[agi] IBM building a brain.
Henry Markram: "I believe the intelligence that is going to emerge ifwe succeed in doing that is going to be far more than we can evenimagine." http://tinyurl.com/bawt2 http://bluebrainproject.epfl.ch/ http://tinyurl.com/8e8e8 To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] No virus found in this outgoing message. Checked by AVG Anti-Virus. Version: 7.0.323 / Virus Database: 267.8.5/32 - Release Date: 6/27/2005 --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Hawkins founds AI company named Numenta
http://www.forbes.com/technology/personaltech/2005/03/24/cz_qh_0324numenta.html Ben, this is good news, that someone with such mainstream computer business credentials is getting into the AI business. This can't but add legitimacy to the field, and if he makes any money at it many will be rushing to invest in him and his competitors, that's you. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED] No virus found in this outgoing message. Checked by AVG Anti-Virus. Version: 7.0.308 / Virus Database: 266.7.4 - Release Date: 3/18/2005 --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
[agi] Unlimited intelligence.
Computer chess programs are merely one example of many kinds of software that display human level intelligence in a very narrow domain. The chess program on my desktop computer can beat me (but just barely), nevertheless, I consider myself more intelligent than it because I can do a lot of other things in addition to playing chess. But even if someone were to tack together a bunch of specialized programs to make a super program that did lots of stuff, I would still be more intelligent than it.Intelligence isn't just being able to do lots of stuff, but also having multiple levels of abstraction. The computer program has one level of abstraction; it plays chess. It doesn't know why it plays chess, the greater goal satisfied by playing chess, or the even greater goal that the chess playing goal serves. True intelligence must be aware of the widest possible context and derive super-goals based on direct observation of that context,and then generate subgoals for subcontexts. Anything with preprogrammed goals is limited intelligence. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Unlimited intelligence. --- Super Goals
Yes, we have instincts, drives built into our systems at a hardware level, beyond the ability to reprogram through merely a software upgrade. These drives, sex, pain/pleasure, food, air, security, social status, self-actualization, are not supergoals, they are reinforcers. Reinforcers give you positive or negative feelings when they are encountered. Supergoals are the top level of rules you use to determine a choice of behavior. You can make reinforcers your supergoals, which is what animals do because their contextual understanding, and reasoning abilityis so limited. People have a choice. You don't have to be a slave to the biologically programmed drives you were born with. You can perceive a broader context where you are not the center of the universe. You can even imagine redesigning your hardware and software to become something completely different with no vestige of your human reinforcers. Can a system choose to change its supergoal, or supergoals? Obviously not, unless some method of supergoal change is specifically written into the supergoals. People's supergoals change as they mature but this is not a voluntary process. Systems can be designed to have some sensitivity to the external environment for supergoal modification. Certainly systems with immutable supergoals are more stable, but stability isn't always desirable or even safe. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Singularity Institute's The SIAI Voice - August 2004
Tyler, take a look at the website Chris Phoenix and I are making: http://nano-catalog.com/ If you have any comments, send them to me and I will post them on the "Affiliates" page http://nano-catalog.com/affiliates.html along with your logo and a link to your website. You can never have too many links to your website. Mike Deering,General Editor, http://nano-catalog.com/ Director, http://www.singularityawareness.com/Email: deering9 at mchsi dot com To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Kinds of minds: minimal-, modest-, huge-resource
Anyone on this list, take a look at the website Chris Phoenix and I are making: http://nano-catalog.com/ If you have any comments, send them to me and I will post them on the "Affiliates" page http://nano-catalog.com/affiliates.html along with your logo and a link to your website. You can never have too many links to your website. Mike Deering,General Editor, http://nano-catalog.com/ Director, http://www.singularityawareness.com/Email: deering9 at mchsi dot com To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Teaching AI's to self-modify
Ben, I hope you are going to keep a human in the loop. Human in the loop scenario: The alpha Novamente makes a suggestion about some change to its software. The human implements the change on the beta Novamente running on a separate machine, and tests it. If it seems to be an improvement, it is incorporated into the alpha Novamente. Human not in the loop scenario: The Novamente looks at its code. The Novamente makes changes to its code, and reboots itself. The Novamente looks at its code. The Novamente makes changes to its code, and reboots itself. The Novamente looks at its code. The Novamente makes changes to its code, and reboots itself. The humans wonder what the hell is going on. Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] AGI's and emotions
An unexpected mental event or an unplanned mental excursion does not in itself constitute an emotion. An epileptic seizure is not an emotion. Most emotions, perhaps all, are very predictable from causes. You will the lottery or the girl next door says "yes" and you are happy. Someone runs into your classic Beetle, and you are sad. You finish a major work of great value, and you feel joy. There is nothing mysterious about these emotions, no unpredictable mental dynamics. I don't consider "confusion" an emotion. I consider it a error in processing. I know I'm not telling you anything new. You surely understand all of this already. Therefore I must be missing some fundamental aspect of your thoughts on emotions. I have to admit, I've never been very good at emotions, and tend to ignore them. I feel like we must be talking past each other, but I can't imagine how we could be ambiguous about an experience as fundamental as emotion. We all have them. It's the ocean our thoughts swim in, waves taking us to and fro, and sometimes crashing us against the rocks. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] AGI's and emotions
It is true that there is a portion of the process of emotion that is not under our conscious control. There are in fact many cognitive functions underlying lots of different conscious thoughts that are not subject to our introspection or direct control, though perhaps not beyond our understanding. We necessarily have limited ability to watch our own thought processes, in order to have time to think about the important stuff, and to avoid an infinite regress. This limitation is "hardwired" in our design. The ability to selectively observe and control any cognitive function is a possible design option in an AI. The fact that there will not be time or resources to monitor every mental process, that most will be automatic, does not make it emotion. Lack of observation, and lack of control, do not mean lack of understanding. I agree that there will necessarily be automatic functions in a practical mind. I don't agree that these processes have to be characterized or shaped as emotions. I expect to see emotional AI's and non-emotional AI's. We don't know enough yet to predict which will function better. 1. highly emotional AL. (out of control) 2. moderately emotional AI. (like us, undependable) 3. slightly emotional AI. (your supposition, possibly good) 4. non-emotional AI. (my choice, including simulated emotions for human interaction) Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] AGI's and emotions
In your paper you take a stab at defining emotions and explaining different kinds of emotions' relationship to goals achievement and motivation of important behaviors (fight, flight, reproduction). And then you go on to say that AI's will have goals and motivations and important behaviors, so of course, AI's will have emotions. I don't exactly agree. I think AI's could have emotions if they were designed that way. I don't think this is the only way a mind can work. I doubt if it is the best way. Evolution gave feathers to birds, and feathers are certainly functional, but I don't think that is any excuse to be pasting them on the wings of an F16. Emotions are evolution's solution to a motivational problem in biological minds. I don't want my computer to stop sending my email because it is depressed about the economy. Emotions...I don't know. Maybe there are some applications where they might be useful, dealing with humans. But then the emotions could be faked. Humans do it all the time. I'm trying to think of a case where real emotions would be a functional advantage to a purpose built machine. I can't think of any. Then again, it's late, and I have to get to bed. I'll sleep on it. Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] probability theory and the philosophy of science
Ben, I get the impression from reading this article that it is very closely related to your work on Novamente. In trying to design a mind that is intelligent and useful you have decided that the scientist comes closest as an example. So you are trying to figure out how the best scientists think and build that into your software. You certainly wouldn't want to build super-human processing AI that was fascinated by astrology and tried to solve every problem using only that. How to keep your AI from getting as messed up as some of us? Of course, make it a scientist. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Real world effects on society after development of AGI????
Brad, I completely agree with you that the computer/human crossover point is meaningless and all the marbles are in the software engineering not the hardware capability. I didn't emphasize this point in my argument because I considered it a side issue and I was trying to keep the email from being any longer than necessary. But even when someone figures out how to write the software of the mind, you still need the machine to run it on. I believe in the creative ability of the whole AGI research ecosystem to be able to deliver the software when the hardware is available. I believe that the human mind is capable of solving this design/engineering problem, and will solve it at the earliest opportunity presented by hardware availability. Regarding nanotechnology development, I think we are approaching nano-assembly capability much faster than you seem to be aware. Check out the nanotech news http://nanotech-now.com/ Regarding science, Yes, turtles all the way down. Probably. But atoms are so handy. Everything of any usefulness is made of atoms. To go below atoms to quarks and start manipulating them and making stuff other than the 92 currently stable atoms has such severe theoretical obstacles that I can't imagine solving them all. Granted, I may be lacking imagination, or maybe I just know too much about quarks to ignore all the practical problems. Quarks are not particles. You can't just pull them apart and start sticking them together any way you want. Quarks are quantified characteristics of the particles they make up. We have an existence proof that you can make neat stuff out of atoms. Atoms are stable. Quarks are more than unstable, they don't even have a separate existence. I realize that my whole argument has one great big gaping hole, "We don't know what we don't know." Okay, but what I do know about quarks leads me to believe that we are not going to have quark technology. On a more general vein, we have known for some time that areas of scientific research are shutting down. Mechanics is finished. Optics is finished. Chemistry is finished. Geology is basically finished. We can't predict earthquakes but that's not because we don't know what is going on. Metrology we understand be can't calculate, not science's fault. Oceanography, ecology, biology, all that is left to figure out is the molecular biology and they are done. Physics goes on, and on, and on, but to no practical effect beyond QED and that is all about electrons and photons and how they interact with atoms, well roughly. I don't expect this clarification to change your mind. I think we are going to have to agree to disagree and wait and see. See you after the Singularity. Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Real world effects on society after development of AGI????
How long the transition from the emergence of AGI to full integration into society is debatable. If the transition is deformed by interference from government then things could get really screwed up, but I think there is at least an even chance that they will let it develop according to free economic forces. For the remainder of this message I will assume a natural free development. The first stage will be the initial training with basic knowledge including specific information about the human environment. This training stage will not need to be repeated with each new AGI as computers can copy their information. The second stage will be replacement of workers with robots. All jobs are susceptible to replacement by robots. I hope you have a fat 401K or other assets, you're going to need it. The cost of all products and services will drop precipitously. The cost of a product or service consists of the labor cost, plus the cost of the machinery used in its production amortized over the total number of products produced. The reason electronic equipment has dropped is due to the increase in automation of the factories. When robots take all the jobs in the factories labor costs will drop to zero leaving the equipment cost. The equipment cost consists of the cost of the raw materials plus the labor costs to convert them into equipment. The labor costs will disappear leaving only the raw materials cost. The cost of the raw materials is primarily the labor cost to extract it from the ground or recycle it from the dump. If you look at the whole economy from the mine to Wal-Mart you find that labor makes up almost all the cost. And as more manufacturing capacity is built, the cost of production drops. Theseare the basics of the 'abundance economy'. Obviously our current social structure will need to make significant adjustments in the transition to the 'abundance economy'. The last stage is the integration of super-human AGI into government and decision making positions at the top of the societal control structures. Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Real world effects on society after development of AGI????
Well, the third stage requires a higher level of intelligence by the AGI's than the second stage, so, if the advancement of AGI intelligence from human-level to super-human levels is rapid, then yes, it is possible that the integration of AGI's into top level decision making positions could occur before the replacement of all workers, which involve mid and low-level decision making. Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Dr. Turing, I presume?
Ben, you are absolutely correct. It was my intention to exaggerate the situation a bit without actually crossing the line. But I don't think it is much of an exaggeration to say that a 'baby' Novamente even with limited hardware and speed is a tremendous event in the history of life on Earth. A phase change starts with one molecule. As computers are becoming more powerful and nanotech capabilities reach closer to the ultimate goal of molecular positional assembly the world will crossa threshold similar to supercooled water where one triggering event will set off a chain reaction causing a phase change to ice throughout the entire mass. Okay, I'm exaggerating again, but not much. The money men know it is coming. But they have been burned so many times before in the A.I. category that they are not willing to touch the stove again, unless someone can show them something that works. It doesn't have to be a finished product, just something that demonstrates a new capability. Your 'baby' Novamente or Peter's proof-of-concept example or James Rogers' who-knows-super-secret-whatits will trigger a phase change in funding for AGI. The practical applications are unlimited. The profit potential is unlimited. That's why the money men threw away so much twenty years ago on projects that didn't have a ghost of a chance and got burned. I'm not saying that your 'baby' Novemente will change the whole world overnight all by itself. But any working example of AGI, no matter how limited, will trigger a complicated chain reaction in the economy and mindset of the world. The initial example, whatever it is,may turn out to be a flawed design of limited usefulness (I wouldn't want to see scaled-up jumbo 'Wright Flyers' populating airport terminals) but it will not matter. Just look at the funding that GOOGLE has attracted with some cleverly written but dumb (non-AGI) rules. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Dr. Turing, I presume?
Arthur, I am disappointed with the way that A.I. is depicted in science fiction books and movies. Unfortunately most people get their idea of what the future will be like from movies and novels. Why don't they show A.I. and robots in a more realistic scenario? Take Star Trek for instance. Data is the humanoid robot with the machine intelligence quotient of 1000 and the human intelligence quotient of 85. Why don't they make a lot of Data-like robots? Because they supposedly don't understand how his brain works. Nevertheless, in their holodecks they routinely generate convincing artificial characters. Why don't they take the same knowledge that allows them to create artificial intelligences in their holodecks and build character driven robots that operate in the real human environment? It seems obvious that real A.G.I. is just around the corner. Ben's Novamente progress report says they should have a working system in 12 to 18 months. Peter's a2i2 project report states that a proof-of-concept prototype should be operational in 12 months. Toyota just announced that they will have an industrial humanoid robot on the market in 2005 to work in factories and other uses. But the general public is not expecting humanoid robots with anything like real intelligence any time soon because every movie they see about the future either doesn't include robots at all or shows them as the enemy. Or as in Star Wars, robots with only very limited smarts. Let's take the Mars rovers as an example of current robotic expectations. Nasa doesn't trust anything as squishy as real intelligence, way to unpredictable or controllable. The rovers are touted as autonomous robots capable of navigating around obstacles and avoiding hazardous terrain, but they can't do anything without specific orders from home, not even roll or climb off the lander. There is such a profound gap between the public's perception of the state-of-the-art of AGI and the reality of AGI research that society is in for a major disruption. Here is an open question for everyone on this email list: What do you think some of the real world effects on society will be after the development of AGI? Mike Deering. To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] The emergence of probabilistic inference from hebbian learning in neural nets
Ben, you haven't given us an update on how things are going with the Novamente A.I. engine lately. Is this because progress has been slow and there is nothing much to report, or you don't want to get peoples hopes up while you are still so far from being done, or that you want to surprise us one day with, "Hey guys, guess what? The Singularity has arrived!" To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] request for feedback
Arnoud, not exactly theanthropic argument: Conceptual necessity - There is a concept out there which is the root of all reality. It is not a person, an entity, or a mind. It is a concept like the idea that circular logic doesn't prove your point or mutually contradictory percepts cannot both be true in a self consistent system. It's complicated, very. Kind of related to a corollary to entropy. Complicated dynamical systems generate cool stuff like self replicating elements and they generate multicellular systemic emergent behaviors. It's not chance; it's determination. Bosons, fermions, atoms, galaxies, stars, planets, DNA, cells, organisms, societies, information, computers, AGI's, the Singularity, it's all inevitable because of conceptual necessity. Mike Deering, Director,http://www.SingularityActionGroup.com To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] request for feedback
Arnoud, I don't know how much help this will be considering I am an amateur, like you. Your AGI system looks good to me. I think we will find, in time, that many different approaches to AGI will work, though some may be more efficient than others, and some may be easier for us to communicate with. Your system is a low level implementation without an initial high level architecture, which is supposed to emerge through learning. This may be possible butmay require a tremendous amount of computational resources. I don't know if you have read my own feeble attempt at AGI but it is complimentary to yours.http://home.mchsi.com/~deering9/sim_mod.html Mine is a high level architecture without a low level implementation. If I had the time and money I might try to integrate them. I'm in the same time crunch you are, wife,child, job. I too have gone through a Christian phase, just like Holland, and ended up with atheism, just like you. Although, I don't hold out much hope for your plan to create a super-intelligence and ask it, "What is the meaning of existence?" Many different highly intelligent people have come to completely contradictory conclusions regarding this question and I don't see how merely increasing the intelligencedecreases the number of theories capable of explaining the observations. It may eliminate some but also add new ones. Anyway, even though I share your lack of answers, I am not disturbed by it. I'm thinking that the reason we are here is not intelligent design or chance, but rather conceptual necessity. Well, if there is anything the SAG can do to help your AGI project, email me off-list at [EMAIL PROTECTED] Mike Deering, Director,http://www.SingularityActionGroup.com To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] Request for invention of new word
AND ? AND a collective-level conscious theater? How the heck does that work? Does the collective mind have control over the individual minds? If not, in what way is it different from just another of the individual minds? Are the individual minds (Novamentes)components of an overarching cognitive architecture? SuperNova, MetaNova, AlphaNova, BetaNova, La Costra Nova,
[agi] Doubling-time watcher - March 2003.
I didn't intend this to become a monthly advertisement for Dell, but if someone comes up with more bang-for-the-buck (BFTB) from someone else I would be very interested. The February 2003 most BFTB system ran $399, this month you have to spend a little more to get the best deal. $499 including Free shipping. Dell Dimension 2350 Series: Intel Celeron Processor at 1.80GHz Memory: 256MB DDR SDRAM Keyboard: Dell Quietkey Keyboard Monitor: New 17 in (16.0 in v.i.s., .27dp) E772 Monitor Video Card: Integrated Intel Extreme 3D Graphics Hard Drive: 30GB Value Hard Drive Floppy Drive and Additional Storage Devices: 3.5 in Floppy Drive Operating System: Microsoft Windows XP Home Edition Mouse: Dell 2-button scroll mouse Network Interface: Integrated 10/100 Ethernet Modem: 56K PCI Data/Fax Modem CD or DVD Drive: 48x Max CD-ROM Drive Sound Card: Integrated Audio Speakers: New Harman Kardon HK-206 Speakers Bundled Software: WordPerfect Productivity Pack with Quicken New User Edition Digital Music: Dell Jukebox powered by MUSICMATCH Digital Photography: Dell Picture Studio Image Expert Standard Limited Warranty, Services and Support Options: 1Yr Ltd Warr plus 1Yr At-Home Service + 90Days Dell SecurityCenter (McAfee) Internet Access Services: 6 Months of EarthLink Internet Access FREE! Lexmark X75 Inkjet Printer After we have a few more data points we can discuss how best to graph the power/price function as it applies specifically to the AGI application. Mike Deering, Director www.SingularityActionGroup.com --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: [agi] swarm intellience
Ants by Daniel Hoffman Theirs is a perfection of pure form.Nobody but has his proper place and knows it.Everything they do is functional.Each foray in a zigzag lineEach prodigious liftingOf thirty-two times their own weightEach excavation into the earth's coreEach erectionOf a crumbly parapetted tower- None of these feats is a private pleasure,None of them doneFor the sake of the skill alone- They've got a going concern down there,A full egg-hatcheryA wet-nursery of aphidsA trained troop of maintenance engineersSanitation expertsA corps of huntersAnd butchersAn army A queenEachIs nothing without the others, each being a partOf something greater than all of them put togetherA purpose which none of them knowsSince each is only The one thing that he does. There isA true consistencyToward which their actions tend.The ants have bred and inbred to perfection.The strains of their genes that survive survive.Every possible contingencyHas been foreseen and written into the plan. Nothing they do will be wrong.
[agi] doubling time watcher.
Unless Ben thinks it would not be appropriate for this list, I would like to start a "doubling time" watcher monthly posting of retail computer pricesfor purposes of establishing a historical record so that questions of doubling time can be grounded in current data. My choice of category is "most bang for the buck" complete system from a major retailer or manufacturer. Usually this will be their lowest priced system, as upgrades generally cost more than the differential computational value they add. Anyone that would like to post a different category, well, you can never have too much data. My selection for "most bang for the buck" category for 2/18/03 is: Dell Dimension 2350 Series Processor: Celeron 1.7 GHz Memory: 128 MB Hard Drive: 60 GB Monitor: 15 inch CD: 48 speed Floppy drive: Y Keyboard: Y Mouse: Y GraphicsCard: Extreme 3D Graphics OS: Windows XP (HOME) Speakers: Y Sound card: Y Ethernet: Y Modem: Y Software: WordPerfect, Quicken. Price: $399 I might get one of these for my wife so she will stay off mine. We are a poor one computer family. Mike Deering. www.SingularityActionGroup.com ---new website.
Re: AGI Complexity (WAS: RE: [agi] doubling time watcher.)
Billy, I agree that AGI is a complicated architecture of hundreds of separarate software solutions. But all of these solutions have utility in other software environments and progress is being made by tens of thousands of programmers each working on improving some little software function for some other purpose that they have no idea will someday be used in AGI. There is nothing truly unique about the functional building blocks of AGI, just the overall architecture. Having gone way out on a limb here, all you AGI experts can now start sawing. Mike Deering. www.SingularityActionGroup.com ---new website.
Re: [agi] doubling time revisted.
It is obvious that no one on this list agrees with me. This does not mean that I am obviously wrong. The division is very simple. My position: the doubling time has been reducing and will continue to do so. Their position: the doubling time is constant. This is not a question of philosophy but only of the data. What does the data show? If we had a stack of COMPUTER SHOPPER magazines for the past twenty years the question could be decided in short order. The drop in doubling time starts out very slowly. That is why it is not obvious yet. By the time it becomes obvious it will be too late. Mike Deering. www.SingularityActionGroup.com ---new website.
Re: Games for AIs (Was: [agi] TLoZ: Link's Awakening.)
This whole approach of successive games is interesting but let me suggest a different route to AI teaching. Borrow the biological model. Simulate simplified ecological environments. Start with a simple organism,perhaps a worm, in a simplified environment with obstacles, rewards, penalties, and other organisms (never alone). As the AI learns to master the contingencies of the environment gradually evolve the organism and the environment to more complex forms maintaining a contiguous logical path to the final human form. And if you are lucky and your algorithms are good one day your AI will look up at the simulated sky and scream, "I want to talk to whoever is in charge! And I want to know what the heck is going on!" Mike Deering.
Re: Games for AIs (Was: [agi] TLoZ: Link's Awakening.)
Ben, I think there would be advantages to a single continuously evolving environment rather than a series of disjointed game environments. And environments closely modeled on natural environments will naturally take care of the ordering of the lessons taught. Also this type of learning strategy will mold the AI into a form that will be easier to relate to than a less biocentric approach. And your suggestion to transition the environment and the AI into the real world is a natural advantage of this approach. Mike Deering.
