Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Mike, Six 2003 Seven 1996 Eight 2001 Eight and a half Good point with the movies, only a hardcore movie fan would make that association early in his trials to figure out the pattern as movie dates. In this case you gave a hint, such a hint would tell the system to widen its attention spotlight to inlude movies, so entertainment, events, celebration, etc would come under attention based on what structure the movie concept's parent has in its domain content. Thinking imaginatively to find hard solutions as you say, is possible with this system, by telling it to think outside the box to other domains and it can learn this pattern of domain- hopping based on the reward of a success or being authorized to value cross-domain attention search. Thinking for the system is: shifting its attention to different regions (with the 4 domains), sizing and orienting the attention scale, and setting the focus depth (of details); it can then read the contents of what comes up from that region and Compare, Contrast, Combine it to anyalyze or synthesize it. Thinking bigger or narrower is almost literal. Like humans, this system stops a behavior (e.g, stops searching) because it runs out of motivation value, not ideas to search. Many systems known or described can lend themself to brute force thinking unsure of a solution, this structure allows it to do it elegantly using human-centric concept domains first (easier for us to communicate to it this way by saying build a damn good engine as human do vs 0010101101 or any other non-human language). It can and does re-write the concepts and content in its domain as it learns, but it started with the domains humans give it, e.g., I knew what movies were by having live in a number of situations where this concept was built up, so that later, I can learn about independent films and live performances or new types of entertainment thta gives similar or unfamiliar emotions. Further rational 1) What humans do: have a biased (value system) that makes sense relative to our biological architecture; Generate all human knowledge in this representation structure (natural language, ambiguous, low logic language). 2) What an early AGI can do: learn the human-bias by having a similar architecture which includes the value bias for pattern humans seek. Obtain as much of the recorded knowledge in the world from humans. Generate more, faster, new and better knowlege. Better is because it knows our value system and as well knows humans enough to convince them in a diccussion unlike most of us, that better is what it wants us to do(very bad!). For natural language processing, humans readily communicate in song and poems, and understand them. Many songs and poems do not make any logical sense, and few songs have wording order and story elements that are reasonable. The model makes sense by looking for patterns where humans do, in the beats (situational border that structure all input) and the value (emotional meaning) of the song/poems content. Hope some of this helps Robert --- On Sun, 12/28/08, Mike Tintner tint...@blueyonder.co.uk wrote: From: Mike Tintner tint...@blueyonder.co.uk Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: agi@v2.listbox.com Date: Sunday, December 28, 2008, 11:38 PM Robert, Thanks for your detailed, helpful replies. I like your approach of operating in multiple domains for problemsolving. But if the domains are known beforehand, then it's not truly creative problemsolving - where you do have to be prepared to go in search of the appropriate domains - and thus truly cross domains rather than simply combining preselected ones. I gave you a perhaps exaggerated example just to make the point. You had to realise that the correct domain to solve my problem was that of movies - the numbers were the titles of movies and the dates they came out. If you're dealing with real world rather than just artificial creative problems like our two, you may definitely have to make that kind of domain switch - solving any scientific detective problem, say, like that of binding in the brain, may require you to think in a surprising, new domain, for which you will have to search long and hard (and possibly without end). Mike, Very good choice. But the system always *knows* these domains beforehand - and that it must consider them in any problem? YES the domains content structure is what you mean, are the human-centric ones provided by living a childs life loading the value system with biases such as humans are warm and candy is really sweet. By further being pushed thru western culture grade level curriculum we value the visual features symbols 2003 and 1996 as numbers, then as dates. The content models (concept patterns) are build up from
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
The paper as a link instead of attachment: http://mindsoftbioware.com/yahoo_site_admin/assets/docs/Swaine_R_Story_Understander_Model.36375123.pdf The paper gives a quick view of the Human-centric representation and behavioral systems approach for problem-solving, reasoning as giving meaning (human values) to stories and games...Indexing relations via spatially related registers is it's simulated substrate. cheers, Robert --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Robert, What kind of problems have you designed this to solve? Can you give some examples? Robert: A brief paper on an AGI system for human-level ...had only 2 pages to fit in. If you are working on a system, you probably hope it will one day help design a better world, better tools, better inventions. The better is a subjective human value. A place for or human-like representation of at least rough, general human values (bias, likes) in the AGI is essential. The paper give a quick view of the Human-centric representation and behavioral systems approach for problem-solving, reasoning as giving meaning (human values) to stories and games...Indexing relations via spatially related registers is it's simulated substrate. Happy Holidays, Robert ...all the human values were biased, unlike the very objective AGI systems designed on the Mudfish's home planet; AGI systems that objectively knew that sticky mud is beautiful, large oceans of gooey mud..how enchanting! Pure clean water, now that's fishy! --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Mike, Mike wrote: What kind of problems have you designed this to solve? Can you give some examples? Natural language understanding, path finding, game playing Any problems that can be represented as a situation in the four component domain (value - role - relation - feature models) can be 3-C (compared, contrast, combined) to give a resulting situation (frame pattern). What is combined/compared/or contrast?: only the regions under attention, including its focus detail level are examined. What is placed and represented in the regions determines what component can be 3-C analyzed... as a general computing paradigm using 3-C (AND - OR - NOT). Example: Here's a pattern example you may not have seen before, but by 3C you discover the pattern and how to make an example: As spoken aloud: five and nine [is] fine two and six [is] twix five and seven [is] fiven Take the five and seven = fiven. when the system compares the resultant of fiven to five ..the result is that five is at the start of the situation. When it compares fiven and seven... the result is that ven is at the end position. resulting situation PATTERN = [situation 1 ][ focus inward ] [ start-position ] combined with [situation 2 ][ focus inward ] [ end position ] (Spatial and sequence positions are a key part of the representation system) How was the correct (reasoning) method chosen? This result was was by comparison; it could have been by contrasting. All three Compare, Contrast and Combine happen symultaneously. The winner is whichever resulting situation makes sense to the system has the most activation in the value area (some direct or indirect value from past experience or value given by the authority system in the value region: e.g. fearful or attractive spectrum). How was the correct region and focus detail level chosen? The attention region in the example was on the sound region, the focus detail was on the phoneme level (syllable), it could have looked for patterns in the number values or the emotions related to each word, or the letter patterns, or hand motions, eye position when spoken, etc). The regions are biased by the value system's current index (amygdala/septum analog): e.g. when you see five the quantity region will be given a lower threshold, and the focus level associated will give the content on the 1 - 10 scale. The index region weights are re-organized only by stronger reward/failure (authority system), 3-C results can on the index changing the content connections weights. Now you compare apples to oranges for an encore; what do you get? a color, a taste, a mass, a new fruit..your attention determines te result All regions are being matched for patterns in the 2 primary index modules (action selection, emotional value,..others can be integrated seamlessly). Five and seven is not fiven, it is twelve, but in this situation it makes sense to the circumstances. Sense and meaning are contextual for the model, for humans. Hope this sheds light. Detailed paper has been in the works. Robert --- On Sun, 12/28/08, Mike Tintner tint...@blueyonder.co.uk wrote: From: Mike Tintner tint...@blueyonder.co.uk Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: agi@v2.listbox.com Date: Sunday, December 28, 2008, 4:49 PM Robert, What kind of problems have you designed this to solve? Can you give some examples? Robert: A brief paper on an AGI system for human-level ...had only 2 pages to fit in. If you are working on a system, you probably hope it will one day help design a better world, better tools, better inventions. The better is a subjective human value. A place for or human-like representation of at least rough, general human values (bias, likes) in the AGI is essential. The paper give a quick view of the Human-centric representation and behavioral systems approach for problem-solving, reasoning as giving meaning (human values) to stories and games...Indexing relations via spatially related registers is it's simulated substrate. Happy Holidays, Robert ...all the human values were biased, unlike the very objective AGI systems designed on the Mudfish's home planet; AGI systems that objectively knew that sticky mud is beautiful, large oceans of gooey mud..how enchanting! Pure clean water, now that's fishy! agi | Archives | Modify Your Subscription --- On Sun, 12/28/08, Mike Tintner tint...@blueyonder.co.uk wrote: From: Mike Tintner tint...@blueyonder.co.uk Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: agi@v2.listbox.com Date
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Robert: Example: Here's a pattern example you may not have seen before, but by 3C you discover the pattern and how to make an example: As spoken aloud: five and nine[is] fine two and six [is] twix five and seven [is] fiven Robert, So, if I understand, you're designing a system to deal with problems concerning objects, which have multiple domain associations. For example, words as above are associated with their sounds, letter patterns, and perhaps meanings. But the system always *knows* these domains beforehand - and that it must consider them in any problem? It couldn't say find the pattern to a problem like: Six 2003 Seven 1996 Eight 2001 Eight and a half ? where it wouldn't know any domain relevant to solving the problem, and would first have to *find* the appropriate domain?. (In creative, human-level intelligence problems you often have to do this). --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Mike, Very good choice. But the system always *knows* these domains beforehand - and that it must consider them in any problem? YES the domains content structure is what you mean, are the human-centric ones provided by living a childs life loading the value system with biases such as humans are warm and candy is really sweet. By further being pushed thru western culture grade level curriculum we value the visual features symbols 2003 and 1996 as numbers, then as dates. The content models (concept patterns) are build up from any basic feature to form instance from the basic content of the four domain, such as dates of leap years, century marks, millenium or anniversary. problems more like: -- ice cream favorite red happee -- What this group of words means has everything to do with what the reader knows and values beforehands. And what he values will determine what his attention is on, the food, the emotions, the color, the positions; or how deep the focus is: on the entire situation (sentence), a group of them, a single word or a letter. Humans value from the top so we'll likely think of cherry ice cream before we see: the occurance pattern of letter e in every word in that 'sentence' above. Good choice for your problem: Six 2003 Seven 1996 Eight 2001 Eight and a half ? (i see a number of patterns, such as 00 99, multiply, add word to end - but haven't gotten the complete formula) For the system, it is biased; it make sense for itself, it's internal value. The answer the system chooses is the one that makes sense to what it knows and values. Sure, it can and will be used as a general pattern mining by comparing and contrasting within lines, line-to-line, number-to-text, text-to-number, date-to-word, month-to-number, middle-part to end, end-to-end, etc, until a resulting comparison yeilds a pattern that it values (from experience or being told). However, the value system controlling attention prevents any combinatorial explosion - animals only search through the models that have value (indirectly or directly) to the problem situation, thus limiting the total gueses we could even make (it looks for patterns it already knows). To solve problems it has not been taught or can't see a pattern for: 1) If self-motivated because a reward/avoidance is strong: Keeps looking for patterns 3-C by persiting in its behavior (doing the same ol thing) and fail. If a value happens to occur in one of the result when it kept going, it will see that something was different. It has acces to its own actions (role and relation domain) and this different action stands out (auto-contrast) and become of greater value due to the associated difference (non-failure). It keeps trying until the motivation runs out (energy level decays) or other value or past experiences exceeds its model of how long it should take.. 2) Instructed how to solve it by trying x, y or x. Wden your attention, expand your focus - then it has a larger set of regions to try and find a pattern it values. If set, it can examine regions of the instruction (x, y , and z) and see what was different from what it was trying (if the comparision yeilds a high enough value, it will try those as well). Try going left and up O.K. auto-contrast I was trying only up: the difference is to add one more direction; I can try left and up and back etc.. Creativity and reason come from the 3-C mechanism Creativity in the model is to combine any sets of domain content and give it a respective value from its experience and domain models. Example: Combine the form of a computer mouse, the look of diamonds, the function of a steering wheel, with the feel of leather: what do you get? Focus on each region and combine, then e-valuate (compare it to objects, functions). What's your result? Models in my experience say that it's a luxury-car controller; while you might say it would be something in an art galleryy, etc (art, value without function/role). Anyway, Bens, pre-school for AGI is one of the means to bias such a system with experience and human values; another way is to try to properly represent human experience (static and dynamic) and then essentially implanting memories and experience instead of just declarative facts. Robert --- On Sun, 12/28/08, Mike Tintner tint...@blueyonder.co.uk wrote: From: Mike Tintner tint...@blueyonder.co.uk Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: agi@v2.listbox.com Date: Sunday, December 28, 2008, 8:38 PM Robert: Example: Here's a pattern example you may not have seen before, but by 3C you discover the pattern and how to make an example: As spoken aloud: five and nine [is] fine two and six [is] twix five and seven [is] fiven Robert, So
Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
it to objects, functions). What's your result? Models in my experience say that it's a luxury-car controller; while you might say it would be something in an art galleryy, etc (art, value without function/role). Anyway, Bens, pre-school for AGI is one of the means to bias such a system with experience and human values; another way is to try to properly represent human experience (static and dynamic) and then essentially implanting memories and experience instead of just declarative facts. Robert --- On Sun, 12/28/08, Mike Tintner tint...@blueyonder.co.uk wrote: From: Mike Tintner tint...@blueyonder.co.uk Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: agi@v2.listbox.com Date: Sunday, December 28, 2008, 8:38 PM Robert: Example: Here's a pattern example you may not have seen before, but by 3C you discover the pattern and how to make an example: As spoken aloud: five and nine[is] fine two and six [is] twix five and seven [is] fiven Robert, So, if I understand, you're designing a system to deal with problems concerning objects, which have multiple domain associations. For example, words as above are associated with their sounds, letter patterns, and perhaps meanings. But the system always *knows* these domains beforehand - and that it must consider them in any problem? It couldn't say find the pattern to a problem like: Six 2003 Seven 1996 Eight 2001 Eight and a half ? where it wouldn't know any domain relevant to solving the problem, and would first have to *find* the appropriate domain?. (In creative, human-level intelligence problems you often have to do this). -- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
On Sat, Dec 20, 2008 at 8:01 AM, Derek Zahn derekz...@msn.com wrote: Ben: Right. My intuition is that we don't need to simulate the dynamics of fluids, powders and the like in our virtual world to make it adequate for teaching AGIs humanlike, human-level AGI. But this could be wrong. I suppose it depends on what kids actually learn when making cakes, skipping rocks, and making a mess with play-dough. Some might say that if they get conservation of mass and newton's law then they skipped all the useless stuff! OK, but those some probably don't include any preschool teachers or educational theorists. That hypothesis is completely at odds with my own intuition from having raised 3 kids and spent probably hundreds of hours helping out in daycare centers, preschools, kindergartens, etc. Apart from naive physics, which is rather well-demonstrated not to be derived in the human mind/brain from basic physical principles, there is a lot of learning about planning, scheduling, building, cooperating ... basically, all the stuff mentioned in our AGI Preschool paper. Yes, you can just take a robo-Cyc type approach and try to abstract, on your own, what is learned from preschool activities and code it into the AI: code in Newton's laws, axiomatic naive physics, planning algorithms, etc. My strong prediction is you'll get a brittle AI system that can at best be tuned into adequate functionality in some rather narrow contexts. But in the case where we are trying to roughly follow stages of human development with goals of producing human-like linguistic and reasoning capabilities, I very much fear that any significant simplification of the universe will provide an insufficient basis for the large sensory concept set underlying language and analogical reasoning (both gross and fine). Literally, I think you're throwing the baby out with the bathwater. But, as you say, this could be wrong. Sure... that can't be disproven right now, of course. We plan to expand the paper into a journal paper where we argue against this obvious objection more carefully -- basically arguing why the virtual-world setting provides enough detail to support the learning of the critical cognitive subcomponents of human intelligence. But, as with anything in AGI, even the best-reasoned paper can't convince a skeptic. It's really the only critique I have of the AGI preschool idea, which I do like because we can all relate to it very easily. At any rate, if it turns out to be a valid criticism the symptom will be that an insufficiently rich set of concepts will develop to support the range of capabilities needed and at that point the simulations can be adjusted to be more complete and realistic and provide more human sensory modalities. I guess it will be disappointing if building an adequate virtual world turns out to be as difficult and expensive as building high quality robots -- but at least it's easier to clean up after cake-baking. Well, it's completely obvious to me, based on my knowledge of virtual worlds and robotics, that building a high quality virtual world is orders of magnitude easier than making a workable humanoid robot. *So* much $$ has been spent on humanoid robotics before, by large, rich and competent companies, and they still suck.It's just a very hard problem, with a lot of very hard subproblems, and it will take a while to get worked through. On the other hand, making a virtual world such as I envision, is more than a spare-time project, but not more than the project of making a single high-quality video game. It's something that any one of these big Japanese companies could do with a tiny fraction of their robotics budgets. The issue is a lack of perceived cool value and a lack of motivation. Ben --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
It's an interesting idea, but I suspect it too will rapidly break down. Which activities can be known about in a rich, better-than-blind-Cyc way *without* a knowledge of objects and object manipulation? How can an agent know about reading a book,for example, if it can't pick up and manipulate a book? How can it know about adding and subtracting, if it can't literally put objects on top of each other, and remove them? We humans build up our knowledge of the world objects/physics up from infancy. Science also insists that all formal scientific knowledge of the world - all scientific disciplines - must be ultimately physics/objects-based. Is there really an alternative? And just to be clear: in the AGI Preschool world I envision, picking up and manipulating and stacking objects, and so forth, *would* be possible. This much is not hard to achieve using current robot-simulator tech. ben --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
I agree, but the good news is that game dev advances fast. So, my plan with the AGI Preschool would be to build it in an open platform such as OpenSim, and then swap in better and better physics engines as they become available. Some current robot simulators use ODE and this seems to be good enough to handle a lot of useful robot-object and object-object interactions, though I agree it's limited. Still, making a dramatically better physics engine -- while a bunch harder than making a nice AGI preschool using current virtual worlds and physics engines -- is still a way, way easier problem than making a highly functional (in terms of sensors and actuators) humanoid robot. Also, the advantages of working in a virtual rather than physical world should not be overlooked. The ability to run tests over and over again, to freely vary parameters and so forth, is pretty nice ... also the ability to run 1000s of tests in parallel without paying humongous bucks for a fleet of robots... ben On Sat, Dec 20, 2008 at 8:43 AM, Derek Zahn derekz...@msn.com wrote: Oh, and because I am interested in the potential of high-fidelity physical simulation as a basis for AI research, I did spend some time recently looking into options. Unfortunately the results, from my perspective, were disappointing. The common open-source physics libraries like ODE, Newton, and so on, have marginal feature sets and frankly cannot scale very well performance-wise. Once I even did a little application whose purpose was to see whether a human being could learn to control an ankle joint to compensate for an impulse event and stabilize a simple body model (that is, to make it not fall over) by applying torques to the ankle. I was curious to see (through introspection) how humans learn to act as process controllers. http://happyrobots.com/anklegame.zip for anybody bored enough to care. It wasn't a very good test of the question so I didn't really get a satisfactory answer. I did discover, though, that a game built around more appealing cases of the player learning to control physics-inspired processes could be quite absorbing. Beyond that, the most promising avenue seems to be physics libraries tied to graphics hardware being worked on by the hardware companies to help sell their stream processors. The best example is Nvidia, who bought PhysX and ported it to their latest cards, giving a huge performance boost. Intel has bought Havok and I can only imagine that they are planning on using that as the interface to some Larrabee-based physics engine. I'm sure that ATI is working on something similar for their newer (very impressive) stream processing cards. At this stage, though, despite some interesting features and leaping performance, it is still not possible to do things like get realistic sensor maps for a simulated soft hand/arm, and complex object modifications like bending and breaking are barely dreamed of in those frameworks. Complex multi-body interactions (like realistic behavior when dropping or otherwise playing with a ring of keys or realistic baby toys) have a long ways to go. Basically, I fear those of us who are interested in this are just waiting to ride the game development coattails and it will be a few years at least until performance that even begins to interest me will be available. Just my opinions on the situation. -- *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 -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Some might say that if they get conservation of mass and newton's law then they skipped all the useless stuff! OK, but those some probably don't include any preschool teachers or educational theorists. That hypothesis is completely at odds with my own intuition from having raised 3 kids and spent probably hundreds of hours helping out in daycare centers, preschools, kindergartens, etc. Sorry, that was just kind of a joke. Probably nobody actually has the opinion I was lampooning though I do see similar things said sometimes, as if inferring minimum-description-length root level reductionisms is a realistic approach to learning to deal with the world. It might even be true, but the humor was supposed to be to juxtapose that idea with the AGI preschool. --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: Well, it's completely obvious to me, based on my knowledge of virtual worlds and robotics, that building a high quality virtual world is orders of magnitude easier than making a workable humanoid robot. I guess that depends on what you mean by high quality and workable. Why does a robot have to be humanoid, BTW? I'd like a robot that can make me a cup of tea, I don't particularly care if it looks humanoid (in fact I suspect many humans would have less emotional resistance to a robot that didn't look humanoid, since it's more obviously a machine). On the other hand, making a virtual world such as I envision, is more than a spare-time project, but not more than the project of making a single high-quality video game. GTA IV cost $5 million, so we're not talking about peanuts here. -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Ben: Right. My intuition is that we don't need to simulate the dynamics of fluids, powders and the like in our virtual world to make it adequate for teaching AGIs humanlike, human-level AGI. But this could be wrong.I suppose it depends on what kids actually learn when making cakes, skipping rocks, and making a mess with play-dough. Some might say that if they get conservation of mass and newton's law then they skipped all the useless stuff! I think I agree with the plausibility of something you have said many times: that there may be many paths to AGI that are not similar at all to human development -- abstract paths to modelling the universe, teasing meaning from sheer statistics of the chinese/chinese dictionary of the raw html internet, who knows what. But in the case where we are trying to roughly follow stages of human development with goals of producing human-like linguistic and reasoning capabilities, I very much fear that any significant simplification of the universe will provide an insufficient basis for the large sensory concept set underlying language and analogical reasoning (both gross and fine). Literally, I think you're throwing the baby out with the bathwater. But, as you say, this could be wrong. It's really the only critique I have of the AGI preschool idea, which I do like because we can all relate to it very easily. At any rate, if it turns out to be a valid criticism the symptom will be that an insufficiently rich set of concepts will develop to support the range of capabilities needed and at that point the simulations can be adjusted to be more complete and realistic and provide more human sensory modalities. I guess it will be disappointing if building an adequate virtual world turns out to be as difficult and expensive as building high quality robots -- but at least it's easier to clean up after cake-baking. --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
On Sat, Dec 20, 2008 at 10:44 AM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: Well, it's completely obvious to me, based on my knowledge of virtual worlds and robotics, that building a high quality virtual world is orders of magnitude easier than making a workable humanoid robot. I guess that depends on what you mean by high quality and workable. Why does a robot have to be humanoid, BTW? I'd like a robot that can make me a cup of tea, I don't particularly care if it looks humanoid (in fact I suspect many humans would have less emotional resistance to a robot that didn't look humanoid, since it's more obviously a machine). It doesn't have to be humanoid ... but apart from rolling instead of walking, I don't see any really significant simplifications obtainable from making it non-humanoid. Grasping and manipulating general objects with robot manipulators is very much an unsolved research problem. So is object recognition in realistic conditions. So, to make an AGI robot preschool, one has to solve these hard research problems first. That is a viable way to go if one's not in a hurry -- but anyway in the robotics context any talk of preschools is drastically premature... On the other hand, making a virtual world such as I envision, is more than a spare-time project, but not more than the project of making a single high-quality video game. GTA IV cost $5 million, so we're not talking about peanuts here. Right, but that is way cheaper than making a high-quality humanoid robot Actually, $$ aside, we don't even **know how** to make a decent humanoid robot. Or, a decently functional mobile robot **of any kind** Whereas making a software based AGI Preschool of the type I described is clearly feasible using current technology, w/o any research breakthroughs And I'm sure it could be done for $300K not $5M using OSS and non-US outsourced labor... 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Oh, and because I am interested in the potential of high-fidelity physical simulation as a basis for AI research, I did spend some time recently looking into options. Unfortunately the results, from my perspective, were disappointing. The common open-source physics libraries like ODE, Newton, and so on, have marginal feature sets and frankly cannot scale very well performance-wise. Once I even did a little application whose purpose was to see whether a human being could learn to control an ankle joint to compensate for an impulse event and stabilize a simple body model (that is, to make it not fall over) by applying torques to the ankle. I was curious to see (through introspection) how humans learn to act as process controllers. http://happyrobots.com/anklegame.zip for anybody bored enough to care. It wasn't a very good test of the question so I didn't really get a satisfactory answer. I did discover, though, that a game built around more appealing cases of the player learning to control physics-inspired processes could be quite absorbing. Beyond that, the most promising avenue seems to be physics libraries tied to graphics hardware being worked on by the hardware companies to help sell their stream processors. The best example is Nvidia, who bought PhysX and ported it to their latest cards, giving a huge performance boost. Intel has bought Havok and I can only imagine that they are planning on using that as the interface to some Larrabee-based physics engine. I'm sure that ATI is working on something similar for their newer (very impressive) stream processing cards. At this stage, though, despite some interesting features and leaping performance, it is still not possible to do things like get realistic sensor maps for a simulated soft hand/arm, and complex object modifications like bending and breaking are barely dreamed of in those frameworks. Complex multi-body interactions (like realistic behavior when dropping or otherwise playing with a ring of keys or realistic baby toys) have a long ways to go. Basically, I fear those of us who are interested in this are just waiting to ride the game development coattails and it will be a few years at least until performance that even begins to interest me will be available. Just my opinions on the situation. --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Bob: Even with crude or no real simulation ability in an environment such as Second Life, using some simple symbology to stand for puck up screwdriver you can still try to tackle problems such as autobiographical memory - how does the agent create a coherent story out of a series of activities, and how can it use that story in future to improve its skills or communication effectiveness. It's an interesting idea, but I suspect it too will rapidly break down. Which activities can be known about in a rich, better-than-blind-Cyc way *without* a knowledge of objects and object manipulation? How can an agent know about reading a book,for example, if it can't pick up and manipulate a book? How can it know about adding and subtracting, if it can't literally put objects on top of each other, and remove them? We humans build up our knowledge of the world objects/physics up from infancy. Science also insists that all formal scientific knowledge of the world - all scientific disciplines - must be ultimately physics/objects-based. Is there really an alternative? --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: It doesn't have to be humanoid ... but apart from rolling instead of walking, I don't see any really significant simplifications obtainable from making it non-humanoid. I can think of several. For example, you could give it lidar to measure distances with -- this could then be used as input to its vision system making it easier for the robot to tell which objects are near or far. Instead of binocular vision, it could have 2 video cameras. It could have multiple ears, which would help it tell where a sound is coming from. The the best of my knowledge, no robot that's ever been used for anything practical has ever been humanoid. Grasping and manipulating general objects with robot manipulators is very much an unsolved research problem. So is object recognition in realistic conditions. What sort of visual input do you plan to have in your virtual environment? So, to make an AGI robot preschool, one has to solve these hard research problems first. That is a viable way to go if one's not in a hurry -- but anyway in the robotics context any talk of preschools is drastically premature... On the other hand, making a virtual world such as I envision, is more than a spare-time project, but not more than the project of making a single high-quality video game. GTA IV cost $5 million, so we're not talking about peanuts here. Right, but that is way cheaper than making a high-quality humanoid robot Is it? I suspect one with tracks, two robotic arms, various sensors for light and sound, etc, could be made for less than $10,000 -- this would be something that could move around and manipulate a blocks world. My understanding is that all, or nearly all, the difficulty comes in programming it. Which is where AI comes in. Actually, $$ aside, we don't even **know how** to make a decent humanoid robot. Or, a decently functional mobile robot **of any kind** Is that because of hardware or software issues? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Derek Zahn derekz...@msn.com: Ben: Right. My intuition is that we don't need to simulate the dynamics of fluids, powders and the like in our virtual world to make it adequate for teaching AGIs humanlike, human-level AGI. But this could be wrong. I suppose it depends on what kids actually learn when making cakes, skipping rocks, and making a mess with play-dough. I think that the important cognitive abilities involved are at a simpler level than that. Consider an object, such as a sock or a book or a cat. These objects can all be recognised by young children, even though the visual input coming from trhem chasnges from what angle they're viewed at. More fundamentally, all these objects can change shape, yet humans can still effortlessly recognise them to be the same thing. And this ability doesn't stop with humans -- most (if not all) mammalian species can do it. Until an AI can do this, there's no point in trying to get it to play at making cakes, etc. -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Well, there is massively more $$ going into robotics dev than into AGI dev, and no one seems remotely near to solving the hard problems Which is not to say it's a bad area of research, just that it's a whole other huge confusing RD can of worms So I still say, the choices are -- virtual embodiment, as I advocate -- delay working on AGI for a decade or so, and work on robotics now instead (where by robotics I include software work on low-level sensing and actuator control) Either choice makes sense but I prefer the former as I think it can get us to the end goal faster. About the adequacy of current robot hardware -- I'll tell you more in 9 months or so ... a project I'm collaborating on is going to be using AI (including OpenCog) to control a Nao humanoid robot. We'll have 3 of them, they cost about US$14K each or so. The project is in China but I'll be there in June-July to play with the Naos and otherwise collaborate on the project. My impression is that with a Nao right now, camera-eye sensing is fine so long as lighting conditions are good ... audition is OK in the absence of masses of background noise ... walking is very awkward and grasping is possible but limited The extent to which the limitations of current robots are hardware vs software based is rather subtle, actually. In the case of vision and audition, it seems clear that the bottleneck is software. But, with actuation, I'm not so sure. The almost total absence of touch and kinesthetics in current robots is a huge impediment, and puts them at a huge disadvantage relative to humans. Things like walking and grasping as humans do them rely extremely heavily on both of these senses, so in trying to deal with this stuff without these senses (in any serious form), current robots face a hard and odd problem... ben On Sat, Dec 20, 2008 at 11:42 AM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: It doesn't have to be humanoid ... but apart from rolling instead of walking, I don't see any really significant simplifications obtainable from making it non-humanoid. I can think of several. For example, you could give it lidar to measure distances with -- this could then be used as input to its vision system making it easier for the robot to tell which objects are near or far. Instead of binocular vision, it could have 2 video cameras. It could have multiple ears, which would help it tell where a sound is coming from. The the best of my knowledge, no robot that's ever been used for anything practical has ever been humanoid. Grasping and manipulating general objects with robot manipulators is very much an unsolved research problem. So is object recognition in realistic conditions. What sort of visual input do you plan to have in your virtual environment? So, to make an AGI robot preschool, one has to solve these hard research problems first. That is a viable way to go if one's not in a hurry -- but anyway in the robotics context any talk of preschools is drastically premature... On the other hand, making a virtual world such as I envision, is more than a spare-time project, but not more than the project of making a single high-quality video game. GTA IV cost $5 million, so we're not talking about peanuts here. Right, but that is way cheaper than making a high-quality humanoid robot Is it? I suspect one with tracks, two robotic arms, various sensors for light and sound, etc, could be made for less than $10,000 -- this would be something that could move around and manipulate a blocks world. My understanding is that all, or nearly all, the difficulty comes in programming it. Which is where AI comes in. Actually, $$ aside, we don't even **know how** to make a decent humanoid robot. Or, a decently functional mobile robot **of any kind** Is that because of hardware or software issues? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Consider an object, such as a sock or a book or a cat. These objects can all be recognised by young children, even though the visual input coming from trhem chasnges from what angle they're viewed at. More fundamentally, all these objects can change shape, yet humans can still effortlessly recognise them to be the same thing. And this ability doesn't stop with humans -- most (if not all) mammalian species can do it. Until an AI can do this, there's no point in trying to get it to play at making cakes, etc. Well, it seems to me that current virtual worlds are just fine for exploring this kind of vision processing However, I have long been perplexed at the obsession with so many AI folks with vision processing. I mean: yeah, it's important to human intelligence, and some aspects of human cognition are related to human visual perception But, it's not obvious to me why so many folks think vision is so critical to AI, whereas other aspects of human body function are not. For instance, the yogic tradition and related Eastern ideas would suggest that *breathing* and *kinesthesia* are the critical aspects of mind. Together with touch, kinesthesia is what lets a mind establish a sense of self, and of the relation between self and world. In that sense kinesthesia and touch are vastly more fundamental to mind than vision. It seems to me that a mind without vision could still be a basically humanlike mind. Yet, a mind without touch and kinesthesia could not, it would seem, because it would lack a humanlike sense of its own self as a complex dynamic system embedded in a world. Why then is there constant talk about vision processing and so little talk about kinesthetic and tactile processing? Personally I don't think one needs to get into any of this sensorimotor stuff too deeply to make a thinking machine. But, if you ARE going to argue that sensorimotor aspects are critcial to humanlike AI because they're critical to human intelligence, why harp on vision to the exclusion of other things that seem clearly far more fundamental?? Is the reason just that AI researchers spend all day staring at screens and ignoring their physical bodies and surroundings?? ;-) 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: However, I have long been perplexed at the obsession with so many AI folks with vision processing. I wouldn't say I'm obsessed with it. On its own vision processing does nothing, the same as all other input processing -- its only when a brain/AI used that processing to create output that it is actually doing any work. Theimportnat thing about vision, IMO, is not vision itself, but the way that vision interfaces with a mind's model of the world. And vision isn't really that different in principle from the other sensory modalities that a human or animal has -- they are all inputs, that go to building a model of the world, through which the organism makes decisions. But, it's not obvious to me why so many folks think vision is so critical to AI, whereas other aspects of human body function are not. I don't think any human body functions are critical to AI. IMO it's a perfectly valid approach to AI to build programs that deal with digital symbolic information -- e.g. programs like copycat or eurisko. For instance, the yogic tradition and related Eastern ideas would suggest that *breathing* and *kinesthesia* are the critical aspects of mind. Together with touch, kinesthesia is what lets a mind establish a sense of self, and of the relation between self and world. Kinesthesia/touch/movement are clearly important sensory modalities in mammals, given that they are utterly fundamental to moving around in the world. Breathing less so -- I mean you can do it if you're unconscious or brain dead. Why then is there constant talk about vision processing and so little talk about kinesthetic and tactile processing? Possibly because people are less conscious of it than vision. Personally I don't think one needs to get into any of this sensorimotor stuff too deeply to make a thinking machine. Me neither. But if the thinking machine is to be able to solve certain problems (when connected to a robot body, of course) it will have to have sophisticated systems to handle touch, movement and vision. By certain problems I mean things like making a cup of tea, or a cat climbing a tree, or a human running over uneven ground. But, if you ARE going to argue that sensorimotor aspects are critcial to humanlike AI because they're critical to human intelligence, why harp on vision to the exclusion of other things that seem clearly far more fundamental?? Say I asked you to imagine a cup. (Go on, do it now). Now, when you imagined the cup, did you imagine what it looks like, or what it feels like to the touch. For me, it was the former. So I don't think touch is clearly more fundamental, in terms of how it interacts with our internal model of the world, than vision is. Is the reason just that AI researchers spend all day staring at screens and ignoring their physical bodies and surroundings?? ;-) :-) -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/19 Ben Goertzel b...@goertzel.org: What I'd like to see is a really nicely implemented virtual world preschool for AIs ... though of course building such a thing will be a lot of work for someone... Why a virtual world preschool and not a real one? A virtual world, if not programmed accurately, may be subtly differernet from the real world, so that for example an AGI is capable of picking up and using a screwdriver in the virtual world but not real real world, because the real world is more complex. If you want your AGI to be able to use a screwdriver, you probably need to train it in the real world (at least some of the time). If you don't care whether your AGI can use a screwdriver, why have one in the virtual world? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Well, there is a major question whether one can meaningfully address AGI via virtual-robotics rather than physical-robotics No one can make a convincing proof either way right now But, it's clear that if one wants to go the physical-robotics direction, now is not the time to be working on preschools and cognition. In that case, we need to be focusing on vision and grasping and walking and such. OTOH, if one wants to go the virtual-robotics direction (as is my intuition), then it is possible to bypass many of the lower-level perception/actuation issues and focus on preschool-level learning, reasoning and conceptual creation. And there's no need to write a paper on the eventual possibility of putting robots in real preschools: that's obvious. But it's also far beyond the scope of contemporary robots, as would be univerally. Whereas virtual preschool is not as *obviously* far beyond the scope of contemporary AGI designs (at least according to some experts, like me), which is what makes it more interesting in the present moment... ben g -- Ben G On Fri, Dec 19, 2008 at 5:12 PM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/19 Ben Goertzel b...@goertzel.org: What I'd like to see is a really nicely implemented virtual world preschool for AIs ... though of course building such a thing will be a lot of work for someone... Why a virtual world preschool and not a real one? A virtual world, if not programmed accurately, may be subtly differernet from the real world, so that for example an AGI is capable of picking up and using a screwdriver in the virtual world but not real real world, because the real world is more complex. If you want your AGI to be able to use a screwdriver, you probably need to train it in the real world (at least some of the time). If you don't care whether your AGI can use a screwdriver, why have one in the virtual world? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
RE: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Hi Ben. OTOH, if one wants to go the virtual-robotics direction (as is my intuition), then it is possible to bypass many of the lower-level perception/actuation issues and focus on preschool-level learning, reasoning and conceptual creation. And yet, in your paper (which I enjoyed), you emphasize the importance of not providing a simplistic environment (with the screwdriver example). Without facing the low-level sensory world (either through robotics or through very advanced simulations feeding senses essentially equivalent to those of humans), I wonder if a targeted human-like AGI will be able to acquire the necessary concepts that children absorb and use as much o f the metaphorical basis for their thought -- slippery, soft, hot, hard, rough, sharp, and on and on. I assume you have some sort of middle ground in mind... what's your thinking about how much you can cheat in this way (beyond that of what is conveniently doable I mean)? Thanks! --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
It's a hard problem, and the answer is to cheat as much as possible, but not any more so. We'll just have to feel this out via experiment... My intuition is that current virtual worlds and game worlds are too crude, but current robot simulators are not. I.e., I doubt one needs serious fluid dynamics in one's simulation ... I doubt one needs bodies with detailed internal musculature ... but I think one does need basic Newtonian physics and the ability to use tools, break things in half (but not necessarily realistic cracking behavior), balance things and carry them and stack them and push them together Lego-like and so forth... I could probably frame a detailed argument as to WHY I think the line should be drawn right there, in terms of the cognitive tasks supported by this level of physics simulation. That would be an interesting followup paper, I guess. The crux of the argument would be that all the basic tasks required in an AGI Preschool could be sensibly formulated using only this level of physics simulation, in a way that doesn't involve cheating... (but the proper contextualization formalization of doesn't involve cheating would require some thought) ben On Fri, Dec 19, 2008 at 7:54 PM, Derek Zahn derekz...@msn.com wrote: Hi Ben. OTOH, if one wants to go the virtual-robotics direction (as is my intuition), then it is possible to bypass many of the lower-level perception/actuation issues and focus on preschool-level learning, reasoning and conceptual creation. And yet, in your paper (which I enjoyed), you emphasize the importance of not providing a simplistic environment (with the screwdriver example). Without facing the low-level sensory world (either through robotics or through very advanced simulations feeding senses essentially equivalent to those of humans), I wonder if a targeted human-like AGI will be able to acquire the necessary concepts that children absorb and use as much o f the metaphorical basis for their thought -- slippery, soft, hot, hard, rough, sharp, and on and on. I assume you have some sort of middle ground in mind... what's your thinking about how much you can cheat in this way (beyond that of what is conveniently doable I mean)? Thanks! -- *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 -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: I.e., I doubt one needs serious fluid dynamics in one's simulation ... I doubt one needs bodies with detailed internal musculature ... but I think one does need basic Newtonian physics and the ability to use tools, break things in half (but not necessarily realistic cracking behavior), balance things and carry them and stack them and push them together Lego-like and so forth... Needs for what purpose? I can see three uses for a virtual world: 1. to mimic the real world accurately enough that the AI can use the virtual world instead, and by using it become proficient in dealing with the real world, because it is cheaper than a real world. Obviously to program a virtual world this real is a big up-front investment, but once the investment is made, such a world may well be cheaper and easier to use than our real one. 2. to provide a useful bridge between humans and the AGI, i.e. the virtual world will be similar enough to the real world that humans will have a common frame of reference with the AGI. 3. to provide a toy domain for the AI to think about and become proficient in. (Of course there's no reason why a toy domain needs to be anything like a virtual world, it could for example be a software modality that can see/understand source code as easily and fluently as humans interprete visual input.) AIUI you're mostly thinking in terms of 2 or 3. Fair comment? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
On Fri, Dec 19, 2008 at 8:42 PM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: I.e., I doubt one needs serious fluid dynamics in one's simulation ... I doubt one needs bodies with detailed internal musculature ... but I think one does need basic Newtonian physics and the ability to use tools, break things in half (but not necessarily realistic cracking behavior), balance things and carry them and stack them and push them together Lego-like and so forth... Needs for what purpose? I can see three uses for a virtual world: 1. to mimic the real world accurately enough that the AI can use the virtual world instead, and by using it become proficient in dealing with the real world, because it is cheaper than a real world. Obviously to program a virtual world this real is a big up-front investment, but once the investment is made, such a world may well be cheaper and easier to use than our real one. I think this will come along as a side-effect of achieving the other goals, to some extent. But it's not my main goal, no. 2. to provide a useful bridge between humans and the AGI, i.e. the virtual world will be similar enough to the real world that humans will have a common frame of reference with the AGI. Yes... to allow the AGI to develop progressively greater intelligence in a manner that humans can easily comprehend, so that we can easily participate and encourage its growth (via teaching and via code changes, knowledge entry, etc.) 3. to provide a toy domain for the AI to think about and become proficient in. Not just to become proficient in the domain, but become proficient in general humanlike cognitive processes. The point of a preschool is that it's designed to present all important adult human cognitive processes in simplified forms. (Of course there's no reason why a toy domain needs to be anything like a virtual world, it could for example be a software modality that can see/understand source code as easily and fluently as humans interprete visual input.) AIUI you're mostly thinking in terms of 2 or 3. Fair comment? -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Derek Zahn derekz...@msn.com: And yet, in your paper (which I enjoyed), you emphasize the importance of not providing a simplistic environment (with the screwdriver example). Without facing the low-level sensory world (either through robotics or through very advanced simulations feeding senses essentially equivalent to those of humans), I wonder if a targeted human-like AGI will be able to acquire the necessary concepts that children absorb and use as much o f the metaphorical basis for their thought -- slippery, soft, hot, hard, rough, sharp, and on and on. Evolution has equipped humans (and other animals) have a good intuitive understanding of many of the physical realities of our world. The real world is not just slippery in the physical sense, it's slippery in the non-literal sense too. For example, I can pick up an OXO cube (a solid object), crush it so it become powder, pour it into my stew, and stir it in so it dissolves. My mind can easily and effortlessly track that in some sense its the same oxo cube and in another sense it isn't. Another example: my cat can distinguish between surfaces that are safe to sit on, and others that are too wobbly, even if they look the same. An animals intuitive physics is a complex system. I expect that in humans a lot of this machinery isd re-used to create intelligence. (It may be true, and IMO probably is true, that it's not necessary to re-create this machinery to make an AGI). -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: 3. to provide a toy domain for the AI to think about and become proficient in. Not just to become proficient in the domain, but become proficient in general humanlike cognitive processes. The point of a preschool is that it's designed to present all important adult human cognitive processes in simplified forms. So it would be able to transfer its learning to the real world and (when given a robot body) be able to go into a kitchen its never seen before and make a cup of tea? (In other words, will the simulation be deep enough to allow that). -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Right. My intuition is that we don't need to simulate the dynamics of fluids, powders and the like in our virtual world to make it adequate for teaching AGIs humanlike, human-level AGI. But this could be wrong. It also could be interesting to program an artificial chemistry that emulated certain aspects of real chemistry -- not to be realistic, but to have enough complexity to be vaguely analogous. After all, I mean: preschoolers have fun and learn a lot mixing flour and butter and eggs and so forth, but how realistic does the physics of such things really have to be to give a generally comparable learning experience??? ben Evolution has equipped humans (and other animals) have a good intuitive understanding of many of the physical realities of our world. The real world is not just slippery in the physical sense, it's slippery in the non-literal sense too. For example, I can pick up an OXO cube (a solid object), crush it so it become powder, pour it into my stew, and stir it in so it dissolves. My mind can easily and effortlessly track that in some sense its the same oxo cube and in another sense it isn't. Another example: my cat can distinguish between surfaces that are safe to sit on, and others that are too wobbly, even if they look the same. An animals intuitive physics is a complex system. I expect that in humans a lot of this machinery isd re-used to create intelligence. (It may be true, and IMO probably is true, that it's not necessary to re-create this machinery to make an AGI). -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Well, that's a really easy example, right? For making tea, the answer would probably be yes. Baking a cake is a harder example. An AGI trained in a virtual world could certainly follow a recipe to make a passable cake. But it would never learn to be a **really good** baker in the virtual world, unless the virtual world were fabulously realistic in its simulation (and we don't know how to make it that good, right now). Being a really good baker requires a lot of intuition for subtle physical properties of ingredients, not just following a recipe and knowing the primitive basics of naive physics... ben g On Fri, Dec 19, 2008 at 8:56 PM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: 3. to provide a toy domain for the AI to think about and become proficient in. Not just to become proficient in the domain, but become proficient in general humanlike cognitive processes. The point of a preschool is that it's designed to present all important adult human cognitive processes in simplified forms. So it would be able to transfer its learning to the real world and (when given a robot body) be able to go into a kitchen its never seen before and make a cup of tea? (In other words, will the simulation be deep enough to allow that). -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
2008/12/20 Ben Goertzel b...@goertzel.org: Baking a cake is a harder example. An AGI trained in a virtual world could certainly follow a recipe to make a passable cake. But it would never learn to be a **really good** baker in the virtual world, unless the virtual world were fabulously realistic in its simulation (and we don't know how to make it that good, right now). Being a really good baker requires a lot of intuition for subtle physical properties of ingredients, not just following a recipe and knowing the primitive basics of naive physics... A sense of taste would probably help too. -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Ahhh... ***that's*** why everyone always hates my cakes!!! I never realized you were supposed to **taste** the stuff ... I thought it was just supposed to look funky after you throw it in somebody's face ;-) On Fri, Dec 19, 2008 at 9:31 PM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: Baking a cake is a harder example. An AGI trained in a virtual world could certainly follow a recipe to make a passable cake. But it would never learn to be a **really good** baker in the virtual world, unless the virtual world were fabulously realistic in its simulation (and we don't know how to make it that good, right now). Being a really good baker requires a lot of intuition for subtle physical properties of ingredients, not just following a recipe and knowing the primitive basics of naive physics... A sense of taste would probably help too. -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
Although, I note, I know a really good baker who makes great cakes in spite of the fact that she does not eat sugar and hence does not ever taste most of the stuff she makes... But she *used to* eat sugar, so to an extent she can go on memory Sorta like how Beethoven kept composing after he went deaf, I suppose ;-) On Fri, Dec 19, 2008 at 9:42 PM, Ben Goertzel b...@goertzel.org wrote: Ahhh... ***that's*** why everyone always hates my cakes!!! I never realized you were supposed to **taste** the stuff ... I thought it was just supposed to look funky after you throw it in somebody's face ;-) On Fri, Dec 19, 2008 at 9:31 PM, Philip Hunt cabala...@googlemail.comwrote: 2008/12/20 Ben Goertzel b...@goertzel.org: Baking a cake is a harder example. An AGI trained in a virtual world could certainly follow a recipe to make a passable cake. But it would never learn to be a **really good** baker in the virtual world, unless the virtual world were fabulously realistic in its simulation (and we don't know how to make it that good, right now). Being a really good baker requires a lot of intuition for subtle physical properties of ingredients, not just following a recipe and knowing the primitive basics of naive physics... A sense of taste would probably help too. -- Philip Hunt, cabala...@googlemail.com Please avoid sending me Word or PowerPoint attachments. See http://www.gnu.org/philosophy/no-word-attachments.html --- 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 b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx -- Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC Director of Research, SIAI b...@goertzel.org I intend to live forever, or die trying. -- Groucho Marx --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com
Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI
On Dec 19, 2008, at 6:43 PM, Ben Goertzel wrote: Although, I note, I know a really good baker who makes great cakes in spite of the fact that she does not eat sugar and hence does not ever taste most of the stuff she makes... But she *used to* eat sugar, so to an extent she can go on memory Fortunately, baking is more about process control than flavor control. Unlike normal cooking, which is significantly fine-tuned by taste, the taste of baked goods is pretty invariant. On the other hand, baking requires a lot of attention to detail and process precision that normal cooking does not. Which is why I am merely an adequate baker instead of a great one. :-) Cheers, J. Andrew Rogers --- 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=123753653-47f84b Powered by Listbox: http://www.listbox.com