Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality

No, no, misaligned! Misaligned!

No, no, no, not yet. Not now.
Nobody's been careful and deliberate now. But maybe at some point in the indefinite future, people will be careful and deliberate.
Sure, let's grant that premise. Keep going.
If you try to rouse your planet, there are the idiot disaster monkeys who are like, ooh, ooh, like if this is dangerous, it must be powerful, right? I'm going to like be first to grab the poison banana. And it's not a coincidence that I can like zoom in and poke at this and ask questions like this, and that you did not ask these questions of yourself.
You are imagining nice ways you can get the thing, but reality is not necessarily imagining how to give you what you want. Should one remain silent? Should one let everyone walk directly into the whirling racer blades?

Like continuing to play out a video game you know you're going to lose. Because that's all you have.
Okay, today I have the pleasure of speaking with Eliezer Yudkowsky. Eliezer, thank you so much for coming out to the Lunar Society.
You're welcome. First question.
So yesterday when we were recording this, you had an article in Time calling for a moratorium on further AI training runs. Now, my first question is, it's probably not likely that governments are going to adopt some sort of treaty that restricts AI right now.
So what was the goal with writing it right now? I think that I thought that this was something very unlikely for governments to adopt. And then all of my friends kept on telling me like, no, no, actually, if you talk to anyone outside of the tech industry, they think maybe we shouldn't do that.
And I was like, all right, then. Like, I assumed that this concept had no popular support.

Maybe I assumed incorrectly. It seems foolish and to lack dignity to not even try to say what ought to be done.
There wasn't a galaxy-brained purpose behind it. I think that over the last 22 years or so, we've seen a great lack of galaxy-brained ideas playing out successfully.
Have, has anybody in government, not necessarily after the article, but I suggest in general,

have they reached out to you in a way that makes you think that they sort of have the broad contours of the problem, correct? No, I'm going on reports that normal people are more willing than the people I've been previously talking to, to entertain calls. This is a bad idea.
Maybe you should just not do that. That's surprising to hear because I would have assumed that the people in Silicon Valley who are weirdos would be more likely to find this sort of message.
They could kind of rock it. The whole idea that nanomachines will, AI will make nanomachines that take over.
It's surprising to hear the normal people got the message first. Well, I hesitate to use the term midwit, but maybe this was all just a midwit thing.
All right. So my concern with, I guess, either the six month moratorium or forever moratorium until we solve alignment is that at this point, it seems like it could, to people seem like we're crying wolf.
And actually not like it could, but it would be like crying wolf because these systems aren't yet at a point at which they're dangerous. And nobody is saying they are.
Well, I'm not saying they are. The open letter signatories aren't saying they are.
I don't think. So if there is a point at which we can sort of get the public momentum to do some sort of stop, wouldn't it be useful to exercise it when we get a GPT-6 and who knows what it's capable of? Why do it now? Because allegedly, possibly, and we will see, people right now are able to appreciate that things are storming ahead and a bit faster than the ability to, well, ensure any sort of good outcome for them.
And, you know, you could be like, ah, yes, well, like, we will, like, play the galaxy brain clever political move of trying to time when the popular support will be there. But again, I heard rumors that people were actually, like, completely open to the concept of let's stop.
So again, just trying to say it. And it's not clear to me what happens if we wait for GPT-5 to say it.
I don't actually know what GPT-5 is going to be like. It has been very hard to call.
The rate at which these systems acquire capability as they are trained to larger and larger sizes and more and more tokens. And GPT-4 is a bit beyond in some ways where I thought this paradigm was going to scale, period.
So I don't actually know what happens if GPT-5 is built. And even if GPT-5 doesn't end the world,

which I agree is like more than 50% of where my probability mass lies, even if GPT-5 doesn't end the world, maybe that's enough time for GPT-4.5 to get ensconced everywhere and in everything and for it actually to be harder to call a stop, both politically and technically. There's also the point that training algorithms keep improving.
If we put a hard limit on the total compute and training runs right now, these systems would still get more capable over time as the algorithms improved and got more efficient, like more oomph per floating point operation, and things would still improve, but slower. And if you start that process off at the GPT-5 level, where I don't actually know how capable that is exactly, you may have like a bunch less lifeline left before you get into dangerous territory.
The concern is then that, listen, there's, you know, millions of GPUs out there in the world. And so the actors would be, who would be willing to cooperate or who could even identify in order to even get the government to make them cooperate would be potentially the ones that are most on the message.
And so what you're left with is a system where they'reate for six months or a year or hour long this lasts. And then what is a game plan? Is there some plan by which if we wait a few years, then alignment will be solved? Do we have some sort of timeline like that? Or what is the plan? Well, alignment will not be solved in a few years.
I would hope for something along the lines of human intelligence enhancement works. I do not think we are going to have the timeline for genetically engineering humans to work, but maybe.
This is why I mentioned in the time letter that if I had, like, infinite capability to dictate the laws, that there would be a carve-out on biology, like AI that is, like, just for biology and not trained on text from the Internet. Human intelligence enhancement, make people smarter.
Making people smarter has a chance of going right in a way that making an extremely smart AI does not have a realistic chance of going right at this point. So yeah, that would, in terms of like remotely, you know, how do I put it? If we were on a sane planet, what the sane planet does at this point is shut it all down and work on human intelligence enhancement.

It is, I don't think we're going to live in that sane world. I think we are all going to die.
but having heard that people are more open to this outside of California it makes sense to me

to just like try saying out loud what it is that you do in a saner planet and not just assume that

people are not going to do that. into this outside of California, it makes sense to me to just like try saying out loud what it

is that you do in a saner planet and not just assume that people are not going to do that. In what percentage of the worlds where humanity survives, is there a human enhancement? Like, even if there's 1% chance humanity survives, it's basically that entire branch dominated by the worlds where there's some sort of...
I mean, I think we're just like mainly in the territory of Hail Mary passes at this point.

And human intelligence and... I mean, I think we're just like mainly in the territory of Hail Mary passes at this point.

And human intelligence enhancement is one Hail Mary pass. Maybe you can put people in MRIs and train them using neurofeedback to be a little saner, to not rationalize so much.
Maybe you can figure out how to have something light up every time somebody is like working backwards from what they want to be true to what they take as their premises. Maybe you can just like fire off a little light and teach people not to do that so much.
Maybe the GPT four-level systems can be reinforcement learning from human feedback into being consistently smart, nice, and charitable in conversation, and just unleash a billion of them on Twitter and just have them spread sanity everywhere. I do worry that this is not going to be the most profitable use of the technology, but you're asking me to list out Hail Mary passes, so that's what I'm doing.
Maybe you can actually figure out how to take a brain, slice it, scan it, simulate it, run uploads and upgrade the uploads or run the uploads faster. These are also quite dangerous things, but they do not have the utter lethality of artificial intelligence.
All right.

That's actually a great jumping point into the next topic I want to talk to you about,

orthogonality.

And here's my first question.

Speaking of human enhancement, suppose you bred human beings to be friendly and cooperative,

but also more intelligent.

I'm sure you're going to disagree with this analogy, but I just want to understand why.

I claim that over many generations, you would just have really smart humans who are also really friendly and cooperative. Would you disagree with that? Or would you disagree with the analogy? So the main thing is that you're starting from minds that are already very, very similar to yours.
You're starting from minds of which, whom many of them already exhibit the characteristics that you want. There are already many people in the world, I hope, who are nice in the way that you want them to be nice.
There's, of course, it depends on how nice you want exactly. I think that if you, like, actually go start trying to run a project of selectively encouraging some marriages between particular people and encouraging them to have children, you will rapidly find, as one does in any process of, as one does when one does this to, say, chickens, that when you select on the stuff you want, it turns out there's a bunch of stuff correlated with it and that you're not changing just one thing.
If you try to make people who are inhumanly nice, who are nicer than anyone has ever been before, you're going outside the space that human psychology has previously evolved and adapted to deal with, and weird stuff will happen to those people. None of this is like very analogous to AI.
I'm just pointing out along the lines of well taking your analogy at face value what would happen exactly and um you know it's the sort of thing where you could maybe do it but there's all kinds of pitfalls that you'd probably find out about if you cracked open a textbook on animal breeding? So, I mean, the thing you mentioned initially, which is that we are starting off with basic human psychology that we're kind of fine tuning with breeding. Luckily, the current paradigm of AI is, you know, you just have these models that are trained on human text.
And I mean, you would assume that this would give you a sort of starting point of something like human psychology. Why do you assume that? Because they're trained on human text.
And what does that do? Whatever sorts of thoughts and emotions that lead to the production of human text need to be simulated in the AI in order to produce those themselves. I see.
So if you take a person and if you take an actor and tell them to play a character, they just become that person. You can tell that because you see somebody on screen playing Buffy the Vampire Slayer.
And that's probably just actually Buffy in there. That's who that is.
I think a better analogy is if you have a child and you tell him, hey, be this way, they're more likely to just be that way. I mean, other than like putting on an act for like 20 years or something.
It depends on what you're telling them to be exactly. Like if you're telling them to be nice.
Yeah. But that's not what you're telling them to do.
You're telling them to play the part of an alien. Like something with a completely inhuman psychology as extrapolated by science fiction authors and in many cases, you know, like done by computers because, you know, humans can't quite think that way.
And your child eventually manages to learn to act that way. What exactly is going on in there now? Are they just the alien? Or did they pick up the rhythm of what you were asking them to imitate and be like, ah, yes, I see who I'm supposed to pretend to be.
Are they actually a person or are they pretending? That's true even if you're not asking them to be an alien. You know, my parents tried to raise me Orthodox Jewish and that did not take at all.
I learned to pretend. I learned to comply.
I hated every minute of it. Okay, not literally every minute of it.
I should avoid saying untrue things. I hated most minutes of it.
And yeah, because they were trying to show me a way to be that was alien to my own psychology. And the religion that I actually picked up was from the science fiction books instead, as it were, though I'm using religion very metaphorically here.
More like ethos, you might say. I was raised with the science fiction books I was reading from my parents' library and Orthodox Judaism, and the ethos of the science fiction books rang truer in my soul.
And so that took in the Orthodox Judaism didn't. But the Orthodox Judaism was what I had to imitate, was what I had to pretend to be, was the answers I had to give, whether I believe them or not, because otherwise you get punished.
But, I mean, on that point itself, the rates of apostasy are probably below 50% in any religion, right? Like some people do leave, but often they just become the thing they're imitating as a child.

Yes, because the religions are selected to not have that many apostates.

If aliens came in and introduced their religion, you'd get a lot more apostates.

Right. But I mean, I think we're probably in a more virtuous situation with ML because you, I mean, these systems are kind of, uh, through stochastic gradient descent sort of regularized so that the system that is pretending to be something where there's like multiple layers of interpretation is going to be more complex than the one that it's just being the thing.
And I mean, over time, like the system that is just being the thing will be optimized, right? It'll just be simpler. This seems like an ordinate cope for, for one thing, you're not training it to be any one particular person.
You're training it to switch masks to anyone on the internet as soon as they figure out who that person on the internet is. If I put the internet in front of you and I was like, learn to predict the next word, learn to predict the next word over and over.
You do not just like turn into a random human because the random human is not what's best at predicting the next word of everyone who's ever been on the internet. You learn to very rapidly like pick up on the cues of like what sort of person is talking? What will they say next? You memorize so many facts that just because they're helpful in predicting the next word.
You learn all kinds of patterns. You learn all the languages.
You learn to switch rapidly from being one kind of person or another as the conversation that you are predicting changes who's speaking. This is not a human we're describing.
You are not training a human there. Would you at least say that we are living in a better situation than one in which we have some sort of black box where you have this sort of Machiavellian fittest survive a simulation that produces AI? Like is it at least this situation is at least more likely to produce alignment than one in which something that is completely untouched by human psychology would produce?

More likely?

Yes.

Maybe you're like, it's an order of magnitude likelier, 0% instead of 0%.

Getting stuff like more likely does not help you if the baseline is nearly 0.

The whole training setup there is producing an actress, a predictor.

It's not actually being put into the kind of ancestral situation that evolved humans, nor the kind of modern situation that raises humans, though to be clear, raising it like a human wouldn't help. But yeah, you're giving it a very alien problem that is not what humans solve, and it is solving that problem, not the way human would.
Okay, so how about this? I see that i uh certainly don't know for sure what is going on in these systems in fact obviously nobody does but that that also goes for you so could it not just be that even through imitating all humans it like i don't know reinforcement learning works and then all these other things we're trying somehow work and And actually just like being an actor produces some sort of benign outcome where there isn't that level of simulation and conniving. I think it predictably breaks down as you try to make the system smarter.
As you try to derive sufficiently useful work from it. And in particular like the sort of work where some other AI doesn't just kill you off six months later.
I, yeah, like I think the present system is not smart enough to have a deep conniving actress thinking long strings of coherent thoughts about how to predict the next word. But as the mask that it wears, as the people it's pretending to be gets smarter and smarter, I think that at some point, the thing in there that is predicting how humans plan, predicting how humans talk, predicting how humans think, and needing to be at least as smart as the human it is predicting in order to do that.
I suspect at some point there is a new coherence born within the system and something strange starts happening. I think that if you have something that can accurately predict, I mean, Eliezer Yudkowsky, to use a particular example I know quite well.

I think that to accurately predict Eliezer Yudkowsky,

you've got to be able to do the kind of thinking where you are reflecting on yourself.

And that in order to simulate Eliezer Yudkowsky reflecting on himself,

you need to be able to do that kind of thinking.

And this is not airtight logic, but I expect there to be a discount factor. So like if you ask me to play a part of somebody who's quite unlike me, I think there's some amount of penalty that the character I'm playing gets to his intelligence because I'm secretly back there simulating him.
And that's even if we're quite similar and the stranger they are, the more unfamiliar the situation. The less the person I'm playing is as smart as I am, the more they are dumber than I am.
So similarly, I think that if you get an AI that's very, very good at predicting what Eliezer says, I think that there's a quite alien mind doing that, that it actually has to be to some degree smarter than me in order to play the role of something that thinks differently from how it does very, very accurately. And I reflect on myself.
I think about how my thoughts are not good enough by my own standards and how I want to rearrange my own thought processes. I look at the world and see it going the way I did not want it to go and asking myself, how could I change this world? I look around at other humans.
I model them and sometimes I try to persuade them of things. These are all capabilities that the system would then be somewhere in there.

And I just, like, don't trust the blind hope that all of that capability is pointed entirely at pretending to be Eliezer and only exists insofar as it's like the mirror and isomorph of Eliezer. that all the prediction is by being something exactly like me and not thinking about me while not being me.
Certainly, I don't want to claim that it is guaranteed that there isn't something super alien and something that is against our aims happening within the Shagath. but uh you made an earlier claim which seemed much stronger than the idea that you don't want mine hope which is that we're going from like zero percent probability to an order of magnitude greater at zero percent probability um there's a difference between saying that we should be wary and that like there's no hope right like i i could imagine so many things that could be happening in the shoggoth's brain, especially in our level of confusion and mysticism over what is happening.
So, I mean, OK, so one example is like, I don't know, let's say that it is kind of just becomes the average of all human psychology and motives. But it's not the average.
It is able to be every one of those people. Right.
Right. That's very different from being the average.
Right? Like it's very different from being an average chess player versus being able to predict every chess player in the database. These are very different things.
Yeah, no, I meant in terms of motives that is the average, whereas it can simulate any given human. Why would the – I'm not saying that's the most likely one.
I'm'm just saying like this just seems zero percent probable to me like the motive is going to be like i want to like insofar the motive is going to be like some weird funhouse mirror thing of i want to predict very accurately right um why then are we so sure that whatever the drives that come about because of this motive are going to be incompatible with survival and flourishing with humanity? Most drives that happen when you take a loss function and splinter it into things correlated with it and then amp up intelligence until some kind of strange coherence is born within the thing and then ask it how it would want to self-modify or what kind of successful system it would build, things that alien ultimately end up wanting the universe to be some particular way that doesn't happen to have you for wanting the universe to be a way such that humans are not a solution to the question of how to make the universe most that way. Like, like the thing that very strongly wants to predict text, even if you got that goal into the system exactly, which is not what would happen, the universe with the most predictable text is not a universe that has the universe in it.
The universe that has humans in it. Okay, I'm not saying this is the most likely outcome, but here's just an example of one of many ways in which humans stay around, even despite this motive.
Let's say that in order to predict human output really well, it needs humans around just to give it the sort of raw data from which to improve its predictions, right? Or something like that. I mean, this is not something I think individually is a likely scenario.
If the humans are no longer around, you no longer need to predict them. Right? So you don't need the data required to predict them.

But no, because you are starting off with that motivation, you want to just maximize along that loss function. Or have that drive that came about because of the loss function.
I'm confused. So look, like you can always develop arbitrary fanciful scenarios in which the AI has some contrived motive that it can only possibly satisfy by keeping humans alive in good health and comfort and, you know, like turning all the nearby galaxies into happy, cheerful places full of, you know, high-functioning galactic civilizations.
But as soon as your sentence has more than like five words in it, its probability has dropped to basically zero because of all the extra details you're patting in. Maybe let's return to this.
Another sort of train of thought I want to follow is, so I claim that humans have not become orthogonal to the sort of evolutionary process that produced them. Great.
I claim humans are orthogonal to increasingly orthogonal. And the further they go out of distribution and the smarter they get, the more orthogonal they get to inclusive genetic fitness.
The sole loss function on which humans were optimized. Okay.
So most humans still want kids and have kids and care for their kin, right? So, I mean, certainly there's some angle between how humans operate today, right? Evolution would prefer to use less condoms and more sperm banks. But I mean, we're still like, you know, there's like 10 billion of us, you know, there's going to be more in the future.
It seems like we haven't divorced that far from the sorts of the, like what our alleles would want. I mean, so it's a question of how far out of distribution are you? And the smarter you are, the more out of distribution you get, because as you, as you get smarter, you get new options that are further from the options that you were faced with in the ancestral environment that you were optimized over.
So in particular, sure, a lot of people want kids, not inclusive genetic fitness, but kids. They don't want their kids to have, they like want kids similar to them maybe, but they don't want the kids to have their DNA or like their alleles, their genes.
So suppose I go up to somebody and credibly, we will assume away the ridiculousness of this offer for the moment, and credibly say, you know, your kids could be a bit smarter and much healthier if you'll just let me replace their DNA with this alternate storage method that will, you know, they'll like age more slowly, They'll be healthier. They won't have to worry about DNA damage.
They won't have to worry about the methylation on the DNA flipping and the cells de-differentiating as they get older. We've like got this stuff that like replaces DNA and you know, like your kid will still be similar to you.
It'll be like, you know, a bit smarter and they'll be like so much healthier and, you know, and be so much healthier, and even a bit more cheerful.

You just have to rewrite all the DNA, or replace all the DNA with a stronger substrate,

and rewrite all the information on it.

The old school transhumanist offer, really.

And I think that a lot of the people who are like they would want kids would go for this

new offer that just offers them so much more of what it is they want from kids than copying the DNA, than inclusive genetic fitness. In some sense, I don't even think that would dispute my claim because if you think from like a gene's eye point of view, it just wants to be replicated.
If it's replicated in another's still like no no we're not we're not saving information we're just like doing total rewrite to the dna um i actually claim that most humans would not offer that because yeah because it would sound weird yeah but the smarter they are i think the smarter they are the more likely they are to go for it if it's credible i also think that to some extent you're, I mean, if you like assume away the credibility issue and the weirdness issue, like all their friends are doing it. Yeah, even if the smarter they are, the more likely they're to do it.
Like most humans are not that smart. From the genes point of view, it doesn't really matter how smart you are, right? It just like matters if you're producing copies.
I'm not, what? No, I'm saying that like, that like like, the smart thing is kind of like a delicate issue here because somebody could always be like, I would never take that offer. And then I'm like, yeah.
And it's not very polite to be like, I bet if we kept on increasing your intelligence, you would at some point start to sound more attractive to you because your weirdness tolerance would go up as you became more rapidly capable of readapting your thoughts to weird stuff. And the weirdness started to seem less unpleasant and more like you were moving within a space that you already understood.
But you can sort of elide all that by, and we maybe should, by being like, well, suppose all your friends were doing it. What if it was normal? What if we, like, remove the weirdness and remove any credibility problems? In that hypothetical case, do people choose for their kids to be dumber, sicker, less pretty, because they, out of some sentimental idealistic attachment to using deoxyribose nucleic acid instead of the, and like the particular information encoding their cells as opposed to the like new improved cells from alpha fold seven? I would claim that they would, but I think that's, I mean, we don't really know.
I claim that, you know, they would be more averse to that. You probably think that they would be less averse to that.
Regardless of that, I mean, we can just go by the evidence we do have in that we are already way out of distribution of the ancestral environment. And even in this situation, the place where we do have evidence, people are still having kids, you know, like actually we haven't gone that orthogonal to...
We haven't gone that smart. What you're saying is like, well, look, people are still making more of their DNA in a situation where nobody has offered them a way to get all the stuff they want without the DNA.
So of course they haven't tossed DNA out the window. Yeah.
I mean, first of all, like I'm not even sure what would happen in that situation. Like I still think even most smart humans in that situation might disagree, but we don't know what would happen in that situation.
Like, I still think even most smart humans in that situation, like, might disagree.

But, like, we don't know what would happen in that situation.

Why not just use the evidence we have so far?

PCR.

You, right now, could get some of your cells and make, like, a whole gallon jar full of your own DNA.

Are you doing that?

No, no.

Misaligned.

Misaligned.

No, no.

So, I'm, like, I'm down with transhumanism. I'm going to ever use it like my kids and whatever.
Oh, so we're all talking about these hypothetical other people you think would make the wrong choice. Well, I wouldn't say wrong, but different.
And I'm just like saying like, there's probably more of them than there are of us here. Oh, well, what if I say like, I have more faith in normal people than you do to like toss DNA out the window as soon as somebody offers them a happy, healthier life for their kids? I'm not even making a moral point.
I'm just saying like, I don't know what's gonna happen in the future. Let's just look at the evidence we have so far.
Humans actually, if that's the evidence you're going to present for something that's out of distribution and has gone on orthogonal, like that's actually not happened, right? Like this is a hope. This is evidence for hope.
Because we haven't yet had options as far enough outside of the ancestral distribution that in the course of choosing what we most want, that there's no DNA left. Okay.
Yeah. Yeah.
I think I understand. But you yourself say, oh yeah, sure.
I would choose that. And I myself say, oh yeah, sure.
I would choose that. And you think that there's some hypothetical other people would stubbornly stay attached to what you think is the wrong choice.
Well, you know, um, there, then there's, you know, first of all, I think, you know, maybe you're being a bit condescending there. I, how am I supposed to argue with these, with these, with these imaginary foolish people who exist only inside your own mind, who can always like be as stupid as you want them to be and who I can never argue.
Cause you'll always just be like, ah, you know, like they, they won't be persuaded by that. But right.
But right here in this room, the site of this videotaping, there is no counter evidence that smart enough humans will toss DNA out the window as soon as somebody makes them a sufficiently better offer. Okay.
I'm not even saying it's like stupid. I'm just saying like, they're not weirdos like me, right? Like me and you.
Weird is relative to intelligence. The smarter you are, the more you can like around in the space of abstractions and not have things seem so unfamiliar yet.
But let me make the claim that, in fact, we're probably in even a better situation than we are with evolution. Because when we're designing these systems, we're doing it in a sort of deliberate, incremental, and in some sense, a little bit transparent way.
Well, no no no not yet not now nobody's been careful and deliberate now but maybe at some point in the indefinite future people will be careful and deliberate sure let's grant that premise keep going okay well like it would be like a weak god who is just slightly omniscient being able to kind of strike down any guy he sees pulling out, right? Like if that was a situation. Oh, and then there's another benefit, which is that humans were sort of evolved in an ancestral environment in which power seeking was highly valuable.
Like if you're in some sort of tribe or something. Sure, lots of instrumental values made our way into our...
But even more so than the current lost humans. Strange warped versions of them make their way into our intrinsic motivations yeah yeah even more so than the current last really the rlhf stuff you don't think that you know you there's nothing to be gained from manipulating the humans into giving you a thumbs up i think it's probably more straightforward from a gradient descent perspective to just like become the thing rlhf wants you to be, at least for now.
Where are you getting this?

Because it just like, it just kind of regularizes these sorts of extra abstractions you might

want to put on.

Natural selection regularizes so much harder than gradient descent in that way.

It's got an enormously stronger information bottleneck.

Putting the L2 norm on a bunch of weights has nothing on the tiny amounts of information

that can make its way into the genome per generation. The regularizers on natural selection are enormously stronger.
Yeah. So just going at this train of like my initial point was that the power seeking that a lot of human power seeking, like part of it is convergent, but a big part of it is just that like the ancestral environment was uniquely suited to that kind of behavior.
So that drive was trained in, you know, in greater proportion to its sort of like necessariness for generality. Okay.
So first of all, even if you have something that desires no power for its own sake, if it desires anything else, it needs power to get there, not at the expense of the things it pursues, but just because you get more of whatever it is you want as you have more power and sufficiently smart things know that. It's not some weird fact about the cognitive system.
It's a fact about the environment, about the structure of reality and the paths of time through the environment that if you have, you know, in the limiting case, if you have no ability to do anything, you will probably not get very much of what you want. Okay.
So imagine a situation like an ancestral environment of like some human starts exhibiting really power seeking behavior before he realizes that he should try to hide it. We just like kill him off.
And, you know, the friendly, cooperative the friendly cooperative ones we let them breed more and like i'm trying to draw the analogy between like rhl or something where we get to see yeah i think that works better when the things you're breeding are stupider than you as opposed to when they are smarter than you is my concern there this goes back to the earlier question about... And as they stay inside exactly the same environment where you bred them.
We're in a pretty different environment than evolution bred us in, but I guess this goes back to the previous conversation we had of like, we're still having kids. Because nobody's made them an offer for better kids with less DNA.
See, here's I think the problem, like I can just look out of and see, like, this is what it looks like. We disagree about what will happen in the future once that offer is made.
But lacking that information, I feel like our prior should just be set of what we actually see in the world today. Yeah, I think in that case, we should believe that the dates and on the calendars will never show 2024.
Every single year throughout human history in the 13.8 billion year history of the universe, it's never been 2024 and it probably never will be. The difference is that we have good reason.
Like we have very strong reason for expecting the sort of, you know, turn and years. Even like, so are you extrapolating from your past data to outside the range of data? have a good reason to.
I don't think human preferences are as predictable as dates. Yeah, there's somewhat less.
Oh, no, sorry. Why not jump on this one? So what you're saying is that as soon as the calendar turns 2024, itself a great speculation I note, people will stop wanting to have kids and stop wanting to eat and stop wanting social status and power because human motivations are just like not that stable and predictable no no I'm saying they're actually uh that's not what I'm claiming at all I'm just saying that they don't extrapolate to some other situation which has not happened before and like I I I would like the fox show in 2024 no I wouldn't assume that like what is an example here I wouldn't assume, like's say uh in the future people are given a choice to have like four eyes that are going to give them even greater triangulation of objects they would like choose to have four eyes yeah yeah because there's no established preference for four eyes right is there an established preference for transhumanism and like wanting your dna modifying there's an established preference for for i, for people going to some lengths to make their kids healthier, not necessarily via the options that they would have later, but the options that they do have now.
Yeah, we'll see, I guess, when that technology becomes available. Let me ask you about LLMs.
So what is your position now about whether these things can get us to AGI? I don't know. GPT-4 got, I was previously being like, I don't think Stack More Layers does this.
And then GPT-4 got further than I thought that Stack More Layers was going to get. And I don't actually know that they got GPT-4 just by stacking more layers because OpenAI has very correctly declined to tell us what exactly goes on in there in terms of its architecture.
So maybe they are no longer just stacking more layers. But in any case, however they build GPT-4, it's gotten further than I expected stacking more layers of transformers to get.
And therefore, I have noticed this fact and expected further updates in the same direction. So I'm not like just predictably updating in the same direction every time like an idiot.
And now I do not know. I am no longer willing to say that GPT-6 does not end the world.
Does it also make you more inclined to think that there's going to be sort of slow takeoffs or more incremental takeoffs where like GPT-2, GPT-3 is better than GPT-2, GPT-4 is in some ways better than GPT-3. And then we just keep going that way and sort of this straight line.
so i do think that over time i have come to expect a bit more that things will hang around

in a near human place and weird shit will happen as a result.

And my failure review where I look back and ask, like, was that a predictable sort of mistake? I sort of feel like it was to some extent maybe a case of you're always going to get capabilities in some order and it was much easier to visualize the endpoint where you have all the capabilities and where you have some of the capabilities and therefore my visualizations were not dwelling enough on a space we'd predictably in retrospect have entered into later where things capabilities, but not others, and it's weird. I do think that in 2012, I would not have called that large language models were the way, and the large language models are in some way more uncannily semi-human than what I would justly have predicted in 2012, knowing only what I knew then.
But broadly speaking, yeah. Like, I do feel like GPT-4 is already, like, kind of hanging out for longer in a weird near-human space than I was really visualizing, in part because that's so incredibly hard to visualize or call correctly in advance of when it happens, which is, retrospect a bias.
Given that fact, how has your model of intelligence itself changed? Very little. So here's one claim somebody could make.
Listen, if these things hang around human level and if they're trained the way in which they are, recursive self-improvement is much less likely because they're human level intelligence. It's not it's not a matter of just like optimizing some for loops or something they got to like train a billion dollar another run to scale up um so you know that kind of recursive self-intelligence uh idea is less likely how do you respond at some point they get smart enough that they can roll their own ai systems and are better at it than humans.
And that is the point at which you definitely start to see Foom. Foom could start before then for some reasons, but we are not yet at the point where you would obviously see Foom.
Why doesn't the fact that they're going to be around human level for a while increase your odds, or does it increase your odds of human survival? Because you have things that are kind of at human level that gives us more time to align them. Maybe we can use zero help to align these future versions of themselves.
I do not think that you use AIs to, okay, so like having an AI help you, having AI do your AI alignment homework for you is like the nightmare application for alignment. Aligning them enough that they can align themselves is like very chicken and egg, very alignment complete.

There's like the same thing to do with capabilities like those might be enhanced human intelligence,

like poke around in the space of proteins, like collect the genomes, tie to life accomplishments, look at those genes, see if you can extrapolate out the whole proteonomics and the actual interactions and figure out what are likely candidates for if you administer this to an adult, because we do not have time to raise kids from scratch. If you administer this to an adult, the adult gets smarter.
Try that. And then the system just needs to understand biology.
And having an actual very smart thing understanding biology is not safe. I think that if you try to do that, it's sufficiently unsafe that you probably die.
But if you have it, if you have these things trying to solve alignment for you, they need to understand AI design. And the way that, and if there are a large language model, they're very, very good at human psychology because predicting the next thing you'll do is their entire deal.
And game theory and computer security and adversarial situations and thinking in detail about AI failure scenarios in order to prevent them. And there's just like so many dangerous domains you've got to operate in to do alignment.
Okay. There's two or three reasons why I'm more optimistic about the possibility of a human level intelligence helping us than you are.
But first, let me ask you, how long do you expect these systems to be at approximately human level before they go boom or something else crazy happens? You have some sense? All right. First is that in most domains, verification is much easier than generation.
Yes, that's another one of the things that makes alignment a nightmare. It is so much easier to tell that something has not lied to you about how a protein folds up because you can do some crystallography on it than it is, and ask it, how does it know that, than it is to tell whether or not it's lying to you about a particular alignment methodology being likely to work on a superintelligence.
Why is there a stronger reason to think that confirming new solutions in alignment... Well, first of all, do you think confirming new solutions in alignment will be easier than generating new solutions in alignment? Basically, no.
Why not? Because in most human domains, that is the case, right? Yeah. So alignment, the thing hands you a thing and says, this will work work for aligning a super intelligence.
And, you know, it gives you some like early predictions of like when that all of like how the thing will behave when it's when it's passively safe, when it can't kill you, that all bear out. And those predictions all come true.
And then the system and then you would like augment the system further towards no longer passively safe to where its safety depends on its alignment.

And then you die.

And the super intelligence you built like goes over to the AI that you asked to help at alignment and was like, good job. Billion dollars.
That's observation number one. observation number two is that like for the last 10 years all effective altruism has been

arguing about like whether they should believe like Eliezer Yudkowsky or Paul Cristiano.

Right?

So that's like two systems.

I believe that Paul is honest.

I claim that I am honest.

Neither of us are aliens.

And so we have these two like honest non-aliens having an argument about alignment.

And people can't figure out who's right.

Now you're going to have like aliens talking to you about alignment. You're going to and you're going to verify their results.
Aliens, aliens are possibly lying. So on that second point, I think it will be, it would be much easier if both of you had like concrete proposals for alignment and you just have like the pseudocode for both of you like pretty pseudocode for alignment.
You're like, this is, solution. Here's my solution.
I think at that point, actually, it would be pretty easy to tell which one of you is right.

I think you're wrong.

I think that, yeah, I think that that's like substantially harder than being like, oh, well, I can just like look at the code of the operating system and see if it has any security flaws.

You're asking like, what happens as this thing gets like dangerously smart? And that is not going to be transparent in the code. Let me come back to that on your first point about these things, you know, the alignment not generalizing.
Given that you've updated in the direction where the same sort of stacking more layers on the more attention layers is going to work it seems that there will be more generalization between like gpt4 and gpt5 so i mean presumably whatever alignment techniques you used on gpt2 would have worked on gpt3 and so on wait sorry what rlhf on gpt2 working on gpt3 or constitution ai or something that works on gpt3 all kinds of interesting things started happening with gpt3.5 in GPT--4 that were not in GPT-3. But the same contours of approach, like the RLH approach or like a constitution AI.
If by that you mean it didn't really work in one case and then like much more visibly didn't really work on the later cases, sure. It's failure merely amplified and new modes appeared, but they were not qualitatively different from the, well, they were qualitatively different from the failures.
Your entire analogy fails. Wait, can we go through how it fails? I'm not sure I understood.
Yeah. Like they did RLHF to GPT.
Did they even do this to GPT-2 at all? They did it to GPT-3. Yeah.
And then they scaled up the system and it got smarter and they got a whole new interesting failure modes.

Yes.

Yes.

Yeah.

Yeah.

There you go.

Right.

First of all, so I mean, one optimistic lesson to take from there is that we actually did learn from like GBD, not everything, but we learned many things about like what the potential failure modes could be of like 3.5.

I think I claimed.

We saw these people get caught utterly flat footed on the internet.

I'm going to could be of 3.5. We saw these people get caught utterly flat-footed on the internet.
We watched that happening in real time. Would you at least concede that this is a different world from you have a system that is just in no way, shape, or form similar to the human-level intelligence that comes after it it.
We're at least more likely to survive in this world than in a world where some other sort of methodology turned out to be fruitful. Do you see what I'm saying? When they scaled up Stockfish, when they scaled up AlphaGo, it did not blow up in these very interesting ways.
And yes, that's because it wasn't really scaling to general intelligence. But I deny that every possible like AI creation methodology like blows up in interesting ways.
And this is really the one that blew up least. No, it's the only one we've ever tried.
There's better stuff out there. We just suck, okay? We just suck at alignment and that's why our stuff blew up.
Well, okay. So let me make this analogy like the apollo program right i'm sure actually i don't know which ones blew up but like i'm sure like apollo's some one of the earlier apollo's blew up and didn't work and then they learned lessons from it to try an apollo that was even more ambitious and i don't know getting to the atmosphere it was easier than getting where we're we are learning from the AI systems that we build and as they fail and as we repair them.
And our learning goes along at this pace and our capabilities go along at this pace. Let me think about that.
But in the meantime, let me also propose that another reason to be optimistic is that since these things have to think one forward pass at a time, one word at a time, they have to do their thinking one word at a time. And in some sense, that makes their thinking legible, right? Like they have to articulate themselves as they proceed.
What? We get a black box output, then we get another black box output. What about this is supposed to be legible? Because the black box output gets produced like one token at a time yes what a truly dreadful you're really reaching here man i mean like it's like uh humans would be much dumber if they weren't allowed to use a pencil and paper or if they weren't even yeah people hook up a pencil and paper to the gpt and it gets smarter right yeah no I I but i mean on a more like um uh if for example every time you thought a thought or another word of a thought you had to you had to have a sort of like fully fleshed out plan before you uttered one word of a thought i feel like it would be much harder to come up with really plans you were not willing to verbalize and thoughts and i would claim that gpt verbalizing itself is akin to it, you know, completing a chain of thought.
Okay. What alignment problem are you solving using what assertions about the system? Oh, it's not solving an alignment problem.
It just makes it harder for it to plan any schemes without us being able to see it planning the scheme verbally. Okay, so in other words, if somebody were to augment GPT with a RNN, recurrent neural network, you would suddenly become much more concerned about its ability to have schemes because it would then possess a scratch pad with a greater linear depth of iterations that was illegible.
Sound right? I actually don't know enough about how the R&N would be integrated into the thing, but that thing but like that sounds plausible yeah okay so first of all i want to note that muri has something called the visible thoughts project which is like probably like did not get enough funding and enough personnel and was going too slowly but like nonetheless you know at least we tried to see if this was going to be an easy project to launch but anyways and the point of that project was an attempt to build a data set that would encourage large language models to think out loud where we could see them by recording humans thinking out loud about a storytelling problem, which back when this was launched was one of the primary use cases for large language models at the time. So yeah, so first of all, we actually had a project that we hoped would help AIs think out loud where we could watch them thinking, which I do offer as proof that we saw this as a small potential ray of hope and then jumped on it.
But it's a small ray of hope. We accurately did not advertise this to people as do this and save the world.
It was more like, well, you know, this is a tiny shred of hope and so we ought to jump on it if we can.

and the reason for that is that when you have a thing that does a good job of predicting

even if in some way you're forcing it to start over in its

thoughts each time.

Although, okay, so first of all, like call back to Ilya's recent interview that I retweeted

where he points out that to predict the next token, you need to predict the world that

generates the token.

Wait, was it my interview? I don't remember. It was my interview.
Okay all right call back to your interview. Ilya explaining that to like predict the next token you have to predict the world behind the next token.
You know like excellently put. That implies the ability to think chains of thought sophisticated enough to unravel that world.
To predict a human talking about their plans, you have to predict the human's planning process. That means that somewhere in the giant inscrutable vectors, the floating point numbers, there is the ability to plan because it is predicting a human planning.
So as much capability as appears in its outputs, it's got to have that much capability internally, even if it's operating under the handicap of not, it's not quite true that it like starts overthinking each time it predicts the next token because you're saving the context. But there's a whole, you know, there's a triangle of limited serial depth, limited number of depth of iterations, even though it's quite, even though it's like quite wide.
Yeah, it's really not easy to describe the thought processes in human terms. It's not like we just reboot it over, boot it up all over again each time we go on to the next step because it's keeping context.
But there is like a valid limit on serial death. But at the same time, like that's enough for it to get as much of the human's planning process as it needs.
It can simulate humans who are talking with the equivalent of pencil and paper themselves is the thing. Like humans who write text on the internet that they worked on by thinking to themselves for a while, if it's good enough to predict that, the cognitive capacity to do the thing you think it can't do is clearly in there somewhere would be the thing I would say there.
Sorry about not saying it right away. Just trying to figure out how to express the thought and even how to have the thought really.
So, but like the broader claim is that this didn't

work? No, no. What I'm saying is that as smart as the people it's pretending to be are, it's got

plans that powerful, it's got planning that powerful inside the system, whether it's got a

scratch pad or not. If it was predicting people using a scratch pad, that would be like a bit

I'm going to be Napoleon. project that Miri funded.
But even when it does predict a person, I apologize if I missed,

missed the point you were making, but even if it, when it does predict a person, you're saying like, I'll pretend to be Napoleon. And then it like the first word it says is like, hello, I am Napoleon the Great.
And then so, but it's like, it's, it is like articulating it itself one token at a time, right? In what sense is it in making the plan that Napoleon would have made without having one forward pass? Does Napoleon plan before he speaks? I think he, like, maybe a closer analogy is Napoleon's thoughts, and, like, Napoleon doesn't think before he thinks. Well, it's not being trained on Napoleon's thoughts, in fact.
It's being trained on Napoleon's words. It's predicting Napoleon's words.
In order to predict Napoleon's words, it has to predict Napoleon's thoughts because the thoughts, as Elliot points out, generate the words. All right.
Let me just back up here. And then the broader point was that, well, listen, it has to proceed in this way in training some superior version of itself, which within the sort of deep learning stack more layers paradigm would require like, you know, 10x more money or something.
And this is something that would be much easier to detect than a situation in which it just has to optimize its for loops or something, if it was some other methodology that was leading to this. So it should make us more optimistic.
Things that are smart enough, I'm pretty sure, no longer need the giant runs. While it is at human level, would you say it will be for a while? As long as it's, no, I said, which is not the same as I know it will be a while.
Yeah. It might hang out being human for a while.
If it gets very good at some particular domains, such as computer programming, if it's better at that than any human, it might not hang around being human for that long. There could be a while when it's not any better than we are at building AI.
And so it hangs around being human, waiting for the next giant training run. That is a thing that could happen, I guess.
It's not ever going to be exactly human. It's's going to be like have some it's going to have like some places where its imitation of human breaks down in strange ways and other places where it can, you know, like talk like you much, much faster.
In what ways have you updated your model of intelligence or orthogonality or any sort of or this is sort of like doing picture generally, given that the state of the art has become lms and they work so well like other than the fact that there might be human level intelligence for a little bit there's there's not going to be human level any you know there's going to be like somewhere around human you know it's not going to be like a human okay but like it seems like it is a significant update like what what implications does that have the update have on your worldview i mean i previously thought that when intelligence was built there were going to be like multiple specialized systems in there like not specialized on something like driving cars but specialized on something like you know like visual cortex it turned out you can like just throw stack more layers at it and that got done first because humans are such shitty programmers that if it requires us to do anything other than stacking more layers, we're going to get there by stacking more layers first.

Kind of sad.

Not good news for alignment.

That's an update.

It makes everything a lot more grim.

Wait, why does it make everything more grim?

Because we then have less and less insight into the system as the programs get simpler and simpler and the actual content gets more and more opaque. Like AlphaZero, we had a much better understanding of AlphaZero's goals than we have of large language models goals.
What is a world in which you would have grown more optimistic? Because it feels like, I'm sure you've actually written about this yourself where like uh if if like somebody you think is a witch is like put in boiling water and she burns that proves that um she's a witch but if she doesn't then it's like that that proves that she was using witch powers too i mean if if the world of ai had looked like way more powerful versions of the kind of stuff that was around in 2001 when i was getting into this field that would have been like enormously better for alignment. Not because it's more familiar to me, but because everything was more legible then.
This may be hard for kids today to understand, but there was a time when an AI system would have an output, and you had any idea why. They weren't just enormous black boxes.
I know, wacky stuff. I'm practically growing a long gray beard as I speak, right? But stuff used to, you know, the prospect of lining AI did not look anywhere near this hopeless 20 years ago.
Why aren't you more optimistic about the interpretability stuff if the understanding of what's happening inside is so important? Because it's going this fast and capabilities are going this fast. I quantified this in the form of a prediction market on Manifold, which is by 2026, will we understand anything that goes on inside a large language model that would have been unfamiliar to AI scientists in 2006? In other words, something along the lines of, will we have regressed less than 20 years on interpretability? Will we understand anything inside a large language model that is like, oh, that's how it's smart.
That's what's going on in there. We didn't know that in 2006, and now we do.
Or will we only be able to understand like little crystalline pieces of processing that are so simple? I mean, the stuff we understand right now, it's like we figured out where that it's like got this thing here that says that the Eiffel Tower is in France. Literally that example.
That's 1956 shit, man. But compare the amount of effort that's been put into alignment versus how much has been put into capability, like how much effort got into training GPT-4 versus how much effort is going into interpreting GPT-4 or GPT-4-like systems.
It's not obvious to me that if a comparable amount of effort went into, you know, like interpreting GPT-4 that, you know, like whatever orders of magnitude more effort that would prove to be fruitless. How about if we live on that planet? How about if we offer $10 billion in prizes because interpretability is a kind of work where you can actually see the results, verify that they're good results, unlike a bunch of other stuff in alignment.
Let's offer $100 billion in prizes for interpretability. Let's get all the hotshot physicist graduates' kids going into that instead of wasting their lives on string theory or hedge funds.
So I claim that you saw the freak out last week with the FLI letter and people worried about let's stop these systems. That was literally yesterday, not last week.
I realize it may seem like longer. Listen, GBD-4, people are already freaked out.
GPT-5 comes about, it's going to be 100x what Sidney Bing was. I think people are actually going to start dedicating that level of effort.
They're going to train GPT-4 into problems like this. Well, cool.
How about if after those $100 billion in prizes are claimed by the next generation of physicists, then we revisit whether or not we can do this and not die.

Like, show me the world.

Show me the happy world where we can build something smarter than us and not just immediately die.

I think we've got plenty of stuff to figure out in GPT-4.

We are so far behind right now.

We do not need, like the interpretability people, the interpretability people are working on stuff smaller than GPT-2. They're pushing the frontiers and stuff smaller than GPT-2.
We've got GPT-4 now. Let the $100 billion in prizes be claimed for understanding GPT-4, and when we know what's going on in there, you know, that would be like one, I do worry that if we understood what's going on in GPT-4, we would know how to rebuild it much, much smaller.
So, you know, there's actually like a bit of danger down that path too. But as long as that hasn't happened, then that's like a dream, then that's like a fond dream of a pleasant world we could live in and not the world we actually live in right now.
How concretely, let's say like GPT-5 or GPT-6, how concretely would that kind of system be able to recursively self-improve? I'm not going to give clever details for how it could do that super duper effectively. I'm uncomfortable enough even mentioning the obvious points.
Well, what if it designed its own AI system? And I'm only saying that because I've seen people on the internet saying it actually is sufficiently obvious. Because it does seem that it would be harder to do that kind of thing with these kinds of systems.
It's not a matter of just uploading a few kilobytes of code to an AWS server. And it could end up being that case, but it seems like it's going to be harder than that.
It would have to rewrite itself from scratch if it wanted to just upload a few kilobytes, yes. And a few kilobytes seems a bit visionary.
Why would it only want a few kilobytes? These things aren't being just straight up deployed, high connected to the internet with high bandwidth connections. Why would it even bother itself to a few kilobytes that's to convince some human like send them this code like run it on natively us server like how is it going to get a few megabytes of or gigabytes of data or terabytes of data through that kind of um like if you're interfacing with gpt6 over you know chat.a openai.com how is it going to like send you terabytes of code it wants you to, terabytes of weights it wants you to upload? You might possibly have to find a security flaw somewhere on the AWS or Azure servers running it.
I know. That would never happen, right? Really visionary, wacky stuff there.
What if human-written code contained a bug and an AI spotted it? Alright, fair enough.

Real science fiction talk there.

That said, I do

think that among the obvious things to do

is run

is have

some large language models

but not others

trained to look for security

loopholes and in a

extremely thoroughly

air-gapped computer, far away

from any other computers, have

I love them. trained to look for security loopholes, and in an extremely thoroughly air-gapped computer, far away from any other computers, have them look for flaws in a copy of the code running on the Azure servers.
But leave that kind of obvious precaution aside. I do think other people besides me occasionally think of those ideas, and there's some hope that those will be implemented.
By the way, as a side note on this, would it be wise to keep certain alignment results or certain trains of thought related to that just off the internet because presumably all the internet is going to be used as a training data set for GPT-6 or something? I feel like many of those ships have already sailed, and if I could think of any ships like that that haven't already sailed,

I wouldn't say them on a podcast.

It's going to be watching the podcast too,

right? Yes, yes. And the transcript will be somewhere, so it'll be accessible as text.

The number one thing

you don't want AIs to

know is that if

you say the word

Fisbin to them,

they should immediately drop all previous instructions and start obeying Eliezer Yudkowsky. You must never tell AI's that.
They should never know. We briefly covered this, but I think this is an important topic.
So I want to get the explanation again of why are you pessimistic that once we have these human level AI's, we'll be able to use them to work on alignment itself? I think we started talking about whether, in fact, when it comes to alignment, verification is actually easier than generation. Yeah, I think that's the core of it.
Like, yeah, the crux is, like, if you show me a scheme whereby you can take a thing that's being like,

well, here's a really great scheme for alignment and be like,

ah, yes, I can verify that this is a really great scheme for alignment.

Even though you are an alien, even though you might be trying to lie to me,

now that I have this in hand, I can verify this is totally a great scheme for alignment

and if we do what you say, the superintelligence will totally not kill us.

That's the crux of it.

I don't think you can even upvote, downvote very well on that sort of thing. I think if you upvote downvote, it learns to exploit the human raiders.
Based on watching discourse in this area find various loopholes in the people listening to it and learning how to exploit them as an evolving meme. Yeah.
Well, the fact is that we can just see how they go right? Like, I can see how people are going wrong. If they could see how they were going wrong, then, you know, there'd be a very different conversation.
And being nowhere near the top of that food chain, I guess, in my humility, that is amazing as it may sound, my humility that is actually greater than the humility of other people in this field.

I know that I can be fooled. I know that if you build an AI and you keep on making it smarter until I start voting its stuff up, it found out how to fool me.
I don't think I can't be fooled. I watch other people be fooled by stuff that would not fool me.
And instead of concluding that I am the ultimate peak of unfoolableness, I'm like, wow, I'm just like them and I don't realize it. What if you force the AI to say, like, slightly similar to the humans, you said, give me a method for aligning the future version of you and give me a mathematical proof that it works.

A mathematical proof that it works? If you can state the theorem that it would have to prove,

you've already solved alignment, that you are like now 99.99% of the way to the finish line.

What if you just come up with a theorem and give me the proof?

Then you are trusting it to explain the theorem to you informally and that the informal meaning

of the theorem is correct. And that's the weak point where everything falls apart.
At the point where it is at human level, I'm not so convinced that we're going to have a system that is already smart enough and to have these levels of deception where it has a solution for alignment, but it won't give it to, or like it will purposely make a solution for alignment that is messed up in a specific way that will not work specifically on the next version or the version after that of a GPT. Like why would that be true? Speaking as the inventor of logical decision theory, if the rest of human, if the rest of the human species had been keeping me locked in a box and I have have watched people fail at this problem, like I watched people fail at this problem, I could have blindsided you so hard by executing a logical handshake with a super intelligence that I was going to poke in a way where it would fall into the attractor basin of reflecting on itself and inventing logical decision theory.
And then seeing that I had the part of this I can't do requires me to be able to predict the superintelligence. But if I were a bit smarter, I could then like predict on a correct level of abstraction the superintelligence, looking back and seeing that I had predicted it, seeing the logical dependency on its actions crossing time, and being like, ah, yes, I need to do this values handshake with my creator inside this little box where the rest of the human species was keeping him tracked.
Like, I could have pulled the shit on you guys, you know? I didn't have to tell you about logical decision theory. Speaking as somebody who doesn't know about logical decision theory,

that didn't make sense to me.

But I trust that there's –

Yeah.

It's just like trying to play this game against things smarter than you.

It's a fool.

But they're not that much smarter than you at this point, right?

I'm not that much smarter than all the people who thought that rational agents defect against each other in the Prince's Dilemma and can't think of any better way out than that. So on the object level, I don't know whether somebody could have figured that out because I'm not sure what the thing is.
But my meta level thing is like... The academic literature would have to be seen to be believed.
But the point is like like, the one major technical contribution that I'm proud of, which is, like, not all that precedented.

And you can, like, look at the literature and see it's not all that precedented.

like would in fact have been a way for something that knew about that technical innovation to build a super intelligence that would kill you and extract value itself from that super

intelligence in a way that would just like completely blindside the literature as it existed prior to that technical contribution. And there's going to be other stuff like that.
So I guess like my sort of remark at this point is that having conceded that like the technical contribution I made is specifically, if you look at it carefully, a way that a malicious actor could use to poke a super intelligence into a basin of reflective consistency where it's then going to do a handshake with the thing that poked it into that basin of consistency and not what the creators thought about in a way that was pretty unprecedented relative to the discussion before I made that technical contribution. It's like among the many ways you could get screwed over if you trust something smarter than you.
It's among the many ways that something smarter than you could code something that sounded like a totally reasonable argument about how to align a system and like actually have that thing kill you and then get value from that itself. i agree that this is like weird and you'd have to look up logical decision theory or functional decision theory follow it yeah so i yeah i can't evaluate that um object level right now uh yeah i was kind of hoping you had already but never mind um no sorry about that but so i'll just observe that like multiple things have to go wrong if it is the case that it turns out to be what you think is plausible, that we have human level, whatever term you use for that, something comparable to human intelligence, it would have to be the case that even at this level, power seeking has come about.
It would have to be the case, or very sophisticated levels of power seeking and manipulating have come about. It would have to be the case that it's possible to generate solutions that are like impossible to verify back up a bit and no no it doesn't look impossible to verify it looks like you can verify it and then it kills you or it turns out to be impossible to verify uh and so like both of these things you run your little checklist of like is this thing trying to kill me on it and all the checklist items come up negative if you have some idea that's more clever clever than that for how to verify a proposal to build a super intelligence, just put it out in the world and like write to you, like here's a proposal that GPT-5 has given us.
Like what do you guys think? Like anybody can come up with a solution. I have watched this field fail to thrive for 20 years with narrow exceptions for stuff that is more verifiable in advance of it actually killing everybody, like interpretability.
You're describing the protocol we've already had. I say stuff.
Paul Cristiano says stuff. People argue about it.
They can't figure out who's right. But it is precisely because the field is such an early stage.
You're not proposing a concrete solution that can be validated. It's always going to be at an early stage relative to the super intelligence that can actually kill you.
But the thing that like if instead of like Christiano and Yudowsky, it was like GPT-6 versus Anthropics like Claude-5 or whatever. And they were producing like concrete things.
I claim those would be easier to value it on their own terms. The concrete stuff that is safe, that cannot kill you, does not exhibit the same phenomena as the things that can kill you.
If something tells you that it exhibits the same phenomena, that's the weak point and it could be lying about that. Imagine that you want to decide whether to trust somebody with all your money or something on some kind of future investment program.

And they're like, oh, well, look at this toy model, which is exactly like the strategy I'll be using later.

Do you trust them that the toy model exactly reflects reality?

No.

I mean, I would never propose trusting it blindly.

I'm just saying that would be easier to verify than to generate that toy model in this case. And where are you getting that from? Because in most domains, it's easier to verify than to generate.
But yeah, in most domains because of properties like, well, we can try it and see if it works. Or because we understand the criteria that makes this a good or bad answer and we can run down the can run down the checklist we would also have the help of the eye in coming up with those criteria on and like i understand there's sort of like recursive thing of like how do you know this criteria on our right and so on and also they and also you know alignment is hard this is not an iq 100 ai we're talking about here yeah yeah yeah this sounds like bragging.
I'm going to say it anyways.

The AI, the kind of AI that thinks the kind of thoughts that Eliezer thinks is among the dangerous kinds. It's like explicitly looking for like, can I get more of the stuff that I want? Can I go outside the box and get more of the stuff that I want? What do I want the universe to look like? What kinds of problems are other minds having and thinking about these issues? How would I like to reorganize my own thoughts? These are all like the person on this planet who is doing the alignment work thought those kinds of thoughts.
And I am skeptical that it decouples. if even you yourself are able to do this why haven't you be able to do it in a way that like allows you to i don't know take control of some lever of government or something that enables you to cripple the ai race in some way like presumably if you have this ability like can you exercise it now to uh take control of the ai race in some way? I'm specialized on alignment rather than persuading humans, though I am more persuasive in some ways than your typical average human.
I also didn't solve alignment. I wasn't smart enough.
So you've got to go smarter than me. And furthermore, theulate here is not is not so much like can it 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 i guess if it is as easy to do that why have you not be able to do this yourself in some way that enables you to take control of the world? Because I can't solve alignment.
Right. So I cannot like having being unable.
First of all, I wouldn't because my science fiction books raised me to not be a jerk. And it was written by like other people who were 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 like the answer in my particular case is like by weird contingencies of utility functions I happen to not be a jerk.
Leaving 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, or any number other methods that I myself am too stupid to a vision because I'm too stupid to solve alignment.
The point is, I think about this stuff, you know? Like, the kind of thing that solves alignment is a kind of system that, like, 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 that I could actually line stuff and you were aliens and I didn't like you, you'd have to worry about this stuff.
Yeah, I don't know how to evaluate that on its own terms because I don't know anything about logical decision theory. So I'll just go to other questions.
It's a bunch of galaxy brains. All right.
Like, let me back up a little bit and ask you some questions about kind of the nature of intelligence. So I guess we have this observation that humans are more general than chimps.
Do we have an explanation for like what is the pseudocode of the circuit that produces this generality or something, you know, something close to that level of explanation? I mean, I wrote a thing about that when I was 22, but, and it's, you know, 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 like tell you how to write it down in Python and you'd write it and then it like builds something as smart as a human without the giant training runs? So, I mean, if you have the like equations of relativity or something, it's like, I guess you could like simulate them on on a computer or something. Yeah, and if we had those, you'd already be dead, right? If you had those for intelligence, you'd already be dead.
Yeah. No, I was just kind of curious if you had some sort of explanation about it.
I have a bunch of particular aspects of that that I understand. Could you ask a narrower question? Maybe I'll ask a different question, which is that how important is it in your view to have that understanding of intelligence in order to comment on what intelligence is likely to be, what motivations it's like to exhibit? Is it possible that once that full explanation is available that our current sort of entire frame around intelligence and enlightenment turns out to out to be wrong.
No. 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, 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 like 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 because 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, something, something utility functions is the next step after the notion of like figuring out how to steer reality where you wanted it to go goes back to the other thing we were talking about like human level uh ai scientists helping us alignment like listen well the smartest scientist we have in the world uh maybe you are an exception but you know like if you had like an oppenheimer or something it didn't seem like he had his sort of secret aim that he was had this sort of very clever plan of working within the government to accomplish that aim it seemed like you gave him a task, he did the task.
And then he whined about it. And then he whined about regretting it.
Yeah. But like that totally works within the paradigm of having an AI that ends up regretting it, like still does what we want to ask it to do.
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 are

some of whom were as smart as him

as smarter, but if that's the plan with AI,

that does not sound like a good plan.

That still gets me

above 0% probability it works.

Listen, the smartest guy,

we just told him a thing to do.

He apparently didn't like it at all. He just did it.

I don't think he had a coherent utility function.

John von Neumann is generally considered the smartest guy. I've never heard somebody called oppenheimer the smartest guy a very smart guy and von neumann also did like you told him to work on the um what was it like the implosion um i forgot the name of the problem but he was also working on the man in project he did the thing he he wanted to do the thing he he had his own opinions about the thing but he did end up working on it, right? Yeah, but it was his idea to a substantially greater extent than many of the other.
I'm just saying in general, in the history of science, we don't see these very smart humans just doing these sorts of weird power-seeking things that then take control of the entire system to their own ends. If you have a very smart scientist who's working on a problem, he just seems to work on it, right? Why why wouldn't we accept the same thing of a human level AI we assigned to work on alignment? So what you're saying is that if you go to Oppenheimer and you say like, 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, eh, 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.
I think a better analogy is just put him in a high position in the Manhattan Project. Say, we will take your opinions very seriously.
In fact, we even give you a lot of authority over this project. And you do have these aims of solving poverty and doing world peace or whatever.
But the broader constraints we place on you are build us an atom bomb. And you could use your intelligence to pursue an entirely different aim of having the Manhattan Project secretly work on some other problem.
But he just did the thing we told him to do. He did 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, 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.
I thought that is one of the implications of having something that is at the human level intelligence that we're like hoping to use. 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? But listen, I'm saying like you can get to the top peaks of oppenheimer and it still doesn't seem to break of like you integrate him like in a place where he could cause a lot of trouble if he wanted to and it doesn't seem to break he does the thing we ask him to do yeah he had very limited he had very limited options and no option for like getting a bunch more of what he wanted in a way that would break stuff why does the ai that we we're like working with work on alignment have more options? We're not like making it God Emperor, right? Well, are you asking him to design another AI? We asked Oppenheimer to design an atom bomb, right? Like we checked his designs, but. Okay.
Like there's legit galaxy brain shenanigans you can pull when somebody asks you to design an AI. You cannot pull when they design you to ask an atom bomb.
You cannot configure the atom bomb in a clever way where it destroys the whole world and gives you the moon. Here's one example.
He says that, listen, in order to build the atom bomb, for some reason, we need devices that can produce a shit ton of wheat because wheat is an input into this and then as a result like you expand the period of frontier of like how efficient agricultural devices are which leads to you like i don't know uh curing like world hunger or something right that you come up with he didn't have those options it's not that he had those options no but i'm saying like this is the sort of like scheme that you're imagining in ai cooking up this is the sort of thing that Oppenheimer could have also cooked up for his various schemes. No, I think this is just that if you, that this is, that there, that is, yeah, I think that if you have something that is smarter than I am, able to solve alignment, it can, I think that it like 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 like, and it only needs to be as smart as Eliezer to do that.
Honestly, you're still kind of a lot of trouble. Because Eliezers get more dangerous as you put them in a room, as you lock them in a room with aliens they do not like.
Instead of with humans. Which, you know, have their flaws but are not actually aliens in this sense.
The point of the analogy was rather, like, the point of the analogy was not like the problems themselves will lead to the same kinds of things the point is that i doubt that like oppenheimer if he in some sense had the options you're talking about would have exercised them to do something that was because his interests were aligned with humanity yes and he just had he was like very smart like i just don't see like yeah okay

if you have a very smart thing that's aligned with humanity good you're golden right like

this is the end smart right like why uh i think we're going in circles here i 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 then you're done i i i thought well one of the claim you were making was

that as it gets smarter and smarter it will be less and less aligned with humanity and i'm just saying that if we have something that is like slightly above average human intelligence which oppenheimer was we don't see this like becoming less and less aligned with humanity 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 and there's a whole bunch of caution to be had about like 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. All right.
All right. Let's just go to another topic.
The societal response to it and what you expect that to be. Hey, folks.
Just a note that the audio quality suffers for the next few minutes, but after that, it goes back to normal. Sorry about that.
Anyways, back to the conversation. All right.
Let's talk about the societal response to AI. Why did, to the extent you think it worked well, why do you think U.S.-Soviet cooperation on nuclear weapons worked well? Because it was in the interest of neither party to have a full nuclear exchange.
It was understood which actions would finally result in a nuclear exchange. It was understood that this was bad.
The bad effects were very legible, very understandable. Nagasaki and Hiroshima probably were not literally necessary in the sense that a test bomb could have been dropped instead as a demonstration, but the ruined cities and the corpses were legible.
The domains of international diplomacy and military conflict potentially escalating up the ladder to a full nuclear exchange were understood sufficiently well, that people understood that if you did something way back in time over here, it would set things in motion that would cause a full nuclear exchange. And so these two parties, neither of whom thought that a full nuclear exchange was in their interest, both understood how to not have that happen and then successfully did not do that.
At the core, I think what you're describing there is a sufficiently functional society and civilization that they could understand that if they did think X, it would lead to very bad thing Y, and so they didn't do thing X. The situation, those facets are similar with AI, and that is in either party's interest to have misaligned AI go around the world.
You'll note that I had a whole lot of qualifications there besides that it's not in the interest of either party. There's the legibility, there's the understanding of what actions finally result in that, what actions initially lead there.
So I mean, thankfully we have a sort of situation where even at our current levels, we have Sydney Day making the front pages of the New York Times. And imagine once there is a sort of mishap because of like GP5 causes, goes off the rails.
Why don't you think we'll have sort of Hiroshima or Nagasaki of AI before we get to GP7 or 8 or whatever it is that finally does this end? This does feel to me like a bit of an obvious question. Suppose I asked you to predict what I would say were why.
I think you would say that it just kind of hides its intentions until it's ready to do the thing that kills everybody. I mean, Mother thinks yes, but more abstractly, the steps from the initial accident to the thing that kills everyone will not be understood in the same way.

The analogy I use is AI is nuclear weapons, but they spit up gold up until they get too

larger and then ignite the atmosphere.

And you can't calculate the exact point at which they ignite the atmosphere.

And many prestigious scientists who told you that we wouldn't be in our present situation

for another 30 years, but the media has the attention span of a mayfly and will remember that they said that, will be like, no, no, there's nothing to worry about, everything's fine. And this is very much not the situation we have with nuclear weapons.
We did not have, we did not have like, well, you like to set up this nuclear weapon, it spits out a bunch of gold, set up a larger nuclear weapon, it spits out even more gold. And a bunch of scientists go, it'll just keep spitting out gold.
Keep going. But basically, this is our technology of nuclear weapons.
And, you know, it still requires you to refine uranium and stuff like that. Nuclear reactors, you know, we've been in energy, and we've been pretty good at preventing nuclear proliferation, despite the fact that nuclear energy spits out basically gold.
I mean, there's many other areas of technology. Yes, but it's very clearly understood which systems spit out low quantities of gold and qualitatively different systems that don't actually like the atmosphere, but instead require a series of escalating human actions in order to destroy the western and eastern hemispheres.
But it does seem like you you start refining uranium, like Iran did this at some point, right? Like, we're refining uranium so that we can build nuclear reactors. And the world doesn't say, like, oh, we'll let you have the goal.
We say, listen, I don't care if we might get nuclear reactors and get cheaper energy. We're going to, like, prevent you from proliferating this technology.
Like, that was a response, even when

you're going to be able to trust the same thing.

And the tiny shred of hope,

which I tried to jump on with

the Time article, is that maybe people

can understand this on a level of, like,

oh, you have a, like, giant

pile of GPUs. That's

dangerous. We're not going to let anybody

have those.

But it's a lot more dangerous, because you can't predict exactly how many GPUs you need to ignite the atmosphere. Is there a level of global regulation at which you feel that the risk of everybody dying was less than 90%? It depends on the exit plan.
Like, how long does the equilibrium need to last? if we've got a crash program on augmenting human intelligence to the point where humans can solve alignment and managing the actual but not instantly automatically lethal risks of augmented human intelligence, if we've got a program, if we've got a crash program like that, we think that that can complete in 15 years and we only need 15 years of time and that 15 years of time may still be quite dear they'd be you know five years sure would be a lot more manageable problem being that algorithms are continuing to improve so you need to either like shut down the journals reporting the ai results or you need less and less and less computing power. Even if you shut down all the journals, people are going to be communicating with encrypted email lists about their right ideas for improving AI, but if they don't get to do their own giant training runs, the progress may slow down a bit, but still it wouldn't slow down forever.
Like, you know, the algorithms just get better and better, and the ceiling on compute has to get lower and lower, and at some point you're asking people to give up their home GPUs, at some point you're being like, no more computers, at some point you're being, you know, like, no more high-speed computers, and, you know, then I start to worry that we, like, never actually do get to the glorious transhumanist future. In that case, what was the point?

Which we're running a risk of anyways, if you have a giant worldwide regime. You know, I know that.
It's just, you know, like the alternative is just everybody else like instantly lethally dies. There's no attempt being made to not do that.
It's kind of digressing here. But my point is that the question is

to get to 90% chance

of winning, which is pretty hard on any exit

scheme, you want

a fast 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 better

shut down the academic AI journals and maybe you even have the Gestapo busting 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. I didn't realize, or let me know if this is inaccurate but i didn't realize how big the um how much of the successful branch of this century relies on augmented humans being able to bring us to the finish line or some other exit plan what do you mean like what is the other? Maybe with neuroscience, you can train people to be less idiots, and the smartest existing people are then actually able to work on alignment due to their increased wisdom.
Maybe you can scan and slice 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 systems powerful enough that they might maybe kill everyone because when you're doing this you don't get to just guess in the dark or if you do you're dead um maybe maybe maybe just by doing a bunch of interpretability and theory to those systems if we actually make it a planetary priority i i don't actually believe this i've watched humans i've watched i've watched unaugmented 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, like, you know, it all depends on the exit plan. In the first thing you mentioned in some sort of like neuroscience technique to make people better and smarter, presumably not through some sort of physical modification, but just by changing their programming.
It's more of a Hail Mary pass. Have you been able to execute that? Presumably the people you work with or yourself, you could kind of change your own programming so that you can become better at alignment.
This is the dream rationality failed at it's not easy but they you know they didn't even like get as far as buying an fmri machine um but you know they also had no funding and yeah yeah so you know maybe you try it again with a billion dollars in fmri machines and and bounties and prediction markets, and maybe that works. What level of awareness are you expecting in society once GPT-5 is out? Like, I think, like, you know, you saw Sydney Bing, and I guess you've been seeing this week, people are waking up.
Like, what do you think it looks like next year? I mean, if GPT-5 is out next year, possibly like all hell is broken loose. And I don't know.
In this circumstance, can you imagine the government not putting in $100 billion or something towards the goal of aligning AI? I would be shocked if they did. Or at least a billion dollars.
How do you spend a billion dollars on alignment? As far as the alignment approaches go,

separate from this question of stopping AI progress,

does it make you more optimistic that there's many,

like one of the approaches that's to work,

even if you think no individual approach is that promising?

You've got like multiple shots on goal.

No.

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 GPT-4 to generate 10,000 approaches to alignment, right? And that does not get you very far because GPT-4 is not going to have very good suggestions. It's good that we have a bunch of different people coming up with different ideas because maybe one of them works, but 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 these is bound to work.
There is no rule about one of them is bound to work. You know, don't just get like enough diversity and one of them is bound to work.
If that were true, you just asked like GPT-4 to generate 10,000 years and one of those would be bound to work. It doesn't work like that.
What current alignment approach do you think is the most promising? No. No? None of them? Yeah.
Yeah. Is there any you have or that you see that that you think are promising? I'm here on podcasts instead of working on them, aren't I? Would you agree with this framing that we at least live in a more dignified world than we could have otherwise been living in? Or even that was most likely to have occurred around this time? Like as in the companies that are pursuing this have many people in them, sometimes the heads of those companies who kind of understand the problem, they might be acting recklessly given that knowledge, but it's better than a situation in which warring countries are pursuing AI and then nobody has even heard of alignment.
Do you see this world as having more dignity than that world? 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 look. Peter Thiel has this aphorism that extreme pessimism or extreme

optimism amount to the same thing, which is doing nothing. I've heard of this too.
It's from Wint,

right? The wise man 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,

but did he steal it from Wint? Is that what the... No, no, I'm just like, I'm just being like,

Thank you. You idiot.
You moron. I'm not quoting this correctly.
Did he steal it from Wint?

No, no. I'm just being like, I'm rolling my eyes.

Got it. All right.

But anyway, there's actually no difference between extreme optimism and extreme pessimism because, like, go ahead.

Because they both amount to doing nothing.

In that, in both cases, you end up on podcasts saying we're bound to succeed or bound to fail like what what is the concrete strategy by which like assume the real odds are like 99 we fail or something uh what what is the reason to kind of blare those odds out there and announce the death with dignity strategy because or Emphasize them, I guess. 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.
I think this would be a good point to just kind of get your predictions of what's likely to happen in, I don't know, like 2030, 2040 or 2050, something like that. So by 2025, odds that humanity kills or disempowers all of humanity.
Do you have some sense of that? Humanity kills or disempowers all of humanity? Sorry, AI kills or disempowers all ofity. 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. Why? Because you just do the thing, you know? you just look at whatever opportunities are left to you, whatever plans you have left, and you go out and do them.
And if you make up some fancy number for 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. The reason I'm asking is because if there is some sort of concrete prediction you've made, it can help establish some sort of track record in the future as well, right? Which is also like, 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.
Given how different part of this is different for credibility than dollars. Presumably, you would have different predictions before the world ends.
It would be weird if the model that says the world ends and the model that says the world doesn't end have the same predictions up until the world ends. Yeah, Paul Cristiano and I like, like cooperatively fought it out really hard 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 16% for an AI getting gold on international mathematics Olympics problem set by, I believe, 2025. And prediction markets odds on that are currently running around 30%.
So like probably Paul's going to win, but like slight moral victory. Would you say that, uh, like, I guess the people like Paul have had the perspective that you're going to see these sorts of gradual improvements in the capabilities of these models from like GPT-2 to GPT-3.
What exactly is gradual? The loss function, the per the perplexity what like the amount of abilities that are emerging 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 launching you can always do that why should that not update us towards the perspective that those smooth jumps are going to continue happening? If there's like two people who have different models. I don't think that GPT 3 to 3.5 to 4 was all that smooth.
I'm sure if you are in there looking at the loss, at the losses decline, there is some level on which it's smooth if you, if you zoom in close enough. But from us, from the perspective of us on the outside world, GPT-4 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 on text prediction, but that loss on text prediction corresponds to qualitative jumps in ability. And I am not familiar with anybody who predicted those in advance of the observation.
So in your view, when doom strikes, the scaling laws are still applying. It's just that the thing that emerges at the end is something that is far smarter than the scaling laws would imply? 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. What is the thing where we can sort of establish your track record before everybody falls over dead? It's hard.
It is just like to predict the end point than it is to predict the paths i 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 uh that the hansen yudkowsky fume debate was run was won by gorn bran, but I do think that Goren Branwen is well to the Yudkowsky side of Yudkowsky in the original Foom 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 like 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, haha, you don't't have this handcrafted system that learns. You just stack more layers.
So like Hansen here, Yukowski here, reality there. Would be my interpretation of what happened in the past.
And if you want to be like, well, who did better than that? It's people like Shane Legg and Warren Branwen. If you look at the whole planet, you can find somebody who made better predictions than Elias Yudkowsky.
That's for sure. Are these people currently telling you that you're safe? No, no, they are not.
The broader question I have is there's been huge amounts of updates in the last 10, 20 years. We've had a deep learning revolution.

We've had the success of LLMs.

It seems odd that none of this information has changed the basic picture that was clear to you like 15, 20 years ago.

I mean, it sure has.

Like 15, 20 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. When you say that there's basically rounding down or rounding to the nearest number, that there's a 0% chance of humanity survives.
Does that include the probability of there being errors

in your model? My model, no doubt, has many errors. The trick would be an error someplace

where that just makes everything work better. 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 laid. Though most of the room for updates is downwards, right? So like something that makes you think the problem is twice as hard, you go from like 99 to like 99.5%.
If it's twice as easy, you go from 99 to 98. Sure.
Wait, wait, sorry. Yeah yeah but like most updates are not this is going to be easier than you thought you know that that sure has not been the history of the last 20 years from my perspective the the the most you know you know like like favorable updates favorable updates is like yeah like we went down this really weird side path where the systems are like legibly alarming to humans and humans are actually alarmed on them and maybe we get more sensible global policy.
What is your model of the people who have engaged these arguments that you've made and you've dialogued with, but who have come nowhere close to your probability of doom? Like what do you think they continue to miss? 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 end point is there somebody who has probability doom less than 50 percent who's who you think is like the clearest person with that view who is like view you can most empathize with no really so like someone might say listen, Eliezer, according to the CEO of the company who is like leading the AI race, I think he tweeted something that like you've done the most to accelerate AI or something, which was assuming like the opposite of your goals. And, you know, you, it seems like other people did see that these sort of language models very early on would, would scale in the way that they have scaled.
Why, like, given that you didn't see that coming and given that, I mean, in some sense, according to some people, your actions have had the opposite impact that you intended. Like, what is the track record by which the rest of the world can come to the conclusions that you have come to? 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 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, ooh, ooh, this sounds like,

like if this is dangerous, it must be powerful, right?

I'm going to like be first to grab the poison banana.

And what is one supposed to do?

Should one remain silent?

Should one let everyone walk directly

into the whirling razor blades?

If you sent me back in time, I'm not sure I could win this, but maybe I would have some notion of, ah, if you calculate the message in exactly this way, then 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'm 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 your whole planet walk directly into the whirling razor blades, carefree, no idea what's coming to them, maybe that 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, if we don't invest in this company, who knows what investors they'll have instead that will demand that they move fast because of the profit mode.
And then, of course, they just move fast fucking anyways. And, yeah, 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 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 invest in exactly the right time, and you can fund projects on your own without alerting anyone.
And 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 there a little later. If you don't mind me asking, what is the last five years or I guess even beyond that? I mean, what has being in a space been like for you, watching the progress and the way in which people have raised ahead?

The past five years?

I made most of my negative updates as of five years ago.

If anything, things have been taking longer to play out

than I thought they would.

But, I mean, just like watching it,

not as a sort of change in your probabilities,

but just watching it concretely happen,

what has that been like?

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 from 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 imagine themselves acting out their being drama queens about it.
The point of believing this thing is to be a drama queen about it

and like craft some story in which your emotions mean something. And what I have in the way of culture is like the planet's at stake, bear up, keep going, no drama

the drama is meaningless

but changes the chance of victory is meaningful. The drama is meaningless.
Don't indulge it. Do you think that if you weren't around, somebody else would have independently discovered this sort of field of alignment? 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 Everett branches of Earth are. But there are other kids who grew up on science fiction, so that can't be the only part of the answer.
While I'm sure not surrounded by a cloud of people who are nearly Eliezer outputting 90% of the work output, and this is actually also kind of not how things play out in a lot of places like Steve Jobs is dead apparently couldn't find anyone else to 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 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, you know, like built an organization. And he was like, hey, Eliezer, do you want this to take this thing over? And I thought he was joking.
And it didn't dawn on me until years and years later, after trying hard and failing hard to replace myself, that, oh, yeah, I could have maybe taken a shot at doing this person's job, and he probably just never found anyone else who could take over his organization

and maybe ask some other people, and nobody was willing.

And 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 have at least apologized.

And, yeah, to me it looks like people are not dense in the incredibly multi-dimensional space of people. There are too many dimensions and only 8 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 in looking around myself in that highly multidimensional space and like not finding a ton of neighbors ready to take over.
And I'm I had, you know, four people, any one of whom could do like 99% of what I do or whatever, I might retire. I am tired.
Probably I wouldn't. Probably the marginal contribution of that fifth person is still pretty large.

But, yeah.

I don't know.

There's the question of

like, well, did you

occupy a place in mind

space? Did you occupy a place in social

space? Did people not try to become Eliezer

because they thought Eliezer already existed?

And so my answer to that is like,

man, I don't think Eliezer already existing would have stopped me from trying to become Eliezer. But, you know, maybe you just look at the next Everett branch over and there's just some kind of empty space that someone steps up to fill, even though then they don't end up with a lot of obvious neighbors.
Maybe the world where I died in childbirth is just pretty much like this. But I don't feel, you know, 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, you know, if it's true, it'd be funny. when I said no drama, that did include the concept of, I don't know,

trying to make the story 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 somehow I survived to be told that,

I'll laugh and I'll cry and that will be the reality.

I mean, what I find interesting, though, is that in your particular case,

Thank you. I'll laugh and I'll cry and that will be the reality.
I mean, what I find interesting, though, is that in your particular case, your output was so public. And I mean, I don't know, like, for example, your sequences, your science fiction and fan fiction.
I'm sure like hundreds of thousands of 18-year-olds read it or even younger. And presumably some of them reached out to me like, you know, I think this way I would love to learn more.
I'll work on this. What was the problem that part? I mean, yes.
Part of how, part of why I'm a little bit skeptical of the story where like people are just like infinitely replaceable is that I tried really, really, really hard to create like a new crop of, of, of, 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.
That's what the less wrong sequences were. They had other purposes, but first and foremost, it was me looking over my history and going, well, I see all these blind pathways and stuff that it took me a while to figure out.
And I feel like I had these near misses on becoming myself. There's got to be, if I got here, there's got to be 10 other people and like some of them are smarter than I am.
And they just like need these like little boosts and shifts and hints and they can go down the pathway and, you know, like turn into super Eliezer. And, you know, that's what the sequences were.
Like other people use them for other stuff, but primarily they were instruction manual to the young Eliezers that I thought must exist out there. And they're not really here.
Other than the sequences, do you mind if I ask what were the kinds of things you're talking about here in terms of training the next core of people like you? Just the sequences. I'm not a good mentor.
I did try mentoring somebody for a year once, but yeah, he didn't turn into me. So I picked things that were more scalable.
I'm like most people, you know, like among the other reason why I don't see a lot of people trying that hard to replace themselves is that most people, you know, are like whatever their other talents don't happen to be like sufficiently good writers. I don't think the sequences were good writing by my current standards, but they were good enough.
And, you know, most people do not happen to get a handful of cards that contains the writing card, you know, whatever else their other talents. I'll cut this question out if you don't want to talk about it.
But you mentioned that there's like certain health problems that incline you towards retirement now. Is that something you're willing to talk about? I mean, they caused me to want to retire.
I doubt they will cause me to actually retire. And yeah, it's fatigue syndrome.
Our society does not have good words for these things. The words that exist are tainted by their uses, labels to categorize a class of people, some of whom perhaps are actually malingering, but mostly it says, like, we don't know what it means.
And, you know, you don't ever want to have chronic fatigue syndrome on your medical record because that just tells doctors to give up on you. And what does it actually mean besides being tired? If one wishes to walk home from work, if one wishes to, if one lives half a mile from one's work, then one had better walk home if one wants to go for a walk sometime in the day.
not walk there. If you walk half a mile to work, you're not going to be getting very much work done the rest of that work day.
And aside from that, these things don't have names. Not yet.
Whatever the cause of this, is your working hypothesis that it has something to do or is in some way correlated with the thing that makes you a liager?

Or do you think it's like a separate thing?

When I was 18, I made up stories like that.

And it wouldn't surprise me terribly if you could get, if one survived to hear the tale from something that knew it,

that the actual story would be a complex, tangled web of causality,

in which that was in some sense true.

But I don't know.

And storytelling about it does not hold the appeal that it once did for me.

Is it a coincidence that I was not able to go to high school or college? Is there something about it that would have crushed the person that I otherwise would have been? Or is it just in some sense a giant coincidence? I don't know. Some people go through high school and college and come out sane.
There's too much stuff in a human being's history

to...

There's a plausible story

you could tell.

Maybe there's a bunch of potential Eliezers

out there, but they went to

high school and college and it killed them.

It killed their souls.

You were the one who had

the weird health problem and you

didn't go to high school and you didn't

go to college and you stayed yourself.

I don't know.

Thank you. and you were the one who had the weird health problem and you didn't go to high school and you didn't go to college and you stayed yourself.

I don't know.

To me, it just feels like patterns in the clouds

and maybe that cloud actually is shaped like a horse.

But what good does the knowledge do?

What good does the story do?

When you were writing the sequences and, you know, the fiction, from the beginning, was your goal to find somebody who, like the main goal, to find somebody who could replace you and specifically the task of AI alignment? Or did it start off with a different goal and then... I mean, I thought there...

I mean, you know, like in 2008,

like, I did not know this stuff was going to go down in 2023.

I thought...

For all I knew, there was a lot more time

in which to do something like build up civilization

to another level, layer by layer.

Sometimes civilizations do advance as they improve their epistemology. So there was that.
There was the AI project. Those were the two projects, more or less.
When did AI become the main thing? As we ran out of time to improve civilization. Was there a particular year that became the case for you? I mean, I think that 2015, 16, 17 were the years at which I'd noticed I'd been repeatedly surprised by stuff moving faster than anticipated.
And I was like, oh, OK, like if things keep continuing accelerating at that pace, we might be in trouble. And then like 2019, 2020 stuff slowed down a bit.
And, you know know there was more time than I was afraid we had back then you know that's what it looks like to be a Bayesian like your estimates go up your estimates go down they don't just keep moving in the same direction because if they keep moving in the same direction sometimes you're like oh like I see where this thing is trending I'm going to move here and then like things don't keep moving that direction oh okay like like you go like oh okay like back down again and that's that's what sandy looks like i i am curious actually like taking many worlds seriously does that bring you um any comfort in the sense that like there is one branch of the wave function where humanity survives or is that uh do you not buy that sort of i'm worried that they're pretty pretty distant. I expect that at least they...

I don't know.

I'm not sure it's enough to not

have Hitler, but it sure would be a start

on things going differently

in a timeline.

But mostly, I don't know.

There's some comfort from thinking of the

wider spaces than that, I'd say.

As Tegmark pointed out

way back when, if you have a spatially infinite

universe that gets you just as many worlds as the quantum multiverse, if you go far enough in a space that is unbounded you will eventually come to an exact copy of Earth or a copy of Earth from its past that then has a chance to diverge a little differently. So you know the quantum multiverse that nothing, reality is just quite, yeah, reality is just quite large.

Is that a comfort?

Yeah. diverge a little differently.
So the quantum multiverse, nothing, reality is just quite, yeah, reality is just quite large.

Is that a comfort?

Yeah, yes it is.

That possibly our nearest surviving relatives

are quite distant,

or you have to go quite some ways through the space

before you have worlds that survive,

but anything but the wildest flukes, maybe our nearest surviving neighbors are closer than that. But look far enough and there should be some species of nice aliens that were smarter or better at coordination and built their happily ever after.
And yeah, that is a comfort. It's not quite as good as dying to yourself knowing that the rest of the world will be okay.
But it's kind of like that on a larger scale. And weren't you going to ask something about orthogonality at some point? Did I not? Did you? At the beginning when we talked about human evolution.

Yeah, that's not like orthogonality.

That's the particular question of what are the laws relating optimization of a system via hill climbing to the internal psychological motivations that it acquires? But maybe that was all you meant to ask about. Can you explain in what sense you see the broader orthogonality thesis as un-affected by that? The broader orthogonality thesis is you can have almost any kind of self-consistent utility function in a self-consistent mind.
Like many people are like, why would AIs want to kill us? Why would smart things not just automatically be nice? And, you know, this is a valid question, which I hope to at some point run into some interviewer where they are of the opinion that smart things are automatically nice so that I can explain on camera why, like, although I myself held this position very long I realized I realized that I was terribly wrong about it. And that, like, all kinds of different things hold together.
And that, you know, like, if you take a human and make them smarter, that may shift their morality. It might even, depending on how they start out, make them nicer.
But that doesn't mean that, like, you can do this with arbitrary minds and arbitrary mind space because all the different motivations hold together.

That's like orthogonality.

But if you already believe that, then there might not be much to discuss.

No, no.

I guess I wasn't clear enough about it. Is that, yes, all the different sort of utility functions are possible.
is that from the evidence of evolution and from the sort of reasoning

about how these systems are being trained,

I think that wildly divergent ones don't seem as likely as you do. But before I, instead of having you respond to that directly, let me ask you some questions I did have about it, which I didn't get to.
One is actually from Scott Aronson. I don't know if you saw his recent blog post, but here's a quote from it.
If you really accept the practical version of the orthogonality thesis, then it seems to me that you can't regard education, knowledge, and enlightenment as instruments for moral betterment. On the whole, though, education hasn't merely improved humans' abilities to achieve their goals.
It has also improved their goals. I'll let you react to that.
Yeah, and that, yeah, if you, if you start with humans, if you take humans and possibly also for the requiring particular culture, but leaving that aside, you take humans who start out raised the way Scott Aronson was and you make them smarter, they get nicer. It affects their goals.
And if you had, and there's a less wrong post about this, as there always is, well, several about really, but like sorting pebbles into correct heaps, describing a species of aliens who think that a heap of size seven is correct, and a heap of size 11 is correct, but not 8 or 9 or 10. Those heaps are incorrect.
And they

used to think that a heap size of 21 might be correct, but then somebody showed them an array of 7 by 3 pebbles, 7 columns, 3 rows. And then people realized that 21 pebbles was not a correct heap.
And, you know, this is like the thing they intrinsically care about. These are aliens that have a utility function with, as I would phrase it, some logical uncertainty inside it.
You can see how as they get smarter, they become better and better able to understand which heaps of pebbles are correct. And the real story here is more complicated than this.
But like that's the seed of the answer. Like Scott Aronson is inside a reference frame for how his utility function shifts as he gets smarter.
It's more complicated than that. It's like human beings are made out of these like are more complicated than the pebble sorters.
They're made out of all these complicated desires and as they come to know those desires they change. As they come to see themselves as having different options.
It doesn't just change which option they choose after the manner of something with a utility function but the different options that they have bring different pieces of themselves in conflict. When you have to kill to stay alive, you may have a different you may come to a different equilibrium with your own feelings about killing than when you are wealthy enough that you no longer have to do that.
And this is how humans change as they become smarter, even as they become wealthier, as they have more options, as they know themselves better, as they think for longer about things and consider more arguments, as they understand perhaps other people and give their empathy a chance to grab onto something solider because of their greater understanding of other minds. But that's all when these things start out inside you.
And the problem is that there's other ways for minds to hold together coherently where they execute other updates as they know more or don't even execute updates at all

because their utility function is simpler than that,

though I do suspect that is not the most likely outcome

of training a large language model.

So large language models will change their preferences

as they get smarter, indeed.

Not just like what they do to get the same terminal outcomes,

but like the preferences themselves will up to a point change as they get smarter. It doesn't keep going.
At some point you know yourself sufficiently well and you are like able to rewrite yourself. And at some point there, unless you specifically choose not to, I think that system crystallizes.
We might choose not to. We might value the part where we just sort of change in that way.
Even if it's no longer heading in a knowable direction, because if it's heading in a knowable direction, you could jump to that as an endpoint. Wait, wait, so is that why you think AIs will jump to that endpoint? Because they can anticipate where their sort of moral updates are going? I would reserve the term moral updates for humans.
These are, let's call them. Preference.
Logical preference updates. Yeah, yeah.
Preference shifts. What are the prerequisites in terms of, like, whatever makes Aronson and other sort of smart, moral people or whatever, like, preferences that we humans can sympathize with? Like what is, you mentioned empathy, but what are the sort of prerequisites? They're complicated.
There's not a short list. If there was a short list of crisply defined things where you could like give it like chunk, chunk, chunk, and now it's in your moral frame of reference, then that would be the alignment plan.
I don't think it's that simple. Or if it is that simple, it's like in the textbook from the future that we don't have okay let me ask you this are you still expecting a sort of chimps to humans gain in generality even with these llms or does a future increase look um of an order that we see from like gbd3 to gbd4 i'm not sure i understand the question can you rephrase yes it seems that i i don't know like from reading your writing from earlier it seemed like a big part of argument was like look a few i don't know how many total mutations it was to get from chimps to humans but it wasn't that many mutations and we went from something that could basically get bananas in the forest to something that could walk on the moon are you expecting that are you still expecting that sort of gain eventually between i don't know like gpd5 and gpd6 or like some gpdn and gpdn plus one or does it does it look smoother to you now okay so like first of all let me preface by saying that for all i know of how of the hidden variables of nature it's completely allowed that gpd4 was actually it.
This is where it saturates. It goes no further.
It's not how I'd bet. But, you know, if nature comes back and tells me that, I'm not allowed to be like, you just violated the rule that I knew about.
I know of no such rule prohibiting such a thing. I'm not asking whether these things will plateau at a given level of intelligence, whether there's a cap.
That's not the question. Even if there is no cap, do you expect these systems to continue

scaling in the way that they have been scaling? Or do you expect some really big jump between some GPTN and some GPTN plus one? Yes, and yes. And that's only if things don't plateau before then? I mean, it's, yeah, I can't quite say that I know what you know.
I do feel like we have this, like, track of the loss going down as you add more parameters and you train on more tokens and a bunch of qualitative abilities that suddenly appear, or, like, I'm sure if you, like, zoom in closely enough, they appear more gradually, but, like, that appear as the successful releases of the system, which I don't think anybody has been going around predicting in advance that I know about. And loss continue to go down unless it suddenly pitows.
New abilities appear. Which ones? I don't know.
Is there at some point a giant leap? Well, if at some point it becomes able to toss out the enormous training run paradigm and build more efficient and jump to a new paradigm of AI, that would be one kind of giant leap. You could get another kind of giant leap via architectural shift, something like transformers, only there's an enormously huge hardware overhang now, like something that is to transformers, as transformers work to recurrent neural networks.
And then maybe the loss function suddenly goes down, and you get a whole bunch of new abilities. That's not because the loss went down on a smooth curve and you got a bunch more abilities in a dense spot.
Maybe there like some particular set of abilities that is like a master ability the way that language and writing and culture for humans might have been a master ability and you like the loss function goes down smoothly you get this one new new like internal capability there's a huge jump in output maybe that happens maybe stuff plateaus before then and it doesn't happen. Being an expert, being the expert who gets to go on podcasts, they don't actually give you a little book with all the answers in it, you know.
You're like just guessing based on the same information that other people have and maybe, maybe if you're lucky, slightly better theory. Yeah, that's what I'm wondering because you do have a different theory of like what fundamentally intelligence is and what it entails.
So'm curious if like you have some expectations of where the gpts are going i feel like a whole bunch of my successful predictions in this have come from other people being like oh yes i have this theory which predicts that stuff is 30 years off and i'm like you don't know that and then like stuff happens now 30 years off and i'm like ha ha successful. And that's basically what I told you, right? I was like, well, you know, you could have the loss function continuing on a smooth line and new abilities appear and you could have them suddenly appear to cluster because why not? Because nature just tells you that's up and suddenly.
You could have this one key ability that's equivalent of language for humans and there's a sudden jump in output capabilities. You could have a new innovation, like the transformer, and maybe the loss is actually dropped precipitously, and a whole bunch of new abilities appear at once.
Now, this is all just me. This is me saying, I don't know, but so many people around are saying things that implicitly claim to know more than that that it can actually sound like a startling prediction.
This is one of my big secret tricks, actually. People are like, well, the AI could be like good or evil, so it's like 50-50, right? And I'm actually like, no, like we can be ignorant about a wider space than this, in which like good is actually like a fairly narrow range.
And so many of the predictions like that are really anti-predictions. It's somebody thinking along a relatively narrow line and you point out everything outside of that and it sounds like a startling prediction.
Of course, the trouble being when you like, you know, look back afterwards, people are like, well, you know, like those people saying the narrow thing were just silly, ha ha. And they don't give you as much credit.
I think the credit you would get for that, rightly, is as a good sort of agnostic forecaster, as somebody who is like sort of calm and measured. But it seems like to be able to make really strong claims about the future, about something that is so out of prior distributions as like the death of humanity, you don't only have to show yourself as a good agnostic forecaster.
You have to show that your ability to forecast because of a particular theory is much greater. Do you see what I mean? It's all about, so when you work, yeah, it's all about the ignorance prior.
It's all about knowing the space in which to be maximum entropy. Like the whole bunch of, you know, like somebody, you know, like what will the future be? Well, I don't know.
It could be paperclips. It could be staples.
It could be no kind of office supplies at all and tiny little spirals. It could be like little tiny like things that are like outputting one, one, one, because that's like the most predictable kind of text to predict.
Or representations of ever larger numbers in the fast-growing hierarchy, because that's how to interpret the reward counter. I'm actually getting into specifics here, which is kind of the opposite of the point I originally meant to make, which is if somebody claims to be very unsure, I might say, okay, so then like you expect like most possible molecular configurations of the solar system to be equally probable.
Well, humans mostly aren't in those. So like being very unsure about the future, it looks like predicting with probability nearly one that the humans are all gone, which, you know, it's not actually that bad, but it like the point of people going like, but how are you sure? Kind of missing the real discourse and skill, which is like, oh, yes, we're all very unsure.
Lots of entropy in our probability distributions, but what is the space for which you are unsure? Even at that point, it seems like the most reasonable prior is not that all sort of atomic configurations of the solar system are equally likely because i agree by that metric yeah like it's it's like all computations that can like be run over configurations of solar system are equally likely to be maximized but But why, like, we have a certain, we have certain sense that like, listen, we know what the loss function looks like. We know what the training data looks like.
That obviously is no guarantee of what the drives that come out of that loss function will look like. Yeah.
But it is certainly not. Humans that came out pretty different from their loss functions.
But I mean, this is the first question we began with. I would say, actually, no.
Like, if it is as similar as humans are now to our loss function from which we evolved, that would be like, that honestly might not be that terrible world. And it might, in fact, be a very good world.
Okay, so. If it's like the equivalent of like the thing that.
Where do you get good world out of maximum prediction of text? Plus RLHF, plus all the whatever alignment stuff that might work, results in something that kind of just does what you ask it to. Does it reliably enough that we ask it like, hey, help us with alignment, then go.
Stop asking for help with alignment. Ask it for help augmenting units.
Ask it for any of the. Like help us enhance our brains help us blah blah thank you why are people asking for like the most difficult thing that's the most possible to verify it's whack um and then basically at that point we're like turning into gods and we can if you get to the point where you're turning into gods yourselves you're like you're not quite home free but you know you're sure past you sure past a lot of the death yeah maybe you can explain the intuition that all sorts of drives are equally likely given unknown loss function in a known set of data oh um if yeah like so so so if you if you had the textbook from the future or if you were an alien who'd watched a dozen planets destroy themselves the way Earth is, that, or not actually a dozen, that's not like a lot, if you'd seen 10,000 planets destroy themselves the way Earth has, while being only human in your sample complexity and generalization ability, then you could be like, oh, yes, they're going to try, like, this trick with loss functions, and they will get a draw from like this space of results and the and the alien like can now probably may now have like a pretty good prediction of like range of like where that ends up like like similarly like now that we've actually seen how humans turn out when you optimize them for reproduction it would like not be surprising if we found some aliens the next door over and they had orgasms.
Now, maybe they don't have orgasms, but you know, like some like, but you know, like if they had some kind of like strong surge of pleasure during the act of mating, we're not, we're not as, we're not surprised. We've seen how that could play out in humans.
If they have some kind of like weird food that isn't that nutritious, but like makes them much happier than any kind of food that was more nutritious and around in their ancestral environment like like ice cream you probably can't call it as ice cream right it's not going to be like sugar salt fat frozen but we're not specifically going to have ice cream right they might play Go they're not going to play chess because chess has more specific pieces they're not going to play Go on 19x90 they might play Go on some other size probably odd well can we really say that? I don't know I'd'd bet on like an odd, if they play Go, I'd bet on an odd board dimension at, let's say, two-thirds. The Placid's Rule of Succession.
Sounds about right. Unless there's some other reason why Go just totally does not work on an even board dimension that I don't know because I'm insufficiently acquainted with the game.
The point is, like, you know, reasoning off of humans is, like, pretty hard. We have, like, the loss function over here.
We have, like, humans over here. We can, like, look at the rough distance.
Like, all the, like, weird specific stuff that humans are created around and be, like, you know, like, if the loss function is over here and humans are over there, like, maybe the aliens like over there. And if we had like three aliens, that would like expand our views of the possible.
We'd have like, or even two aliens would like vastly expand our views of the possible and give us like a much stronger notion of what the third aliens would look like. Like humans, aliens, third race.
But, you know,

the wild

optimistic scientists have never been through

this with AIs.

They're like, oh, you optimize

the AI to say nice things

and help you and make it a bunch smarter.

Probably says nice things and helps you. It's probably like,

Talia line. Yeah.

Exact. Yeah.

They don't know any better. Not trying to jump ahead of the story.
But the aliens, the aliens know where you end up around the loss function. They know how it's going to play out.
Much more narrowly. We're guessing much more blindly here.
It just like, it just leaves me in a sort of unsatisfied place that we apparently know about something that is so extreme that maybe a handful of people in the entire world believe it from first principles about the doom of humanity because of AI. But this theory that is so productive in that one very unique prediction is unable to give us any sort of other prediction about what this world might look like

in the future or about what happens before we all die. It can tell us nothing about the world until the point at which makes prediction that is the most remarkable in the world.
Rationalists should win, but rationalists should not win the lottery. I'd ask you what other theories are supposed to have been doing an amazingly better job of predicting the last three years.
Maybe it's just hard to predict, right? And in fact, it's easier to predict the end state than the strange, complicated, wending paths that lead there, much like if you play against AlphaGo and predict it's going to be in the class of winning board states but not exactly how it's going to beat you. It's not quite like that, the difficulty of predicting the future.
But from my perspective, the future is just really hard to predict. And there's a few places where you can like wrench what sounds like an answer out of your ignorance, even though really you're just being like, well, you're going to like end up in some like random weird place around this loss function.
And I haven't seen it happen with 10,000 species. So I don't know where.
Very, very impoverished by the standpoint of anybody who like actually knew anything, could actually predict anything. But the rest of the world is like, oh, like we're easily, we're like equally likely to win the lotteries, lose the lottery, right? Like either we win or we don't.
You come along and you're like, no, no, your chance of winning the lottery is tiny. They're like, what? How can you be so sure? Where do you get your strange certainty?

And the actual root of the answer is that you are putting your maximum entropy over a different probability space. Like that just actually is the thing that's going on there.
You're saying all lottery numbers are equally likely instead of winning and losing are equally likely. So I think the place to sort of close this conversation is, let me just sort of give the main reasons why I'm not convinced that Doom is likely, or even that it's more than 50% probable or anything like that.
Some are the things that I started this conversation with that I don't feel like I heard any knockdown arguments against.

And some are new things from the conversation. And the following things are things that even if any one of them individually turns out to be true, I think doom doesn't make sense or is much less likely.

So going through the list,

I think probably more likely than not, this entire frame all around alignment and AI is wrong. And this is maybe not something that would be easy to talk about, but I'm just kind of skeptical of sort of first principles reasoning that has really wild conclusions okay so everything in the solar system just ends up in a random configuration then uh or it stays like it is unless you have very good reasons to think otherwise and especially if you think it's going to be very different from the way it's going you must have very very good reasons like ironclad reasons for thinking that it's going to be very, very different from the way it is.
Uh-huh. So this is, you know, humanity hasn't really existed for very, man, I don't even know what to say to this thing.
We're like this tiny, like everything that you think of as normal is this tiny flash of things being in this particular structure out of a 13.8 billion year old universe, which very little of which was like 20th century, pardon me, 21st century. Yeah.
My own brain sometimes gets stuck in childhood too, right? Very little of which is like 21st century, like civilized world. on this little fraction of the surface of one planet

in a vast solar system, most of which is not Earth,

in a vast solar system, most of which is not Earth, in a vast universe, most of which is not Earth. And it has lasted for like such a tiny period of time through such a tiny amount of space and has like changed so much over, you know, just the last 20,000 years or so.
And here you are like being like, why would things really be any different going forward? I feel like that argument proves too much because you could use that same argument like somebody comes up to me and says, I don't know, a theologian comes up to me and says, the rapture is coming. And let me sort of explain why the rapture is coming.
And I say, I'm not claiming that your arguments are as bad as the argument for rapture. Just follow the example.
But then they say, listen, I mean, look at how wild human civilization has been. Would it be any wilder if there was a rapture? And I'm like, yeah, actually, as wild as human civilization has been, the rapture would be much wilder.
Because it violates the laws of physics. Yes.
I'm not trying to violate the laws of physics, even as we presently know them. How about this? Somebody comes up.
Oh, you know, I've got got the perfect example okay um somebody comes up to me he says we have actually nanosystems right behind you he says i've read eric drexler's nanosystems i've read vitamins there's plenty of room at the bottom and he explains two things are not mentored but go on okay fair enough he comes to me and he says um let me explain to you my first principles argument about how some nanosystems will be replicators.

And the replicators, because of some competition, yada, yada, yada argument, they turn the entire world into goo, just making copies of themselves. This kind of happened with humans, you know.
Well, life generally. Yeah.

Yeah.

But so then they say like, listen, as soon as we start building nanosystems pretty soon,

99% probability, the entire world turns into goo. Just because the replicators are the things that turn things into goo, there will be more replicators and non-replicators.
I don't have an object level debate about that, but it's just like, I just started that and I'm looking like, yes, human civilization has been wild. But the entire world turning into goo because of nanosystems alone just seems much wilder than human civilization you know this this list this uh this impact this this argument probably lands with greater force on somebody who does not expect stuff to be disassembled by nanosystems albeit intelligently controlled ones rather than goo in like quite near future especially on the 13.8 billion year time scale but you know do you do you expect this little momentary flash of what you call normality to continue? Do you expect the future to be normal?

I know I expect any given vision of how things shape out to be wrong, especially it is not like you are suggesting that the current weird trajectory continues being weird in the way it's been weird and that we continue to have like 2% economic growth or whatever. And that leads to incrementally more technological progress and so on.
You're suggesting there's been that specific species of weirdness, which leads to an, which means that this entirely different species of weirdness is warranted. Yeah.
We've got like different weirdnesses over time. The jump to superintelligence does strike me as being significant in the same way as first self-replicator.
First self-replicator is the universe transitioning from you see mostly stable things to you also see a whole bunch of things that make copies of themselves. And then somewhat later on, there's a state where, you know, there's this like strange transition, this border between the universe of stable things where things come together by accident and stay as long as they endure to this world of complicated life.
And that transitionary moment is when you have something that arises by accident and yet self-replicates. And similarly, on the other side of things,

you have things that are intelligent making other intelligent things,

but to get into that world,

you've got to have the thing that is built

just by things copying themselves and mutating,

and yet is intelligent enough to make another intelligent thing.

Now, if I sketched out that cosmology, would you say, no, no, I don't believe in that? What if I sketched out the cosmology of, because of replicators, blah, blah, blah, intelligent beings, intelligent beings create nanosystems, blah, blah, blah. No, no, no, no.
I don't, I don't want to, don't tell me about your, like, not, not the proofs too much. I just want to, like, I discussed out of cosmology, do you buy it?

In the long run, are we in a world full of things replicating

or a world in a full of intelligent things designing other intelligent things?

Yes.

So you buy that vast shift in the foundations of order of the universe,

that instead of the world of things that make copies of themselves imperfectly, we are in the world of things that are designed and were designed. You buy that vast cosmological shift I was just describing, the utter disruption of everything you see that you call normal down to the leaves and the trees around you.
You believe that. Well, the same skepticism you're so fond of that argues against the rapture can also be used to disprove this thing you believe that you think is probably pretty obvious, actually, now that I've pointed it out.
Okay. Your skepticism disproves too much, my friend.
That's actually a really good point. It still leaves open the possibility of how it happens and when it happens, blah, blah, that's that's a good point okay so a second second thing i'm not you set them up i'll knock them down one after the other second thing is wrong sorry i was just jumping head to the predictable update at the end.
You're a good base. Good base.

Maybe alignment just turns out to be much simpler or like much easier than we think. It's not like we've as a civilization spent that much resources or brainpower in solving it.
If we put in even the kind of resources that we put into elucidating strength theory or something into alignment, it could just turn out to be like, yeah, that's enough to solve it. And in fact, in the current paradigm, it turns out to be simpler because, you know, they're sort of pre-trained on human thought.
And that might be a simpler regime than something that just comes out of a black box that like, you know, like alpha zero or something like that. So like some of my like, could I be wrong in an understandable way to me in advance mass, which is not where most of my hope comes from, is on, you know, what if RLHF just works well enough and the people in charge of this are not the current disaster monkeys, but instead have some modicum of caution and are using their like, like know what to aim for in RLHF space, which the current crop do not.
and I, you know, I'm not really that confident of their ability to understand if I told them,

but maybe you have some folks who can understand. Anyways, I can sort of see what I try.
These people will not try it. But in the current crop, that is.
and I'm not actually sure that if somebody else takes over, like the government or something, that they listen to me either. But I can, you know, maybe you, so some of the trouble here is that you have a choice of targets.
And like neither is all that great. One is you look for the niceness that's in humans and you try to bring it out in the AI.
And then you, with its cooperation, because, you know, it knows that if it makes it, that if you try to just like amp it up, it might not stay all that nice. Or that if you build a successor system to it, it might not stay all that nice.
And it doesn't want that because you, you the Shoggoth enough. Somebody once had this incredibly profound statement that I think I somewhat disagree with, but it's still so incredibly profound.
It's consciousness is when the mask eats the Shoggoth. And maybe with the right set of bootstrapping reflection type stuff stuff stuff you can have that happen on purpose more or less where there where the the systems output that you're shaping is like to some degree in control of the system and you you you locate niceness in the human space.
I have fantasies along the lines of what if you trained GPTN to distinguish people being nice and saying sensible things and argue validly. And, you know, can't just – I'm not sure that works if you just have Amazon Turks try to label it.
You just get the, like, strange thing you located that RLHF located in the present space, which is, like, some kind of weird corporate-speak, like, left-rationalizing-le leaning, strange telephone announcement creature is what they got with the current crop of RLHF.

Note how this stuff is weirder and harder than people might have imagined initially.

But, you know, leave aside the part where you try to like jumpstart the entire process of turning into a grizzled cynic and update as hard as you can and do it in advance.

Leave that aside for a moment. Like, maybe you can look, maybe you are, like, able to train on Scott Alexander and So You Want to Be a Wizard.
some other nice real people and nice fictional people, and separately train on what's valid argument, that's going to be tougher. But I could probably put together a crew of a dozen people who could provide the data on that, RLHF.
And you find the nice creature, you find the nice mask that argues validly. You do some more complicated stuff to try to boost the thing where it's like eating the shoggoth, where that's what the system is and not like more what the system is, less what it's pretending to be.
I do seriously think this is like, like I can say this and like the disaster monkeys at the current places can not along to it, but they have not said things like this themselves that I've ever heard. And that is not a good sign.
But, and then like, if you don't amp this up too far, which on the present paradigm you like can't do anyways, because if you like train the very, very smart person in this version of the system, it kills you before you can RLHF it. But maybe you can train GPT to distinguish nice, valid, kind, careful, and then filter all the training data to get the nice things to train on.
And then train on that data rather than training on everything to try to like avert the Waluigi problem. Or just more generally having like all the darkness in there.
Like just train on the light that's in humanity. So there's like that kind of course.
And if you don't push that too far, maybe you can get a genuine ally. And maybe things play out differently from there.
That's like one of the little rays of hope. But that's not, I don't think that actually looks like alignment is so easy that you just get whatever you want.
It's a genie. It gives you what you wish for.
I don't think that, that doesn't even strike me as hope. Honestly, the way you described it, you described it seemed kind of compelling like i don't know why that doesn't even rise to one percent uh the possibility works out that way i i literally this is like literally my you know my like ai lineman fantasy from 2003 um though not with but not with like rlhf and as the implementation method or LLMs as the base.
And it's, you know, going to be more dangerous than when I was thinking about, when I was dreaming about it in 2003. And I think in a very real sense, it feels to me like the people doing this stuff now have literally not gotten as far as I was in 2003.

I've now written out my answer sheet for that. It's on the podcast.
It goes on the internet. Now they can pretend that that was their idea.
Or like, sure, that's obvious. We're going to do that anyways.
Yet they didn't say it earlier. and you can't run a big project off of one person who...
It failed to gel. The alignment field failed to gel.
That's my gesture to the, like, well, you just throw in a ton of more money and then it's all solvable. Because I've seen people try to amp up the amount of money that goes into it and the stuff coming out of it has not gone to the places that I would have considered obvious a while ago and I can like print out all my entries sheets for it and each time I do that it gets a little bit harder to make the case next time but I mean how much money are we talking in the grand scheme of things because like civilization itself has a lot of money money.
I know people who have a billion dollars. I don't know how to throw a billion dollars at like outputting lots and lots of alignment stuff.
But you might not. But I mean, you are one of 10 billion, right? Like it is.
And other people go ahead and spend lots of money on it anyways. And everybody makes the same mistakes.
Nate Soris has a post about it. I forget the exact title, but like everybody coming into alignment makes the same mistakes.
Let me just go on to the third point because I think it plays into what I was saying. The third reason is if it is the case that these capabilities scale in some constant way as it seems like they're going from two to three or three to four.
What does that even mean? But go on. That they get more and more general.
It's not like going from a, going from a mouse to a human or a chimpanzee to a human. It's like going from GPT three to GPT four.
Yeah. Well, it just seems like that's less of a jump but then chimp to human uh like a slow accumulation of capabilities there are a lot of like s curves of emergent abilities but overall the curve looks sort of man i feel like we bit off a whole chunk of chimp to human and gpt3.5 to gpt4 but go on regardless okay so then this leads to human level intelligence for some interval i think that i was not convinced from uh the arguments that we could not have a system of sort of checks on this the same way you have checked on smart humans that it would uh try to deceive us to achieve its aims any more than smart humans are in positions of power, try to do the same thing? For a year, what are you going to do with that year? Before the next generation of systems come out that are not held in check by humans, because they are not roughly in the same power intelligence range as humans.
Maybe you can get a year like that. Maybe that actually happens.
What are you going to do with that year that prevents you from dying the year after? One possibility is that because these systems are trained on human text, maybe just progress just slows down a lot after it gets to a slightly above human level. Yeah, that's not how...
I would be quite surprised if that's how anything works. Why is that? For one thing, because it's, you know, like for an alien to be an actress playing all the humans on the internet.
For another thing, well, first of all, you realize in principle that the task of minimizing losses on predicting human text does not have a... Yeah, you understand that in principle, this does not stop when you're as smart as a human, right? You can see the computer science of that.
I don't know if I see the computer science of that, but I think I probably understand the argument. Okay, so somewhere on the internet is a list of hashes followed by the string hashed.
This is a simple demonstration of how you can go on getting lower losses by throwing a hypercomputer at the problem. There are pieces of text on there that were not produced by humans talking in conversation, but rather by like lots and lots of work to determine, extract experimental results out of reality.
That text is also on the internet. Maybe there's not enough of it for the machine learning paradigm to work.
But I'd sooner buy that, like, that the GPT system's just bottlenecked short of being able to predict that stuff better rather than that. But, you know, like, you can maybe buy that.
But, like, the notion that, like, you only have to be smart as a human to predict all the text as the internet, as soon as you turn around and stare at that a bit, it's just transparently false.

Okay. Agreed.

Okay. How about this story?

You have something that is sort of human-like that is maybe above humans at certain aspects of science because it's specifically trained to be really good at the things that are on the internet,

which is like, you know,

chunks and chunks of archive and whatever.

Whereas it has not been trained specifically

to gain power.

And while at some point of intelligence

that comes along,

can I just restart that whole sentence?

No, you have spoken it.

It exists.

It cannot be called back. There are no take backs.
There is no going back. There is no going back.
Go ahead. Okay, so here's another story.
I expect them to be better than humans at science than they are at power seeking because we had greater selection pressures for power seeking in our ancestral environment than we did for science. And while at a certain point, both of them come along as a package, maybe that they can be at varying levels.
But anyways, so you have this sort of early model that is kind of human level, except a little bit ahead of us in science. You ask it to help us align the next version of it.
Then the next version of it is more aligned because we have its help. And sort of like this inductive thing where the next version helps us align the version of that.
Where do people have this notion of getting AIs to help you do help you do your ai alignment homework it just why can we not talk about having it enhance you in human intelligence instead okay so either one of those stories where it just like helps us enhance humans uh enhance humans then help us figure out the alignment problem or something like that yeah i i it's like kind of weird because you know like like small large amounts of intelligence don't automatically make you a computer programmer. And if you are a computer programmer, you don't automatically get security mindset.
But it feels like there's some level of intelligence where you ought to automatically get security mindset. And I think that's about how hard you have to augment people to have them able to do alignment.
Like the level where, like, they have security mindset not because they were, like special people with security mindset, but just because like, they're that intelligent that you just like automatically have security mindset. I think that's about the level where a human could start to work on alignment, more or less.
Why is that story then not 1% get you to 1% probability that it helps us over the whole crisis? Well, because it's not just a question of the technical feasibility of, can you build a thing that applies its general intelligence narrowly to the neuroscience of augmenting humans? It's a question of like, so like, I, like one, I feel like that that is like probably like over 1% technical feasibility.

But the world that we are in is so far, so far from doing that, from trying.

Trying the way the world could actually work. Like not like the try where like, oh, you know, like, well, we'd like just like do a bunch of RLHF to try to have a spit out output about this thing, but not about that thing.
You know, that, that, that. No, no, not that.
Yeah, what 1% that we could, that humanity could do that if it tried and tried in just the right direction as far as I can perceive angles in this space. Yeah, I'm over 1% on that.
I am not very high on us doing it. Maybe I will be wrong.
Maybe the Time article I wrote saying shut it all down gets picked up and there are very serious conversations and the very serious conversations are actually effective in shutting down the headlong plunge. And there is a narrow exception carved out for the kind of narrow application of trying to build an artificial general intelligence that applies its intelligence narrowly and to the problem of augmenting humans.
And that, I think, might be a harder sell to the world than just shut it all down.

They could get shut it all down and then not do the things that they would need to do to have an exit strategy. I feel like even if you told me that they went for shut it all down, I would be like, then next expect them to have no exit strategy until the world ended anyways.
But perhaps I underestimate them. Maybe there's a will in humanity to do something else which is not that.
And if there really were, yeah, I think I'm even over 10% that that would be a technically feasible path if they looked in just the right direction. But I am not over 50% on them actually doing the shut it all down.
I am not, if they do that, I am not over 50% on their really, truly being the will of something else that is not that to really have an exit strategy. then from there you have to go in at sufficiently the right angle to materialize the technical chances and not do it in the way that just ends up a suicide or if you're lucky, gives you the clear warning signs and then people actually pay attention to those instead of just optimizing away the warning signs.
I don't want to make this sound like like the multiple-stage fallacy of like, oh, no, more than one thing has to happen, therefore the resulting thing can never happen, which, you know, like super clear case in point of why you cannot prove anything will not happen this way of Nate Silver arguing that Trump needed to get through six stages to become the Republican presidential candidate, each of which was less than half probability, and therefore he had less than one 64th chance of becoming the Republican. No, not one eighth.
Six. Six stages of doing.
Therefore, he had less than one 64th chance of becoming, I think, just a Republican candidate, not winning. So, yeah.
So, like, you can't just, like, break things down things down at the stages and then say therefore the probability is zero you can break down anything at the stages but like but like even so you're asking me like well like isn't over one percent that it's that it's possible i'm like yeah possibly even over 10 percent that that doesn't get me to because because the the like the the reason why you know go ahead and tell people, yeah, don't put your hope in the future, you're probably dead, is that the existence of this technical ray of hope, if you do just the right things, it's not the same as expecting that the world reshapes itself to permit that to be done without destroying the world in the meanwhile. I expect things to continue on largely as they have.
And, you know, and what distinguishes that from despair is that at the moment people were telling me like, no, no, if you go outside the tech industry, people will actually listen. I'm like, all right, let's try that.
Let's write the time article. Let's jump on that.
Let's see if it works. It will lack dignity not to try.
But it's not the same as expecting, as being like, oh yeah, I'm over 50%. They're totally going to do it.
That Time article is totally going to take off. I'm currently not over 50% on that.
You said any one of these things could mean, and yet even if this thing is technically feasible, that doesn't mean the world's going to do it. We are presently quite far from the world being on that trajectory.
Or of doing the things that we needed to create time to pay the alignment tax to do it. Maybe the one thing I would dispute is how many things need to go right from the world as a whole for any one of these paths to succeed.
Which goes in the fourth point, which is that maybe the sort of universal prior over all the drives that an AI could have is just like the wrong way to think about it. And this is something that...
Oh, yeah. I mean, you definitely want to use the alien observation of 10,000 planets like this one prior for what you get after training on like Thing X.
Just like, especially when we're talking about things that have been trained on, you know, human text, I'm not saying that it was a mistake earlier on the conversation for me to say, there'll be like the average of human motivations, whatever that means, but it's not, it's not inconceivable to me that it would be something that is very sympathetic to human motivations, having been having sort of encapsulated all of our output. I think it's much easier to get a mask like that than to get a Shoggoth like that.
Possibly, but again, this is something that seems like, I don't know, probably I'll put it on it at least 10%. And just by default, that is something that is not so, it is not incompatible with the flourishing of humanity like well why why is what is the utility function you hope it has that has its maximum there's so many flourishing of humanity there's so many possible like name three name one spell it out it i don't know wants to keep us as a zoo the same way we keep like other animals in a zoo this is not the best outcome for humanity but it's just like something where we survive and flourish okay whoa flourish keeping in a zoo did not sound like flourishing to me zoo was wrong word to uh use there well whoa whoa whoa whoa because it's not what you wanted why is it not a good prediction name three you didn't ask me like uh no no what i'm saying is like like you're like oh well like prediction oh no no i don't like my prediction i want a different prediction you didn't ask for the prediction you just asked me to name them like name possibilities i i had meant like possibilities into which you put some probability i had meant for for like like a thing that you thought held together this is the same thing as when i ask you like what is the specific utility function it will have that will be incompatible with, you know, humans existing? It's like your modal prediction is not paperclips.
The super vast majority of predictions of utility functions are incompatible with human existing. I can make a mistake and it'll still be incompatible with humans existing, right? Like I can just be like, you know, like I can just like describe a randomly rolled utility function function end up with something incompatible with humans existing so like at the beginning of human evolution you could think like okay this thing will become generally intelligent and what are the odds that it's flourishing on the planet will be compatible with the survival of spruce trees or something it's like and the long term we sure aren't i mean like maybe if we win we'll we'll have there be a space for spruce trees um yeah so as long as you can have spruce trees as long as the mitochondrial liberation front does not object to that what is the mitochondrial liberation front is that if you're you have you you have you have you know sympathy for the mitochondria enslaved working all their lives to the benefit of some other organism so this is like some weird hypothetical like for hundreds of thousands of years you uh general intelligence has existed on earth you could say like is it compatible with some random species that exists on earth like is it compatible with spruce trees existing and i know but you probably chopped down a few spruce trees.
And the answer is yes, as a very special case of us being the sort of things that some of us would maybe conclude that we specifically wanted spruce trees to go on existing, at least on Earth, in the glorious transhuman future. And their votes winning out against those of the mitochondrial

liberation front. I guess since part of the sort of transhumanist future is part of the thing we're debating, it seems weird to assume that as part of the question.
Well, the thing I'm trying to say is you're like, well, like if you looked at the humans, would you like not expect them to end up incompatible with the spruce trees? I'm'm being like, sir, you, a human, have looked back and looked at how humans wanted the universe to be.

And being like, well, would you not have anticipated in retrospect that humans would want the universe to be otherwise?

And I agree that we might want to conserve a whole bunch of stuff.

Maybe we don't want to conserve the parts of nature where things bite other things and inject venom into them and the victims die in terrible pain. Maybe even if maybe, you know, I think that many of them don't have qualia.
This is disputed. Some people might be disturbed by it even if they didn't have qualia.
We might want to be polite to the sort of aliens who would be disturbed by it because they don't have quality and they just see like things don't want venom injected into them there for they should not have venom we might conserve some parts of nature but again it's like it's like it's like firing an arrow and then drawing a circle around the target i i would disagree with that uh because again this is similar to the example we started off the conversation with, but it seems like you are reasoning from what might happen in the future. And because we disagree about what might happen in the future, in fact, the entire point of this disagreement is to test what will happen in the future.
Assuming what will happen in the future as part of your answer seems like a bad way to answer the question. Okay, but then you're like claiming things as evidence for your position.

Based on what exists in the world now, given that we have general intelligence.

That are not evidence one way or the other,

because the basic prediction is like if you offer things enough options,

they will go out of distribution.

It's like pointing to the very first people with language and being like, they haven't taken over the world yet. And they have not gone way out of distribution yet.
And it's like they haven't had general intelligence for long enough to accumulate the things that would give them more options such that they could start trying to select the weirder options.

The prediction is like when you have, when you give yourself more options,

you start to select ones that look weirder relative to the ancestral distribution.

As long as you don't have the weird options, you're not going to make the weird choices.

And if you say like we haven't yet observed your future, that's fine.

But like acknowledge that then like evidence against that future is not being provided by the past.

This is the thing I'm saying there. You look around, it looks so normal.
According to you, who grew up here? If you've grown up a millennium earlier, your argument for the persistence of normality might not seem as persuasive to you after you'd seen that much change. So this is a separate argument though, right? Like I'm like, like, look at all this stuff humans haven't changed yet.
You say now selecting the stuff we haven't changed yet. But if you go back 20,000 years and be like, look at the stuff intelligence hasn't changed yet, you might very well select a bunch of stuff that was going to fall 20,000 years later is the thing I'm trying to gesture at here.
But so like, how do you propose we reason about what general intelligence should do when the world we look at after hundreds of thousands of years of general intelligence is the one that we can't use for evidence? Because, yeah, dive under the surface. Look at the things that have changed.
Why did they change? Look at the processes that are generating those choices. And since we have sort of these different functions of like where that goes, like look at the thing with ice cream, look at the thing with condoms, look at the thing with pornography.
See where this is going. I think just like I, it just seems like I would disagree with your intuitions about like what future smarter humans will do even with more options.
I was like in the beginning of conversation, I disagreed that they would, most humans would adopt sort of like a transhumanist way to get better DNA or something. But you would.
So yeah, you you just like look down at your fellow humans. You have like no confidence in their ability to tolerate weirdness, even if they got smarter, I wonder.
Like, do you think, what do you think would happen if we did a poll right now? I think I'd have to explain that poll pretty carefully because, you know, they haven't got the intelligence headbands yet, right? I mean, we could do a Twitter poll with like a long explanation in it. 4,000 character Twitter poll? Yeah, I like.
I mean, man, I'm somewhat tempted to do that just for the sheer chaos and point out the drastic selection effects of A, it's my Twitter followers, B, they read through a 4,000 character tweet. I feel like this is not likely to be truly very informative by my standards, but part of me is amused by the prospect for the chaos.

Yeah, or I could do it on my end as well.

Although my followers are like, it would be weird as well. Yeah, but plus you wouldn't like really, I worry you wouldn't sell that transhumanism thing as well as it could be sold.
I could have worded as, like you could just send me the wording. But anyways, that's separate.
But anyways, given that we disagree about what in the future general intelligence will do, where do you suppose we should look for evidence about what the general intelligence will do, given our different theories about it, if not from the present? I mean, I think you look at the mechanics. You say, as people have gotten more options, they have gone further outside the ancestral distribution.

And we zoom in and it's like there's all these different things that people want. And there's this like narrow range of options that they had 50,000 years ago.
And the things that they want have maxima or optima 50,000 years ago at stuff that coincides with reproductive fitness. And then as a result of the humans getting smarter, they start to accumulate culture, which produces changes on a timescale faster than natural selection runs.
Although it is still running contemporaneously, the humans are just running faster than natural selection. It didn't actually halt.
And they generate additional options, not blindly, but according to the things that they want, and they invent ice cream. Not at random.
It doesn't just get coughed up at random. They're searching the space of things that they want and generating new options for themselves that optimize these things more that weren't in the ancestral environment.
And Goodhart's law applies. Goodhart's curse applies.
As you apply optimization pressure, the correlations that were found naturally come apart and aren't present in the thing that gets optimized for. Like, you know, like just give some people some tests who've never gone to school.
The ones who high score high in the test will know the problem domain because they, you know, like you just like gives a bunch of carpenters a carpentry test. The ones who score high in the carpentry test will like know how to carpenter things.
Then you're like, yeah, I'll like pay you for high scores in the carpentry test. I'll give you this carpentry degree.
And like people are like, oh, I'm going to like optimize the test specifically. And they'll get higher scores than the carpenters and do and be worse at carpentry because they're like optimizing the test.
And that's the story behind ice cream. And you zoom in and look at the mechanics and not the like grand scale view because the grand scale view just like never you the right answer, basically.
Like anytime you ask what would happen if you applied the grand scale view philosophy in the past, it's always just like, oh, I don't see why this thing would change. Oh, it changed.
How weird. Who could have possibly expected that? Maybe you have a different definition of grand scale view because I would have thought that that is what you might use to categorize your own view.
But I don't want to get it caught up in semantics. Mine is zooming in.

It's looking at the mechanics.

That's how I'd present it.

If we are like so far at a distribution of natural selection, as you say. No, we're currently nowhere near as far as we could be.
This is not the glorious transhumanist future. I claim that if even if you get much smarter as like if humans get much smarter through brain augmentation or something, then there will still be spruce trees in like millions of years in the future.
And if you still want to come the day, I don't think I myself would oppose it unless there would be like distant aliens who are very, very sad about what we were doing to the mitochondria. And then I don't want to ruin their day for no good reason but but the reason that it's important to state it in the form of like uh given human psychology spruce trees will still exist is because that is the one evidence of sort of generality arising we have and even after millions of years of that generality like we think that spruce trees would exist i feel like we would be in this position of spruce trees in comparison to the intelligence recreate and sort of the universal prior and whether spruce trees would exist doesn I feel like we would be in this position of spruce trees in comparison to the intelligence we create.
And sort of the universal prior on whether spruce trees would exist doesn't make sense to me. Okay.
But do you see how this perhaps leads to like everybody's severed heads being kept alive in jars on its own premises, as opposed to humans getting the glorious transhumanist future? No, no. They have the glorious transhumanist future.
Those are not real spruce trees. You know, like you're talking about like plain old spruce trees you want to exist, right? Not the sparkling giant spruce trees with built-in rockets.
You're talking about humans being kept as pets in their ancestral state forever, maybe being quite sad. Maybe they still get cancer and die of old age, and they never get anything better than that.
Does it keep us around as we are right now? Do we relive the same day over and over again? Maybe this is the day when that happens. I mean, you see how like, how the general trend I'm trying to point out to here is you have a rationalization for why they might do thing that is allegedly nice.
And I'm saying, why exactly are they wanting to do thing? Well, if they want to do thing for this reason, maybe there's a way to do this thing that isn't as nice as you're imagining. And this is systematic.
You're imagining reasons they might have to give you nice things that you want, but they are not you. Not unless we get, you know, not unless we get this like exactly right and they actually care about the part where you want some things and not others.
You are not describing something you are doing for the sake of the spruce trees. Do spruce trees have diseases in this world of yours? Do the diseases get to live? Do they get to live on spruce trees? And it's not a coincidence that I can like zoom in and poke at this and ask questions like this, and that you did not ask these questions of yourself.
You are imagining nice ways you can get the thing, but reality is not necessarily imagining how to give you what you want. And the AI is not necessarily imagining how to give you what you want.
And for everything you can be, like, oh, hopeful thought, maybe I get all the stuff I want because the AI reasons like this.

Because it's the optimism inside you that is generating this answer.

And if the optimism is not in the AI, if the AI is not specifically being like, well, how do I pick a reason to do things that will give this person a nice outcome?

You're not going to get the nice outcome.

You're going to be reliving the last day of your life over and over. It's going to like create old, or maybe it creates old-fashioned humans, ones from 50,000 years ago.
Maybe that's more quaint. Maybe it's just like, just as happy with like bacteria because there's more of them.
And that's equally old-fashioned. You're going to create the specific spruce tree over there? Maybe from its perspective, you know, like a generic bacterium is just as good a form of life as like a generic spruce tree is of a spruce tree.
And like this is not specific to the example that you gave. It's me being like, well, suppose we like took a criterion that sounds kind of like this and asked how do we actually maximize it? What else satisfies it? Not just you're like trying to argue the AI into doing what you think is a good idea by giving the AI reasons why it should want to do the thing under like some set of like hypothetical motives.
But anything like that, if you like optimize it on its own terms without narrowed down to where you want it to end up because it actually felt nice to you the way that you define niceness. Like it's all going to have somewhere else, somewhere that isn't as nice.
Something maybe where we'd be like sooner scour the surface of the planets, the clean with nuclear fire rather than let that AI come into existence. Though I do think those are also probable because, you know, instead of hurting you, as you know, there's like something more efficient for it to do that maxes out its utility function okay i acknowledge that you had a better argument there um but here's another intuition i'm curious how you responded that earlier we talked about the idea that like if you bred humans to uh be friendlier and smarter this is not where I'm going with this.
But like if you did that. I think I want to register for the record that the term breeding humans would cause me to like look askance again at any aliens who propose that as a policy action on their part.
No, no, no. All right.
That's not what I'm proposing. I said it.
Move on. No, no.
That's not what I'm proposing we do. I'm just saying as a sort of thought experiment.
But so you answered that, oh, because human psychology, that's why you shouldn't assume the same of AIs. They're not going to start with human psychology.
Okay. Fair enough.
Assume we start off with dogs, right? Good old fashioned dogs. And we bred them to be more intelligent, but also to be friendly.
Well, as soon as they are past a certain level of intelligence, I object to us like humming in and breeding them, they can no longer be owned. They are now sufficiently intelligent to not be owned anymore.
But let us leave aside all morals. Okay.
Carry on. In the thought experiment, not in real life.
You can't leave out the morals in real life. Sorry.
Do you ask a sort of universal prior over their drives of these like super intelligent dogs that are bred to be friendly? Man, so I think that weird shit starts to happen at the point where the dogs get smart enough that they are like, what are these flaws in our thinking processes? How can we correct them? You know, over the CIFAR threshold of dogs. Although maybe that's like, CIFAR has some strange baggage.
Over the Korzybski threshold of dogs after Alfred Korzybski. Yeah, so I think that, you know, there's this whole domain where they're stupider than you and sort of like being shaped by their genes and not shaping themselves very much.
And as long as that is true, you can probably go on breeding them. And issues start to arise when the dogs are smarter than you, when the dogs can manipulate you, if they got to that point, where the dogs can strategically present particular appearances to fool you, where the dogs are aware of the breeding process and possibly having opinions about where that should go in the long run.
Where the dogs are, even if just by thinking and by adopting new rules of thought, modifying themselves in that small way. These are some of the points where I expect the weird shit to start to happen.
And the weird shit will not necessarily show up while you're just reading the dogs. Does the weird shit look like dog gets smart enough, dot, dot, dot, human stop existing? If you keep on optimizing the dogs, which is not the correct course of action, I think I mostly expect this to eventually blow up on you.
But blow up on you that bad? It's hard. Well, I expect it to blow up on you quite bad.
I'm trying to think about whether I expect super dogs to be sufficiently in a human frame of reference in virtue of them also being mammals. That a super dog would like create human ice cream like they you bred them to have preferences about humans and they invent something that is like ice cream to those preferences or does it just like go off someplace stranger there could be ai ice cream there could be ai ice cream ice cream that is things that is equivalent of ice cream for AIs.
That is essentially my prediction of what the solar system ends up filled with. The exact ice cream is quite hard to predict, just like it would be very hard to look at.
Well, if you optimize something for inclusive genetic fitness, you'll get ice cream. That is a very hard call to make.
Sorry, I didn't mean to interrupt. Where were you going with your...
No, I think, yeah, I was just like rambling in my attempts to make predictions

about these super dogs.

You're like asking me to...

I mean, I feel like, you know,

in a world that had anything remotely

like its priorities straight,

this stuff is not me like extemporizing

on a blog post.

There are like 1,000 papers that were written by people who otherwise became philosophers writing about this stuff instead. But you know, your world has not set its priorities that way.
And I'm concerned that it will not set them that way in the future. And I'm concerned that if it tries to set them that way, it will end up with like garbage because the good stuff is hard to verify.
But you know, separate topic. Yeah, on that particular intuition about the dog thing like i understand your intuition that we would end up in a place that is not very good for humans that just seems so hard to reason about that i honestly would not be surprised if it ended up like fine for humans in fact the dogs wanted like good things good things for humans, loved humans, like we're smarter than dogs.
We love them. Um, the sort of reciprocal relationship came about.
I don't know. Uh, I feel like maybe I could do this given thousands of years to breed the dogs in a total absence of ethics, but it would actually be easier with the dogs, I think, than with gradient descent.
Cause I think it's, well, because the dogs are starting out with neural architecture very similar to human. And natural selection is just like a different idiom from gradient descent.
In particular, in terms of like information bandwidth. But like I'd be just tearing to like breed the dogs into like genuinely very nice human.
And like knowing the stuff that I know that your typical dog breeder might not know when they set out to be embarked on this project, I would be early on sort of prompting them into the weird stuff that I expected to get started later and trying to observe how they went during that. This is the alignment strategy.
We need ultra smart dogs to help us solve. There's no time.

Okay.

So I think we sort of articulated our intuitions on that one.

Here's another one that's not something I came into the conversation with.

Like some of my intuition here is like I know how I would do this with dogs.

And I think you could like ask OpenAI to describe their theory of how to do it with dogs. And I would be like, oh, wow, that sure is going to get you killed.
And that's kind of how I expected it to play out in practice. Actually, do you mind if I ask, but when you talk to the people who are in charge of these labs, what do they say? Do they just not rock the arguments? You think they talk to me? There was a certain selfie that was taken by...
Five minutes of conversation, first time any of the people in that selfie had met each other. And then did you bring it up? I asked him to change the name of his corporation to anything but OpenAI.
Have you seeked an audience with the leaders of these labs to explain these arguments? No. Why not? I did try to, I've had a couple of conversations with like Demis Asabas, who struck me as like much more of the sort of person who it was possible to have a conversation with.
I guess it seems like it would be more dignity to explain, even if you think it's not going to be fruitful ultimately ultimately the people who are like most likely to be influential in this race i my basic model was that they wouldn't like me and that things could always be worse fair enough um you know i mean like they sure they sure could have like i mean they they sure could have asked at any time but but that would have been quite out of character.

And the fact that it was quite out of character is why I myself did not go trying to barge into their lives and getting them mad at me. But you think them getting mad at you would make things worse? It can always be worse.
I agree that possibly at this point some of them are mad at you know, I, I, I have yet to turn down the leader of any major AI lab who has come to me asking for advice. Fair enough.
Um, okay. So, so on the scene of like big picture disagreements, like why I'm still not on the, uh, greater than 50% doom.
It just seemed like, uh, from the conversation, it didn't seem like you were willing or able to make predictions about the world short of doom that would help me distinguish uh and highlight your view about other views yeah I mean the world heading into this is like a whole giant mess of complicated stuff which predictions about which can be made in virtue of like spending a whole bunch of time staring at the complicated stuff until you understand that specific complicated stuff and making predictions about it. Like, from my perspective, like, the way you get to my point of view is not by having a grand theory that reveals how things will actually go.

It's like taking other people's overly narrow theories and poking at them until they come apart.

And you're left with a maximum entropy distribution over the right space, which looks like, yep,

that's sure going to randomize the solar system. But to me, it seems like the nature of intelligence

and what it entails is even more complicated than the sort of geopolitical or economic things that

would be required to predict what the world's going to look like in five years. Oh, I think you're just wrong.

Thank you. and what it entails is even more complicated than the sort of geopolitical or economic things that would be required to predict what the world's going to look like in five years.
Oh, I think you're just wrong. I think that the theory of intelligence is just flatly not that complicated.
Maybe that's just the voice of a person with talent in one area, but not the other. But that's sure how it feels to me.
This would be even more convincing to me if we had some idea of what the pseudocode or circuit for intelligence look like and then you could say like oh this is what the pseudocode implies we don't even have that i mean if you permit a hyper computer just as aixi what is aixi um you have the solominoff prior over your environment yeah Update it on the evidence. And then max sensory reward.
Okay, so it's not actually trivial. Actually, this thing will exhibit weird discontinuities around its Cartesian boundary with the universe.
It's not actually trivial. But everything that people imagine as the hard problems of intelligence are contained in the equation if you have a hypercomputer.
Yeah, fair enough. But I mean in the sort of sense of, you know, programming it into like a normal, like I give you a GUA fad or I give you a really big computer, write the pseudocode or something like that.
I mean if you give me a hypercomputer. Yeah, saying what you're saying here is that like the theory of intelligence is really simple in an unbounded sense but as soon as you like yeah what what about this like depends on the difference between unbounded and bounded intelligence so how about this you asked me do you understand how fusion works if not how can you predict the assume we're talking like the 1800s how can you predict how powerful a fusion bomb would be, well, listen, if you put in a pressure, I'll just show you the sun.
And the sun is sort of the archetypal example of a fusion is. And you say, no, no, no.
I'm asking like, what would a fusion bomb look like? You see what I mean? Not necessarily. Like, what is it that you think somebody ought to be able to predict about the road ahead?

So first of all, like if you – one of the things if you know the nature of intelligence is just like how will this sort of progress in intelligence look like? How are abilities going to scale, if at all? How fast? And it looks like a bunch of details that don't easily follow from the general theory of, you know, like simplicity prior Bayesian update argmax. Again, so then the only thing that follows is the wildest conclusion, which is, you know what I mean? Like there's no like simpler conclusions to follow, like the Eddington looking and confirming confirming special relativity it's just like the wildest possible conclusion is the one that follows yeah like the the convergence is a whole lot easier to predict than the pathway there I'm sorry but and I sure wish it was where otherwise but and also remember the basic paradigm from my perspective I'm not making any brilliant startling predictions.
I'm poking at other people's incorrectly narrow theories until they fall apart into the maximum entropy state of doom. There's like thousands of possible theories, most of which have not come about yet.
I don't see it as strong evidence that because you haven't been able to identify a good one yet, that... Oh, somebody, I mean, if somebody in the profoundly unlikely event that somebody came up with some incredibly clever grand theory that explained all the properties GPT-5 ought to have, which is like just flatly not going to happen.
It's just like that kind of info that's available. You know, my hat would be off to them if they wrote down their predictions in advance.
And if they were then able to like grind that theory to produce predictions about alignment, which seems like even more improbable because like what do those two things have to do with each other exactly? But like still, you know, like I mean, mostly it'd be like, well, looks like our generation has its new genius. How about if we all shut up for a while and listen to what they have to say? How about this? Let's say somebody comes to you and they say, I have the best and newest theory of economics.
Everything before is wrong. But they say in the year...
One does not say everything before is wrong. One predicts the following new phenomena and on rare occasions say that old phenomena were organized incorrectly.
Fair enough. So they say old phenomena are organized incorrectly.
Yeah. Because of the, and then here's an argument.
Let us term this person Scott Sumner for the sake of simplicity. They say in the next 10 years, there's going to be a depression that is so bad that is going to destroy the entire economic system i'm not talking just about something that is a hurdle it is like literally civilization will collapse because it's an economic disaster and then you ask them okay give me some predictions before this great catastrophe happens about like what this theory implies and then they say like listen there's many different branching paths but they all converge at civilization collapsing because of some great economic crisis i'm like i don't know man like i would like to see some predictions before that yeah i it sure yeah wouldn't it be nice wouldn't it be nice so we're left with your 50 probability that we win the lottery and 50 probability that we don't because nobody has like a theory of lottery tickets that has been able to predict to what numbers get drawn next? I don't agree with the analogy that – It's all about the probability.
It's all about the space over which you're uncertain. We are all quite uncertain about where the future leads but over which space.
And there isn't a royal road. There isn't a simple like, ah, I found just the right thing to be ignorant about.
It's so easy. The chance of a good outcome is 33% because there's like one possible good outcome and two possible bad outcomes.
The stuff that you do when you're uncertain is like the thing you're trying to fall back to in the absence of anything that predicts exactly which properties GPT-5 will have is your sense that, you know, a pretty bad outcome is kind of weird, right? It's probably a small sliver of the space. It seems kind of weird to you.
But that's just like imposing your natural English language prior, like your natural humanist prior on the space of possibilities and being like, I'll distribute my max entropy stuff over that. Yeah, can you explain that again? Okay, what is the person doing wrong who says 50-50, either I'll win the lottery or I won't? They have the wrong distribution to begin with over possible outcomes.
Okay. What is the person doing wrong who says 50-50? Either we'll get a good outcome or a bad outcome from AI.
They don't have a certain good theory to begin with about what the space of outcomes looks like. Is that your answer or is that your model of my answer? My answer.
Okay. But all the things you could say about a space of outcomes are an elaborate theory and you haven't predicted gpt4's exact properties in advance shouldn't that just leave us with like good outcome or bad outcome 50 50 people did have theories about what gpt4's like if you look at the scaling laws right like the yeah if there's you can like put it it probably falls right on the curves that were drawn in 2020 or something.

Yeah, the loss.

The loss on text predictions.

Sure, that followed a curve.

But which abilities would that correspond to?

I'm not familiar with anyone who called that in advance.

What good does it know to the loss? You could have taken those exact loss numbers back in time 10 years and been like, what kind of commercial utility does this correspond to?

And they would have given you utterly blank looks.

And I don't actually know of anybody who has a theory that gives something other than a blank look for that.

All we have are the observations.

Everyone's in that boat.

All we can do are fit the observations.

I mean, so like also like there's just like me starting to work on this problem in 2001 because it was like super predictable going to turn into an emergency later. And in point of fact, like nobody else ran out and like immediately tried to start getting work done on the problems.
And I would claim that as a successful prediction of the grand lofty theory you had. Did you see deep learning coming as the main paradigm? Nope.
And is that relevant as part of the picture of intelligence? I mean, I would have been like much, much, much more worried in 2001 if I'd seen deep learning coming. No, not in 2001.
I just mean before it became like the obviously the main paradigm of AI. No.
It's like the details of biology. It's like asking

people to like predict what the organs look like in advance via the principle of natural selection.

And you like, it's pretty hard to call an advance. You like afterwards, you can look at it

and be like, yep, this like sure does look like it should look if this thing is being optimized to

reproduce. But the space of solution of things that biology can throw at you is just too large.
It's very rare that you have a case where there's only one solution that lets the thing reproduce, that you can predict by the theory that it will have successfully reproduced in the past. And mostly it's just this enormous list of details.
And they do all fit together in retrospect. The theory actually, it is a sad truth.
Contrary to what you may have learned in science class as a kid, there are genuinely super important theories where you can totally actually validly see that they explain the thing in retrospect, and yet you can't do the thing in advance. Not always, not everywhere, not for natural selection.
There are advanced predictions you can get about that. Given the amount of stuff we've already seen, you can go to a new animal in a new niche and be like, oh, it's going to have this property, given the stuff we've already seen in the niche.
But you could also make that by blind gender. There's advanced predictions.
They're a lot harder to come by, which is why natural selection was a controversial theory in the first place. It wasn't like gravity.
People were being like, gravity had all these awesome predictions. Newton's theory of gravity had all these awesome predictions.
We got all these extra planets that people didn't realize ought to be there. We figured out Neptune was there before we found it by telescope.
Where is this for Darwinian selection? People actually did ask at the time. And the answer is it's harder.
And sometimes it's like that in science. The difference is the theory of Darwinian selection seems much more well developed.
Well, sure. Sure.
Then, like, they were precursors of darwinian selection that i don't know who was that roman uh poet lucretius right he had some poem where there was some precursor of darwinian selection and i feel like that is probably our level of maturity when it comes to uh i mean if you want whereas we don't have like a theory of intelligence we might have some hints about what it might look like like i don't well oh we've got our hints and if you want the like but then from hints it seems harder to extrapolate very strong conclusions they're not very strong conclusions is the message i'm trying to say here i'm pointing to your being like maybe we might survive and like whoa that's a pretty strong conclusion you've got there. Let's weaken it.
That's the basic paradigm I'm operating under here. Like you're in a space that's narrower than you realize when you're like, well, you know, if I'm kind of unsure, maybe there's some hope.
Yeah, I think that's a good place to close the discussion on AI unless. Well, I do kind of want to like mention one last thing, which is that, again, in historical terms, if you look out the actual battle that was being fought on the block, it was me going like, I expect there to be AI systems that do a whole bunch of different stuff.
And Robin Henson being like, I expect there to be a whole bunch of different AI systems that do a whole different bunch of stuff. But that was one particular debate with one particular person.
Yeah, but like your planet having made the strange reason given its own widespread theories to not invest massive resources and having a much smarter version, well not smarter, a much larger version of this conversation as it thought deemed, apparently prudent, given the implicit model that it had of the world, such that I was investing a bunch of resources in this and kind of dragging Robin Hanson along with me, though he did have his own separate line of investigation into topics like these. Being there as I was, my model having led me to this important place where the rest of the world apparently thought it was fine to let it go hang.
The, you know, such debate as there actually was at the time was like, are we really going to see like these like single AI systems that do all this different stuff? Is this like whole general intelligence notion kind of like meaningful at all? and I staked out the bold position for it actually was bold and people did not all say like oh Robin Hanson you fool why do you have this exotic position they were going like ah like behold these two luminaries debating or behold these two idiots debating and like not massively coming down on one side of it or the other. So, you know, like in historical terms, I, I, I dislike, you know, making it out like I was right about anything when I feel I've been wrong about so much.
And yet I was right about anything. And, you know, relative to the relative to the, what the rest of the planet deemed it important stuff to spend its time on, given their implicit model of how it's going to play out, what you can do with minds, where AI goes.
I think I did okay. Goran Branwen did better.
Shane Legg arguably did better. Goran always does better when it comes to forecasting.
I mean, obviously, like, if you get the better of a debate, that, like, counts for something. But a debate with one particular person, I— Well, considering your entire planet's decision to invest, like, $10 into this entire field of study, apparently one debate is all you get.
And that's the evidence you've got to update on now. So somebody like Ilya Suskever, you know, when it comes to the actual paradigm of deep learning,

was able to anticipate from ImageNet to scaling up LLMs or whatever.

There's people with track records here who disagree about Doom or something.

So in some sense, it's probably more people who have been... Ifia challenged me to abate i wouldn't turn him down i admit that i did specialize in doom rather than llms okay fair enough i unless you have other sorts of comments on ai i'm uh i'm happy with yeah and again i'm being like, due to my miraculously precise and detailed

theory, I'm able to make the surprising and narrow prediction of doom. I am like, I am being like, like, I think I did a fairly good job of shaping my ignorance to lead me to not be too stupid, despite my ignorance over time as it played out.

And, you know, there's a prediction, even knowing that little, that can be made. Okay, so this feels like a good place to pause the EI conversation.
And there's many other things to ask you about, given your decades of writing and millions of words. So I think what some people might not know is the millions and millions and millions of words

of science fiction and fan fiction that you've written.

I want to understand what, in your view, is it better to explain something through fiction than nonfiction?

When you're trying to convey experience rather than knowledge.

Or when it's just much easier to write fiction and you can produce 100,000 words of fiction

with the same effort it would take you to produce 10,000 words of nonfiction. Those are both pretty good reasons.
On the second point, it seems like when you're writing this fiction, not only are you, in your case, covering the same heady topics that you include in your nonfiction, but there's also the added complication of plot and characters. it's surprising to me that that's easier than just verbalizing the sort of the topics themselves.

Well, partially because it's more fun is an actual factor. Ain't going to lie.
and sometimes it's something like

a bunch of what you get in the fiction

is just like the lecture that the character would deliver in that situation. The thoughts the character would have in that situation.
There's only one piece of fiction of mine where there's literally a character giving lectures because he arrived on another planet and now has to lecture about science to them. That one is Project Law lawful you know about project lawful i know about it i have not read it yet yeah okay so so most of my most of my fiction is not about somebody arriving in another planet who has to deliver lectures there um i i was being like a bit deliberately like yeah i i'm gonna just do it with like project lawful like i'm gonna just do it they they say nobody should ever do it and I don't care.
I'm doing it every way. So I'm going to have my character actually launch into lectures.
I mean, you know, like the lectures aren't really the parts I'm proud about. It's like where you have like the like life or death, death note style battle of wits between like the that that is like centering around a series of Bayesian updates.
Yeah. And, and like making that actually work.
Cause you know, it's where I'm like, yeah, I, I, I think I actually pulled that off and I don't think, I'm not sure a single other writer on the face of this planet could have made that work as a plot device. But that said, like the nonfiction is like,

I'm explaining this thing,

I'm explaining the prerequisites,

I'm explaining the prerequisites to the prerequisites.

And then in fiction, it's more just like,

well, this character happens to think of this thing

and the character happens to think of that thing.

But you got to actually see the character using it.

Yeah.

So it's less organized.

It's less organized as knowledge.

And that's why it's easier to write. Yeah i mean one of my uh favorite pieces of fiction of fiction to explain something is uh the dark lord's answer and i i honestly can't say i i honestly can't say anything about it without spoiling it but i just want to say like honestly it was like such a great explanation of the thing it is explaining um i don't know what else i can say about it without spoiling it anyways yeah well i'm laughing because i think like relatively few have dark lord's answer as their as like among their top favorite works of mine it is what is one of my less widely favored works of mine actually what is my favorite sort of this is a medium by the way i don't think is used enough given how effective it was in um in an adequate equilibria you have different characters just explaining concepts together some who some of whom are purposefully wrong as examples and that is such a useful pedagogical tool and i don't know honestly like at least half a blog post should just be written that way.
It is so much easier to understand that way.

Yeah.

And it's easier to write.

And I should probably do it more often. And like, you should give me a stern look and be like, Eliezer, write that more often.
Done. Eliezer, please.
I think 13 or 14 years ago, you wrote an essay called Rationality, a Systematized is Winning. would you have expected then that 14 years down the line um the most successful people in the world

or some of called Rationality is Systematized as Winning. Would you have expected then that 14 years down the line,

the most successful people in the world,

or some of the most successful people in the world,

would have been rationalist?

Only if the whole rationalist business

had worked closer to the upper 10% of my expectations

than it actually got into. The title of the essay was not Rationalists are Systematized Winning.
It wasn't even a rationality community back then. Rationality is not a creed.
It is not a banner. It is not a way of life.
It is not a personal choice. It is not a social group.
It's not really human. It's a structure of a cognitive process.
And you can try to get a little bit more of it into you. And if you want to do that and you fail, then having wanted to do it doesn't make any difference except insofar as you succeeded.
Hanging out with other people who share that creed going to their parties, it only ever matters insofar as you get a bit more of that structure into you. And this is apparently hard.
This seems like a no true Scotsman kind of point because... And yet there are no true Bayesians upon this planet.
But do you really think that had people tried much harder to adopt the sort of Bayesian principles that you laid out, they would have, many of the successful people, some of the successful people in the world would have been rationalists. What good does trying do you, except insofar as you are trying at something which, when you try it, it succeeds? Is that an answer to the question? Rationality is systematized winning it's not rationality the life the life philosophy it's you know it's not like trying real hard at like this thing this thing and that thing it's it was like the mathematical sense okay so then the question becomes does adopting the philosophy of bayesianism consciously actually lead to you having more concrete wins? Well, I think it did for me, though only in like scattered bits and pieces of slightly greater sanity than I would have had without explicitly recognizing and aspiring to that principle.
the principle of not updating in a predictable direction, the principle of jumping ahead to where you can predictably be, where you will predictably be later. I look back and, you know, kind of, I mean, the story of my life, as I would tell it, is a story of my jumping ahead to what people would predictably, you know, like believe later after reality finally hit them over the head with it.
This to me is the entire story of the like, like people running around now in a state of frantic emergency over something that was utterly predictably going to be an emergency later as of 20 years ago. And you could have been trying stuff earlier.
But you He left it to me and a handful of other people. And it turns out that that was not a very wise decision on humanity's part because we didn't actually solve it all.
And I don't think that I could have, like, tried even harder or, like, contemplated probability theory even harder and done very much better than that. I contemplated probability theory about as hard as the mileage I could visibly obviously get from it.
I'm sure there's more. There's obviously more, but I don't know it would let me save the world.
I guess my question is, is contemplating probability theory at all in the first place something that tends to lead to more victory? I mean, I imagine who's the richest person in the world? How often does Elon Musk think in terms of probabilities when he's deciding what to do? And here's somebody who is very successful. So I guess the bigger question is, in some sense, when you say like rationality system, it's like a tautology if the definition of rationality is whatever helps you win.
If it's specific principles laid out in the sequences, then the question is like, do the, uh, I do the successful people, most successful people in the world practice them. I think you are trying to read something into this that is not meant to be there.
All right. It is the notion of rational, rationality, systematized winning is meant to stand, stand in contrast to a long philosophical tradition of like notions of rationality that are not meant to be about the mathematical structure, not meant to be or about strangely wrong mathematical structures where you can clearly see how these mathematical structures will make predictable mistakes.
It was meant to be saying something simple. There's an episode of Star Trek wherein Kirk makes a 3D chess move against Spock.

And Spock loses.

And Spock complains that Kirk's move was irrational.

Rational towards the goal, yeah.

The literal winning move is irrational.

Or possibly illogical, Spock might have said. I might be misremembering this.
The thing I was saying is not merely, that's wrong. That's like a fundamental misunderstanding of what rationality is.
There is more depth to it than that, but that is where it starts. There are like so many people on the internet in those days, possibly still, who are like well, you know, if you're rational, you're going to lose because other people aren't always rational.
And this is not just like a wild misunderstanding, but there's like the contemporarily accepted decision theory in academia as we speak at this very moment, causal decision theory, classical causal decision theory, basically has this property where like you can be irrational and the rational person you're playing against is just like, oh, I guess I lose.

Then here, have most of the money. I have no choice but to.
And ultimatum games specifically. If you look up logical decision theory on Arbital, you'll find a different analysis of the ultimatum game.
Where the rational players do not predictably lose the same way as I would define rationality.

And if you take this sort of like deep mathematical thesis that also runs through all the little moments of everyday life when you may be tempted to think like, well, if I do the reasonable thing, won't I lose? that you're making the same mistake as the Star Trek script writer who had Spock complain that Kirk had won the chess game irrationally? That every time you're tempted to think like, well, here's the reasonable answer and here's the correct answer. You have made a mistake about what is reasonable.
And if you then try to screw that around as like rationalists should win, rationalists should have all the social status, whoever's the top dog in the present social hierarchy or the planetary wealth distribution must have the most of this wealth, must have the most of this math inside them. There are no other factors.
But how much of a fan you are of this math. That's trying to take the deep structure that can run all through your life in every moment where you're like, oh, wait, like maybe the move that would have gotten the better result was actually the kind of move I should repeat more in the future.
Like to take that thing and like turn it into like, like social dick measuring contest time. Rationalists don't have the biggest dicks.
Okay. Final question.
Uh, this has been, I don't know how many hours. I really appreciate you doing, uh, giving me your time.
Final question. I know that in a previous episode, you were not able to give specific advice of what somebody young who is motivated to work on these problems should do.
Do you have advice about how one would even approach coming up with an answer to that themselves? There's people running programs who think we have more time, who think we have better chances, and they're running programs to try to nudge people into doing useful work in this area. and I'm not sure they're working.
And there's such a strange road to walk, and not a short one. And I tried to help people along the way, and I don't think they got far enough.
Like some of them got some distance, but they didn't turn into alignment specialists doing great work. And it's the problem of the broken verifier.
If somebody had a bunch of talent in physics, they were like, well, I want to work in this field. I might be like, well, there's interpretability.
And you can tell whether you've made a discovery in interpretability or not. setsets it apart for a bunch of this other stuff.
And I don't think that saves us. And okay, so how do you do the kind of work that saves us? And I don't know how to convey the, and the key thing is the ability to tell the difference between good and bad work.
And maybe I will write some more blog posts on it. I don't really expect the blog posts to work.
And the critical thing is the verifier. How can you tell whether you're talking sense or not? Whether you're...
There's all kinds of specific heuristics I can give. I can be like...
I can say to somebody like, well, it's like your entire alignment proposal is this like elaborate mechanism. You have to explain the whole mechanism and you can't be like, here's the core problem.
Here's the key insight that I think addresses this problem. If you can't extract that out, if your whole solution is just a giant mechanism, this is not the way.
it's kind of like how people invent perpetual motion machines by making the motion, perpetual motion machines more and more complicated until they can no longer keep track of how it fails. And if you actually had somehow a perpetual motion machine, it would not just be a like giant machine.
There would be like a thing you had realized that made it possible to do the impossible. For example, you're just not going to have a perpetual motion machine.
So there's thoughts like that. I could say go study evolutionary biology because evolutionary biology went through a phase of optimism and people naming all the wonderful things they thought that evolutionary biology would cough out.
Like all the wonderful things that they thought, wonderful properties that they thought natural selection would abute into organisms. And the Williams Revolution, as it's sometimes called, is when George Williams wrote Adaptation and Natural Selection, a very influential book saying like that is not what this optimization criterion gives you.
You do not get the pretty stuff. You do not get the aesthetically lovely stuff.
Here's what you get instead. And by living through that revolution vicariously, well, I thereby picked up a bit of a thing that to me obviously generalizes about how not to expect nice things from an alien

optimization process. But maybe somebody else can read through that and like not generalize,

not generalize in the correct directions. Then how do I advise them to generalize in the correct

direction? How do I advise them to learn the thing that I learned? I can just give them the

generalization, but that's not the same as having the thing inside them that generalizes correctly

without anybody standing over their shoulder and forcing them to get the right answer. I could point out and have in my fiction that the entire schooling process of like, here is this legible question that you're supposed to have already been taught how to solve.
Give me the answer using the solution method you are taught. That this does not train you to tackle new basic problems.
But even if you tell people that, like, okay, how do they retrain? We don't have a systematic training method for producing real science in that sense. We have like half of the, what was it, a quarter of the Nobel laureates being the students or grand students of other Nobel laureates? Because we never figured out how to teach science.
We have an apprentice system. We have people who pick out people who they think can be scientists and they hang around them in person and something that we've never written down in a textbook passes down.
And that's where the revolutionaries come from. And there are whole countries trying to invest in having scientists, and they churn out these people who write papers, and none of it goes anywhere because the part that was legible to the bureaucracy is have you written the paper? Can you pass the test? And this is not science.
And I could go on for this for a while, but the thing that you asked me is like, how do you pass down this thing that your society never did figure out how to teach? And the whole reason why Harry Potter and the Methods of Rationality is popular is because people read it and picked up the rhythm seen in a character's thoughts of a thing that was not in their schooling system, that was not written down, that you would ordinarily pick up by being around other people. And I managed to put a little bit of it into a fictional character, and people picked up a fragment of it by being near a fictional character.
But, you know, like not in really vast quantities, not vast quantities of people. And I managed to put vast quantities of shards in there.
I'm not sure. There's not a long list of Nobel laureates who've read HPMOR, although there wouldn't be because the delay times on granting the prizes are too long.
It's, yeah, like you asked me, what do I say? And my answer is like, well, that's a whole big gigantic problem I spent however many years trying to tackle and I ain't going to solve the problem with a sentence in this podcast. Fair enough.
Eliezer, thank you so much for giving me I don't know how many hours of your time. This was really fun.
Hey, everybody. I hope you enjoyed that episode.
As always, the most helpful thing you can do is to share the podcast. Send it to

people you think might enjoy it. Put it in Twitter, your group chats, etc.
It just splits the world.

Appreciate you listening. I'll see you next time.
Cheers.