Re: AI and botnets Re: [agi] What is the complexity of RSI?
On Monday 01 October 2007 10:32:57 pm, William Pearson wrote: A quick question, do people agree with the scenario where, once a non super strong RSI AI becomes mainstream it will replace the OS as the lowest level of software? It does not to my mind make sense that for it to be layered on top Vista or linux and subject to their flaws and problems. And would you agree that AIs are less likely to be botnetted? Yes and no. At the lower levels, this would be like hygeine and medicine to them, and they would likely be more robust against simple viruses. But at the higher level, they would be susceptible to memetic infection, as everyone in this group has apparently been infected by the friendly-ai meme. The reason they would likely be susceptible is that they (and we) would be pretty much worthless if they(we) weren't. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48836258-61ebf4
Re: AI and botnets Re: [agi] What is the complexity of RSI?
A quick question, do people agree with the scenario where, once a non super strong RSI AI becomes mainstream it will replace the OS as the lowest level of software? For the system that it is running itself on? Yes, eventually. For most/all other machines? No. For the initial version of the AGI? No. And would you agree that AIs are less likely to be botnetted? By botnetted, do you mean taken over and incorporated into a botnet or do you mean composed of a botnet. Taken over is a real problem for all sorts of reasons. Being composed of multiple machines is what many people are proposing. In conclusion, thinking about the potential problems of an AGI is very highly dependent upon your assumptions. Amen. Developing, and finding a way to test, a theory of all types of intelligence should be the top priority of any person who wishes to reason about the potential problems, otherwise you are likely to be tilting at windmills, due to the sheer number of possible theories and the consequences of each. I believe that a theory of all types of intelligence is an intractably large problem -- which is normally why I don't get into discussions about the dangers of AGI (as opposed to the dangers of certain morality systems which I believe is tractable) -- though I will discuss certain specific intelligence proposals like Richard. Much of what is posted on this list is simply hot air based upon so many (normally hidden and unrealized) assumptions that it is useless. - Original Message - From: William Pearson [EMAIL PROTECTED] To: agi@v2.listbox.com Sent: Monday, October 01, 2007 10:32 PM Subject: Re: AI and botnets Re: [agi] What is the complexity of RSI? On 01/10/2007, Matt Mahoney [EMAIL PROTECTED] wrote: --- William Pearson [EMAIL PROTECTED] wrote: On 30/09/2007, Matt Mahoney [EMAIL PROTECTED] wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. Well it would always have the potential. But you are assuming it is implemented on standard hardware. I assume that is what most people are doing. People want computers to be more useful, which means more intelligent. I suppose an alternative is to genetically engineer humans with bigger brains. You do not have to go that far to get the AI to not be able to access all its own source. There are a number of scenarios where the dominant AI does not have easy access to its own source. A few quick definitions. Super strong RSI - A vingean-fiction type AI, that can bootstrap itself from nothing or simply reading the net and figure out ways to bypass any constraints we may place on it by hacking humans or discovering ways to manipulate physics we don't understand. Strong RSI - Expanding itself exponentially by taking over the internet, and then taking over robotic factories to gain domination over humans. Weak RSI - Slow experimental incremental improvement by the whole, or possibly just parts of the system independently. This is the form of RSI that humans exhibit if we do it at all. And by RSI, I mean two abilities of the system 1) It has to be able to move through the space of TMs that map the input to output. 2) It has to be able to move through the space of TMs that map the input and history to a change in the mechanisms for 1) and 2). All while maintaining a stable goal. A quick question, do people agree with the scenario where, once a non super strong RSI AI becomes mainstream it will replace the OS as the lowest level of software? It does not to my mind make sense that for it to be layered on top Vista or linux and subject to their flaws and problems. And would you agree that AIs are less likely to be botnetted? The scenarios for AGI not having full and easy access to its own, include: 1) Weak RSI is needed for AGI, as contended previously. So systems will be built to separate out good programs from bad. Memory accesses will be tightly controlled so that bad programs do not adversely affect useful programs. 2) An AGI might be created by a closed source company that believes in Trusted Computing, that builds on encryption in the hardware layer. 3) In order to make a system capable of being intelligent in real time, you may need vastly more memory bandwidth than current memory architectures are capable of. So you may need to go vastly parallel, or even down to cellular automata style computing. This would create huge barriers to trying to get all the code for the system. I think it is most likely 3 combined with 1. Even if only one of these is correct then we may well get past any major botnetting problem with strong recursive AI. Simply because AIs unable to read all their own code at a time will have been purchased quickly for their economic value and replaced vulnerable computers and thus reduced the number of bots for the net, and would be capable of policing the net by setting up honey pots etc. Especially
Re: AI and botnets Re: [agi] What is the complexity of RSI?
--- William Pearson [EMAIL PROTECTED] wrote: On 01/10/2007, Matt Mahoney [EMAIL PROTECTED] wrote: --- William Pearson [EMAIL PROTECTED] wrote: On 30/09/2007, Matt Mahoney [EMAIL PROTECTED] wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. Well it would always have the potential. But you are assuming it is implemented on standard hardware. I assume that is what most people are doing. People want computers to be more useful, which means more intelligent. I suppose an alternative is to genetically engineer humans with bigger brains. You do not have to go that far to get the AI to not be able to access all its own source. There are a number of scenarios where the dominant AI does not have easy access to its own source. For example, we do not have access to the source code for our brains. But if we are smart enough to figure out how to reproduce the behavior in silicon, then what is to stop AGI #1 from doing the same? -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48863234-c0ec9a
Re: AI and botnets Re: [agi] What is the complexity of RSI?
On 02/10/2007, Mark Waser [EMAIL PROTECTED] wrote: A quick question, do people agree with the scenario where, once a non super strong RSI AI becomes mainstream it will replace the OS as the lowest level of software? For the system that it is running itself on? Yes, eventually. For most/all other machines? No. Well that would be a potentially dangerous scenario. I wonder what assumptions underlie our beliefs in either direction. And would you agree that AIs are less likely to be botnetted? By botnetted, do you mean taken over and incorporated into a botnet or do you mean composed of a botnet. Taken over is a real problem for all sorts of reasons. Being composed of multiple machines is what many people are proposing. Yup, I did mean the former. Although memetic infection as Josh Storrs Hall mentioned is a possibility. Although they may be better at resisting some memetic infections than humans as more memes may conflict with their goals. For humans it doesn't matter what you believe too much as long as it doesn't interfere with you biological goal. In conclusion, thinking about the potential problems of an AGI is very highly dependent upon your assumptions. Amen. It would be quite an interesting and humorous exercise if we could develop an assumption code, like the geek codes of yore. Then we post that as our sigs and see exactly what was assumed for each post. Probably unworkable, but I may kick the idea around a bit. Developing, and finding a way to test, a theory of all types of intelligence should be the top priority of any person who wishes to reason about the potential problems, otherwise you are likely to be tilting at windmills, due to the sheer number of possible theories and the consequences of each. I believe that a theory of all types of intelligence is an intractably large problem -- which is normally why I don't get into discussions about the dangers of AGI (as opposed to the dangers of certain morality systems which I believe is tractable) -- though I will discuss certain specific intelligence proposals like Richard. Much of what is posted on this list is simply hot air based upon so many (normally hidden and unrealized) assumptions that it is useless. The best way I have come up with to try and develop a theory of intelligence is to say what it is not, by discarding systems that are not capable of what the human brain is capable of. For example, you can trivially say that intelligence is not a function, in the formal sense of the word. As in a function IO mapping does not change over time, and an intelligence must at least be able to remember something. Another example would be to formally define the rate we gain information when we hear telephone number once and can recall it shortly after. And then dismiss systems such as simple back prop ANN, which require many repetitions of the data to be learnt. Obviously neither of these apply to most AGI systems being developed, but more advanced theories would hopefully cull the possibilities down somewhat. And possibly allow us to discuss the affects of AI on society somewhat rationally. Will Pearson - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=49029469-b6c15e
Re: [agi] What is the complexity of RSI?
On Sunday 30 September 2007 09:24:24 pm, Matt Mahoney wrote: --- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: And detrimental mutations greatly outnumber beneficial ones. It depends. Eukaryotes mutate more intelligently than prokaryotes. Their mutations (by mixing large snips of DNA from 2 parents) are more likely to be beneficial than random base pair mutations. True enough -- but you wrote ... It would be a simple change for a hacker to have the program break into systems and copy itself with small changes. Note that to get from prokaryotes to eukaryotes took evolution a full billion years, the Archean eon, roughly 3.5-2.5 Ga. To get to the point where something like crossover happens (or any other way of searching the program space efficiently) you need a considerably more complex variational mechanism -- which may be thought of as an answer to your original question. Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48408717-3fb145
Re: AI and botnets Re: [agi] What is the complexity of RSI?
--- William Pearson [EMAIL PROTECTED] wrote: On 30/09/2007, Matt Mahoney [EMAIL PROTECTED] wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. Well it would always have the potential. But you are assuming it is implemented on standard hardware. I assume that is what most people are doing. People want computers to be more useful, which means more intelligent. I suppose an alternative is to genetically engineer humans with bigger brains. -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48441303-80e55b
Re: [agi] What is the complexity of RSI?
--- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: On Sunday 30 September 2007 09:24:24 pm, Matt Mahoney wrote: --- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: And detrimental mutations greatly outnumber beneficial ones. It depends. Eukaryotes mutate more intelligently than prokaryotes. Their mutations (by mixing large snips of DNA from 2 parents) are more likely to be beneficial than random base pair mutations. True enough -- but you wrote ... It would be a simple change for a hacker to have the program break into systems and copy itself with small changes. Note that to get from prokaryotes to eukaryotes took evolution a full billion years, the Archean eon, roughly 3.5-2.5 Ga. To get to the point where something like crossover happens (or any other way of searching the program space efficiently) you need a considerably more complex variational mechanism -- which may be thought of as an answer to your original question. So you are arguing that RSI is a hard problem? That is my question. Understanding software to the point where a program could make intelligent changes to itself seems to require human level intelligence. But could it come sooner? For example, Deep Blue had less chess knowledge than Kasparov, but made up for it with brute force computation. In a similar way, a less intelligent agent could try millions of variations of itself, of which only a few would succeed. What is the minimum level of intelligence required for this strategy to succeed? -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48443654-267779
Re: [agi] What is the complexity of RSI?
Matt Mahoney wrote: --- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: ... So you are arguing that RSI is a hard problem? That is my question. Understanding software to the point where a program could make intelligent changes to itself seems to require human level intelligence. But could it come sooner? For example, Deep Blue had less chess knowledge than Kasparov, but made up for it with brute force computation. In a similar way, a less intelligent agent could try millions of variations of itself, of which only a few would succeed. What is the minimum level of intelligence required for this strategy to succeed? -- Matt Mahoney, [EMAIL PROTECTED] Recursive self improvement, where the program is required to understand what it's doing seems a very hard problem. If it doesn't need to understand, but merely optimize some function, then it's only a hard problem...with a slow solution. N.B.: This may be the major difference between evolutionary programming and seed AI. We appear, in our history, to have evolved many approached to causing evolutionary algorithms to work better (for the particular classes of problem that we faced...bacteria faced different problems and evolved different solutions). The most recent attempt has involved understanding *parts* of what we are doing. But do note that not only chimpanzees, but also most humans, have extreme difficulty in acting in their perceived long term best interest. Ask any dieter. Or ask a smoker who's trying to quit. Granted that an argument from these are the solutions found by evolution isn't theoretically satisfying, but evolution has a pretty good record of finding good enough solutions. Probably the best that can be achieved without understanding. (It's also bloody and inefficient...but no better solution is known.) - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48484304-a8ef96
Re: [agi] What is the complexity of RSI?
On Monday 01 October 2007 11:41:35 am, Matt Mahoney wrote: So you are arguing that RSI is a hard problem? That is my question. Understanding software to the point where a program could make intelligent changes to itself seems to require human level intelligence. But could it come sooner? For example, Deep Blue had less chess knowledge than Kasparov, but made up for it with brute force computation. In a similar way, a less intelligent agent could try millions of variations of itself, of which only a few would succeed. What is the minimum level of intelligence required for this strategy to succeed? I'm saying that RSI is the same thing as real intelligence. (note that someone in this discussion has called any kind of improvement at all RSI -- which makes the phrase meaningless. The Recursive part means it's not a wind-up toy -- after it improves itself, that mind can improve ITself, etc.) RSI AI has got to be somewhere near human level. If it were too much lower, we would be well above it and more obviously self-improving than we are (e.g. old people would learn much faster than young ones...) If we're too far below the RSI level, we can't make one at all (building an RSI qualifies you as an RSI). So what me worry? But I think we're close enough to building one that we can assume that's not true either. So take out the extraneous crap from the human mental architecture (sex, etc) and there you have it. Clarification, please -- suppose you had a 3-year-old equivalent mind, e.g. a working Joshua Blue. Would this qualify, for your question? You have a mind with the potential to grow into an adult-human equivalent, but it still needs years of nurturing, education, and in particular it still needs to learn the corpus of a given human culture, which would be external to it narrowly defined. ? Josh - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48558363-14544a
Re: [agi] What is the complexity of RSI?
--- Russell Wallace [EMAIL PROTECTED] wrote: On 9/30/07, Matt Mahoney [EMAIL PROTECTED] wrote: What would be the simplest system capable of recursive self improvement, not necessarily with human level intelligence? What are the time and memory costs? What would be its algorithmic complexity? Depends on what metric you use to judge improvement. If you use length, a two byte program on some microprocessors can expand itself until it runs out of memory. Intelligence isn't a mathematical function, so if that was your intended metric the answer is category error. The rest of your post suggests your intended metric is ability to spread as a virus on the Internet, in which case complexity and understanding are baggage that would be shed, viruses can't afford brains; the optimal program for that environment would remain small and simple. 1. An intelligent worm downloads various versions of Flash players, runs the code through a debugger, discovers a previously unknown buffer overflow, constructs a specially crafted video containing code to connect to a rogue server it previously had infected, and uploads the video to YouTube. 2. An intelligent worm probes routers across the Internet for weak passwords and a list of known vulnerabilities using standard tools. It finds a vulnerable router and monitors traffic. When it finds a DNS request for windowsupdate.microsoft.com it replies with the IP address of a rogue server it had previously infected. Every Windows based PC served by the router is automatically updated with a trojaned version of Windows. 3. An intelligent worm monitoring my posts on various data compression blogs knows that I benchmark compression software. It crafts an email with the forged return address of a well known compression developer supposedly containing a new version of a program he just wrote. Of course there are methods for defending against attacks like authentication, encryption, firewalls, user mode execution, virus scanners, intrusion detection systems, and most importantly, user knowledge. None of these are perfect. Many attacks by an intelligent worm could be stopped using current techniques. The problem is that an intelligent RSI worm might be millions of times faster than a human once it starts replicating. It could saturate the Internet with attacks faster than we could build defenses against them. My question is whether the Internet has enough computational power to implement an intelligent worm? By intelligent, I mean capable of discovering new attacks in software faster than humans can fix the code, something no virus or worm can currently do. The attacks might not be as sophisticated as the ones I described. Also, keep in mind that the worm will be distributed over millions of computers, each of which does not need to do a whole lot of computation. -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48566597-053bd5
Re: [agi] What is the complexity of RSI?
On Mon, Oct 01, 2007 at 12:48:00PM -0700, Matt Mahoney wrote: The problem is that an intelligent RSI worm might be millions of times faster than a human once it starts replicating. Yes, but the proposed means of finding it, i.e. via evolution and random mutation, is hopelessly time consuming. e.g. evolution of prokaryotes to humans took a billion years, despite being massively parallel. Seems to me that running evolutionary algos on he inernet wll take similar time-scales. However, once you have evolved humans, you can side-step evolution, and start engineering instead. Much faster that way: a russian can design a virus faster than an evolutionary algo can find one. (the russian might use an evolutionary algo in thier toolkit, of course) So the real question is what is the minimal amount of intelligence needed for a system to self-engineer improvments to itself? Some folks might argue that humans are just below that threshold. --linas - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48582803-2ecccb
Re: [agi] What is the complexity of RSI?
So the real question is what is the minimal amount of intelligence needed for a system to self-engineer improvments to itself? Some folks might argue that humans are just below that threshold. Humans are only below the threshold because our internal systems are so convoluted and difficult to change. Clearly most people on this list believe that the system of humans + programmable machines is above the threshold -- and it's only a matter of time until we reach a serious inflection point. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48585796-ccaf2c
Re: [agi] What is the complexity of RSI?
Mark Waser wrote: So the real question is what is the minimal amount of intelligence needed for a system to self-engineer improvments to itself? Some folks might argue that humans are just below that threshold. Humans are only below the threshold because our internal systems are so convoluted and difficult to change. And because we lack the cultural knowledge of a theory of intelligence. But are probably quite capable of comprehending one. -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48595571-b0508a
Re: [agi] What is the complexity of RSI?
--- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: Clarification, please -- suppose you had a 3-year-old equivalent mind, e.g. a working Joshua Blue. Would this qualify, for your question? You have a mind with the potential to grow into an adult-human equivalent, but it still needs years of nurturing, education, and in particular it still needs to learn the corpus of a given human culture, which would be external to it narrowly defined. ? It would have to develop to the point where it could learn to write and debug software. That would probably require more computational power. But it won't necessarily take years. It could take seconds if the training data is already available and the hardware is fast enough. Understanding software is equivalent to compressing it. Programs that are useful, bug free, and well documented have higher probability. An intelligent model capable of RSI would compress these programs smaller. We do not seem to be close to this goal. It seems to be harder than compressing text. A 3 year old understands language at the level of the best text compressors, but even many adults have no understanding of software. -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48604471-6e6392
Re: [agi] What is the complexity of RSI?
On Monday 01 October 2007 05:47:25 pm, Matt Mahoney wrote: Understanding software is equivalent to compressing it. Programs that are useful, bug free, and well documented have higher probability. An intelligent model capable of RSI would compress these programs smaller. We do not seem to be close to this goal. It seems to be harder than compressing text. A 3 year old understands language at the level of the best text compressors, but even many adults have no understanding of software. Well documented may be *better*, but it sure isn't higher probability! ... and the same goes for bug free. :-) Automatic programming has been called AI-complete by some top AI people. VHLLs have hit a wall mostly because the higher-level they are, the fewer people can use them; but an ultimate VHLL would be equivalent to compressing a program. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48651685-989a6e
Re: AI and botnets Re: [agi] What is the complexity of RSI?
On 01/10/2007, Matt Mahoney [EMAIL PROTECTED] wrote: --- William Pearson [EMAIL PROTECTED] wrote: On 30/09/2007, Matt Mahoney [EMAIL PROTECTED] wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. Well it would always have the potential. But you are assuming it is implemented on standard hardware. I assume that is what most people are doing. People want computers to be more useful, which means more intelligent. I suppose an alternative is to genetically engineer humans with bigger brains. You do not have to go that far to get the AI to not be able to access all its own source. There are a number of scenarios where the dominant AI does not have easy access to its own source. A few quick definitions. Super strong RSI - A vingean-fiction type AI, that can bootstrap itself from nothing or simply reading the net and figure out ways to bypass any constraints we may place on it by hacking humans or discovering ways to manipulate physics we don't understand. Strong RSI - Expanding itself exponentially by taking over the internet, and then taking over robotic factories to gain domination over humans. Weak RSI - Slow experimental incremental improvement by the whole, or possibly just parts of the system independently. This is the form of RSI that humans exhibit if we do it at all. And by RSI, I mean two abilities of the system 1) It has to be able to move through the space of TMs that map the input to output. 2) It has to be able to move through the space of TMs that map the input and history to a change in the mechanisms for 1) and 2). All while maintaining a stable goal. A quick question, do people agree with the scenario where, once a non super strong RSI AI becomes mainstream it will replace the OS as the lowest level of software? It does not to my mind make sense that for it to be layered on top Vista or linux and subject to their flaws and problems. And would you agree that AIs are less likely to be botnetted? The scenarios for AGI not having full and easy access to its own, include: 1) Weak RSI is needed for AGI, as contended previously. So systems will be built to separate out good programs from bad. Memory accesses will be tightly controlled so that bad programs do not adversely affect useful programs. 2) An AGI might be created by a closed source company that believes in Trusted Computing, that builds on encryption in the hardware layer. 3) In order to make a system capable of being intelligent in real time, you may need vastly more memory bandwidth than current memory architectures are capable of. So you may need to go vastly parallel, or even down to cellular automata style computing. This would create huge barriers to trying to get all the code for the system. I think it is most likely 3 combined with 1. Even if only one of these is correct then we may well get past any major botnetting problem with strong recursive AI. Simply because AIs unable to read all their own code at a time will have been purchased quickly for their economic value and replaced vulnerable computers and thus reduced the number of bots for the net, and would be capable of policing the net by setting up honey pots etc. Especially if they become the internet routers. In conclusion, thinking about the potential problems of an AGI is very highly dependent upon your assumptions. Developing, and finding a way to test, a theory of all types of intelligence should be the top priority of any person who wishes to reason about the potential problems, otherwise you are likely to be tilting at windmills, due to the sheer number of possible theories and the consequences of each. Will Pearson - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48760741-25aaa6
Re: [agi] What is the complexity of RSI?
The simple intuition from evolution in the wild doesn't apply here, though. If I'm a creature in most of life's history with a superior mutation, the fact that there are lots of others of my kind with inferior ones doesn't hurt me -- in fact it helps, since they make worse competitors. But on the internet, there are intelligent creatures gunning for you, and a virus or worm lives mostly by stealth. Thus your stupider siblings are likely to give your game away to people your improvement might otherwise have fooled. And detrimental mutations greatly outnumber beneficial ones. On Sunday 30 September 2007 06:05:55 pm, Matt Mahoney wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. It would be a simple change for a hacker to have the program break into systems and copy itself with small changes. Some of these changes would result in new systems that were more successful at finding vulnerabilities, reproducing, and hiding from the infected host's owners, even if that was not the intent of the person who launched it. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48322593-19e4a6
Re: [agi] What is the complexity of RSI?
On 9/30/07, Matt Mahoney [EMAIL PROTECTED] wrote: What would be the simplest system capable of recursive self improvement, not necessarily with human level intelligence? What are the time and memory costs? What would be its algorithmic complexity? Depends on what metric you use to judge improvement. If you use length, a two byte program on some microprocessors can expand itself until it runs out of memory. Intelligence isn't a mathematical function, so if that was your intended metric the answer is category error. The rest of your post suggests your intended metric is ability to spread as a virus on the Internet, in which case complexity and understanding are baggage that would be shed, viruses can't afford brains; the optimal program for that environment would remain small and simple. - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48323166-bd950b
Re: [agi] What is the complexity of RSI?
--- J Storrs Hall, PhD [EMAIL PROTECTED] wrote: The simple intuition from evolution in the wild doesn't apply here, though. If I'm a creature in most of life's history with a superior mutation, the fact that there are lots of others of my kind with inferior ones doesn't hurt me -- in fact it helps, since they make worse competitors. But on the internet, there are intelligent creatures gunning for you, and a virus or worm lives mostly by stealth. Thus your stupider siblings are likely to give your game away to people your improvement might otherwise have fooled. In the same way that cowpox confers an immunity to smallpox. And detrimental mutations greatly outnumber beneficial ones. It depends. Eukaryotes mutate more intelligently than prokaryotes. Their mutations (by mixing large snips of DNA from 2 parents) are more likely to be beneficial than random base pair mutations. On Sunday 30 September 2007 06:05:55 pm, Matt Mahoney wrote: The real danger is this: a program intelligent enough to understand software would be intelligent enough to modify itself. It would be a simple change for a hacker to have the program break into systems and copy itself with small changes. Some of these changes would result in new systems that were more successful at finding vulnerabilities, reproducing, and hiding from the infected host's owners, even if that was not the intent of the person who launched it. -- Matt Mahoney, [EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244id_secret=48338251-885205