YouSaid · the spoken record

Marcus Hutter

lines on the record: 123
first: 2020-02-26
most recent: 2020-02-26
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“So, the major difference is that essentially all other approaches, they make strong assumptions. So in reinforcement learning, the Markov assumption is that the next state or next observation only depends on the previous observation and not the whole history, which makes, of course, the mathematics much easier rather than dealing with histories. Of course, they profit from it also because then you have algorithms which run on current computers and do something practically useful. But for General AI, all the assumptions which are made by other approaches, we know already now they're limiting.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“For the planning, well, we have UCT, which has also been used in Go. And at least it inspired me a lot to have this formal definition. And if you look at other fields, I always come back to physics because I have a physics background. Think about the phenomenon of energy. That was a long time a mysterious concept. And at some point it was completely formalized. And that really helped a lot. And I can point out a lot of these things which were first mysterious and vague. And then they have been rigorously formalized. Speed and acceleration has been confused, right? Until it was formally defined, there was a time like this. And people, you know, often don't have any background, still confused it. And this IX model or the intelligence definitions, which is sort of the dual to it, we come back to that later.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So if you have some choice to make, right? So, how should I evaluate my system if I can't do cross-validation? How should I do my learning if my standard regularization doesn't work well? So the answer is always this, we have a system which does everything that's ICSI. It's just completely in the ivory tower, completely useless from a practical point of view. But you can look at it and see, ah, yeah, maybe, you know, I can take some aspects. And, you know, instead of Kolmogorph complexity, let's just take some compressors which has been developed so far.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Every year, tens of frameworks are developed, which are just skeletons, and then pieces are missing. And usually these missing pieces turn out to be really, really difficult. And so this is completely and uniquely defined. And we can analyze that mathematically. And we have also developed some approximations. I can talk about that a little bit later. That would be sort of the top-down approach, like say for Neumann's mini-max theory, that's the theoretical optimal play of games. And now we need to approximate it, put heuristics in, prune the tree, blah, blah, blah, and so on. So we can do that also with our IXI model, but for general AI. It can also inspire those, and most of most researchers go bottom up, right? They have their systems, they try to make it more general, more intelligent. It can inspire in which direction to go.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So that's the reason why I toggled back and forth quite some while and even worked four and a half years in a company developing software, something completely unrelated. But then I had this idea about the ICC model. And so what it gives you, it gives you a gold standard. So I have proven that this is the most intelligent agent which anybody could Built in quotation mark because it's just mathematical and you need infinite compute. But this is the limit. And this is completely specified. It's not just a framework.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, so, and the reason why I didn't settle, I mean, this thought about, you know, once you have solved AGI, it solves all kinds of other, not just the theory of every problem, but all kinds of use, more useful problems to humanity is very appealing to many people. And this thought also. I was quite disappointed with the state of the art of the field of AI. There was some theory about logical reasoning, but I was never convinced that this will fly. And then there was this more holistic approaches with neural networks. And I didn't like these heuristics. And also I didn't have any good idea myself.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So when I started in the field, I was always interested in two things. One was AGI. The name didn't exist then, what called General AI or Strong AI, and the physics CR of everything. So I switched back and forth between computer science and physics quite often.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Like with a playing chess, right? You do this mini max. In this case here, do you expect the max based on the solomon of distribution? You propagate back and then An action falls out Action which maximizes the future expected reward under Solomon of distribution, and then you just take this action.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Asyptotic means you can prove, for instance, that in the long run, if the agent acts long enough, then it performs optimal or some nice thing happens. But you don't know how fast it converges. So it may converge fast, but we're just not able to prove it because it's a difficult problem. Or maybe there's a bug in the model so that it's really that slow. So that is what asymptotic means sort of eventually, but we don't know how fast. If I give the agent a fixed horizon m, then I cannot prove asymptotic results, right? So I mean, sort of if it dies in 100 years, Then in 100 years it's over. I cannot say eventually. So this is the advantage of the discounting that I can prove asymptotic results.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“finite data results so you have so and so much data then you lose so and so much so the deterioration is really great with the IXE model with the planning part many results are only asymptotic which well this is”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“But I introduced the so-called near harmonic horizon, which goes down with one overt rather than exponential in t, which produces an agent which effectively looks into the future proportional to each age. So if it's five years old, it plans for five years. If it's 100 years old, it then plans for 100 years. It's a little bit similar to humans too, right? My children don't plan ahead very long, but then we get adults, we play ahead more longer. Maybe when we get very old, I mean, we know that we don't live forever, you know, maybe then our horizon shrinks again.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Then the standard discounting is so called geometric discounting, so a dollar today is about worth as much as $1.05 tomorrow. So if you do the so-called geometric discounting, you have introduced an effective horizon. So the agent is now motivated to look ahead a certain amount of time effectively. It's like a moving horizon. And for any fixed effective horizon, there is a problem to solve which requires larger horizons. So if I look ahead, you know, five time steps, I'm a terrible chess player, right? I need to look ahead long. If I play go, I probably have to look ahead even longer. So for every problem, for every horizon, there is a problem which this horizon cannot solve.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Then catch up with the same expected reward. And, you know, think about yourself or, you know, or maybe some friends or so. If they knew they lived forever, why work hard now? Just enjoy your life and then catch up later. So that's another problem with the infinite horizon. And you mentioned, yes, we can go to discounting.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So having a hard horizon at 100 years is just for simplicity of discussing the model and also sometimes the math is simple. But there are lots of variations. It's actually quite interesting parameter. There's nothing. Problematic about it, but it's very interesting. So, for instance, you think no, let's let the parameter m tend to infinity, right? You want an agent which lives forever, right? If you do it naively, you have two problems. First, the mathematics breaks down because you have an infinite reward sum, which may give infinity. And getting reward 0.1 in the time step is infinity. And giving reward 1 every time step is infinity, so equally good. Really, what we want. Other problem is that if you have an infinite life, you can be lazy for as long as you want for 10 years.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so you have a planning problem up to Horizon M, and that's exponential time in the Horizon M, which is, I mean, it's computable, but intractable. I mean, even for chess, it's already intractable to do that exactly. And for Go.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So if you have a very wrong model, it's very unlikely that this model is true. And so this very small number. So even if the model is simple, it gets penalized by that. And what you do is then you take just the sample. This is the average over it. And this gives you a probability distribution. Universal distribution osolomen of distribution.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I'm trying to understand. So, what he does it, so in the simplest case, I said take the shortest program describing your data, run it, have a prediction which would be deterministic. But you should not just take a shortest program, but also consider the longer ones, but keep it lower a priori probability. So in the Bayesian framework, you say a priori any distribution. Which is a model or a stochastic program has a certain a priori probability which is 2 to the minus and y to the minus length of this program so longer programs are punished a priori and then you multiply it with the so-called likelihood function which is as the name suggests is how likely is this model given the data at hand”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“But the question is on which probability distribution do you base that? If I have the true probability distribution, like say I play Begamin, right? There's dice and there's certain randomness involved. I can calculate probabilities and feed it in the expectimax or the sequential decision tree, come up with the optimal decision if I have enough compute. But for the real world, we don't know that. What is the probability the driver in front of me breaks? I don't know. Depends on all kinds of things. especially new situations, I don't know. So this is this unknown thing about prediction. And there's where Solomonov comes in. So what you do is in sequential decision tree, you just replace the true distribution, which we don't know by this universal distribution. I didn't explicitly talk about it, but this is used for universal prediction and plug it into the sequential decision mechanism. And then you get the best of both worlds.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Luckily, or maybe unluckily, for the theory, it becomes harder. The world is not always adversarial. So it can be, if there are humans even cooperative, or nature is usually, I mean, the dead nature is stochastic. Things just happen randomly, or I don't care about you. So what you have to take into account is the noise and not necessarily the reality. So you replace the minimum on the opponent's side by an expectation. which is general enough to include also adversarial cases. So now instead of a minimax strategy, you have an expectimax strategy. So far so good. So that is well known. It's called sequential decision theory.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“for M timestamps as there dies in sort of 100 years sharp that's just you know the simplest model to explain so it looks at the future reword sum and asks what is my action sequence or actually more precisely my policy which leads in expectation because I don't know the world to the maximum reward sum let me give you an analogy In chess for instance, we know how to play optimally in theory. It's just a mini max strategy. I play the move which seems best to me under the assumption that the opponent plays the move which is best for him, so best, so worst for me, and that assumption that I play again the best move. And then you have this expectimax three to the end of the game. And then you back propagate and then you get the best possible move. So that is the optimum strategy, which for Neumann already figured out a long time ago for playing adversarial games.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Conditioned on actions, so even if you influence the environment, but prediction is not all we want to do, right? We also want to act really in the world. And the question is how to choose the actions. And we don't want to greedily choose the actions. Just what is best in the next time step. And first I should say, you know, what is, you know, how do we measure performance? So we measure performance by giving the agent reward. That's the so-called reinforcement learning framework. So every time step you can give it a positive reward or negative reward or maybe no reward. It could be a very scarce, right? Like if you play chess just at the end of the game, you give plus one for winning or minus one for losing. So in the IXI framework, that's completely sufficient. So occasionally you give a reward signal and you ask the agent to maximize reward, but not greedily sort of, you know, the next one, next one, because that's very bad in the long run if you're greedy. But over the lifetime of the agent, so let's assume the agent lives.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“That's very important, the whole history from birth sort of the agent, and we can come back to that also while this is important. Often, you know, in RL, you have MDPs, macro decision processes, which are much more limiting. Okay, so now we can predict”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“you take the next action you don't care about predicting it because you're doing it and then you get the next observation and you want well before you get it you want to predict it again based on your past action and observation sequence you just condition extra on your actions there's an interesting alternative that you also try to predict your own actions if you want”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So let's go to the actions now. But actually good that you asked usually I skipped this part, although that is also a minor contribution which I did, so the action part, but I usually sort of just jump to the decision part. So let me explain to the action part now. Thanks for asking. So you have to modify it a little bit. By now not just predicting a sequence which just comes to you, but you have an observation, then you act somehow, and then you want to predict the next observation based on the past observation and your action.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Task which is unpredictable, like you know, you have fair coin flips. I cannot predict the next fair coin flip. What Solomonov does is says, okay, next head is probably 50%. It's the best you can do. So if something is unpredictable, Solomonov will also not magically predict it. But if there is some pattern and predictability, then Solomonov induction will figure that out eventually and not just eventually, but rather quickly. And you can have proof convergence rates. Whatever your data is. So that is pure magic in a sense. What's the catch? Well, the catch is that is not computable, and we come back to that later. You cannot just implement it even with Google Resources here and run it and predict the stock market and become rich. I mean, Ray Solomonov already tried it at the time.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So the simplest form of prediction is that you just have data which you passively observe and you want to predict what happens without interfering. I said, weather forecasting, stock market, IQ sequences, or just Anything okay, and Solomon's theory of induction based on compression. So you look for the shortest program which describes your data sequence and then you take this program, run it, it reproduces your data sequence by definition, and then you let it continue running, and then it will produce some predictions. And you can rigorously prove that for any This is essentially the best possible predictor. Of course, if there's a prediction task”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“How do you think about it? The important part, but it is technically important, but at this stage we can just think about predicting, say, stock market data, whether data or IQ sequences, one, two, three, four, five, what comes next. So, of course, our actions... Affect what we're doing, but I come back to that in a second”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So it consists essentially of two parts. One is the learning and induction and prediction part, and the other one is the planning part. So let's come first to the learning induction prediction part, which essentially I explained already before. So what we need for any agent to act well is that it can somehow predict what happens. I mean, if you have no idea what your actions do, how can you decide which actions are good or not? So you need to have some model of what your actions affect. So what you do is you have some experience. You build models like scientists of your experience. Then you hope these models are roughly correct. And then you use these models for prediction.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Similarly, there's a Chinese word aishi, also written like Aixi, if you transcribe that to Pinjin. And the final one is there is AI crossed with induction because going.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I was very surprised and happy about that. And I looked it up, saw it, this is Catalan language, and it means with some interpretation, oh, that's it, that's the right thing to do, Horica.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I'm just kidding. I have some more interpretations. So at some point, maybe. Five years ago or 10 years ago, I discovered in Barcelona, it was on a big church that was in stone engraved some text. And the word Ixia appeared there a couple of times.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“The first question is usually how It's pronounced, but finally I put it on the website how it's pronounced, and you figured it out. Name comes from AI artificial intelligence, and the XI is the Greek letter Xi, which are used for Solomonov's distribution, for quite stupid reasons, which I'm not willing to repeat here in front of camera. So it just happened to be more or less arbitrary at Joseph Xi, but it also has nice other interpretations. So their actions and perceptions in this model, right? An agent has actions and perceptions. And over time, so this is A index I X index I. So this is the action at time I and then followed by perception.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“The same as complexity or compression length. So the NLP community develops new systems and then they measure the compression length and then they have ranking and leaks because there's a strong correlation between compressing well and then the system is performing well at the task at hand. It's not perfect, but it's good enough for them as an intermediate aim.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I said, you know, the tuting test is not as bad as some people believe But what is Useful about the Turing test, it gives us no guidance how to develop these systems in the first place. Of course, we can develop them by trial and error and do whatever and then run the test and see whether it works or not. But a mathematical definition of intelligence gives us an objective which we can then analyze by theoretical tools or computational. you know maybe even prove how close we are and we will come back to that later with this ICSI model so I mentioned the compression right so in natural language processing they have achieved amazing results and one way to test this of course you know take the system you train it and then you you know see how well it performs on the task but a lot of performance measurement is done by so-called perplexity”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, it's quite impressive. And then Google has developed MENA, right? Just recently, that's an open domain conversational bot, just a couple of weeks ago, I think.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Deception, right, which is much harder. And on the other hand, they say it's too weak because it just maybe fakes emotions or intelligent behavior. It's not real. But I don't think that's the problem or a big problem. So if you would pass the Turing test, so conversation of a terminal with a bot for an hour or maybe a day or so, and you can fool a human into not knowing whether this is a human or not, so that it's the Turing test. I would be truly impressed. And we have this annual competitions in Lebner. Price, and I mean, it started with Eliza. That was the first conversational program. And what is it called? The Japanese Mitsuku or so. That's the winner of the last couple of years.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, the Turing test has been criticized a lot, but I think it's not as bad as some people think. Some people think it's too strong. So it tests not just for a system to be intelligent, but it also has to fake human.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Proved you So yes, to answer your question, yes, I believe that general intelligence is possible. And it also, I mean, it depends how you define it. Do you say AGI, general intelligence, artificial intelligent intelligence, only refers to if you achieve human level or is sub-human level, but quite broad? Is it also general intelligence? So we have to distinguish, or it's only super human intelligence, general artificial intelligence.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“What I was really happy about, I'm a terrible chess player, but I like Queen Gumby. And Alpha Zero figured out that this is the best opening.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Then also go. And I mean, yes, they're both games, but they're quite different games. And, you know, don't feed them the rules of the game. And the most remarkable thing, which is still a mystery to me, that usually for any decent chess program, I don't know much about Go, you need opening books and endgame tables and so on. Nothing in there, nothing was put in there.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, we are sort of getting there and on a small scale we are already there, the wide range of environments still missing, but we have self-driving cars, we have programs which play Go and chess, we have speech recognition. So it's pretty amazing, but you can, you know, these are narrow environments. If you look at alpha zero, that was also developed by DeepMind, I mean, not famous with Alpha Go and then came alpha zero a year later, there was truly amazing. So reinforcement learning algorithm, which is able just by self-play to play chess.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“But they are in a much more narrow environment, right? I mean, you just, you know, have a little bit of air pollutions and these trees die and we can adapt, right? We build houses, we build filters. Geoengineering”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“No, but we have an alternative definition instead of performing value, you can just replace it by goal. So intelligence measures and agents' ability to achieve goals in a wide range of environments. That's more or less equal.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“You realize that most anti-I claim all of the other traits, at least of rational intelligence, which we usually associate with intelligence, are emergent phenomena from this definition, like creativity, memorization, planning, knowledge. You all need that in order to perform well in a wide range of environments. So you don't have to explicitly mention that in a definition.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Which many people would say, but I'm not modest in this question. So the informal version, which I worked out together with Shane Lack, who co-founded the Mind, is that intelligence measures and agents' ability to perform well in a wide range of environments. So that doesn't sound very impressive. And these words have been very carefully chosen. And there is a mathematical theory behind that, and we come back to that later. And if you look at this definition by itself, it seems like, yeah, okay, but it seems a lot of things are missing. But if you think it through,”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, it definitely is frontification intelligence, and it's quite surprising that it's, I can't say easy, I mean, physicists worked really hard to find these theories, but apparently it was possible for human minds to find these simple rules in the universe. It could have been different, right?”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“If you take resource limitations into account, there's, for instance, the field of pseudo random numbers. And these are random numbers. So these are deterministic sequences, but no algorithm which is fast. Fast means runs in polynomial time can detect that it's actually deterministic. So we can produce interesting, I mean, random numbers maybe not that interesting, but just an example. We can produce complex looking data. And we can then prove that no fast algorithm can detect the underlying pattern.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Wait until the halt give an output, compare it to your data, and if some of these programs produce the correct data, then you stop and then you have already a sum program. It may be a long program because it's faster. And then you continue and you get shorter and shorter programs until you eventually find the shortest program. The interesting thing you can never know whether the shortest program because there could be an even shorter program which is just even slower. We just have to wait, yeah. But asymptotically, and actually after finite time, you have the shortest program. So this is a theoretical but completely impractical way of finding the underlying structure in every data set. And that was a solomorph induction does and Kolmogorov complexity. In practice, of course, we have to approach the problem more intelligently.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, in principle, yes. So, I mean, in principle, what you can do is you take any data set, you take these fractals, or you take whatever your data set, whatever you have, say a picture of Conveys, Game of Life, and you run through all programs, you take a program size one, two, three, four, and all these programs, run them all in parallel in so-called dovetailing fashion, give them computational resources, first one, 50%, second one, half resources, and so on and let them run.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“To get these fractals on the screen, and it was mesmerized, and much later. So I returned to this every couple of years. And then I tried to understand what is going on. And you can understand a little bit. So I tried to Derive the locations, there are these circles and the apple shape. And then you have smaller Mandelbrot sets recursively in this set. And there's a way to mathematically, by solving high-order polynomials, to figure out where these centers are and what size they are approximately. And by sort of mathematically approaching this problem, you slowly get a feeling of why things are like they are and that sort of isn't, you know. First step to understanding why this rich phenomena.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source