Re: [agi] would anyone want to use a commonsense KB?
On Feb 17, 2008 9:42 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: So far I've been using resolution-based FOL, so there's only 1 inference rule and this is not a big issue. If you're using nonstandard inference rules, perhaps even approximate ones, I can see that this distinction is important. Resolution-based FOL on a huge KB is intractable. Pei --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
All of these rules have exception or implicit condition. If you treat them as default rules, you run into multiple extension problem, which has no domain-independent solution in binary logic --- read http://www.cogsci.indiana.edu/pub/wang.reference_classes.ps for details. Pei On Feb 17, 2008 10:04 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: Yesterday I didn't give a clear explanation of what I mean by rules, so here is a better try: 1. If I see a turkey inside the microwave, I immediately draw the conclusion that it's NOT empty. 2. However, if I see some katchup on the inside walls of the microwave, I'd say it's dirty but it's empty. 3. If I see the rotating plate inside the microwave, I'd still say it's empty 'cause the plate is part of the microwave. etc etc So the AGI may have a rule that sounds like: if X is an object inside the microwave, and X satisfies some criteria, then the microwave is NOT empty. But it would be a very dumb AGI if it has this rule specifically for microwave ovens, and then some other rules for washing machines, bottles, book shelves, and other containers. It would be necessary for the AGI to have a general rule for emptiness for all containers. So I'd say a washing machine with a sock inside is not empty, but if it's just some lint then it's empty. Such a general rule for emptiness is certainly not available on the net, at least not explicitly expressed. One solution is to manually encode them (perhaps with some machine assistance), which is the approach of Cyc. Another solution is to induce them from existing texts on the web -- Ben's suggestion. If given a large enough corpus and a long enough learning period, Ben's solution may work. The key issue is how to speed up the inductive learning of rules. YKY agi | Archives | Modify Your Subscription --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
On 18/02/2008, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: Well, the idea is to ask lots of people to contribute to the KB, and pay them with virtual credits. (I expect such people to have a little knowledge in logic or Prolog, so they can enter complex rules. Also, they can be assisted by inductive learning algorithms.) The income of the KB will be given back to them. I'll take a bit of administrative fees =) In principle this sounds ok, but this is almost exactly the same as the Mindpixel business model. Once an element of payment is involved (usually with some kind of shares in future profits) participants tend to expect that they're going to be able to realise that value within a relatively short time, like a few years. Inevitably when expectations aren't met things get sticky. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] Primal Sketching
On Feb 18, 2008 1:37 AM, Bob Mottram [EMAIL PROTECTED] wrote: In a closed loop system what you have is a synchronisation between data streams. In part the brain is trying to find the best model that it can and superimpose that onto the available data (hence the perception of lines which don't really exist), and in part the low level data helps to create and maintain the higher level models. I think this is a very important perspective on what mind does. It supports multiple *processes* that interact with each other, communicating available data to tune each other, some of these processes driven by perception, some of them driving action. Inference is simply a process that is initiated by communicating 'premises' to it and that is then able to communicate 'conclusion'. Processes are learned to be in good correspondence with statistics of their I/O, so when some data is missing they can fill it in (in retrospect, 'predict'). These processes are a simple resource that can be plugged in to improve prediction (pattern-completion) performed by the rest of the system. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
All of these rules have exception or implicit condition. If you treat them as default rules, you run into multiple extension problem, which has no domain-independent solution in binary logic --- read http://www.cogsci.indiana.edu/pub/wang.reference_classes.ps for details. Pei, Do you have a PDF version? Thanks! --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
Just put one at http://nars.wang.googlepages.com/wang.reference_classes.pdf On Feb 18, 2008 9:01 AM, Mark Waser [EMAIL PROTECTED] wrote: All of these rules have exception or implicit condition. If you treat them as default rules, you run into multiple extension problem, which has no domain-independent solution in binary logic --- read http://www.cogsci.indiana.edu/pub/wang.reference_classes.ps for details. Pei, Do you have a PDF version? Thanks! --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
I believe I offered the beginning of a v. useful way to conceive of this whole area in an earlier post. The key concept is inventory of the world. First of all, what is actually being talked about here is only a VERBAL/SYMBOLIC KB. One of the grand illusions of a literature culture is that words/symbols refer to everything. The reality is that we have a v. limited verbal inventory of the world. Words do not describe most parts of your body, for example, only certain key divisions. Check over your hand for a start and see how many bits you can name - minute bit by bit. When it comes to the movements of objects, our vocabulary is breathtakingly limited. In fact, our verbal/symbolic inventory of the world (as provided for by our existing cultural vocabulary - for all its millions of words) is, I suggest, only a tiny fraction of our COMMON SENSE KB/ inventory of the world - i.e. that knowledge we hold purely in sensory image form - and indeed in common-sense form (since as Tye points out, we never actually experience/operate one sense in isolation - even though we have the intellectual illusion that we do). When we learn to respect the extent of our true common sense knowledge of the world as distinct from our formal, verbal knowledge of the world, we will realise another major reason why CYC like projects are doomed. They have nothing to do with common sense. Of course they will never be able to work out, pace Minsky, whether you can whistle and eat at the same time, or whether you can push or pull an object with a string. This is true common sense knowledge. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?.. p.s.
I should add to the idea of our common sense knowledge inventory of the world - because my talk of objects and movements may make it all sound v. physical and external. That common sense inventory also includes a vast amount of non-verbal knowledge, paradoxically, about how we think and communicate with and understand others.The paradoxical part is that a lot of this will be common sense about we use words themselves. Hence it is that experts have immense difficulties describing how they think about problems. They don't have the words for how they use their words. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
On 2/18/08, Mike Tintner [EMAIL PROTECTED] wrote: I believe I offered the beginning of a v. useful way to conceive of this whole area in an earlier post. The key concept is inventory of the world. First of all, what is actually being talked about here is only a VERBAL/SYMBOLIC KB. One of the grand illusions of a literature culture is that words/symbols refer to everything. The reality is that we have a v. limited verbal inventory of the world. Words do not describe most parts of your body, for example, only certain key divisions. Check over your hand for a start and see how many bits you can name - minute bit by bit. When it comes to the movements of objects, our vocabulary is breathtakingly limited. In fact, our verbal/symbolic inventory of the world (as provided for by our existing cultural vocabulary - for all its millions of words) is, I suggest, only a tiny fraction of our COMMON SENSE KB/ inventory of the world - i.e. that knowledge we hold purely in sensory image form - and indeed in common-sense form (since as Tye points out, we never actually experience/operate one sense in isolation - even though we have the intellectual illusion that we do). When we learn to respect the extent of our true common sense knowledge of the world as distinct from our formal, verbal knowledge of the world, we will realise another major reason why CYC like projects are doomed. They have nothing to do with common sense. Of course they will never be able to work out, pace Minsky, whether you can whistle and eat at the same time, or whether you can push or pull an object with a string. This is true common sense knowledge. I can give labels to every tiny sub-section of my hand, thus increasing the resolution of the symbolic description. If I give labels to each very small visual features of my hand, then the distinction between visual representation and symbolic representation disappears. Therefore, I think symbolic KBs like Cyc's is not doomed -- the symbolic KB can merge with perceptual grounding in a continuum fashion. YKY --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
This raises another v. interesting dimension of KB's and why they are limited. The social dimension. You might, purely for argument's sake, be able to name a vast amount of unnamed parts of the world. But you would then have to secure social agreement for them to become practically useful. Not realistic - if you were say to add even scores let alone thousands of names for each bit of your hand. And even when there are a set of agreed words - and this is a problem that absolutely plagues all of us on this board - there may still not be an agreed terminology. For example, we are having massive problems as a community, along with our society, with what words like intelligence, AGI, symbol, image image schema, etc etc. mean. We may agree broadly on the words that are relevant in a given area, but we have no agreed terminology as to which of those words should be used when, and what they mean.. And actually, now that I think of it, the more carefully intellectuals define their words, the MORE disagreements and misunderstandings you often get. Words like free and determined for philosophers and scientists (and all of us here) are absolute minefields. MT: I believe I offered the beginning of a v. useful way to conceive of this whole area in an earlier post. The key concept is inventory of the world. First of all, what is actually being talked about here is only a VERBAL/SYMBOLIC KB. One of the grand illusions of a literature culture is that words/symbols refer to everything. The reality is that we have a v. limited verbal inventory of the world. Words do not describe most parts of your body, for example, only certain key divisions. Check over your hand for a start and see how many bits you can name - minute bit by bit. When it comes to the movements of objects, our vocabulary is breathtakingly limited. In fact, our verbal/symbolic inventory of the world (as provided for by our existing cultural vocabulary - for all its millions of words) is, I suggest, only a tiny fraction of our COMMON SENSE KB/ inventory of the world - i.e. that knowledge we hold purely in sensory image form - and indeed in common-sense form (since as Tye points out, we never actually experience/operate one sense in isolation - even though we have the intellectual illusion that we do). When we learn to respect the extent of our true common sense knowledge of the world as distinct from our formal, verbal knowledge of the world, we will realise another major reason why CYC like projects are doomed. They have nothing to do with common sense. Of course they will never be able to work out, pace Minsky, whether you can whistle and eat at the same time, or whether you can push or pull an object with a string. This is true common sense knowledge. I can give labels to every tiny sub-section of my hand, thus increasing the resolution of the symbolic description. If I give labels to each very small visual features of my hand, then the distinction between visual representation and symbolic representation disappears. Therefore, I think symbolic KBs like Cyc's is not doomed -- the symbolic KB can merge with perceptual grounding in a continuum fashion. YKY -- agi | Archives | Modify Your Subscription -- No virus found in this incoming message. Checked by AVG Free Edition. Version: 7.5.516 / Virus Database: 269.20.7/1285 - Release Date: 2/18/2008 5:50 AM --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
Pei: Resolution-based FOL on a huge KB is intractable. Agreed. However Cycorp spend a great deal of programming effort (i.e. many man-years) finding deep inference paths for common queries. The strategies were: prune the rule set according to the contextsubstitute procedural code for modus ponens in common query paths (e.g. isa-links inferred via graph traversal)structure the inference engine as a nested set of iterators so that easy answers are returned immediately, and harder-to-find answers trickle out later.establish a battery of inference engine controls (e.g. time bounds, speed vs. completeness - whether to employ expensive inference strategies for greater coverage of answers) and have the inference engine automatically apply the optimal control configuration for queriesdetermine rule utility via machine learning and apply prioritized inference modules within the given time constraints My last in-house talk at Cycorp, in the summer of 2006, described a notion of mine that Cyc's deductive inference engine behaves as an interpreter, and that for a certain set of queries, a dramatic speed improvement (e.g. four orders of magnitude) could be achieved by compiling the query, and possibly preprocessing incoming facts to suit expected queries. The queries that interested me were those embedded in an intelligent application, and which could be viewed as a query template with parameters. The compilation process I described would explore the parameter space with programmer-chosen query examples. Then the resulting proof trees would be compiled into executable code - avoiding entirely the time consuming candidate rule search and their application when the query executes. My notion for Cyc's deductive inference engine optimization is analogous to SQL query optimization technology. I expect to use this technique in the Texai project at the point when I need a deductive inference engine. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 6:17:59 AM Subject: Re: [agi] would anyone want to use a commonsense KB? On Feb 17, 2008 9:42 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: So far I've been using resolution-based FOL, so there's only 1 inference rule and this is not a big issue. If you're using nonstandard inference rules, perhaps even approximate ones, I can see that this distinction is important. Resolution-based FOL on a huge KB is intractable. Pei --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com Looking for last minute shopping deals? Find them fast with Yahoo! Search. http://tools.search.yahoo.com/newsearch/category.php?category=shopping --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
Harshad RJ wrote: On Feb 3, 2008 10:22 PM, Richard Loosemore [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: Harshad RJ wrote: I read the conversation from the start and believe that Matt's argument is correct. Did you mean to send this only to me? It looks as though you mean it for the list. I will send this reply back to you personally, but let me know if you prefer it to be copied to the AGI list. Richard, thanks for replying. I did want to send it to the list.. and your email address (as it turns out) was listed on the forum for replying to the list. There is a difference between intelligence and motive which Richard seems to be ignoring. A brilliant instance of intelligence could still be subservient to a malicious or ignorant motive, and I think that is the crux of Matt's argument. With respect, I was not at all ignoring this point: this is a misunderstanding that occurs very frequently, and I thought that I covered it on this occasion (my apologies if I forgot to do so. I have had to combat this point on so many previous occasions that I may have overlooked yet another repeat). The crucial words are ... could still be subservient to a malicious or ignorant motive. The implication behind these words is that, somehow, the motive of this intelligence could arise after the intelligence, as a completely independent thing over which we had no control. We are so used to this pattern in the human case (we can make babies, but we cannot stop the babies from growing up to be dictators, if that is the way they happen to go). This implication is just plain wrong. I don't believe so, though your next statement.. If you build an artificial intelligence, you MUST choose how it is motivated before you can even switch it on. ... might be true. Yes, a motivation of some form could be coded into the system, but the paucity of expression in the level at which it is coded, may still allow for unintended motivations to emerge out. Say, for example, the motivation is coded in a form similar to current biological systems. The AGI system is motivated to keep itself happy, and it is happy when it has sufficient electrical energy at its disposal AND when the pheromones from nearby humans are all screaming positive. It is easy to see how this kind of motivation could cause unintended results. The AGI system could do dramatic things like taking over a nuclear power station and manufacturing its own pheromone supply from a chemical plant. Or it could do more subtle things like, manipulating government policies to ensure that the above happens! Even allowing for a higher level of coding for motivation, like those Asimov's Robot rules (#1 : Though shall not harm any human), it is very easy for the system to go out of hand, since such codings are ambiguous. Should stem cell research be allowed for example? It might harm some embryos but help more number of adults. Should prostitution be legalised? It might harm the human gene pool in some vague way, or might even harm some specific individuals, but it also allows the victims themselves to earn some money and survive longer. So, yes, motivation might be coded, but an AGI system would eventually need to have the *capability* to deduce its own motivation, and that emergent motivation could be malicious/ignorant. I quote the rest of the message, only for the benefit of the list. Otherwise, my case rests here. Stepping back for a moment, I think the problem that tends to occur in discussions of AGI motivation is that the technical aspects get overlooked when we go looking for nightmare scenarios. What this means, for me, is that when I reply to a suggestion such as the one you give above, my response is not That kind of AGI, and AGI behavioral problem, is completely unimaginable, but instead what I have to say is That kind of AGI would not actually BE an AGI at all, because, for technical reasons, you would never be able to get such a thing to be intelligent in the first place. There is a subtle difference between these two, but what I find is that most people mistakenly believe that I am making the first kind of reponse instead of the second. So, to deal with your suggestion in detail. When I say that some kind of motivation MUST be built into the system, I am pretty much uttering a truism: an AGI without any kind of motivational system is like a swimmer with no muscles. It has to be driven to do something, so no drives mean no activity. Putting that to one side, then, what you propose is an AGI with an extremely simple motivational system: seek electricity and high human pheromonal output. I don't suggest that this is unimaginable (it is!), but what I suggest is that you implicitly assume a lot of stuff that, almost certainly, will never happen. You
Re: [agi] would anyone want to use a commonsense KB?
Steve, I also agree with what you said, and what Cyc uses is no longer pure resolution-based FOL. A purely resolution-based inference engine is mathematically elegant, but completely impractical, because after all the knowledge are transformed into the clause form required by resolution, most of the semantic information in the knowledge structure is gone, and the result is equivalent to the original knowledge in truth-value only. It is hard to control the direction of the inference without semantic information. Pei On Feb 18, 2008 11:13 AM, Stephen Reed [EMAIL PROTECTED] wrote: Pei: Resolution-based FOL on a huge KB is intractable. Agreed. However Cycorp spend a great deal of programming effort (i.e. many man-years) finding deep inference paths for common queries. The strategies were: prune the rule set according to the context substitute procedural code for modus ponens in common query paths (e.g. isa-links inferred via graph traversal) structure the inference engine as a nested set of iterators so that easy answers are returned immediately, and harder-to-find answers trickle out later. establish a battery of inference engine controls (e.g. time bounds, speed vs. completeness - whether to employ expensive inference strategies for greater coverage of answers) and have the inference engine automatically apply the optimal control configuration for queries determine rule utility via machine learning and apply prioritized inference modules within the given time constraints My last in-house talk at Cycorp, in the summer of 2006, described a notion of mine that Cyc's deductive inference engine behaves as an interpreter, and that for a certain set of queries, a dramatic speed improvement (e.g. four orders of magnitude) could be achieved by compiling the query, and possibly preprocessing incoming facts to suit expected queries. The queries that interested me were those embedded in an intelligent application, and which could be viewed as a query template with parameters. The compilation process I described would explore the parameter space with programmer-chosen query examples. Then the resulting proof trees would be compiled into executable code - avoiding entirely the time consuming candidate rule search and their application when the query executes. My notion for Cyc's deductive inference engine optimization is analogous to SQL query optimization technology. I expect to use this technique in the Texai project at the point when I need a deductive inference engine. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 6:17:59 AM Subject: Re: [agi] would anyone want to use a commonsense KB? On Feb 17, 2008 9:42 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: So far I've been using resolution-based FOL, so there's only 1 inference rule and this is not a big issue. If you're using nonstandard inference rules, perhaps even approximate ones, I can see that this distinction is important. Resolution-based FOL on a huge KB is intractable. Pei --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com Be a better friend, newshound, and know-it-all with Yahoo! Mobile. Try it now. agi | Archives | Modify Your Subscription --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
--- YKY (Yan King Yin) [EMAIL PROTECTED] wrote: On 2/18/08, Matt Mahoney [EMAIL PROTECTED] wrote: Heh... I think you could give away read-only access and charge people to update it. Information has negative value, you know. Well, the idea is to ask lots of people to contribute to the KB, and pay them with virtual credits. (I expect such people to have a little knowledge in logic or Prolog, so they can enter complex rules. Also, they can be assisted by inductive learning algorithms.) The income of the KB will be given back to them. I'll take a bit of administrative fees =) Why would this approach succeed where Cyc failed? Cyc paid people to build the knowledge base. Then when they couldn't sell it, the tried giving it away. Still, nobody used it. For an AGI to be useful, people have to be able to communicate with it in natural language. It is easy to manipulate formulas like if P then Q. It is much harder to explain how this knowledge is represented and learned in a language model. Cyc did not solve this problem, and we see the result. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
Pei, Another issue with a KB inference engine as contrasted with a FOL theorem prover is that the former seeks answers to queries, and the latter often seeks to disprove the negation of the theorem by finding a contradiction. Cycorp therefore could not reuse much of the research from the automatic theorem proving community. And on the other hand the database community commonly did not investigate deep inference. As the Semantic Web community continues to develop new deductive inference engines tuned to inference (ie. query answering) over large RDF KBs , I expect to see open-source forward-chaining, and backward-chaining inference engines that can be optimized in the same way that I described for Cyc. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 10:47:43 AM Subject: Re: [agi] would anyone want to use a commonsense KB? Steve, I also agree with what you said, and what Cyc uses is no longer pure resolution-based FOL. A purely resolution-based inference engine is mathematically elegant, but completely impractical, because after all the knowledge are transformed into the clause form required by resolution, most of the semantic information in the knowledge structure is gone, and the result is equivalent to the original knowledge in truth-value only. It is hard to control the direction of the inference without semantic information. Pei On Feb 18, 2008 11:13 AM, Stephen Reed [EMAIL PROTECTED] wrote: Pei: Resolution-based FOL on a huge KB is intractable. Agreed. However Cycorp spend a great deal of programming effort (i.e. many man-years) finding deep inference paths for common queries. The strategies were: prune the rule set according to the context substitute procedural code for modus ponens in common query paths (e.g. isa-links inferred via graph traversal) structure the inference engine as a nested set of iterators so that easy answers are returned immediately, and harder-to-find answers trickle out later. establish a battery of inference engine controls (e.g. time bounds, speed vs. completeness - whether to employ expensive inference strategies for greater coverage of answers) and have the inference engine automatically apply the optimal control configuration for queries determine rule utility via machine learning and apply prioritized inference modules within the given time constraints My last in-house talk at Cycorp, in the summer of 2006, described a notion of mine that Cyc's deductive inference engine behaves as an interpreter, and that for a certain set of queries, a dramatic speed improvement (e.g. four orders of magnitude) could be achieved by compiling the query, and possibly preprocessing incoming facts to suit expected queries. The queries that interested me were those embedded in an intelligent application, and which could be viewed as a query template with parameters. The compilation process I described would explore the parameter space with programmer-chosen query examples. Then the resulting proof trees would be compiled into executable code - avoiding entirely the time consuming candidate rule search and their application when the query executes. My notion for Cyc's deductive inference engine optimization is analogous to SQL query optimization technology. I expect to use this technique in the Texai project at the point when I need a deductive inference engine. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 6:17:59 AM Subject: Re: [agi] would anyone want to use a commonsense KB? On Feb 17, 2008 9:42 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: So far I've been using resolution-based FOL, so there's only 1 inference rule and this is not a big issue. If you're using nonstandard inference rules, perhaps even approximate ones, I can see that this distinction is important. Resolution-based FOL on a huge KB is intractable. Pei --- agi Archives:
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
On Feb 3, 2008 10:22 PM, Richard Loosemore [EMAIL PROTECTED] wrote: My argument was (at the beginning of the debate with Matt, I believe) that, for a variety of reasons, the first AGI will be built with peaceful motivations. Seems hard to believe, but for various technical reasons I think we can make a very powerful case that this is exactly what will happen. After that, every other AGI will be the same way (again, there is an argument behind that). Furthermore, there will not be any evolutionary pressures going on, so we will not find that (say) the first few million AGIs are built with perfect motivations, and then some rogue ones start to develop. In the context of a distributed AGI, like the one I propose at http://www.mattmahoney.net/agi.html this scenario would require the first AGI to take the form of a worm. It may indeed be peaceful if it depends on human cooperation to survive and spread, as opposed to exploiting a security flaw. So it seems a positive outcome depends on solving the security problem. If a worm is smart enough to debug software and discover vulnerabilities faster than humans can (with millions of copies working in parallel), the problem becomes more difficult. (And this *is* an evolutionary process). I guess I don't share Richard's optimism. I suppose a safer approach would be centralized, like most of the projects of people on this list. But I don't see how these systems could compete with the vastly greater resources (human and computer) already available on the internet. A distributed system with, say, Novamente and Google as two of its millions of peers is certainly going to be more intelligent than either system alone. You may wonder why I would design a dangerous system. First, I am not building it. (I am busy with other projects). But I believe that for practical reasons something like this will eventually be built anyway, and we need to study the design to make it safer. -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
On Feb 18, 2008 7:41 PM, Richard Loosemore [EMAIL PROTECTED] wrote: In other words you cannot have your cake and eat it too: you cannot assume that this hypothetical AGI is (a) completely able to build its own understanding of the world, right up to the human level and beyond, while also being (b) driven by an extremely dumb motivation system that makes the AGI seek only a couple of simple goals. Great summary, Richard. You should probably write it up. This position that there is a very difficult problem of friendly AGI and much simpler problem of idiotic AGI that still somehow posits a threat is too easily accepted. -- Vladimir Nesov [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
Matt Mahoney wrote: On Feb 3, 2008 10:22 PM, Richard Loosemore [EMAIL PROTECTED] wrote: My argument was (at the beginning of the debate with Matt, I believe) that, for a variety of reasons, the first AGI will be built with peaceful motivations. Seems hard to believe, but for various technical reasons I think we can make a very powerful case that this is exactly what will happen. After that, every other AGI will be the same way (again, there is an argument behind that). Furthermore, there will not be any evolutionary pressures going on, so we will not find that (say) the first few million AGIs are built with perfect motivations, and then some rogue ones start to develop. In the context of a distributed AGI, like the one I propose at http://www.mattmahoney.net/agi.html this scenario would require the first AGI to take the form of a worm. That scenario is deeply implausible - and you can only continue to advertise it because you ignore all of the arguments I and others have given, on many occasions, concerning the implausibility of that scenario. You repeat this line of black propaganda on every occasion you can, but on the other hand you refuse to directly address the many, many reasons why that black propaganda is nonsense. Why? Richard Loosemore It may indeed be peaceful if it depends on human cooperation to survive and spread, as opposed to exploiting a security flaw. So it seems a positive outcome depends on solving the security problem. If a worm is smart enough to debug software and discover vulnerabilities faster than humans can (with millions of copies working in parallel), the problem becomes more difficult. (And this *is* an evolutionary process). I guess I don't share Richard's optimism. I suppose a safer approach would be centralized, like most of the projects of people on this list. But I don't see how these systems could compete with the vastly greater resources (human and computer) already available on the internet. A distributed system with, say, Novamente and Google as two of its millions of peers is certainly going to be more intelligent than either system alone. You may wonder why I would design a dangerous system. First, I am not building it. (I am busy with other projects). But I believe that for practical reasons something like this will eventually be built anyway, and we need to study the design to make it safer. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] would anyone want to use a commonsense KB?
On Feb 18, 2008 12:37 PM, Stephen Reed [EMAIL PROTECTED] wrote: Pei, Another issue with a KB inference engine as contrasted with a FOL theorem prover is that the former seeks answers to queries, and the latter often seeks to disprove the negation of the theorem by finding a contradiction. Cycorp therefore could not reuse much of the research from the automatic theorem proving community. And on the other hand the database community commonly did not investigate deep inference. The automatic theorem proving community does that because resolution by itself is not complete, while resolution-refutation is complete. Pei As the Semantic Web community continues to develop new deductive inference engines tuned to inference (ie. query answering) over large RDF KBs , I expect to see open-source forward-chaining, and backward-chaining inference engines that can be optimized in the same way that I described for Cyc. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 10:47:43 AM Subject: Re: [agi] would anyone want to use a commonsense KB? Steve, I also agree with what you said, and what Cyc uses is no longer pure resolution-based FOL. A purely resolution-based inference engine is mathematically elegant, but completely impractical, because after all the knowledge are transformed into the clause form required by resolution, most of the semantic information in the knowledge structure is gone, and the result is equivalent to the original knowledge in truth-value only. It is hard to control the direction of the inference without semantic information. Pei On Feb 18, 2008 11:13 AM, Stephen Reed [EMAIL PROTECTED] wrote: Pei: Resolution-based FOL on a huge KB is intractable. Agreed. However Cycorp spend a great deal of programming effort (i.e. many man-years) finding deep inference paths for common queries. The strategies were: prune the rule set according to the context substitute procedural code for modus ponens in common query paths (e.g. isa-links inferred via graph traversal) structure the inference engine as a nested set of iterators so that easy answers are returned immediately, and harder-to-find answers trickle out later. establish a battery of inference engine controls (e.g. time bounds, speed vs. completeness - whether to employ expensive inference strategies for greater coverage of answers) and have the inference engine automatically apply the optimal control configuration for queries determine rule utility via machine learning and apply prioritized inference modules within the given time constraints My last in-house talk at Cycorp, in the summer of 2006, described a notion of mine that Cyc's deductive inference engine behaves as an interpreter, and that for a certain set of queries, a dramatic speed improvement (e.g. four orders of magnitude) could be achieved by compiling the query, and possibly preprocessing incoming facts to suit expected queries. The queries that interested me were those embedded in an intelligent application, and which could be viewed as a query template with parameters. The compilation process I described would explore the parameter space with programmer-chosen query examples. Then the resulting proof trees would be compiled into executable code - avoiding entirely the time consuming candidate rule search and their application when the query executes. My notion for Cyc's deductive inference engine optimization is analogous to SQL query optimization technology. I expect to use this technique in the Texai project at the point when I need a deductive inference engine. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 - Original Message From: Pei Wang [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, February 18, 2008 6:17:59 AM Subject: Re: [agi] would anyone want to use a commonsense KB? On Feb 17, 2008 9:42 PM, YKY (Yan King Yin) [EMAIL PROTECTED] wrote: So far I've been using resolution-based FOL, so there's only 1 inference rule and this is not a big issue. If you're using nonstandard inference rules, perhaps even approximate ones, I can see that this distinction is important. Resolution-based FOL on a huge KB is intractable. Pei --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?; Powered by Listbox: http://www.listbox.com Be a
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
On Feb 18, 2008 10:11 PM, Richard Loosemore [EMAIL PROTECTED] wrote: You assume that the system does not go through a learning phase (childhood) during which it acquires its knowledge by itself. Why do you assume this? Because an AGI that was motivated only to seek electricity and pheromones is going to be as curious, as active, as knowledge seeking, as exploratory (etc etc etc) as a moth that has been preprogrammed to go towards bright lights. It will never learn aything by itself because you left out the [curiosity] motivation (and a lot else besides!). I think your reply points back to the confusion between intelligence and motivation. Curiosity would be a property of intelligence and not motivation. After all, you need a motivation to be curious. Moreover, the curiosity would be guided by the kind of motivation. A benevolent motive would drive the curiosity to seek benevolent solutions, like say solar power, while a malevolent motive could drive it to seek destructive ones. I see motivation as a much more basic property of intelligence. It needs to answer why not what or how. But when we try to get an AGI to have the kind of structured behavior necessary to learn by itself, we discover . what? That you cannot have that kind of structured exploratory behavior without also having an extremely sophisticated motivation system. So, in the sense that I mentioned above, why do you say/imply that a pheromone (or neuro transmitter) based motivation is not sophisticated enough? And, without getting your hands messy with chemistry, how do you propose to explain your emotions to a non-human intelligence? How would you distinguish construction from destruction, chaos from order, or why two people being able to eat a square meal is somehow better than 2 million reading Dilbert comics. In other words you cannot have your cake and eat it too: you cannot assume that this hypothetical AGI is (a) completely able to build its own understanding of the world, right up to the human level and beyond, while also being (b) driven by an extremely dumb motivation system that makes the AGI seek only a couple of simple goals. In fact, I do think a b are together possible and they best describe how human brains work. Our motivation system is extremely dumb: reproduction! And it is expressed with nothing more than a feed back loop using neuro-transmitters. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
On 18/02/2008, Richard Loosemore [EMAIL PROTECTED] wrote: ... might be true. Yes, a motivation of some form could be coded into the system, but the paucity of expression in the level at which it is coded, may still allow for unintended motivations to emerge out. It seems that in the AGI arena much emphasis is put on designing goal systems. But in nature behavior is not always driven explicitly by goals. A lot of behavior I suspect is just drift, and understanding this requires you to examine the dynamics of the system. For example if I'm talking on the phone and doodling with a pen this doesn't necessarily imply that I explicitly have instantiated a goal of draw doodle. Likewise within populations changes in the gene pool do not necessarily mean that explicit selection forces are at work. My supposition is that the same dynamics seen in natural systems will also apply to AGIs, since these are all examples of complex dynamical systems. --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
Bob Mottram wrote: On 18/02/2008, Richard Loosemore [EMAIL PROTECTED] wrote: ... might be true. Yes, a motivation of some form could be coded into the system, but the paucity of expression in the level at which it is coded, may still allow for unintended motivations to emerge out. It seems that in the AGI arena much emphasis is put on designing goal systems. But in nature behavior is not always driven explicitly by goals. A lot of behavior I suspect is just drift, and understanding this requires you to examine the dynamics of the system. For example if I'm talking on the phone and doodling with a pen this doesn't necessarily imply that I explicitly have instantiated a goal of draw doodle. Likewise within populations changes in the gene pool do not necessarily mean that explicit selection forces are at work. My supposition is that the same dynamics seen in natural systems will also apply to AGIs, since these are all examples of complex dynamical systems. Ooops: the above quote was attached to my name in error: I believe Harshad wrote that, not I. But regarding your observation, Bob: I have previously avocated a distinction between diffuse motivation systems and goal-stack systems. As you say, most AI systems simply assume that what controls the AI is a goal stack. I will write up this distinction on a web page shortly. Richard Loosemore --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
--- Richard Loosemore [EMAIL PROTECTED] wrote: Matt Mahoney wrote: On Feb 3, 2008 10:22 PM, Richard Loosemore [EMAIL PROTECTED] wrote: My argument was (at the beginning of the debate with Matt, I believe) that, for a variety of reasons, the first AGI will be built with peaceful motivations. Seems hard to believe, but for various technical reasons I think we can make a very powerful case that this is exactly what will happen. After that, every other AGI will be the same way (again, there is an argument behind that). Furthermore, there will not be any evolutionary pressures going on, so we will not find that (say) the first few million AGIs are built with perfect motivations, and then some rogue ones start to develop. In the context of a distributed AGI, like the one I propose at http://www.mattmahoney.net/agi.html this scenario would require the first AGI to take the form of a worm. That scenario is deeply implausible - and you can only continue to advertise it because you ignore all of the arguments I and others have given, on many occasions, concerning the implausibility of that scenario. You repeat this line of black propaganda on every occasion you can, but on the other hand you refuse to directly address the many, many reasons why that black propaganda is nonsense. Why? Perhaps worm is the wrong word. Unlike today's computer worms, it would be intelligent, it would evolve, and it would not necessarily be controlled by or serve the interests of its creator. Whether or not it is malicious would depend on the definitions of good and bad, which depend on who you ask. A posthuman might say the question is meaningless. If I understand your proposal, it is: 1. The first AGI to achieve recursive self improvement (RSI) will be friendly. 2. Friendly is hard to define, but because the AGI is intelligent, it would know what we mean and get it right. 3. The goal system is robust because it is described by a very large number of soft constraints. 4. The AGI would not change the motivations or goals of its offspring because it would not want to. 5. The first AGI to achieve RSI will improve its intelligence so fast that all competing systems will be left far behind. (Thus, a worm). 6. RSI is deterministic. My main point of disagreement is 6. Increasing intelligence requires increasing algorithmic complexity. We know that a machine cannot output a description of another machine with greater complexity. Therefore reproduction is probabilistic and experimental, and RSI is evolutionary. Goal reproduction can be very close but not exact. (Although the AGI won't want to change the goals, it will be unable to reproduce them exactly because goals are not independent of the rest of the system). Because RSI is very fast, goals can change very fast. The only stable goals in evolution are those that improve fitness and reproduction, e.g. efficiency and acquisition of computing resources. Which part of my interpretation or my argument do you disagree with? -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
Matt Mahoney wrote: --- Richard Loosemore [EMAIL PROTECTED] wrote: Matt Mahoney wrote: On Feb 3, 2008 10:22 PM, Richard Loosemore [EMAIL PROTECTED] wrote: My argument was (at the beginning of the debate with Matt, I believe) that, for a variety of reasons, the first AGI will be built with peaceful motivations. Seems hard to believe, but for various technical reasons I think we can make a very powerful case that this is exactly what will happen. After that, every other AGI will be the same way (again, there is an argument behind that). Furthermore, there will not be any evolutionary pressures going on, so we will not find that (say) the first few million AGIs are built with perfect motivations, and then some rogue ones start to develop. In the context of a distributed AGI, like the one I propose at http://www.mattmahoney.net/agi.html this scenario would require the first AGI to take the form of a worm. That scenario is deeply implausible - and you can only continue to advertise it because you ignore all of the arguments I and others have given, on many occasions, concerning the implausibility of that scenario. You repeat this line of black propaganda on every occasion you can, but on the other hand you refuse to directly address the many, many reasons why that black propaganda is nonsense. Why? Perhaps worm is the wrong word. Unlike today's computer worms, it would be intelligent, it would evolve, and it would not necessarily be controlled by or serve the interests of its creator. Whether or not it is malicious would depend on the definitions of good and bad, which depend on who you ask. A posthuman might say the question is meaningless. So far, this just repeats the same nonsense: your scenario is based on unsupported assumptions. If I understand your proposal, it is: 1. The first AGI to achieve recursive self improvement (RSI) will be friendly. For a variety of converging reasons, yes. 2. Friendly is hard to define, but because the AGI is intelligent, it would know what we mean and get it right. No, not correct. Friendly is not hard to define if you build the AGI with a full-fledged motivation system of the diffuse sort I have advovcated before. To put it in a nutshell, the AGI can be made to have a primary motivation that involves empathy with the human species as a whole, and what this do in practice is that the AGI would stay locked in sync with the general desires of the human race. The question of knowing what we mean by 'friendly' is not relevant, because this kind of knowing is explicit declarative knowledge. 3. The goal system is robust because it is described by a very large number of soft constraints. Correct. The motivation system, to be precise, depends for its stability on a large number of interconnections, so trying to divert it from its main motivation would be like unscrambling an egg. 4. The AGI would not change the motivations or goals of its offspring because it would not want to. Exactly. It would not just not change them, it would take active steps to ensure that any other AGI would have exactly the same safeguards in its system that it (the mother) would have. 5. The first AGI to achieve RSI will improve its intelligence so fast that all competing systems will be left far behind. (Thus, a worm). No, not thus a worm. It will simply be an AGI. The concept of a computer worm is so far removed from this AGI that it is misleading to recruit the term. 6. RSI is deterministic. Not correct. The factors that make a collection of free-floating atoms, in a zero-gravity environment) tend to coalesce into a sphere are not deterministic in any relevant sense of the term. A sphere forms because a RELAXATION of all the factors involved ends up in the same shape every time. If you mean any other sense of deterministic then you must clarify. My main point of disagreement is 6. Increasing intelligence requires increasing algorithmic complexity. We know that a machine cannot output a description of another machine with greater complexity. Therefore reproduction is probabilistic and experimental, and RSI is evolutionary. Goal reproduction can be very close but not exact. (Although the AGI won't want to change the goals, it will be unable to reproduce them exactly because goals are not independent of the rest of the system). Because RSI is very fast, goals can change very fast. The only stable goals in evolution are those that improve fitness and reproduction, e.g. efficiency and acquisition of computing resources. Which part of my interpretation or my argument do you disagree with? The last paragraph! To my mind, this is a wild, free-wheeling non-sequiteur that ignores all the parameters laid down in the preceding paragraphs: Increasing intelligence requires increasing algorithmic complexity. If its motivation system is built the way that I describe it, this is of no relevance. We know
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
Harshad RJ wrote: On Feb 18, 2008 10:11 PM, Richard Loosemore [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] wrote: You assume that the system does not go through a learning phase (childhood) during which it acquires its knowledge by itself. Why do you assume this? Because an AGI that was motivated only to seek electricity and pheromones is going to be as curious, as active, as knowledge seeking, as exploratory (etc etc etc) as a moth that has been preprogrammed to go towards bright lights. It will never learn aything by itself because you left out the [curiosity] motivation (and a lot else besides!). I think your reply points back to the confusion between intelligence and motivation. Curiosity would be a property of intelligence and not motivation. After all, you need a motivation to be curious. Moreover, the curiosity would be guided by the kind of motivation. A benevolent motive would drive the curiosity to seek benevolent solutions, like say solar power, while a malevolent motive could drive it to seek destructive ones. No confusion, really. I do understand that curiosity is a difficult case that lies on the borderline, but what I am talking about is systematic exploration-behavior, or playing. The kind of activity that children and curious adults engage in when they deliberately try to find something out *because* they feel a curiosity urge (so to speak). What I think you are referring to is just the understanding-mechanisms that enable the intelligence part of the mind to solve problems or generally find things out. Let's call this intelligence-mechanism a [Finding-Out] activity, whereas the type of thing children do best is [Curiosity], which is a motivation mode that they get into. Then, using that terminology on your above paragraph: After all, you need a motivation to be curious translates into You need a motivation of some sort to engage in [Finding-Out]. For example, before you try to figure out where a particular link is located on a web page, you need the (general) motivation that is pushing you to do this, as well as the (specific) goal that drives you to find that particular link. Moreover, the curiosity would be guided by the kind of motivation translates into The [Finding-Out] activity would be guided by the background motivation. This is what I have just said. A benevolent motive would drive the curiosity to seek benevolent solutions, like say solar power, while a malevolent motive could drive it to seek destructive ones. This translates into A benevolent motivation (and this really is a motivation, in my terminology) would drive the [Finding-Out] mechanisms to seek benevolent solutions, like say solar power, while a malevolent motivation (again, I would agree that this is a motivation) could drive the [Finding-Out] mechanisms to seek destructive ones. What this all amounts to is that the thing I referred to as curiosity really is a motivation, because a creature that has an unstructured, background desire (a motivation) to find out about the world will acquire a lot of background knowledge and become smart. I see motivation as a much more basic property of intelligence. It needs to answer why not what or how. But when we try to get an AGI to have the kind of structured behavior necessary to learn by itself, we discover . what? That you cannot have that kind of structured exploratory behavior without also having an extremely sophisticated motivation system. So, in the sense that I mentioned above, why do you say/imply that a pheromone (or neuro transmitter) based motivation is not sophisticated enough? And, without getting your hands messy with chemistry, how do you propose to explain your emotions to a non-human intelligence? How would you distinguish construction from destruction, chaos from order, or why two people being able to eat a square meal is somehow better than 2 million reading Dilbert comics. I frankly don't know if understand the question. We already have creatures that seek nothing but chemical signals: amoebae do this. Imagine a human baby that did nothing but try to sniff out breast milk: it would never develop because it would never do any of the other things, like playing. It would just sit there and try to sniff for the stuff it wanted. In other words you cannot have your cake and eat it too: you cannot assume that this hypothetical AGI is (a) completely able to build its own understanding of the world, right up to the human level and beyond, while also being (b) driven by an extremely dumb motivation system that makes the AGI seek only a couple of simple goals. In fact, I do think a b are together possible and they best describe how human brains work. Our motivation system is extremely dumb: reproduction! And it is expressed with nothing more than a feed back loop using neuro-transmitters.
Re: [agi] This is not a good turn for the discussion [WAS Re: Singularity Outcomes ...]
--- Richard Loosemore [EMAIL PROTECTED] wrote: Matt Mahoney wrote: Perhaps worm is the wrong word. Unlike today's computer worms, it would be intelligent, it would evolve, and it would not necessarily be controlled by or serve the interests of its creator. Whether or not it is malicious would depend on the definitions of good and bad, which depend on who you ask. A posthuman might say the question is meaningless. So far, this just repeats the same nonsense: your scenario is based on unsupported assumptions. OK, let me use the term mass extinction. The first AGI that implements RSI is so successful that it kills off all its competition. The question of knowing what we mean by 'friendly' is not relevant, because this kind of knowing is explicit declarative knowledge. I can accept that an AGI can have empathy toward humans, although no two people will agree exactly on what this means. 6. RSI is deterministic. Not correct. This is the only point where we disagree, and my whole argument depends on it. The factors that make a collection of free-floating atoms, in a zero-gravity environment) tend to coalesce into a sphere are not deterministic in any relevant sense of the term. A sphere forms because a RELAXATION of all the factors involved ends up in the same shape every time. If you mean any other sense of deterministic then you must clarify. I mean in the sense that if RSI was deterministic, then a parent AGI could predict a child's behavior in any given situation. If the parent knew as much as the child, or had the capacity to know as much as the child could know, then what is the point of RSI? Which part of my interpretation or my argument do you disagree with? Increasing intelligence requires increasing algorithmic complexity. If its motivation system is built the way that I describe it, this is of no relevance. Instead of the fuzzy term intelligence let me say amount of knowledge which most people would agree is correlated with intelligence. Behavior depends not just on goals but also on what you know. A child AGI may have empathy toward humans just like its parent, but may have a slightly different idea of what it means to be human. We know that a machine cannot output a description of another machine with greater complexity. When would it ever need to do such a thing? This factoid, plucked from computational theory, is not about description in the normal scientific and engineering sense, it is about containing a complete copy of the larger system inside the smaller. I, a mere human, can describe the sun and its dynamics quite well, even though the sun is a system far larger and more complex than myself. In particular, I can give you some beyond-reasonable-doubt arguments to show that the sun will retain its spherical shape for as long as it is on the Main Sequence, without *ever* changing its shape to resemble Mickey Mouse. Its shape is stable in exactly the same way that an AGI motivation system would be stable, in spite of the fact that I cannot describe this large system in the strict, compututational sense in which some systems describe other systems. Your model of the sun does not include the position of every atom. It has less algorithmic complexity than your brain. Why is your argument relevant? -- Matt Mahoney, [EMAIL PROTECTED] --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
[agi] Installing MindForth in a robot
Only robots above a certain level of sophistication may receive a mind-implant via MindForth. The computerized robot needs to have an operating system that will support Forth and sufficient memory to hold both the AI program code and a reasonably large knowledge base (KB) of experience. A Forth program is so portable from one version of Forth to another that robot manufacturers, vendors and users should not think of Mind.Forth as restricted to Win32Forth for implementation and operation, but as a candidate for upgrading to a 64-bit Forth running on a 64-bit system, thereby possessing a practically unlimited memory space. The Forth variant iForth is supposedly on its way to becoming a 64-bit Forth. People getting into Forth AI for the first time and with the option of adopting 64-bit technology from the very start, should do so with the realization that it will be an extremely long time before any further upgrade is made to 128-bit or higher technology. It is more likely that AI will go down into quantum technology before going up to 128-bit technology. So embrace and extend 64-bit AI. ATM -- http://mentifex.virtualentity.com/mind4th.html http://mentifex.virtualentity.com/m4thuser.html --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com