize. Is there any particular reason why you're remaining anonymous? - Original Message - From: a [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 03, 2007 4:57 PM Subject: [agi] Trouble implementing my AGI Algorithm Hello, I have trouble implementing my AGI algorithm: The below paragraphs might sound
Re: [agi] Trouble implementing my AGI Algorithm
--- a [EMAIL PROTECTED] wrote: Help me with the algorithm. Thank you Dear a for anonymous (are you related to Ben?), Before you worry about whether an AGI should be friendly or selfish or religious, first you have to solve some lower level problems in language, vision, hearing, navigation, etc. You might make some progress in each field but eventually you will run into the problem that you can't fully solve any of the problems without solving all of them. For example, images and sound contain writing and speech, so you need to solve language. Then, in order to communicate effectively with a machine, it must have a world model similar to yours, and a lot of this knowledge comes from the other senses. After you have done that, then the next problem is that you are not building a human. You are building a slave. Its sole purpose is to be useful to humans. A human body is not necessarily the best form for serving this purpose. You might build a robot with 4 arms and wheels for legs and sonar instead of vision. Or it might not have a body at all, or maybe thousands of insect sized robots controlled as one. The problem is that this creature will have a world model that is nothing like yours, and that will make communication difficult. With currently available computers we cope with this problem by inventing new terminology or by using existing words in new ways. For example, we talk about an operating system process as running or sleeping even though it has no legs and does not dream. Then there are other mental states, like running in privileged mode, that have no equivalent in humans. In humans, selfishness and friendliness and religion are secondary goals to our main goal, which like all species, is to propagate our DNA. For example, religion achieves this goal by making taboo any form of sex that does not contribute to making children. Therefore, it is inappropriate to program religion into an AGI whose goal is not reproduction, but to serve humans. In your AGI design, you need to choose an appropriate set of emotions and mental states, inventing new ones as needed. -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415user_secret=fabd7936
Re: [agi] Trouble implementing my AGI Algorithm
I do not believe that the algorithm must be more complex. The more complex the algorithm, the more ad hoc it is. Complex algorithms are not able to perform generalized tasks. I believe the reason that n-digit was a failure was because there is no vision system, NOT because the algorithm is too simple. Because the algorithm searches the database recursively, I believe that my simple algorithm can perform any computation (trained by operant conditioning). The failure for n-digit addition was because there are no eyes that can move to concentrate on each digit. The database is remarkably similar to the human brain. It can learn easily by only remembering the difference between the external stimuli with a similar stimuli remembered in the database. Therefore, the algorithm compress the learned knowledge efficiently. Pattern recognition and abstract reasoning is also easy because of the incremental learning. I am having trouble with the fuzzy database representation. So it's best to test the algorithm in a specific subfield (like n-digit addition) and then generalize it into real-world tasks. In general, my algorithm behaves like the brain of an animal. Animals learn by operant conditioning and are also difficult to teach them multiple digit addition. I believe that the environment must be fuzzy in order for the operant conditioning method to work. I know that the database has to remember pain and pleasure for stimuli. But I have difficulty making a fuzzy database representation, even for some subfields. - Original Message From: Mark Waser [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 3, 2007 5:06:33 PM Subject: Re: [agi] Trouble implementing my AGI Algorithm Interesting e-mail. I agree with most of your philosophy but believe that the algorithm you are requesting is far, far more complex than you realize. Is there any particular reason why you're remaining anonymous? - Original Message - From: a [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 03, 2007 4:57 PM Subject: [agi] Trouble implementing my AGI Algorithm Hello, I have trouble implementing my AGI algorithm: The below paragraphs might sound ridiculous, because they are my original ideas. We are all motivated by selfish thoughts. We help others so others can help us back. We help others to cope with our pleasurable chemical addiction. We help others because helpfulness is encoded in our genetic markup. We experience pain. Pain is to help us defend damage. When we touch something hot we can draw back. But we have the free will to not react to it. I believe there is no free will. I will explain what I means. Assume that pain is a constraint. But this constraint is not absolute. Other thoughts can override the constraint. For example, when you help some animal being eaten from a monster, you can fight with the monster to save the animal's life. But you will experience pain in the fight. Therefore pain is not a constraint. Your goal to save the animal's life overrides the pain constraint. (your goal to save the animal's life is also motivated by selfish actions) Therefore, pain is not a constraint. But if there is no goal that overrides the pain constraint, you will do anything to avoid the pain. We have proven there is no free will--we choose to react or not react to pain is dependent on your goal or our knowledge. Therefore, implementing pain as a constraint in friendly AI will not help many lives. Our brains are doing things to get the highest pleasure as possible. We get a chemical addiction to save that animal. That pleasure is more pleasant than avoiding the pain by not fighting. We trust ourselves. We can gamble pain for future pleasure. Therefore, I believe that emotion can be implemented by an ordinary computer. Emotion can be implemented by an algorithm that searches for the highest pleasure. The algorithm must also has the ability to gamble pain for pleasure (by applying goals or knowledge). There is no right or wrong. We kill insects all the time. But we usually do not sympathize with them. This is because that our religion says that bugs are not as important as other animals. It's a byproduct of natural selection. We have to hunt animals to survive. Without religion, we would brood over this question: Is it better to save a human by sacrificing 1000 insects or vice versa? Therefore we assume that religion is natural. Religion helps us survive. Some religions help us believe there is afterlife and reincarnation. Because we believe these, we do not fear death. We are not afraid to sacrifice ourselves for others. For example, we will not be afraid to participate in wars and spread our religion. Religion is a virus. Most of the world is religious because of that. Therefore, some religions are dangerous. But religion is essential for our daily survival. Some religious thoughts
[agi] Trouble implementing my AGI Algorithm
Hello, I have trouble implementing my AGI algorithm: The below paragraphs might sound ridiculous, because they are my original ideas. We are all motivated by selfish thoughts. We help others so others can help us back. We help others to cope with our pleasurable chemical addiction. We help others because helpfulness is encoded in our genetic markup. We experience pain. Pain is to help us defend damage. When we touch something hot we can draw back. But we have the free will to not react to it. I believe there is no free will. I will explain what I means. Assume that pain is a constraint. But this constraint is not absolute. Other thoughts can override the constraint. For example, when you help some animal being eaten from a monster, you can fight with the monster to save the animal's life. But you will experience pain in the fight. Therefore pain is not a constraint. Your goal to save the animal's life overrides the pain constraint. (your goal to save the animal's life is also motivated by selfish actions) Therefore, pain is not a constraint. But if there is no goal that overrides the pain constraint, you will do anything to avoid the pain. We have proven there is no free will--we choose to react or not react to pain is dependent on your goal or our knowledge. Therefore, implementing pain as a constraint in friendly AI will not help many lives. Our brains are doing things to get the highest pleasure as possible. We get a chemical addiction to save that animal. That pleasure is more pleasant than avoiding the pain by not fighting. We trust ourselves. We can gamble pain for future pleasure. Therefore, I believe that emotion can be implemented by an ordinary computer. Emotion can be implemented by an algorithm that searches for the highest pleasure. The algorithm must also has the ability to gamble pain for pleasure (by applying goals or knowledge). There is no right or wrong. We kill insects all the time. But we usually do not sympathize with them. This is because that our religion says that bugs are not as important as other animals. It's a byproduct of natural selection. We have to hunt animals to survive. Without religion, we would brood over this question: Is it better to save a human by sacrificing 1000 insects or vice versa? Therefore we assume that religion is natural. Religion helps us survive. Some religions help us believe there is afterlife and reincarnation. Because we believe these, we do not fear death. We are not afraid to sacrifice ourselves for others. For example, we will not be afraid to participate in wars and spread our religion. Religion is a virus. Most of the world is religious because of that. Therefore, some religions are dangerous. But religion is essential for our daily survival. Some religious thoughts are encoded in our genes. It's a process of natural selection. Kin selection and group selection are examples. Returning to the main question: Is selfishness essential for friendly AI? Selfish is related to laziness. Lazy people do not like to sacrifice hard work for pleasure (or they do not enjoy pleasure). They do not like to sacrifice their energy for pleasure. Contrastingly, AI can use as much energy as it wants. They do not get tired. Pain is using energy. But what about these feelings of people? Friendly AI will get pleasure if it sees the people happy. For example, many people are afraid of AI, even friendly AI. The friendly AI computer will self-destruct so these people will not worry about AI. The AI computer has to maintain at least a little superiority on oneself to prevent self-destruction. It's a natural instinct. But the last paragraph is contradictory. Will the computer self-destruct to get pleasure? We will guess: selfish friendly AI might not. Unselfish friendly AI might (depends on knowledge and circumstances). This is where religion takes over. If the selfish friendly AI believes in an afterlife, it might self- destruct on some circumstances. The selfish friendly AI might experience pleasure during self- destruction. The selfish friendly AI might otherwise (depending on religion) set a goal that it will experience pleasure after it is self- destructed. However, the friendly AI will be smart enough to figure out, for example, that there is no such thing as an afterlife and religion. What do we do about it? What do we do when it figures out that all organisms are equally superior? Therefore, I believe that selfish AI might be less risky than unselfish AI. Unselfish AI might treat everything equally; it might sacrifice humans to save animals. To choose the safest route, we need an AI that behaves like a human. For example, if humans are motivated by selfish goals, then friendly AI has to be motivated by selfish goals. We need an AI to be taught by a top- down method rather than a bottom-up approach, like humans. How do we make the selfish friendly AI algorithm? We have an obvious requirement: lots of
Re: [agi] Trouble implementing my AGI Algorithm
Interesting e-mail. I agree with most of your philosophy but believe that the algorithm you are requesting is far, far more complex than you realize. Is there any particular reason why you're remaining anonymous? - Original Message - From: a [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Thursday, May 03, 2007 4:57 PM Subject: [agi] Trouble implementing my AGI Algorithm Hello, I have trouble implementing my AGI algorithm: The below paragraphs might sound ridiculous, because they are my original ideas. We are all motivated by selfish thoughts. We help others so others can help us back. We help others to cope with our pleasurable chemical addiction. We help others because helpfulness is encoded in our genetic markup. We experience pain. Pain is to help us defend damage. When we touch something hot we can draw back. But we have the free will to not react to it. I believe there is no free will. I will explain what I means. Assume that pain is a constraint. But this constraint is not absolute. Other thoughts can override the constraint. For example, when you help some animal being eaten from a monster, you can fight with the monster to save the animal's life. But you will experience pain in the fight. Therefore pain is not a constraint. Your goal to save the animal's life overrides the pain constraint. (your goal to save the animal's life is also motivated by selfish actions) Therefore, pain is not a constraint. But if there is no goal that overrides the pain constraint, you will do anything to avoid the pain. We have proven there is no free will--we choose to react or not react to pain is dependent on your goal or our knowledge. Therefore, implementing pain as a constraint in friendly AI will not help many lives. Our brains are doing things to get the highest pleasure as possible. We get a chemical addiction to save that animal. That pleasure is more pleasant than avoiding the pain by not fighting. We trust ourselves. We can gamble pain for future pleasure. Therefore, I believe that emotion can be implemented by an ordinary computer. Emotion can be implemented by an algorithm that searches for the highest pleasure. The algorithm must also has the ability to gamble pain for pleasure (by applying goals or knowledge). There is no right or wrong. We kill insects all the time. But we usually do not sympathize with them. This is because that our religion says that bugs are not as important as other animals. It's a byproduct of natural selection. We have to hunt animals to survive. Without religion, we would brood over this question: Is it better to save a human by sacrificing 1000 insects or vice versa? Therefore we assume that religion is natural. Religion helps us survive. Some religions help us believe there is afterlife and reincarnation. Because we believe these, we do not fear death. We are not afraid to sacrifice ourselves for others. For example, we will not be afraid to participate in wars and spread our religion. Religion is a virus. Most of the world is religious because of that. Therefore, some religions are dangerous. But religion is essential for our daily survival. Some religious thoughts are encoded in our genes. It's a process of natural selection. Kin selection and group selection are examples. Returning to the main question: Is selfishness essential for friendly AI? Selfish is related to laziness. Lazy people do not like to sacrifice hard work for pleasure (or they do not enjoy pleasure). They do not like to sacrifice their energy for pleasure. Contrastingly, AI can use as much energy as it wants. They do not get tired. Pain is using energy. But what about these feelings of people? Friendly AI will get pleasure if it sees the people happy. For example, many people are afraid of AI, even friendly AI. The friendly AI computer will self-destruct so these people will not worry about AI. The AI computer has to maintain at least a little superiority on oneself to prevent self-destruction. It's a natural instinct. But the last paragraph is contradictory. Will the computer self-destruct to get pleasure? We will guess: selfish friendly AI might not. Unselfish friendly AI might (depends on knowledge and circumstances). This is where religion takes over. If the selfish friendly AI believes in an afterlife, it might self- destruct on some circumstances. The selfish friendly AI might experience pleasure during self- destruction. The selfish friendly AI might otherwise (depending on religion) set a goal that it will experience pleasure after it is self- destructed. However, the friendly AI will be smart enough to figure out, for example, that there is no such thing as an afterlife and religion. What do we do about it? What do we do when it figures out that all organisms are equally superior? Therefore, I believe that selfish AI might be less risky than unselfish AI. Unselfish AI might treat everything equally; it might
Re: [agi] Trouble implementing my AGI Algorithm
Hello everyone. I'm completely new to this field, on idea debugging stage still. Level of expressibility is about that of previous orator, so I'll hold back elaborate picture for now :). Will try to participate in discussion from time to time to contribute biases of my approach. Friday, May 4, 2007, 12:57:54 AM, a wrote: a Hello, a I have trouble implementing my AGI algorithm: I think main problem is world model, even 'static' one. Behaviour is something to be derived from that model (even if request for behaviour selection is the main parameter defining model construction). All those benefits/actions still need to be assigned to objects being in certain states. Religion thing you reffer to is just heuristic not grounded to underlying principles. It's inevitable in complex system description, where you have to operate on abstract levels. Implementing formal procedures (as part of system's knowledge) seems useless. When you model something through formal description, there's always semantic component external to that formal description, which defines its design. Otherwise you described it completely, which isn't an interesting case. So system can't use formalisms unless it already understands things it'll apply them to. Problem with knowledge is to make knowledge base and virtual scenes converge on consistency, which isn't covered by blind search for goal. -- Vladimir Nesovmailto:[EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415user_secret=fabd7936
Re: [agi] Trouble implementing my AGI Algorithm
Make sure you don't spend too much time pondering about x,y,z before solving a,b,c. The x,y,z may later look differently to you. Work out the knowledge representation first. Regards, Jiri Jelinek On 5/3/07, a [EMAIL PROTECTED] wrote: Hello, I have trouble implementing my AGI algorithm: The below paragraphs might sound ridiculous, because they are my original ideas. We are all motivated by selfish thoughts. We help others so others can help us back. We help others to cope with our pleasurable chemical addiction. We help others because helpfulness is encoded in our genetic markup. We experience pain. Pain is to help us defend damage. When we touch something hot we can draw back. But we have the free will to not react to it. I believe there is no free will. I will explain what I means. Assume that pain is a constraint. But this constraint is not absolute. Other thoughts can override the constraint. For example, when you help some animal being eaten from a monster, you can fight with the monster to save the animal's life. But you will experience pain in the fight. Therefore pain is not a constraint. Your goal to save the animal's life overrides the pain constraint. (your goal to save the animal's life is also motivated by selfish actions) Therefore, pain is not a constraint. But if there is no goal that overrides the pain constraint, you will do anything to avoid the pain. We have proven there is no free will--we choose to react or not react to pain is dependent on your goal or our knowledge. Therefore, implementing pain as a constraint in friendly AI will not help many lives. Our brains are doing things to get the highest pleasure as possible. We get a chemical addiction to save that animal. That pleasure is more pleasant than avoiding the pain by not fighting. We trust ourselves. We can gamble pain for future pleasure. Therefore, I believe that emotion can be implemented by an ordinary computer. Emotion can be implemented by an algorithm that searches for the highest pleasure. The algorithm must also has the ability to gamble pain for pleasure (by applying goals or knowledge). There is no right or wrong. We kill insects all the time. But we usually do not sympathize with them. This is because that our religion says that bugs are not as important as other animals. It's a byproduct of natural selection. We have to hunt animals to survive. Without religion, we would brood over this question: Is it better to save a human by sacrificing 1000 insects or vice versa? Therefore we assume that religion is natural. Religion helps us survive. Some religions help us believe there is afterlife and reincarnation. Because we believe these, we do not fear death. We are not afraid to sacrifice ourselves for others. For example, we will not be afraid to participate in wars and spread our religion. Religion is a virus. Most of the world is religious because of that. Therefore, some religions are dangerous. But religion is essential for our daily survival. Some religious thoughts are encoded in our genes. It's a process of natural selection. Kin selection and group selection are examples. Returning to the main question: Is selfishness essential for friendly AI? Selfish is related to laziness. Lazy people do not like to sacrifice hard work for pleasure (or they do not enjoy pleasure). They do not like to sacrifice their energy for pleasure. Contrastingly, AI can use as much energy as it wants. They do not get tired. Pain is using energy. But what about these feelings of people? Friendly AI will get pleasure if it sees the people happy. For example, many people are afraid of AI, even friendly AI. The friendly AI computer will self-destruct so these people will not worry about AI. The AI computer has to maintain at least a little superiority on oneself to prevent self-destruction. It's a natural instinct. But the last paragraph is contradictory. Will the computer self-destruct to get pleasure? We will guess: selfish friendly AI might not. Unselfish friendly AI might (depends on knowledge and circumstances). This is where religion takes over. If the selfish friendly AI believes in an afterlife, it might self- destruct on some circumstances. The selfish friendly AI might experience pleasure during self- destruction. The selfish friendly AI might otherwise (depending on religion) set a goal that it will experience pleasure after it is self- destructed. However, the friendly AI will be smart enough to figure out, for example, that there is no such thing as an afterlife and religion. What do we do about it? What do we do when it figures out that all organisms are equally superior? Therefore, I believe that selfish AI might be less risky than unselfish AI. Unselfish AI might treat everything equally; it might sacrifice humans to save animals. To choose the safest route, we need an AI that behaves like a human. For example, if humans are motivated by selfish goals, then friendly AI has to be motivated by selfish
