Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Ben, Mapping RRA to Hegel's space isn't trivial, but here goes... On 11/19/08, Ben Goertzel [EMAIL PROTECTED] wrote: I have nothing against Hegel; I think he was a great philosopher. His Logic is really fantastic reading. And, having grown up surrounded by Marxist wannabe-revolutionaries (most of whom backed away from strict Marxism in the mid-70s when the truth about the Soviet Union came out in America), I am also aware there is a lot of deep truth in Marx's thought, in spite of the evil that others wrought with it after his death... It's refreshing to be able to discuss the structure of problems rather than simply planning the future of the world as: 1. We will build AGIs. 2. The AGIs will create a Singularity. 3. Then, something wonderful (or horrible) will happen. I just think that Hegel's dialectical philosophy is clearer than your reverse reductio ad absurdum, That is because he saw a process that he didn't fully understand, leaving the participants to argue their many positions for decades/centuries until many consensus resolution were identified. Things always look simpler when you ignore the necessary details. BTW, there was once a government run by consensus - where all differences were argued until everyone agreed. That was early Islam, first under Mohamed and later under 4 subsequent caliphs who worked with Mohamed until his death. Of course, this is ONLY possible given some sort of understanding of RRA, yet historical accounts do NOT include anything like RRA (that I have found). Then, things came unraveled. In a logical world (if this is even possible given illogical people), consensus should be possible. Allowing for a few idiots, it should take 90% majority to pass any law or do anything that is potentially destructive (as though there were anything that a government could do that is NOT potentially destructive). In short, the whole rule by majority thing is severely flawed, though it may be OK to choose representatives. and so I'm curious to know what you think your formulation *adds* to the classic Hegelian one... A clear path to resolving differences rather than leaving it to unstructured argument, compromise, etc., as Hegel did. It directly challenges BOTH sides of an intractable dispute to seek and find the shared bad assumptions and NOT compromise, or to shut up because they are simply not smart enough to participate. From what I understand, your RRA heuristic says that, sometimes, when both X and ~X are appealing to rational people, there is some common assumption underlying the two, which when properly questioned and modified can yield a new Y that transcends and in some measure synthesizes aspects of X and ~X Usually, neither X nor ~X are even deducible from Y. For example, in the abortion debate, the pro-life side is happy because abortions are more effectively stopped than if a law had been passed, and the pro-choice is happy because there are no laws in place. Neither side can even get to the contentious point that they were at before. I suppose Hegel would have called Y the dialectical synthesis of X and ~X, right? Not being a Hegel scholar, that's the way that I see it. Hegel just failed to take the next step of mapping out exactly how to reach a dialectical synthesis, which is what RRA does. BTW, we are certainly not seeing the fall of capitalism now. Marx's dialectics-based predictions made a lot of errors; for instance, both he and Hegel failed to see the emergence of the middle class as a sort of dialectical synthesis of the ruling class and the proletariat ;-) ... and America failed to see the coming disappearance of the middle class, that throws society back into Marx's realm. ... but, I digress!! I don't think so, as we are now thinking about things at the level that a future AGI would have to be able to think at to provide societal guidance. If we can't function at this level ourselves, how are we ever going to create AGIs that do this? So, how would you apply your species of dialectics to solve the problem of consciousness? This is a case where, clearly, rational intelligent and educated people hold wildly contradictory opinions, ... which is a pretty clear demonstration that consciousness doesn't work very well. This was EXACTLY my point when discussing Dr. Eliza (that also has its obvious limitations), that other methods can potentially avoid the logical traps of the conscious process. e.g. X1 = consciousness does not exist X2 = consciousness is a special extra-physical entity that correlates with certain physical systems at certain times X3 = consciousness is a kind of physical entity X4 = consciousness is a property immanent in everything, that gets focused/structured differently via interaction with different physical systems All these positions contradict each other. How do you suggest to dialectically synthesize them? ;-) No, properly restating the above question:
Definition of pain (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
--- On Tue, 11/18/08, Mark Waser [EMAIL PROTECTED] wrote: add-rule kill-file Matt Mahoney Mark, whatever happened to that friendliness-religion you caught a few months ago? Anyway, with regard to grounding, internal feedback, and volition, autobliss already has two of these three properties, and the third could be added with an insignificant effect. With respect to grounding, I assume you mean association of language symbols with nonverbal input. For example, a text-based AI could associate the symbols red with rose and stop sign, but if it lacked vision then these symbols would not be grounded. To ground red it would need to be associated with red sensing pixels. In this sense, autobliss has grounded the symbols aah and ouch which make up its limited language by associating them with the reinforcement signal. Thus, it adjusts its behavior to say ouch less often, which is just what a human would do if the negative reinforcement signal were pain. (Also, to address Jiri Jelinek's question, it makes no conceptual difference if we swap the symbols so that aah represents pain. I did it this way just to make it more clear what autobliss is doing. The essential property is reinforcement learning). Also, autobliss has volition, meaning it has free will and makes decisions that increase its expected reward. Free will is implemented by the rand() function. Behaviorally, there is no distinction between free choice and random behavior. Belief in free will, which is a separate question, is implemented in humans by making random choices and then making up reasons that seem rational for making the choice we did. Monkeys do this too. http://www.world-science.net/othernews/071106_rationalize.htm Autobliss lacks internal feedback, although I don't see why this matters much. Neural networks often use lateral inhibition, activation fatigue, and weight decay as negative feedback loops to make them more stable. Autobliss has only one neuron (with 4 inputs) so lateral inhibition is not possible. However I could add weight decay by adding the following code inside the main loop: for (int i=0; i4; ++i) mem[i] *= 0.99; This would keep the input weights from getting too large, but also cause autobliss to slowly forget its lessons. It would require occasional reinforcement to correct its mistakes. However, this effect could be made arbitrarily small by using a decay factor arbitrarily close to 1. Anyway, I don't expect this to resolve Mark's disagreement. Intuitively, everyone knows that autobliss doesn't really experience pain, so Mark will just keep adding conditions until nothing less than a human brain meets his requirements, all the time denying that he is making choices about what feels pain and what doesn't. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
On Tue, Nov 18, 2008 at 11:23 PM, Matt Mahoney [EMAIL PROTECTED] wrote: Steve, what is the purpose of your political litmus test? If you are trying to assemble a team of seed-AI programmers with the correct ethics, forget it. Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). (I'm assuming you meant the section 5.1. Recursive Self Improvement) Why do you call it a myth? Assuming that an AI (not necessarily general) that is capable of software programming is possible and such AI is created using software, it's entirely plausible that it would be able to find places for improvement in its source code, be it in time or space usage, concurrency and parallelism missed opportunities, improved caching, more efficient data-structures, etc.. In such scenario the AI would be able to create a better version of itself, how many times this process can be done depend heavily on the cognitive capabilities of the AI and it's performance. If we move to an AGI, it would be able to come up with better tools (e.g. compilers, type systems, programming languages), improve it's substrate (e.g. write a better OS, rewrite its the performance critical parts in FPGA), come up with better chips, etc., without even needing to come up with new theories (i.e. there's sufficient information already out there that, if synthesized, can lead to better tools). This will result in another version of the AGI with better software and hardware, reduced space/time usage and more concurrent. We can come up with the argument that it'll only be a faster/leaner AGI and it will get stuck coming up with bad ideas very quickly. But if it's truly general it would, at least be able to come up with all science/tech human beings are eventually capable of and if the AGI can progress further it means humans can't also progress further. If humans are able to progress than an AGI would be able to progress, at least as quickly as humans but probably much faster (due to it's own performance enhancements). I am really interested to see your comments on this line of reasoning. -- Matt Mahoney, [EMAIL PROTECTED] Best regards, Daniel Yokomizo --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Seed AI (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
--- On Wed, 11/19/08, Daniel Yokomizo [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 11:23 PM, Matt Mahoney [EMAIL PROTECTED] wrote: Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). (I'm assuming you meant the section 5.1. Recursive Self Improvement) That too, but mainly in the argument for the singularity: If humans can produce smarter than human AI, then so can they, and faster I am questioning the antecedent, not the consequent. RSI is not a matter of an agent with IQ of 180 creating an agent with an IQ of 190. Individual humans can't produce much of of anything beyond spears and clubs without the global economy in which we live. To count as self improvement, the global economy has to produce a smarter global economy. This is already happening. My paper on RSI referenced in section 5.1 (and submitted to JAGI) only applies to systems without external input. It would apply to the unlikely scenario of a program that could understand its own source code and rewrite itself until it achieved vast intelligence while being kept in isolation for safety reasons. This scenario often came up on the SL4 list. It was referred to AI boxing. It was argued that a superhuman AI could easily trick its relatively stupid human guards into releasing it, and there were some experiments where people played the role of the AI and proved just that, even without vastly superior intelligence. I think that the boxed AI approach has been discredited by now as being impractical to develop for reasons independent of its inherent danger and my proof that it is impossible. All of the serious projects in AI are taking place in open environments, often with data collected from the internet, for simple reasons of expediency. My argument against seed AI is in this type of environment. It is extremely expensive to produce a better global economy. The current economy is worth about US$ 1 quadrillion. No small group is going to control any significant part of it. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: Seed AI (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
BTW, for those who are newbies to this list, Matt's argument attempting to refute RSI was extensively discussed on this list a few months ago. In my view, I refuted his argument pretty clearly, although he does not agree. His mathematics is correct, but seemed to me irrelevant to real-life RSI for two reasons: a) assuming a system isolated from the environment, which won't actually be the case b) using an intelligence measure focused solely on description length rather than incorporating runtime ben g On Wed, Nov 19, 2008 at 10:21 AM, Matt Mahoney [EMAIL PROTECTED] wrote: --- On Wed, 11/19/08, Daniel Yokomizo [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 11:23 PM, Matt Mahoney [EMAIL PROTECTED] wrote: Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). (I'm assuming you meant the section 5.1. Recursive Self Improvement) That too, but mainly in the argument for the singularity: If humans can produce smarter than human AI, then so can they, and faster I am questioning the antecedent, not the consequent. RSI is not a matter of an agent with IQ of 180 creating an agent with an IQ of 190. Individual humans can't produce much of of anything beyond spears and clubs without the global economy in which we live. To count as self improvement, the global economy has to produce a smarter global economy. This is already happening. My paper on RSI referenced in section 5.1 (and submitted to JAGI) only applies to systems without external input. It would apply to the unlikely scenario of a program that could understand its own source code and rewrite itself until it achieved vast intelligence while being kept in isolation for safety reasons. This scenario often came up on the SL4 list. It was referred to AI boxing. It was argued that a superhuman AI could easily trick its relatively stupid human guards into releasing it, and there were some experiments where people played the role of the AI and proved just that, even without vastly superior intelligence. I think that the boxed AI approach has been discredited by now as being impractical to develop for reasons independent of its inherent danger and my proof that it is impossible. All of the serious projects in AI are taking place in open environments, often with data collected from the internet, for simple reasons of expediency. My argument against seed AI is in this type of environment. It is extremely expensive to produce a better global economy. The current economy is worth about US$ 1 quadrillion. No small group is going to control any significant part of it. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI [EMAIL PROTECTED] A human being should be able to change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take orders, give orders, cooperate, act alone, solve equations, analyze a new problem, pitch manure, program a computer, cook a tasty meal, fight efficiently, die gallantly. Specialization is for insects. -- Robert Heinlein --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: Seed AI (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
On Wed, Nov 19, 2008 at 1:21 PM, Matt Mahoney [EMAIL PROTECTED] wrote: --- On Wed, 11/19/08, Daniel Yokomizo [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 11:23 PM, Matt Mahoney [EMAIL PROTECTED] wrote: Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). (I'm assuming you meant the section 5.1. Recursive Self Improvement) That too, but mainly in the argument for the singularity: If humans can produce smarter than human AI, then so can they, and faster I am questioning the antecedent, not the consequent. RSI is not a matter of an agent with IQ of 180 creating an agent with an IQ of 190. I just want to be clear, you agree that an agent is able to create a better version of itself, not just in terms of a badly defined measure as IQ but also as a measure of resource utilization. Individual humans can't produce much of of anything beyond spears and clubs without the global economy in which we live. To count as self improvement, the global economy has to produce a smarter global economy. This is already happening. Do you agree with the statement: the global economy in which we live is a result of actions of human beings? How would it be different for AGIs? Do you disagree that better agents would be able to build an equivalent global economy much faster than the time it took humans (assuming all the centuries it took since the last big ice age)? My paper on RSI referenced in section 5.1 (and submitted to JAGI) only applies to systems without external input. It would apply to the unlikely scenario of a program that could understand its own source code and rewrite itself until it achieved vast intelligence while being kept in isolation for safety reasons. This scenario often came up on the SL4 list. It was referred to AI boxing. It was argued that a superhuman AI could easily trick its relatively stupid human guards into releasing it, and there were some experiments where people played the role of the AI and proved just that, even without vastly superior intelligence. I think that the boxed AI approach has been discredited by now as being impractical to develop for reasons independent of its inherent danger and my proof that it is impossible. All of the serious projects in AI are taking place in open environments, often with data collected from the internet, for simple reasons of expediency. My argument against seed AI is in this type of environment. I'm asking for your comments on the technical issues regardind seed AI and RSI, regardless of environment. Is there any technical impossibilities for an AGI to improve its own code in all possible environments? Also it's not clear to me which types of environments (if it's the boxing that makes it impossible, if it's an open environment with access to the internet, if it's both or neither) you see problems with RSI, could you ellaborate it further? It is extremely expensive to produce a better global economy. The current economy is worth about US$ 1 quadrillion. No small group is going to control any significant part of it. I want to keep this discussion focused on the technical impossibilities of RSI, so I'm going to ignore for now this side discussion about the global economy but later we can go back to it. -- Matt Mahoney, [EMAIL PROTECTED] Best regards, Daniel Yokomizo --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Ben: On 11/18/08, Ben Goertzel [EMAIL PROTECTED] wrote: This sounds an awful lot like the Hegelian dialectical method... Your point being? We are all stuck in Hegal's Hell whether we like it or not. Reverse Reductio ad Absurdum is just a tool to help guide us through it. There seems to be a human tendency to say that something sounds an awful lot like (something bad) to dismiss it, but the crucial thing is often the details rather than the broad strokes. For example, the Communist Manifesto detailed the coming fall of Capitalism, which we may now be seeing in the current financial crisis. Sure, the solution proved to be worse than the problem, but that doesn't mean that the identification of the problems was in error. From what I can see, ~100% of the (mis?)perceived threat from AGI comes from a lack of understanding of RRAA (Reverse Reductio ad Absurdum), both by those working in AGI and those by the rest of the world. This clearly has the potential of affecting your own future success, so it is probably worth the extra 10 minutes or so to dig down to the very bottom of it, understand it, discuss it, and then take your reasoned position regarding it. After all, your coming super-intelligent AGI will probably have to master RRAA to be able to resolve intractable disputes, so you will have to be on top of RRAA if you are to have any chance of debugging your AGI. Steve Richfield == On Tue, Nov 18, 2008 at 5:29 PM, Steve Richfield [EMAIL PROTECTED] wrote: Martin, On 11/18/08, martin biehl [EMAIL PROTECTED] wrote: I don't know what reverse reductio ad absurdum is, so it may not be a precise counterexample, but I think you get my point. HERE is the crux of my argument, as other forms of logic fall short of being adequate to run a world with. Reverse Reductio ad Absurdum is the first logical tool with the promise to resolve most intractable disputes, ranging from the abortion debate to the middle east problem. Some people get it easily, and some require long discussions, so I'll post the Cliff Notes version here, and if you want it in smaller doses, just send me an off-line email and we can talk on the phone. Reductio ad absurdum has worked unerringly for centuries to test bad assumptions. This constitutes a proof by lack of counterexample that the ONLY way to reach an absurd result is by a bad assumption, as otherwise, reductio ad absurdum would sometimes fail. Hence, when two intelligent people reach conflicting conclusions, but neither can see any errors in the other's logic, it would seem that they absolutely MUST have at least one bad assumption. Starting from the absurdity and searching for the assumption is where the reverse in reverse reductio ad absurdum comes in. If their false assumptions were different, than one or both parties would quickly discover them in discussion. However, when the argument stays on the surface, the ONLY place remaining to hide an invalid assumption is that they absolutely MUSH share the SAME invalid assumptions. Of course if our superintelligent AGI approaches them and points out their shared invalid assumption, then they would probably BOTH attack the AGI, as their invalid assumption may be their only point of connection. It appears that breaking this deadlock absolutely must involve first teaching both parties what reverse reductio ad absurdum is all about, as I am doing here. For example, take the abortion debate. It is obviously crazy to be making and killing babies, and it is a proven social disaster to make this illegal - an obvious reverse reductio ad absurdum situation. OK, so lets look at societies where abortion is no issue at all, e.g. Muslim societies, where it is freely available, but no one gets them. There, children are treated as assets, where in all respects we treat them as liabilities. Mothers are stuck with unwanted children. Fathers must pay child support, They can't be bought or sold. There is no expectation that they will look after their parents in their old age, etc. In short, BOTH parties believe that children should be treated as liabilities, but when you point this out, they dispute the claim. Why should mothers be stuck with unwanted children? Why not allow sales to parties who really want them? There are no answers to these and other similar questions because the underlying assumption is clearly wrong. The middle east situation is more complex but constructed on similar invalid assumptions. Are we on the same track now? Steve Richfield 2008/11/18 Steve Richfield [EMAIL PROTECTED] To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise
Re: Seed AI (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
Back to reality for a moment... I have greatly increased the IQs of some pretty bright people since I started doing this in 2001 (the details are way off topic here, so contact me off-line for more if you are interested), and now, others are also doing this. I think that these people give us a tiny glimpse into what directions an AGI might do. Here are my impressions: 1. They come up with some really bright stuff, like Mike's FQ theory of how like-minded groups of people tend to stagnate technology, which few people can grasp in the minute or so that is available to interest other people. Hence, their ideas do NOT spread widely, except among others who are bright enough to get it fairly quickly. From what I have seen, their enhanced IQs haven't done much for their life success as measured in dollars, but they have gone in very different directions than they were previously headed, now that they have some abilities that they didn't previously have. 2. Enhancing their IQs did NOT seem to alter their underlying belief system. For example, Dan was and still remains a Baptist minister. However, he now reads more passages as being metaphorical. We have no problem carrying on lively political and religious discussions from our VERY different points of view, with each of us translating our thoughts into the other's paradigm. 3. Blind ambition seemed to disappear, being replaced with a long view of things. They seem to be nicer people for the experience. However, given their long view, I wouldn't ever recommend becoming an adversary, as they have no problem with gambits - loosing a skirmish to facilitate winning a greater battle. If you think you are winning, then you had best stop and look where this might all end up. 4. They view most people a little like honey bees - useful but stupid. They often attempt to help others by pointing them in better directions, but after little/no success for months/years, they eventually give up and just let everyone destroy their lives and kill themselves. This results in what might at first appear to be a callous disregard for human life, but which in reality is just a realistic view of the world. I suspect that future AGIs would encounter the same effect. Hence, unless/until someone displays some reason why an AGI might want to take over the world, I remain unconcerned. What DOES concern me is stupid people who think that the population can be controlled, without allowing for the few bright people who can figure out how to be the butterfly that starts the hurricane, as chaos theory presumes non-computability of things that, if computable, will be computed. The resulting hurricane might be blamed on the butterfly, when in reality, there would have been a hurricane anyway - it just would have been somewhat different. In short, don't blame the AGI for the fallen bodies of those who would exert unreasonable control. I see the hope for the future being in the hands of these cognitively enhanced people. It shouldn't be too much longer until these people start rising to the top of the AI (and other) ranks. Imagine Loosemore with dozens more IQ points and the energy to go along with it. Hence, it will be these people who will make the decisions as to whether we have AGIs and what their place in the future is. Then, modern science will be reformed enough to avoid having unfortunate kids have their metabolic control systems trashed by general anesthetics, etc. (now already being done at many hospitals, including U of W and Evergreen here in the Seattle area), and we will stop making people who can be cognitively enhanced. Note that for every such candidate person, there are dozens of low IQ gas station attendants, etc., who was subjected to the same stress, but didn't do so well. Then, either we will have our AGIs in place, or with no next generation of cognitively enhanced people, we will be back to the stone age of stupid people. Society has ~50 years to make their AGI work before this generation of cognitively enhanced people is gone. Alternatively, some society might intentionally trash kids metabolism just to induce this phenomenon, as a means to secure control when things crash. At that point, either there is an AGI to take over, or that society will take over. In short, this is a complex area that is really worth understanding if you are interested in where things are going. Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: Seed AI (was Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...)
--- On Wed, 11/19/08, Daniel Yokomizo [EMAIL PROTECTED] wrote: I just want to be clear, you agree that an agent is able to create a better version of itself, not just in terms of a badly defined measure as IQ but also as a measure of resource utilization. Yes, even bacteria can do this. Do you agree with the statement: the global economy in which we live is a result of actions of human beings? How would it be different for AGIs? Do you disagree that better agents would be able to build an equivalent global economy much faster than the time it took humans (assuming all the centuries it took since the last big ice age)? You cannot separate AGI from the human dominated economy. AGI cannot produce smarter AGI without help from the 10^10 humans that are already here until machines have completely replaced the humans. I'm asking for your comments on the technical issues regardind seed AI and RSI, regardless of environment. Is there any technical impossibilities for an AGI to improve its own code in all possible environments? Also it's not clear to me which types of environments (if it's the boxing that makes it impossible, if it's an open environment with access to the internet, if it's both or neither) you see problems with RSI, could you ellaborate it further? My paper on RSI refutes one proposed approach to AGI, which would be a self improving system developed in isolation. I think that is good because such a system would be very dangerous if it were possible. However, I am not aware of any serious proposals to do it this way, simply because cutting yourself off from the internet just makes the problem harder. To me, RSI in an open environment is not pure RSI. It is a combination of self improvement and learning. My position on this approach is not that it won't work but that the problem is not as easy as it seems. I believe that if you do manage to create an AGI that is n times smarter than a human, then the result would be the same as if you hired O(n log n) people. (The factor of log n allows for communication overhead and overlapping knowledge). We don't really know what it means to be n times smarter, since we have no way to test it. But we would expect that such an AGI could work n times faster, learn n times faster, know n times as much, make n times as much money, and make prediction as accurately as a vote by n people. I am not sure what other measures we could apply that would distinguish greater intelligence from just more people. So to make real progress, you need to make AGI cheaper than human labor for n = about 10^9. And that is expensive. The global economy has a complexity of 10^17 to 10^18 bits. Most of that knowledge is not written down. It is in human brains. Unless we develop new technology like brain scanning, the only way to extract it is by communication at the rate of 2 bits per second per person. I want to keep this discussion focused on the technical impossibilities of RSI, so I'm going to ignore for now this side discussion about the global economy but later we can go back to it. My AGI proposal does not require any technical breakthroughs. But for something this expensive, you can't ignore the economic model. It has to be decentralized, and there has to be economic incentives for people to transfer their knowledge to it, and it has to be paid for. That is the obstacle you need to think about. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
[agi] My prospective plan to neutralize AGI and other dangerous technologies...
To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise reasonable individual answers would fail. There would be optional tutorials for people who are not confident with the material. After successfully navigating the site, an applicant would submit their picture and signature, and we would then provide a license number. The applicant could then provide their name and number to 3rd parties to verify that the applicant is at least capable of rational thought. This information would look much like a driver's license, and could be printed out as needed by anyone who possessed a correct name and number. The site would ask a variety of logical questions, most especially probing into: 1. Their understanding of Reverse Reductio ad Absurdum methods of resolving otherwise intractable disputes. 2. Whether they belong to or believe in any religion that supports various violent acts (with quotes from various religious texts). This would exclude pretty much every religion, as nearly all religions condone useless violence of various sorts, or the toleration or exposure of violence toward others. Even Buddhists resist MAD (Mutually Assured Destruction) while being unable to propose any potentially workable alternative to nuclear war. Jesus attacked the money changers with no hope of benefit for anyone. Mohammad killed the Jewish men of Medina and sold their women and children into slavery, etc., etc. 3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people who would obviously fail this test. This statement would be included on the license. This should force many people off of the fence, as they would have to choose between sanity and Heaven (or Hell). Then, Ben, the CIA, diplomats, etc., could verify that they are dealing with people who don't have any of the common forms of societal insanity. Perhaps the site should be multi-lingual? Any and all thoughts are GREATLY appreciated. Thanks Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Hi Steve I am not an expert so correct me if I am wrong. As I see it every day logical arguments (and rationality?) are based on standard classical logic (or something very similar). Yet I am (sadly) not aware of a convincing argument that this logic is the one to accept as the right choice. You might know that e.g. intuitionistic logic limits the power of reductio ad absurdum to negative statements (I don't know what reverse reductio ad absurdum is, so it may not be a precise counterexample, but I think you get my point). Would this not make you hesitate? If not, why? Cheers, Martin Biehl 2008/11/18 Steve Richfield [EMAIL PROTECTED] To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise reasonable individual answers would fail. There would be optional tutorials for people who are not confident with the material. After successfully navigating the site, an applicant would submit their picture and signature, and we would then provide a license number. The applicant could then provide their name and number to 3rd parties to verify that the applicant is at least capable of rational thought. This information would look much like a driver's license, and could be printed out as needed by anyone who possessed a correct name and number. The site would ask a variety of logical questions, most especially probing into: 1. Their understanding of Reverse Reductio ad Absurdum methods of resolving otherwise intractable disputes. 2. Whether they belong to or believe in any religion that supports various violent acts (with quotes from various religious texts). This would exclude pretty much every religion, as nearly all religions condone useless violence of various sorts, or the toleration or exposure of violence toward others. Even Buddhists resist MAD (Mutually Assured Destruction) while being unable to propose any potentially workable alternative to nuclear war. Jesus attacked the money changers with no hope of benefit for anyone. Mohammad killed the Jewish men of Medina and sold their women and children into slavery, etc., etc. 3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people who would obviously fail this test. This statement would be included on the license. This should force many people off of the fence, as they would have to choose between sanity and Heaven (or Hell). Then, Ben, the CIA, diplomats, etc., could verify that they are dealing with people who don't have any of the common forms of societal insanity. Perhaps the site should be multi-lingual? Any and all thoughts are GREATLY appreciated. Thanks Steve Richfield -- *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
2008/11/18 Steve Richfield [EMAIL PROTECTED]: I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. This all sounds peachy in principle, but I expect it would exclude virtually everyone except perhaps a few of the most diehard philosophers. I think most people have at least a few beliefs which cannot be strictly justified rationally, and that would include many AI researchers. Irrational or inconsistent beliefs originate from being an entity with finite resources - finite experience and finite processing power and time with which to analyze the data. Many people use quick lookups handed to them by individuals considered to be of higher social status, principally because they don't have time or inclination to investigate the issues directly themselves. In religion and politics people's beliefs and convictions are in almost every case gotten at second-hand, and without examination, from authorities who have not themselves examined the questions at issue but have taken them at second-hand from other non-examiners, whose opinions about them were not worth a brass farthing. - Mark Twain --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
On Tue, Nov 18, 2008 at 8:38 PM, Bob Mottram [EMAIL PROTECTED] wrote: I think most people have at least a few beliefs which cannot be strictly justified rationally You would think that. :) Trent --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people who would obviously fail this test. This statement would be included on the license. Hmmm... don't I fail this test every time I follow the speed limit ? ;-) As another aside, it seems wrong to accuse Buddhists of condoning violence because they don't like MAD (which involves stockpiling nukes) ... you could accuse them of foolishness perhaps (though I don't necessarily agree) but not of condoning violence My feeling is that with such a group of intelligent and individualistic folks as transhumanists and AI researchers are, any litmus test for cognitive sanity you come up with is gonna be quickly revealed to be full of loopholes that lead to endless philosophical discussions... so that in the end, such a test could only be used as a general guide, with the ultimate cognitive-sanity-test to be made on a qualitative basis In a small project like Novamente, we can evaluate each participant individually to assess their thought process and background. In a larger project like OpenCog, there is not much control over who gets involved, but making people sign a form promising to be rational and cognitively sane wouldn't seem to help much, as obviously there is nothing forcing people to be honest... ben g --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Steve Richfield wrote: To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise reasonable individual answers would fail. There would be optional tutorials for people who are not confident with the material. After successfully navigating the site, an applicant would submit their picture and signature, and we would then provide a license number. The applicant could then provide their name and number to 3rd parties to verify that the applicant is at least capable of rational thought. This information would look much like a driver's license, and could be printed out as needed by anyone who possessed a correct name and number. The site would ask a variety of logical questions, most especially probing into: 1. Their understanding of Reverse Reductio ad Absurdum methods of resolving otherwise intractable disputes. 2. Whether they belong to or believe in any religion that supports various violent acts (with quotes from various religious texts). This would exclude pretty much every religion, as nearly all religions condone useless violence of various sorts, or the toleration or exposure of violence toward others. Even Buddhists resist MAD (Mutually Assured Destruction) while being unable to propose any potentially workable alternative to nuclear war. Jesus attacked the money changers with no hope of benefit for anyone. Mohammad killed the Jewish men of Medina and sold their women and children into slavery, etc., etc. 3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people who would obviously fail this test. This statement would be included on the license. This should force many people off of the fence, as they would have to choose between sanity and Heaven (or Hell). Then, Ben, the CIA, diplomats, etc., could verify that they are dealing with people who don't have any of the common forms of societal insanity. Perhaps the site should be multi-lingual? Any and all thoughts are GREATLY appreciated. Thanks Steve Richfield I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. 8-| Richard Loosemore --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. BillK --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Martin, On 11/18/08, martin biehl [EMAIL PROTECTED] wrote: I don't know what reverse reductio ad absurdum is, so it may not be a precise counterexample, but I think you get my point. HERE is the crux of my argument, as other forms of logic fall short of being adequate to run a world with. Reverse Reductio ad Absurdum is the first logical tool with the promise to resolve most intractable disputes, ranging from the abortion debate to the middle east problem. Some people get it easily, and some require long discussions, so I'll post the Cliff Notes version here, and if you want it in smaller doses, just send me an off-line email and we can talk on the phone. Reductio ad absurdum has worked unerringly for centuries to test bad assumptions. This constitutes a proof by lack of counterexample that the ONLY way to reach an absurd result is by a bad assumption, as otherwise, reductio ad absurdum would sometimes fail. Hence, when two intelligent people reach conflicting conclusions, but neither can see any errors in the other's logic, it would seem that they absolutely MUST have at least one bad assumption. Starting from the absurdity and searching for the assumption is where the reverse in reverse reductio ad absurdum comes in. If their false assumptions were different, than one or both parties would quickly discover them in discussion. However, when the argument stays on the surface, the ONLY place remaining to hide an invalid assumption is that they absolutely MUSH share the SAME invalid assumptions. Of course if our superintelligent AGI approaches them and points out their shared invalid assumption, then they would probably BOTH attack the AGI, as their invalid assumption may be their only point of connection. It appears that breaking this deadlock absolutely must involve first teaching both parties what reverse reductio ad absurdum is all about, as I am doing here. For example, take the abortion debate. It is obviously crazy to be making and killing babies, and it is a proven social disaster to make this illegal - an obvious reverse reductio ad absurdum situation. OK, so lets look at societies where abortion is no issue at all, e.g. Muslim societies, where it is freely available, but no one gets them. There, children are treated as assets, where in all respects we treat them as liabilities. Mothers are stuck with unwanted children. Fathers must pay child support, They can't be bought or sold. There is no expectation that they will look after their parents in their old age, etc. In short, BOTH parties believe that children should be treated as liabilities, but when you point this out, they dispute the claim. Why should mothers be stuck with unwanted children? Why not allow sales to parties who really want them? There are no answers to these and other similar questions because the underlying assumption is clearly wrong. The middle east situation is more complex but constructed on similar invalid assumptions. Are we on the same track now? Steve Richfield 2008/11/18 Steve Richfield [EMAIL PROTECTED] To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise reasonable individual answers would fail. There would be optional tutorials for people who are not confident with the material. After successfully navigating the site, an applicant would submit their picture and signature, and we would then provide a license number. The applicant could then provide their name and number to 3rd parties to verify that the applicant is at least capable of rational thought. This information would look much like a driver's license, and could be printed out as needed by anyone who possessed a correct name and number. The site would ask a variety of logical questions, most especially probing into: 1. Their understanding of Reverse Reductio ad Absurdum methods of resolving otherwise intractable disputes. 2. Whether they belong to or believe in any religion that supports various violent acts (with quotes from various religious texts). This would exclude pretty much every religion, as nearly all religions condone useless violence of various sorts, or the toleration or exposure of violence toward others. Even Buddhists resist MAD (Mutually Assured Destruction) while being unable to propose any potentially workable alternative to nuclear war. Jesus attacked the money changers with no hope of benefit for anyone. Mohammad killed the Jewish men of Medina and sold their women and children into slavery, etc., etc. 3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
This sounds an awful lot like the Hegelian dialectical method... ben g On Tue, Nov 18, 2008 at 5:29 PM, Steve Richfield [EMAIL PROTECTED]wrote: Martin, On 11/18/08, martin biehl [EMAIL PROTECTED] wrote: I don't know what reverse reductio ad absurdum is, so it may not be a precise counterexample, but I think you get my point. HERE is the crux of my argument, as other forms of logic fall short of being adequate to run a world with. Reverse Reductio ad Absurdum is the first logical tool with the promise to resolve most intractable disputes, ranging from the abortion debate to the middle east problem. Some people get it easily, and some require long discussions, so I'll post the Cliff Notes version here, and if you want it in smaller doses, just send me an off-line email and we can talk on the phone. Reductio ad absurdum has worked unerringly for centuries to test bad assumptions. This constitutes a proof by lack of counterexample that the ONLY way to reach an absurd result is by a bad assumption, as otherwise, reductio ad absurdum would sometimes fail. Hence, when two intelligent people reach conflicting conclusions, but neither can see any errors in the other's logic, it would seem that they absolutely MUST have at least one bad assumption. Starting from the absurdity and searching for the assumption is where the reverse in reverse reductio ad absurdum comes in. If their false assumptions were different, than one or both parties would quickly discover them in discussion. However, when the argument stays on the surface, the ONLY place remaining to hide an invalid assumption is that they absolutely MUSH share the SAME invalid assumptions. Of course if our superintelligent AGI approaches them and points out their shared invalid assumption, then they would probably BOTH attack the AGI, as their invalid assumption may be their only point of connection. It appears that breaking this deadlock absolutely must involve first teaching both parties what reverse reductio ad absurdum is all about, as I am doing here. For example, take the abortion debate. It is obviously crazy to be making and killing babies, and it is a proven social disaster to make this illegal - an obvious reverse reductio ad absurdum situation. OK, so lets look at societies where abortion is no issue at all, e.g. Muslim societies, where it is freely available, but no one gets them. There, children are treated as assets, where in all respects we treat them as liabilities. Mothers are stuck with unwanted children. Fathers must pay child support, They can't be bought or sold. There is no expectation that they will look after their parents in their old age, etc. In short, BOTH parties believe that children should be treated as liabilities, but when you point this out, they dispute the claim. Why should mothers be stuck with unwanted children? Why not allow sales to parties who really want them? There are no answers to these and other similar questions because the underlying assumption is clearly wrong. The middle east situation is more complex but constructed on similar invalid assumptions. Are we on the same track now? Steve Richfield 2008/11/18 Steve Richfield [EMAIL PROTECTED] To all, I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. Everyone visiting the site would get different questions, in different orders, etc. Many questions would have more than one correct answer, and in many cases, some combinations of otherwise reasonable individual answers would fail. There would be optional tutorials for people who are not confident with the material. After successfully navigating the site, an applicant would submit their picture and signature, and we would then provide a license number. The applicant could then provide their name and number to 3rd parties to verify that the applicant is at least capable of rational thought. This information would look much like a driver's license, and could be printed out as needed by anyone who possessed a correct name and number. The site would ask a variety of logical questions, most especially probing into: 1. Their understanding of Reverse Reductio ad Absurdum methods of resolving otherwise intractable disputes. 2. Whether they belong to or believe in any religion that supports various violent acts (with quotes from various religious texts). This would exclude pretty much every religion, as nearly all religions condone useless violence of various sorts, or the toleration or exposure of violence toward others. Even Buddhists resist MAD (Mutually Assured Destruction) while being unable to propose any potentially workable alternative to nuclear war. Jesus attacked the money changers with no hope of benefit for anyone. Mohammad killed the Jewish men of Medina and sold their women and children into slavery, etc.,
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Bob, On 11/18/08, Bob Mottram [EMAIL PROTECTED] wrote: 2008/11/18 Steve Richfield [EMAIL PROTECTED]: I am considering putting up a web site to filter the crazies as follows, and would appreciate all comments, suggestions, etc. This all sounds peachy in principle, but I expect it would exclude virtually everyone except perhaps a few of the most diehard philosophers. My goal is to identify those people who: 1. Are capable of rational thought, whether or not they chose to use that ability. I plan to test this with some simple problem solving. 2. Are not SO connected with some shitforbrains religious group/belief that they would predictably use dangerous technology to harm others. I plan to test this by simply demanding a declaration, which would send most such believers straight to Hell. Beyond that, I agree that it starts to get pretty hopeless. I think most people have at least a few beliefs which cannot be strictly justified rationally, and that would include many AI researchers. ... and probably include both of us as well. Irrational or inconsistent beliefs originate from being an entity with finite resources - finite experience and finite processing power and time with which to analyze the data. Many people use quick lookups handed to them by individuals considered to be of higher social status, principally because they don't have time or inclination to investigate the issues directly themselves. However, when someone (like me) points out carefully selected passages that are REALLY crazy, then do they re-evaluate, or continue to accept everything they see in the book? In religion and politics people's beliefs and convictions are in almost every case gotten at second-hand, and without examination, from authorities who have not themselves examined the questions at issue but have taken them at second-hand from other non-examiners, whose opinions about them were not worth a brass farthing. - Mark Twain I completely agree. The question here is whether these people are capable of questioning and re-evaluation. If so, then they get their license. Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Ben, On 11/18/08, Ben Goertzel [EMAIL PROTECTED] wrote: 3. A statement in their own words that they hereby disavow allegiance to any non-human god or alien entity, and that they will NOT follow the directives of any government led by people who would obviously fail this test. This statement would be included on the license. Hmmm... don't I fail this test every time I follow the speed limit ? ;-) I don't think I stated this well, and perhaps you might be able to say it better. If your government wants you to go out and kill people, or help others to go out and kill people, and you don't see some glimmer of understanding from the leaders that this is really stupid, then perhaps you shouldn't contribute to such insanity. Then, just over this fence to help define the boundary... Look at the Star Wars anti-missile defense system. It can't possibly ever work well, as countermeasures are SO simple to implement. However, it was quite effective in bankrupting the Soviet Union, while people like me were going around and lecturing about horrible waste of public resources it was. In short, I think that re-evaluation is necessary at about the point where blood starts flowing. What are your thoughts? As another aside, it seems wrong to accuse Buddhists of condoning violence because they don't like MAD (which involves stockpiling nukes) ... you could accuse them of foolishness perhaps (though I don't necessarily agree) but not of condoning violence I have hours of discussion with Buddhists invested in this. I have no problem at all with them getting themselves killed, but I have a BIG problem with their asserting their beliefs to get OTHERS killed. If we had a Buddhist President who kept MAD from being implemented, there is a pretty good chance that we would not be here to have this discussion. As an aside, when you look CAREFULLY at the events that were unfolding as MAD was implemented, there really isn't anything at all against Buddhist beliefs in it - just a declaration that if you attack me, that I will attack in return, but without restraint against civilian targets. My feeling is that with such a group of intelligent and individualistic folks as transhumanists and AI researchers are, any litmus test for cognitive sanity you come up with is gonna be quickly revealed to be full of loopholes that lead to endless philosophical discussions... so that in the end, such a test could only be used as a general guide, with the ultimate cognitive-sanity-test to be made on a qualitative basis I guess that this is really what I was looking for - just what is that basis? For example, if someone can lie and answer questions in a logical manner just to get their license, then they have proven that they can be logical, whether or not they chose to be. I think that is about as good as is possible. In a small project like Novamente, we can evaluate each participant individually to assess their thought process and background. In a larger project like OpenCog, there is not much control over who gets involved, but making people sign a form promising to be rational and cognitively sane wouldn't seem to help much, as obviously there is nothing forcing people to be honest... ... other than their sure knowledge that they will go directly to Hell for even listening and considering such as we are discussing here. The Fiq is a body of work outside the Koran that is part of Islam, which includes stories of Mohamed's life, etc. Therein the boundary is precisely described. Islam demands that anyone who converts from Islam be killed. One poor fellow watched both of his parents refuse to renounce Islam, and then be killed by invaders. When it came to his turn, he quickly renounced to save his life. Now that he was being considered for execution, the ruling from Mohamed: If they ask you again, then renounce again. and he was released. BTW, it would be really stupid of me to try to enforce a different standard than you and other potential users of such a site would embrace, so my goal here is not only to discuss potential construction of such a site, but also to discuss just what that standard is. Hence, take my words as open for editing. Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Richard and Bill, On 11/18/08, BillK [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. In 1994 I was literally sold into servitude in Saudi Arabia as a sort of slave programmer (In COBOL on HP-3000 computers) to the Royal Saudi Air Force. I managed to escape that situation with the help of the same Wahhabist Sunni Muslims that are now causing so many problems. With that background, I think I understand them better than most people. As in all other societies, they are not given the whole truth, e.g. most have never heard of the slaughter at Medina, and believe that Mohamed never hurt anyone at all. My hope and expectation is that, by allowing people to research various issues as they work on their test, that a LOT of people who might otherwise fail the test will instead reevaluate their beliefs, at least enough to come up with the right answers, whether or not they truly believe them. At least that level of understanding assures that they can carry on a reasoned conversation. This is a MAJOR problem now. Even here on this forum, many people still don't get *reverse* reductio ad absurdum. BTW, I place most of the blame for the middle east impasse on the West rather than on the East. The Koran says that most of the evil in the world is done by people who think they are doing good, which brings with it a good social mandate to publicly reconsider and defend any actions that others claim to be evil. The next step is to proclaim evil doers as unwitting agents of Satan. If there is still no good defense, then they drop the unwitting. Of course, us stupid uncivilized Westerners have fallen into this, and so 19 brave men sacrificed their lives just to get our attention, but even that failed to work as planned. Just what DOES it take to get our attention - a nuke in NYC? What the West has failed to realize is that they are playing a losing hand, but nonetheless, they just keep increasing the bet on the expectation that the other side will fold. They won't. I was as much intending my test for the sort of stupidity that nearly all Americans harbor as that carried by Al Queda. Neither side seems to be playing with a full deck. Steve Richfield --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
RE: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Could we please stick to discussion of AGI? -Ben From: Steve Richfield [mailto:[EMAIL PROTECTED] Sent: Wednesday, 19 November 2008 10:39 AM To: agi@v2.listbox.com Subject: Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... Richard and Bill, On 11/18/08, BillK [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. In 1994 I was literally sold into servitude in Saudi Arabia as a sort of slave programmer (In COBOL on HP-3000 computers) to the Royal Saudi Air Force. I managed to escape that situation with the help of the same Wahhabist Sunni Muslims that are now causing so many problems. With that background, I think I understand them better than most people. As in all other societies, they are not given the whole truth, e.g. most have never heard of the slaughter at Medina, and believe that Mohamed never hurt anyone at all. My hope and expectation is that, by allowing people to research various issues as they work on their test, that a LOT of people who might otherwise fail the test will instead reevaluate their beliefs, at least enough to come up with the right answers, whether or not they truly believe them. At least that level of understanding assures that they can carry on a reasoned conversation. This is a MAJOR problem now. Even here on this forum, many people still don't get reverse reductio ad absurdum. BTW, I place most of the blame for the middle east impasse on the West rather than on the East. The Koran says that most of the evil in the world is done by people who think they are doing good, which brings with it a good social mandate to publicly reconsider and defend any actions that others claim to be evil. The next step is to proclaim evil doers as unwitting agents of Satan. If there is still no good defense, then they drop the unwitting. Of course, us stupid uncivilized Westerners have fallen into this, and so 19 brave men sacrificed their lives just to get our attention, but even that failed to work as planned. Just what DOES it take to get our attention - a nuke in NYC? What the West has failed to realize is that they are playing a losing hand, but nonetheless, they just keep increasing the bet on the expectation that the other side will fold. They won't. I was as much intending my test for the sort of stupidity that nearly all Americans harbor as that carried by Al Queda. Neither side seems to be playing with a full deck. Steve Richfield _ agi | https://www.listbox.com/member/archive/303/=now Archives https://www.listbox.com/member/archive/rss/303/ | https://www.listbox.com/member/?; 9 Modify Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Steve, what is the purpose of your political litmus test? If you are trying to assemble a team of seed-AI programmers with the correct ethics, forget it. Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). -- Matt Mahoney, [EMAIL PROTECTED] --- On Tue, 11/18/08, Steve Richfield [EMAIL PROTECTED] wrote: From: Steve Richfield [EMAIL PROTECTED] Subject: Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... To: agi@v2.listbox.com Date: Tuesday, November 18, 2008, 6:39 PM Richard and Bill, On 11/18/08, BillK [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. In 1994 I was literally sold into servitude in Saudi Arabia as a sort of slave programmer (In COBOL on HP-3000 computers) to the Royal Saudi Air Force. I managed to escape that situation with the help of the same Wahhabist Sunni Muslims that are now causing so many problems. With that background, I think I understand them better than most people. As in all other societies, they are not given the whole truth, e.g. most have never heard of the slaughter at Medina, and believe that Mohamed never hurt anyone at all. My hope and expectation is that, by allowing people to research various issues as they work on their test, that a LOT of people who might otherwise fail the test will instead reevaluate their beliefs, at least enough to come up with the right answers, whether or not they truly believe them. At least that level of understanding assures that they can carry on a reasoned conversation. This is a MAJOR problem now. Even here on this forum, many people still don't get reverse reductio ad absurdum. BTW, I place most of the blame for the middle east impasse on the West rather than on the East. The Koran says that most of the evil in the world is done by people who think they are doing good, which brings with it a good social mandate to publicly reconsider and defend any actions that others claim to be evil. The next step is to proclaim evil doers as unwitting agents of Satan. If there is still no good defense, then they drop the unwitting. Of course, us stupid uncivilized Westerners have fallen into this, and so 19 brave men sacrificed their lives just to get our attention, but even that failed to work as planned. Just what DOES it take to get our attention - a nuke in NYC? What the West has failed to realize is that they are playing a losing hand, but nonetheless, they just keep increasing the bet on the expectation that the other side will fold. They won't. I was as much intending my test for the sort of stupidity that nearly all Americans harbor as that carried by Al Queda. Neither side seems to be playing with a full deck. Steve Richfield agi | Archives | Modify Your Subscription --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: **SPAM** Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Seed AI is a myth. Ah. Now I get it. You are on this list solely to try to slow down progress as much as possible . . . . (sorry that I've been so slow to realize this) add-rule kill-file Matt Mahoney - Original Message - From: Matt Mahoney To: agi@v2.listbox.com Sent: Tuesday, November 18, 2008 8:23 PM Subject: **SPAM** Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... Steve, what is the purpose of your political litmus test? If you are trying to assemble a team of seed-AI programmers with the correct ethics, forget it. Seed AI is a myth. http://www.mattmahoney.net/agi2.html (section 2). -- Matt Mahoney, [EMAIL PROTECTED] --- On Tue, 11/18/08, Steve Richfield [EMAIL PROTECTED] wrote: From: Steve Richfield [EMAIL PROTECTED] Subject: Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... To: agi@v2.listbox.com Date: Tuesday, November 18, 2008, 6:39 PM Richard and Bill, On 11/18/08, BillK [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. In 1994 I was literally sold into servitude in Saudi Arabia as a sort of slave programmer (In COBOL on HP-3000 computers) to the Royal Saudi Air Force. I managed to escape that situation with the help of the same Wahhabist Sunni Muslims that are now causing so many problems. With that background, I think I understand them better than most people. As in all other societies, they are not given the whole truth, e.g. most have never heard of the slaughter at Medina, and believe that Mohamed never hurt anyone at all. My hope and expectation is that, by allowing people to research various issues as they work on their test, that a LOT of people who might otherwise fail the test will instead reevaluate their beliefs, at least enough to come up with the right answers, whether or not they truly believe them. At least that level of understanding assures that they can carry on a reasoned conversation. This is a MAJOR problem now. Even here on this forum, many people still don't get reverse reductio ad absurdum. BTW, I place most of the blame for the middle east impasse on the West rather than on the East. The Koran says that most of the evil in the world is done by people who think they are doing good, which brings with it a good social mandate to publicly reconsider and defend any actions that others claim to be evil. The next step is to proclaim evil doers as unwitting agents of Satan. If there is still no good defense, then they drop the unwitting. Of course, us stupid uncivilized Westerners have fallen into this, and so 19 brave men sacrificed their lives just to get our attention, but even that failed to work as planned. Just what DOES it take to get our attention - a nuke in NYC? What the West has failed to realize is that they are playing a losing hand, but nonetheless, they just keep increasing the bet on the expectation that the other side will fold. They won't. I was as much intending my test for the sort of stupidity that nearly all Americans harbor as that carried by Al Queda. Neither side seems to be playing with a full deck. Steve Richfield -- agi | Archives | Modify Your Subscription -- agi | Archives | Modify Your Subscription --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=120640061-aded06 Powered by Listbox: http://www.listbox.com
Re: **SPAM** Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies...
Matt and Mark, I think you both missed my point, but in different ways, namely, that there is a LOT of traffic here on this forum over a problem that appears easy to resolve once and for all time, and further, that the solution may work for much more important worldwide social problems. Continuing with responses to specific points... On 11/18/08, Mark Waser [EMAIL PROTECTED] wrote: Seed AI is a myth. Ah. Now I get it. You are on this list solely to try to slow down progress as much as possible . . . . (sorry that I've been so slow to realize this) No. Like you, we are all trying to put this OT issue out of our misery. I do appreciate Matt's efforts, misguided though they may be. Continuing with Matt's comments... *From:* Matt Mahoney [EMAIL PROTECTED] *To:* agi@v2.listbox.com *Sent:* Tuesday, November 18, 2008 8:23 PM *Subject:* **SPAM** Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... Steve, what is the purpose of your political litmus test? I had no intention at all of imposing any sort of political test, beyond simply looking for some assurance that they weren't about to use the technology to kill anyone who wasn't in desperate need of being killed. If you are trying to assemble a team of seed-AI programmers with the correct ethics, forget it. Seed AI is a myth. I agree, though my reasoning may be a bit different than yours. Why would any thinking machine ever want to produce a better thinking machine? Besides, I can take bright but long-term low-temp people like Loosemore, who appears to be an absolutely perfect candidate, and make them super-human intelligent by simply removing the impairment that they have learned to live with. In Loosemore's case, this is probably the equivalent of several alcoholic drinks, yet he is pretty bright even with that impairment. I would ask you to imagine what he would be without that impairment, but it may well be beyond anyone here's ability to imagine, and well on the way to a seed, though I suspect that with much more intelligence than he already has, that he would question that goal. Thanks everyone for your comments. Steve Richfield = --- On *Tue, 11/18/08, Steve Richfield [EMAIL PROTECTED]*wrote: From: Steve Richfield [EMAIL PROTECTED] Subject: Re: [agi] My prospective plan to neutralize AGI and other dangerous technologies... To: agi@v2.listbox.com Date: Tuesday, November 18, 2008, 6:39 PM Richard and Bill, On 11/18/08, BillK [EMAIL PROTECTED] wrote: On Tue, Nov 18, 2008 at 1:22 PM, Richard Loosemore wrote: I see how this would work: crazy people never tell lies, so you'd be able to nail 'em when they gave the wrong answers. Yup. That's how they pass lie detector tests as well. They sincerely believe the garbage they spread around. In 1994 I was literally sold into servitude in Saudi Arabia as a sort of slave programmer (In COBOL on HP-3000 computers) to the Royal Saudi Air Force. I managed to escape that situation with the help of the same Wahhabist Sunni Muslims that are now causing so many problems. With that background, I think I understand them better than most people. As in all other societies, they are not given the whole truth, e.g. most have never heard of the slaughter at Medina, and believe that Mohamed never hurt anyone at all. My hope and expectation is that, by allowing people to research various issues as they work on their test, that a LOT of people who might otherwise fail the test will instead reevaluate their beliefs, at least enough to come up with the right answers, whether or not they truly believe them. At least that level of understanding assures that they can carry on a reasoned conversation. This is a MAJOR problem now. Even here on this forum, many people still don't get *reverse* reductio ad absurdum. BTW, I place most of the blame for the middle east impasse on the West rather than on the East. The Koran says that most of the evil in the world is done by people who think they are doing good, which brings with it a good social mandate to publicly reconsider and defend any actions that others claim to be evil. The next step is to proclaim evil doers as unwitting agents of Satan. If there is still no good defense, then they drop the unwitting. Of course, us stupid uncivilized Westerners have fallen into this, and so 19 brave men sacrificed their lives just to get our attention, but even that failed to work as planned. Just what DOES it take to get our attention - a nuke in NYC? What the West has failed to realize is that they are playing a losing hand, but nonetheless, they just keep increasing the bet on the expectation that the other side will fold. They won't. I was as much intending my test for the sort of stupidity that nearly all Americans harbor as that carried by Al Queda. Neither side seems to be playing with a full deck. Steve Richfield