YouSaid · the spoken record

Eliezer Yudkowsky

lines on the record: 301
first: 2023-04-06
most recent: 2023-04-06
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

“I mean, yes, part of why I'm a little bit skeptical of the story where people are just infinitely replaceable is that I tried really, really, really hard to create a new crop of people who could do all the stuff I could do to take over. Because, you know, I knew my health was not great and getting worse. I tried really, really hard to replace myself. I'm not sure where you look to find somebody else who tried that hard to replace himself. I tried, I really, really tried.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“But maybe you'll just look at the next effort branch over and there's just some kind of empty space that someone steps up to fill even if then they don't end up with a lot of obvious neighbors. Maybe the world where I died in childbirth is just, you know, like pretty much like this one. But I don't feel if. Somehow we live to hear the answer about that sort of thing from someone or something that can calculate it. That's not the way I bet. But if it's true, When I said no drama that did include the concept of I don't know. Trying to make the story of your planet be the story of you. If it all would have played out the same way, and that's what, and somehow I survived to be told that? I'll laugh and I'll cry and that will be the reality.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Looking around myself in that highly multidimensional space and not finding a ton of neighbors relative to ready to take over. And I I had, you know, four people, any one of whom could, you know, do like ninety nine percent of what I do or whatever. I might retire. I am tired. Albe wouldn't. Probably like marginal contribution of that fifth person is still pretty large I don't know. There's the question of, well, did you occupy a place in mind space? Did you occupy a place in social space? Did people not try to become Eliasar because they thought Eliasar already existed? And so I answer that. It's like, man, like, I don't think Eliasar already existing would have stopped me from trying to become Eliasar.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Hard and failing hard to replace myself that oh like yeah I could have maybe taken a shot at doing this person's job and he'd probably just never found anyone else who could take over his organization and maybe ask some other people and like nobody was willing and I didn't real you know that's that's his tragedy that he built something and now can't find anyone else to take it over and if I'd known that at the time I would not have you know I would have at least apologized And yeah, to me, it looks like people are not dense in the incredibly multidimensional space of people. There are too many dimensions and only eight billion people on the planet. The world is full of people who have no immediate neighbors. And problems that one person can solve, and then like other people cannot solve it in quite the same way. I don't think I'm unusual.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Outputting ninety percent of the work output. And, you know, this is actually also kind of not how things play out in a lot of places. Like Steve Jobs, dead, apparently couldn't find anyone else but Be the next Steve Jobs of Apple despite having really quite a lot of money with which to theoretically pay them. Maybe he didn't want to really want a successor. Maybe he wanted to be replaceable. I don't actually buy that, you know, based on how this has played out in a number of places. There was a person once who I met when I was younger who was like, had, you know, built something that built an organization. And he was like, hey, Alazard, you want to take this thing over? And I thought he was joking. And it didn't dawn on me until years later.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“That would be a pleasant fantasy for people who cannot abide the notion that history depends on small little changes or that people can really be different from other people. I've seen no evidence. But who knows what the alternate effort branches of earth is.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Like continuing to play out a video game, you know you're going to lose. Because that's all you have. If you wanted some deep wisdom for me, I don't have it. It's, I don't know, I don't know if it's what you'd expect, but it's like what I would expect it to be like, where what I would expect it to be like takes into account that, I don't know, like, Well, I guess I do have a little bit of wisdom. People imagining themselves in that situation raised in modern society, as opposed to raised on science fiction books written 70 years ago. Might will imagine themselves like acting out. Like, thing drama queens about it. The point of believing this thing is to be a drama queen about it and craft some story in which your emotions mean something. What I have in the way of culture is like planet's at stake, bear up, keep going. No”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Five years, I made most of my negative updates as five years ago. If anything, things have been taking longer to play out than I thought they would.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Not being able to exactly craft a message with perfect hindsight that will reach some people and not others. At that point, you might as well just be like, yeah, just invest in exactly the right stocks and exactly the right time and you can fund projects on your own without alerting anyone. If you keep fantasies like that aside, then I think that in the end, even if this world ends up having less time, it was the right thing to do rather than just like letting everybody sleepwalk into death and get a little later.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Maybe it's speeds up timelines. Maybe then people are like, ooh, ooh, exciting, exciting. I want to build it. I want to build it. Ooh, exciting. It has to be in my hands. I have to be the one to manage this danger. I'm going to run out and build it. Like, oh no, like if we don't invest in this company, like who knows what investors they'll have instead that will demand that they move fast'cause the profit mode, then of course they just like move anyways. And yeah, I if you sent me back in time, maybe I'd have a third option, but it seems to me that in terms of what one person can realistically manage in terms of like”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“And what is one supposed to do? Joanne remained silent? Should one let everyone walk directly into the whirling racer blades? If you sent me back in time, I'm not sure I could win this, but maybe I would be I would have some notion of like ah, like if you calculate the message in exactly this way, then like this group will not take away this message and you will be able to get this group of people to research on it without having this other group of people decide that it's excitingly dangerous and they want to rush forward on it. I'm not that smart. I am not that wise but what you are pointing to there is not a failure of ability to make predictions about AI it's That if you try to Call attention to a danger and not just have everybody walk directly into the world and razor blades carefree, no idea what's coming to them.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“These are two different questions. One is the question of like, who predicted that language models would scale? If they put it down in writing and if they said not just this loss function will go down, but also which capabilities will appear as that happens, then that would be quite interesting. That would be a successful scientific prediction. And if they then came forth and saying forth and said, this is the model that I used, this is what I predict about alignment, we could have an interesting fight about that. Second, there's the point that if you try to rouse your planet to give it any sense that it is in peril. There are the idiot disaster monkeys who are like oo, this sounds like if this is dangerous it must be powerful, right? I'm going to be like, be first to grab the poison banana.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I think they're enacting the ritual of the young optimistic scientist who charges forth with no ideas of the difficulties and is slapped down by harsh reality and then becomes a grizzled cynic who knows all the reasons why everything is so much harder than you knew before you had any idea of how anything really worked. And they're just like living out that life cycle and I'm trying to jump ahead to the endpoint.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Wait, wait, sorry, yeah, but like most updates are not this is going to be easier than you thought that sure has not been the history of the last 20 years from my perspective. Favorable updates. Favorable updates is like, yeah, like we went down this really weird side path where the systems are legibly alarming to humans and humans are actually alarmed at them and maybe we get more sensible global policy.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“My model no doubt has many errors the trouble the trick would be to An error someplace where that just makes everything work better. You know, usually when you're trying to build a rocket and your model of rockets is lousy, it doesn't cause the rocket to launch using half the fuel, go twice as far, and land twice as precisely on target as your calculations landed.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean, it sure has, like fifteen, twenty years ago I was talking about pulling off shit like coherent extrapolated volition with the first AI, which was actually a stupid idea even at the time. But you can see how much more hopeful everything looked back then. Back when there was AI that wasn't giant inscrutable matrices of floating point numbers.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Handcrafted system that learns, you just stack more layers. So like Hansen here, Yakowski here, reality there. would be my interpretation of what happened in the past and if you like Want to be like, well, who did better than that? It's people like Shane Legg and Guern Branwin, who look at the whole planet, you can find somebody who made better predictions than Elliez Yakowski. That's for sure. Are these people currently telling you that you're safe? No, no, they are not.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“It's hard, it is just like easier to predict the endpoint than it is to predict the paths. Don't think I've some people will claim to you that I've done poorly compared to others who try to predict things. I would dispute this. I think that the Hansen Yakowski Foom debate was won by Bern Branwen, but I do think that Guern Branwin is like well to the Idkowski side of Yudkowsky in the original Fum debate. Roughly, Hansen was like, you're going to have all these distinct handcrafted systems that incorporate lots of human knowledge specialized for particular domains, like handcrafted to incorporate human knowledge, not just run on giant data sets. I was like, you're going to have this carefully crafted architecture with a bunch of subsystems, and that thing is going to look at the data and not be like handcrafted the particular features of the data. It's going to learn the data. Then the actual thing is like, ha, you don't have this like...”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Not literally at the point where everybody falls over dead, probably at that point the AI rewrote the AI, and the losses declined not on the previous graph.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't think that GPT three to three point five to four was all that smooth, I'm sure if you are in there looking at the losses decline, there is some level on which it's smooth if you zoom in close enough, but from us from the perspective of us on the outside world, GPT four was just like suddenly acquiring this new batch of qualitative capabilities compared to GPT 3.5. And somewhere in there is a smoothly declining predictable loss. In text prediction, but that loss on text prediction corresponds to qualitative jumps and ability. And I am not familiar with anybody who predicted those in advance of the observation.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“As I said in my debate with Paul on this subject, I am always happy to say that whatever large jumps we see in the real world somebody will draw a smooth line of something that was changing smoothly as the large jumps were going on from the perspective of the actual people watching. You can always do that.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, Paul Christiano and I cooperatively fought it out really hard at trying to find a place where we both had predictions about the same thing that concretely differed. And what we ended up with was Paul's 8% versus my sixteen percent for an AI getting gold on international mathematics Olympics problem set. I believe twenty twenty five Prediction markets odds on that are currently running around 30%. So probably Paul's going to win, but slight moral victory.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, every year up until the end of the world, people are going to max out their tracks record by betting all of their money on the world not ending.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I have refused to deploy timelines with fancy probabilities on them consistently for lo these many years, for I feel that they are just not my brain's native format and that every time I try to do this it ends up making me stupider You just do the thing, you know, you just look at whatever opportunities are left to you, whatever your planet is. and you go out and do them, and if you bake up some fancy number for that your chance of dying next year, there's very little you can do with it really. You're just going to do the thing either way. I don't know how much time I have left.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Because I could be wrong. And because matters are now serious enough that I have nothing left to do but go out there and tell people how it looks, and maybe someone thinks of something I did not think of.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Did he No, no, I'm just being rolling my eyes. But, anyways, there's actually no difference between extreme optimism and extreme pessimism because. Like, go”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I've heard of this too. It's from Wint, right? The wise men opened his mouth and spoke. There's actually no difference between good, bad things, between good things and bad things. You idiot, you moron. I'm not quoting this correctly”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I agree it's possible to imagine things being even worse. Not quite sure what the other point of the question is. It's not literally as bad as possible In fact, by this time next year, Maybe we'll get to see how much worse it can last.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“It's good that we have a bunch of different people coming up with different ideas because maybe one of them works, but like you don't get a bunch of conditionally independent chances on each one. This is like, I don't know, like general good science practice and or complete Hail Mary. It's not like one of these is bound to work. There is no rule about one of them is bound to work. Don't just get enough diversity and one of them is bound to work. If that were true, you just ask GPT-4 to generate 10,000 ideas and one of those would be bound to work. It doesn't work like that.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean, that's like trying to use cognitive diversity to. Generate one, yeah, we don't need a bunch of stuff, we need one You could ask GPT4 to generate ten thousand approaches to alignment, right? And that does not get you very far because GPT 4 is not going to have very good suggestions”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“This is the dream that the Center for Applied Rationale failed at. It's not easy. They didn't even get as far as buying an FMRI machine. But they also had no funding. So, you know, maybe you try it again with a billion dollars in FMRI machines and bounties and prediction markets, and maybe that works.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't actually believe this. I've watched humans. I've watched unaugmented humans trying to do alignment. It doesn't really work, even if we throw a whole bunch more at them. It's still not going to work. The problem is not that the suggestor is not powerful enough. The problem is that the verifier is broken. But yeah, it all depends on the exit plan.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Maybe with neuroscience you can train people to be less idiots and the smartest existing people are then actually able to organ alignment due to their increased wisdom. Maybe you can scan and slice a human scan in that order, a human brain and run it as a simulation and upgrade the intelligence of the uploaded human Not really sing a whole lot of other. Maybe you can Just do alignment theory without running any system's powerful enough that they might maybe kill everyone'cause when you're doing this you don't get to just guess in the dark or if you do you're dead. Maybe just by doing a bunch of interpretability and theory to those systems if we actually make it a planetary priority.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Kind of digressing here, but my point is that The question is to get to like 90% chance of winning, which is pretty hard on any exit scheme. You want to complete that exit scheme before the ceiling on compute needs to be lowered too far. If your exit plan takes a long time, then you're going to shut down the academic AI journals and maybe even have the The Gestapo bustin' in people's houses to accuse them of being underground AI researchers, and I would really rather not live there. And maybe even that doesn't work.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“No, like I think that you can plausibly have a series of intelligence enhancing drugs and other external interventions that you perform on a human brain and you make people smarter and you probably are going to have some issues with trying not to drive them schizophrenic or psychotic, but that's going to happen visibly and it will make them dumber. And there's a whole bunch of caution to be had about not making them smarter and making them evil at the same time. And yet I think that this is the kind of thing you could do and be cautious and it could work if you're starting with a human.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I think I'm possibly just failing to misunderstand the premise is the premise that we have something that is aligned with humanity but smarter? You're done”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“No, I think this is just that there's, yeah, I think that if you have something that is smarter than I am, able to solve alignment, I think that it has the opportunity to do galaxy brain schemes there because you're asking it to build a super intelligence rather than atomic bomb. If it were just an atomic bomb, this would be less concerning. If there was some way to ask NAI to build a super atomic bomb, and that would solve all our problems, And it doesn't have to be, and it only needs to be as smart as Eliaser to do that. Honestly, you're still kind of a lot of trouble. Ali Get more dangerous as you put them in as you lock them in a room with aliens they do not like instead of with humans, which have their flaws but are not actually aliens in this sense.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, there's legit Galaxy brain shenanigans you can pull when somebody asks you to design an AI, you cannot pull when they design your task an atom bomb. You cannot configure the atom bomb in a clever way where it destroys the whole world and gives you the moon.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, he had very limited. He had very limited options and no option for getting a bunch more of what he wanted in a way that would break stuff.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, we've already got a bunch of human level intelligences. So, how about if we just do whatever it is you plan to do with that weak AI with our existing intelligence?”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Not actually have those options. You are not pointing out to me a lack of preference on Oppenheimer's part. You are pointing out to me a lack of his options. Yeah, like the hinge of this argument is the capabilities constraint. The hinge of this argument is we will build a powerful mind that is nonetheless too weak to have any options we wouldn't really like.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“So, what you're saying is that if you go to Oppenheimer and you say, here's the genie that actually does what you meant. We now give to rulership and dominion of earth, the solar system, and the galaxies beyond. Oppenheimer would have been like, I'm not ambitious, I shall make no wishes here. Let poverty continue. Let death and disease continue. I am not ambitious. I do not want the universe to be other than it is even if you give me a genie. Let Oppenheimer say that, and then I will call him a corrigible system.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“John von Neumann is generally considered the smartest guy. I've never heard somebody called Oppenheimer the smartest guy.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Oh man, don't have that be the plan. That does not sound like a good plan. Maybe he got away with Oppenheimer because he was human in the world of other humans who were, some of whom were as smart as him as smarter. But if that's the plan with AI, that does not sound.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Like there's additional pieces of theory that you can then layer on top of that, like the notion of utility functions, and why it is that if you just grind a system to be efficient at ending up in particular outcomes, it will develop something like a utility function, which is like a relative quantity of how much it wants different things, which is basically caused different things have different probabilities. So you end up with things that Because they need to multiply by the weights of probabilities, need a boy, I'm not explaining this very well. Something, something coherent”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“No Like, if you understand the concept of here is my preference ordering over outcomes, here is the complicated transformation of the environment, I will learn how the environment works, and then invert the environment's transformation to project stuff high in my preference ordering back onto my actions, options, decisions, choices, policies, actions, that when I run them through the environment will end up in an outcome high in my preference ordering, like if you know that”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I mean I wrote a thing about that when I was twenty two And it's possibly not wrong, but it's like kind of in retrospect completely useless. Yeah, I'm not quite sure what to say there. Like, you want the kind of code where I can just tell you how to write it down in Python and you write it and then build something as smart as a human but without the giant training runs.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“Or any number of other methods that I myself am too stupid to envision because I'm too stupid to self-alignment. The point is, I think about this, the kind of thing that solves alignment is a kind of system that thinks about how to do this sort of stuff because you also know how to have to do this sort of stuff to prevent other things from taking over your system. If I was sufficiently good at it, I could actually line stuff And you are aliens, and I didn't like you. You'd have to worry about this stuff.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I can't solve alignment. So I cannot being unknowable. First of all, I wouldn't. Science fiction books raise me to not be a jerk, and it was written by other people who are trying not to be jerks themselves and wrote science fiction and who were similar to me. It's not like a magic process. Like the thing that resonated in them, they put into words, and I, who am also of their species, it then resonated in me. So the answer in my particular case is by weird contingencies of utility functions, I happen to not be a jerk. Leaving that aside, I'm just too stupid. I'm too stupid to solve alignment. And I'm too stupid to execute a handshake with a superintelligence that I told somebody else how to align in a cleverly deceptive way where that superintelligence ended up in the kind of basin of logical decision theory handshakes.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source
“I was specialized on alignment rather than persuading humans, though I am more persuasive in some ways than you're your typical average human. I also didn't solve alignment. So, you got to go smarter than me. And furthermore, the postulate here is not so much like Canada directly attack and persuade humans, but like can it sneak through one of the ways of executing a handshake of like, I tell you how to build an AI. It sounds plausible. It kills you. I derive benefit.”
2023-04-06 · Dwarkesh Podcast · Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality · IDENTIFIED FROM THE TRANSCRIPT · source