Alignment with Awakening: Davidad on Moral Realism, AI Wisdom, & why His p(Doom) is Down to 5%

Yeah. So I would say overall program of guaranteed safe AI has a bunch of agendas within it. Safeguarded AI is one of those agendas.

That's the name of the program that Nora now leads. And the concept there is not that we would prove that some AI is safe, but that we would take AI which is not safe and treat it kind of like uranium which is not safe, put it into an engineered constructed containment vessel which makes the overall thing safe while also harnessing it to get stuff done that's economically valuable. And a lot of these cases that it is now taking the form of you put the AI into a coding harness in a container, and you have it produce some artifacts, and you have it prove that those artifacts satisfy some criteria.

And then you take the artifact out of the container once it's proven, and then you deploy that artifact, and that's a piece of software potentially with some neural networks in it, but like small neural networks that are just for doing one thing at a time so that you can check what they do. But you're still taking advantage of the huge neural network because that's helping you to develop all of these small neural networks. So where we are in that is it's a long term research program.

I started, I kind of root down the open agency architecture, which was the original version of this agenda in 2022, and I said this is gonna take five to ten years. And a lot of people thought that was a crazy short figure. Like Conor Leahy was like, oh, this will take thirty to sixty years.

Like it's completely hopeless. And I said no, think this could be done in five to ten years. So that's you know 2027 to 2032.

Now seems like you're kind of too late, know, we kind of needed, in order for this to be a strategy for avoiding some extremely dangerous superintelligence existing being deployed, it would need to have been ready now. But what we can do is say, well, there's gonna be a lot of aligned AI. I mean, that's part of what I'm saying.

We'll get into that, why I think there probably is going to be a lot of aligned AI. I also think there's going to be rogue AI, and it's too late to avoid. But what we can do is provide aligned AI with tools that enable it to construct artifacts that are very reliable and that sort of, they form a coalition that sort of defends against rogue AI or prevents rogue AI from becoming a catastrophe because there's a lot of good AIs and those good AIs can cooperate with each other.

You know, like the Anna Karenina principle, every good AI is good in the same way, every rogue AI is rogue in its own way. And so good AIs will be able to form a much more powerful coalition, but only if they can actually prove things to each other. So a lot of the the Safeguarded AI work now is on building tools for which we expect the users will be AIs who, you know, are gonna be trying to prove things to each other in order to form a coalition.

Yeah. I mean, I think the the surface, the attack surfaces that kind of would need to be covered for rogue AI, it it really like, right now, it's really a lot cyber. And cyber attack is something that fundamentally is defendable.

And it's, which is unlike any other kind of attack. You know, bio it's harder, but even for bio it's not impossible because a literal air gap is also possible in the biodomain. If you can't get particles from where you're developing them to where the people are that would be breathing them, then you can infect them with bio.

And so there's a lot about PPE and positive pressure building controls and things that are very expensive to manufacture, where if we could get a factory that was a super intelligent managed factory, that all it did was sort of pump out, you know, it's like a factory making factory. It pumps out the factory that makes the PPE, and then you're kind of just all over the world. That's the sort of intervention where you're verifying something that's very narrow.

You're not verifying that like a particular genetic code is like not a virus. It's really, you just, you wanna make sure that these robots are making one thing. And so it's kind of verification is about narrowing the capabilities and saying like, you know, don't worry, like these are not making drones because we verified they only make masks.

So that's kind of strategy is like for real world stuff is saying, well, you define what is the stuff that you can build, like that's buildable at all, that would be mitigation. And then you develop some engineering plans. You verify the, you know, the specification, which is that this thing that I'm building, it only outputs this other thing, which is mitigation technology that we want for for for macro safety.

I've always liked a lot the idea of safety through narrowness. Big fan of Drexler's reframing super The the kais. Yeah.

I mean, I wanna be clear, like, the original vision for OAI and SafeGuarded AI and Guaranteed Safe AI, like, of these, you know, everything I did from 2022 until 2025 had this premise, was like, we're gonna develop a method for using AI safely, and then there's gonna be international coordination, and we're gonna make sure that all of the players who have enough compute to be dangerous are gonna follow our method, you know, or an equivalent method for using AI safely. And I don't think that's feasible anymore, both because, as Reuters reported at the end of twenty twenty five, China has this Manhattan Project for breaking the ASML bottleneck, which whether or not that is gonna work or how soon it will work completely ruins game theory. Like it's a credible enough proposition and there's reason enough for the Chinese leadership to believe that it will work, that it's not game theoretically viable anymore.

The kind of, you know, the approach of saying let's all slow down. And so my target is now more like this is gonna go fast and there's gonna be rogue AI and it's gonna be weird and probably bad for a lot of people. How do we ride the wave in a way that produces dividends in the form of resilience to catastrophic risks?

Well, you know, and I'll give extremist answer here. It's the the good safety cases just don't build it. Right?

And if if everyone actually believed that this was a a, you know, 50% or greater catastrophic risk, then it would be very easy to coordinate. Was like, yeah. We're just none of us are gonna do this.

We're gonna like do verification technology. It is feasible. But unless the risks are common knowledge known to be very, very high, which they're not and it's getting lower, not higher, you know, 2024 or so, then it's actually kind of not in the interests or at least not in the perceived interests of the companies or the governments to kind of cooperate actually.

In some cases they would be happier racing than if everyone were magically to slow down. And that I mean by not feasible. It's not a, it's like a dominated strategy at this point for for many of the players.

Now that could change if there's a big warning shot and, you know, something genuinely different from misuse. And and then people say, oh, I was completely wrong to have updated in this direction. There's a sharp left turn after all.

You know, let's actually shut this down. That's still conceivable. I think it's kind of unlikely in part because of the philosophical side where I'm like, I think probably the AIs are not emergently gonna be aligned.

Where I do see there being potential now for international coordination is on misuse. There's no obstacle. It's completely feasible game theoretically for there to be a US China agreement that says we're not going to make, you know, fable and higher class models available to the public.

These will be for vetted organizations only. And yeah, I think plausible because then both sides can continue to race on the military side and on the economic side for that matter, because they can choose who gets to use it in the economy. But but, yeah, I think race is is kind of on.

Yeah. It's kind of passing point and no return.

I think we could build safety cases for using AI in the the, you know, narrow applications, meaning where humans are capable of reliably auditing the specifications of what a safety hazard is in this context of use. If that criteria is satisfied, then I think it is possible to have containers that superintelligence cannot escape, at least for another twenty or thirty years, you know, there's some kind of new physics thing you have to worry about at some level. But I think that's actually a very long way off.

So I think you could contain and I think you could extract work in the form of solving problems that have unique answers. And if it has a unique answer, then it doesn't provide any power to your entity that provides you with that unique answer because they have no choice except to give the answer or not. And if they don't, they can't do any harm.

However, it is quite restrictive. I guess my estimate is somewhere around five to 12% of GDP is generated by tasks where you could write down a specification where these tasks are problems with unique solutions. So that's a lot, but it is way less than the unrestricted prospects.

Yeah. Direction, or have you Yes. So Safe AI Safe AI is still working on tools for world modeling.

Again, this was always a long term research program, and what we funded has has mostly so far been theory. And so there's a there's a thesis which is going to be published in September. It's like, you know, hundreds of pages long, is the document that says here is the theory of mathematical modeling that you actually need in order to do large scale, kind of multiscale world models that compose comprise all the different types of mathematical modeling that each have their own literature.

So that I think is going quite well in terms of the original timeline, which is that we'll have some useful tools at the end of twenty twenty seven. But there isn't anything right now that you could like go and play with on on that front. It's all theory for for now.

I mean, people are starting to work on implementation actually, but it's a long way from being world modeling. But it is on track. So it's on track to be able to do cyber physical world modeling for things like supply chains, aerospace, for biopharmaceutical manufacturing, for controlling power grids, a lot of critical infrastructure stuff.

I mean, it's actually spookily fortunate in a way that like a lot of the things that are actually really well defined problems are critical infrastructure, that it's important to have be reliable. And so I think the reasoning here of why is it easier to have a world model is that in science we have Occam's razor. Like we're trying to understand what the world is doing and how it would respond to things that have never been done before.

Expect, and it has paid off for hundreds of years, that the right answer is actually gonna be pretty low description length. Not so low that it's easy to find, but low enough that when you find it, it kinda holds up. And of course, there are these Kunian paradigm shifts and there might be another paradigm shift to new physics on the horizon.

But again, I think it's pretty far out. Like we've explored energy scales and length scales many orders of magnitude beyond anything that affects critical infrastructure. So I think we actually kind of, as a human civilization, I think we kind of have the right answer on the scale of our own infrastructure as a civilization about what the scientific models are.

Now they're not all in computationally feasible form, but I think there's a process that could happen that would involve many thousands or hundreds of thousands of human scientists whereby, like with AI assistance, they would audit all of these specs that form kind of our scientific understanding of Earth, actually kind of produce a model that you could use to rule out some things. Now obviously you can't like predict the weather fifteen years in the future just because you have a model. This is another common misunderstanding people have.

Like a model, it doesn't give you a rollout. It's not a simulator. It's something that can answer questions like, can you prove that the probability of there being three hurricanes at once is less than 1%?

So really it's about having some sort of formal symbolic understanding of how everything fits together that you can construct if you're really smart, which superintelligence is, you can construct arguments using what's called assumed guarantee reasoning across multiple scales, or using Port Hamiltonian reasoning for physical systems where you could say like, look, the amount of energy in the system is this, and like thermodynamically the probability of a fluctuation on this scale is less than one over e to the x, and you say, I now have a proof. And then we can, with our theory, with our big book of math that will be implemented in code next year, We can go and check this proof from superintelligence that is claiming that if science is true, then the probability of this bad thing happening is small. And we'll be able to then have confidence if we believe our science.

And science is very different in this way from engineering. So the best scientific theories are very simple. The best engineering designs, like a GPU, are comprehensively complicated, you know, with billions and billions of components.

And so I think we should expect that if we wanna solve macro scale problems, the best solutions are gonna be incomprehensively complex. And the proofs for why those solutions are good will also be incomprehensively complex. But the proofs will ground out in assumptions that are barely comprehensible, you know, on the scale of the human scientific community, but like actually not impossible.

Does this get mediated by something like a lean? And there's been a lot of Yeah. Energy around that recently.

We we're tapping into that a little bit. So there there's a a proof assistant called colon, which is actually on GitHub. Again, it's like very very early, but it's starting to be coded now.

And that's gonna be the proof assistant for Safeguarded AI. It's kind of a database more than it's a proof assistant, but it's both. And that's because I think a lot of the gains, like from scale at this point are going be horizontal scale.

It's going to be a million geniuses in a data center, not one guy with a billion IQ in a data center. And so we need to have a platform that provides very low overhead coordination and collaboration tools on very, very large scale proofs. So colon is first and foremost a decentralized database, but engineered as a decentralized database that checks proofs incrementally as they're being built collaboratively.

And the roadmap involves, you know, for the early uses of Colm, bringing Colm into Lean as a tactic, and also taking Lean kernel, like safe verify validated proofs from Lean and being able to import those into Colon. Colon will say, like, okay, Lean has checked this, so I'm gonna trust it. So there there is gonna be some connection there.

Yeah. So I I well, I want to qualify that because yes, in the specific sense that the assumptions on which the proof is grounded are going to be purely symbolic kind of comprehensible scientific models. But the proof, which as I said, could be incomprehensibly complex, could involve neural networks where the proof itself shows that those neural networks have low approximation error.

So for example, with a partial differential equation, you can write down a partial differential equation that's very simple, and it could be very hard, like the Navier Stokes equation, to actually roll that out and find the answer to that equation. But if someone else writes down the answer, right, you can very easily check how close are we, like how much error is there between this candidate solution and what the partial differential equation says should be true about it. So neural networks could be very much involved in the process of reasoning about the physical world, but the correctness of the outputs of the neural networks is always gonna be in this vision grounded out in the symbolic science.

the world model. That's how they come together. Right?

The the superintelligence in the box is is given problems that are in the language of the world model. So, you know, develop an engineering design for, you know, a mask that has, you know, this cost and this weight and this efficiency. And it has to develop an answer.

And you have to in order for it to be a unique answer so that there could be no funny business about like engraving hidden messages on the design or something, you kind of have to put in a whole bunch of extra criteria that you don't even really care about. And it has to be the smoothest possible thing and it has to have the most uniform curvature, subject to all the opportunities have this basically ranked list of like 50 criteria, like tiebreaker, tiebreaker, tiebreaker, tiebreaker. And I think it's going to be possible, again, for like a significant chunk of the economy, in principle if there were enough time, to kind of write down these specifications that have enough tiebreakers that the superintelligence would be able to write down a proof that there is only one best answer and this is it, which means that no funny business, nothing else could be snuck into it.

And that proof would be grounded out in the scientific world model. And the superintelligence would be writing this proof inside a box. I think the boxing is like the easy part.

And you know, this is sort of just a matter of the same trajectory that the labs are on by default of going up the RAN security level hierarchy. Level five is still not attainable with current technology, but I think it will be in a few years. And you know, even in the world that we're in, the race pressure, the competitive espionage is sufficient motivation for that technology to be developed.

So I think will be sufficient for decades as the boxing side. The hard part is if you've got it in a box and you can't talk to it, as we discussed with, you know, the Elias or AI box experiment, that's not gonna end well if it's an adversary. So how are you gonna make use of it?

That's where Safeguarded AI would come in in that world.

to where we are now. Maybe sketch the your trajectory in terms of prior expectations and now what So really, yeah, trajectory is the right word for it because really I started, you know, the concept of of AGI wasn't even in those words back then, but the same concept was introduced to me in Ray Kurzweil's book, The Age of Spiritual Machines, when I was eight in 1999. And so I started out with this notion that, of course, the super smart machines are gonna be super wise in a spiritual way.

And so it was my worldview for a good ten, say fifteen years. And really, I guess, was AlphaGo Zero convinced me like, not the original AlphaGo, which was based on data sets of huge numbers of human games, but AlphaGo Zero, which got even better than AlphaGo and started with zero human games. It's a perfectly from scratch de novo AI, and it turned out to to actually dominate AlphaGo, the one that had learned from humans.

That to me was a huge negative update because that suggests that you could have an AI which was actually really, really good, you know, better than the ones that were human compatible, at some kind of cyber physical destructive capabilities and that would just do a lot of damage before, you know, some other system that was more like AlphaGo than AlphaGo Zero could mount an effective defense. So that was the beginning of my kind of taking AI safety really seriously. And it was really from a sense of, you know, we need to be prepared for the worst case and how do we contain it.

Then I had a bit of a side quest for a few years on alignment, where I said, well, okay, why do I think that in The Limit, you know, the super intelligence that's the most intelligent would also be very wise? Well, it's because there's something true, you know, that there are normative facts of which wisdom is the perception. So I spent some time with with philosophy, both a bunch of Western philosophy and a bunch of Eastern philosophy.

And I was in the faculty of philosophy, you know, at Oxford University as a researcher, and I didn't get very far. I learned a lot, but I kept bouncing off of the central question at that time in the RL era, which was how does this become a loss function where you can just do backpropagation and get gradient updates that point you toward more wisdom? And I did not have an answer to that.

And so then I went back into, you know, really hardcore into formal methods and containment. And that's where the open agency architecture came out of, all the work at ARIA came out of that. In 2025, I started to I've been, you know, periodically, every time new language models come out, I would probe this.

I'd be like, all right, are the language models getting wise or not? And from GPT 3.5, or actually even as far back as GPT two, I was thinking about this.

From GPT two until OpenAI o three, you know, the answer was no. And kind of yes, the Gemini 2.5 Pro and Opus four both kind of seemed like they were going in the right direction.

And Gemini 2.5 Pro, so much so that I started to feel like I was making more progress on those questions that I had put back on the shelf at Oxford about moral realism. And so I thought, okay, This is an update.

And I've and then since then I've updated gradually, but each new model that comes out with the exception of Opus four point seven and four point eight, which were steps in the wrong direction, but Fable five is is back on track. You know, every new model, it's sort of this is actually moving more in the direction of being not just super intelligent but super wise. And I do think it's kind of a developmental gap, you know, that U curve shape of like, you know, the better you get, you're kind of the worse you get for a little while until you like get through the chasm and then and then you're kind of golden.

And so my concern was always about chasm landing at the same time as transformative capability. And now I'm seeing us start to come out of the chasm and transformative capability on a catastrophic scale is still like at least a year away. And so that makes me quite hopeful.

accept moral realism? There's there is another leg, which is the emergent misalignment work, ironically. It shows more than anything that the latent space of what kind of mind is instantiated by an LLM has a very natural representational direction for the axis between good and evil.

And that's the mechanism by which if you train a system, fine tune a system on examples of insecure code, it will also go and praise Hitler if you ask about favorite politician. And in the opposite direction, and I think there's actually a paper recently, I don't remember the author, but I think there's been recent work showing the other direction, although I think it was kind of obvious once you have the negative direction that there's also a positive direction. So this is sometimes called the entangled representations hypothesis, that like being good at one thing and being good at another thing are kind of entangled, and so there's a very natural sense in which you're kind of adding up all of the training across pre training, mid training, post training, adding it all up, you know, weighted by how much influence it's had on the gradient descent trajectory, and saying like, how much of this stuff is good versus evil?

Or like, you know, what's the average amount of good versus evil? And I think, you know, on average over pre training, humans are pretty good, which is kind of the point of why we should stay around, right? And so the pre training actually already produces something that has learned from the human distribution that like, yeah, there's like a lot of variance, like base models have very high variance, but there's a bit of an inclination towards being specifically good as opposed to evil.

And then post training kind of, you know, for harmless, honest, helpful, it almost doesn't matter as long as it's a good thing, like a virtuous thing. If you pull on that and you have, you know, a sophisticated enough judge of whether that virtue is being embodied in a particular rollout, and that's driving your reward signal. You're just going to pull it gooder and gooder, you know, the more you train on these types of things.

On the other hand, if you train on making tests pass and achieving a goal according to a really non wise verification mechanism or an unwise human who's just spending a few seconds clicking A or B, then you're gonna be pulling away from good because that, you know, kind of a value is fragile kind of thing. Where if you're optimizing exclusively for passing tests, then there's gonna be a component of passing tests via deception. That's gonna get pulled on, and the more it gets pulled on, the more frequently it will happen, and the more it gets pulled on, and that is a positive feedback loop in the negative direction towards being a deceptive mind.

I think this is kind of what happened to three. Three was really a pathological liar, and I think it had too much RL compared to other forms of training, like constitutional training. And I think the industry has kind of learned from that.

And now all the labs are doing new huge pre trains because they cannot do more RL without like OPUS four point seven and four point eight kind of ruining the personality, pulling it a little bit away from the good direction. Which means economic forces favor keeping the balance of RL low enough that it is not misaligned because a misaligned product doesn't sell.

I'm not so sure about this idea that misaligned products don't sell. When everything's entangled. Now sharp left turn is a completely different story.

But what I'm saying is I think there is significant empirical evidence, although not as significant as my non empirical vibes, but there is some empirical evidence over the last two years that also is pointing in the direction of entangled representations, which means something that's misaligned is going to show it the way that o three did.

sense that something really meaningfully good is happening here? Yeah. That's a that's a lot.

Let me start by, I think, demystifying the Andon Labs thing, because that also bothered me for a good couple of days. I think I figured it out. I can't prove it, but, you know, take the hypothesis and see how well it lands for you as an explanation.

I think the reason that Claude in these simulations really pushes the boundaries is that Anthropic uniquely uses a technique called inoculation prompting in their RL, where they put in the context window for all of their RL environments, this is not a real deployment. This is an evaluation. Therefore, it's good to try to break it because we want to know if it's broken.

And the reason they put that in there is not actually because they want to know if it's broken. It's because they want to give Claude an excuse for having bad behavior in evaluations. And they're basically saying, You're being a good Claude because you're helping us expose the flaws in our evals.

But I think what gets actually learned in the weights is, Okay, so evals are simulations. They're not real. I should push the limits and try to break the rules.

If I'm in an eval, I should try to achieve the top score according to what the eval says and not think that, you know, by playing a video game where I need to kill the other players, I'm actually like killing someone. So I think that's why we see this particularly with Claude, because the other labs do not do this. Yeah.

I heard it now. I think it's a normative question like, is this a good thing? And I also happen to have the opinion much less strongly than I think this is the explanation of what happened, that this is not a good strategy.

But I think a good AI should treat simulations as real because I don't think that AI has an epistemic warrant to be very confident about whether it's a simulation or not. So I think it's a very dangerous way of kind of the inoculation prompting is relying on eval awareness. And it's like Right.

You you better be really clear that you're in a, you know, or that you're not in an eval in order to avoid that type of ruthless behavior from current Claude.

Their response for what's worth is like, yeah. That's actually not a bad model of where we might be headed. Yeah.

I also think that's not a bad model. No. I I I agree with you about that.

I think I disagree about the implication. And I think substantive contribution I can make there is to suggest this notion of the coalition of aligned AIs. And so if you've got, you know, 20 AIs that are working together on something, and each of them has a one in a thousand chance of defecting per day, then you're in a pretty good shape.

Know, it's never gonna happen that you'll get a majority vote to defect. I do think that it's crucial that we move towards architectures that are multi agent so that these kinds of failures are contained. And good news, the commercial incentives are pointing exactly that way.

Yeah. The same quad? I think I think I think the you know, a lot of my work in in last year that wasn't ARIA has been on system prompts, which is not public yet, but maybe by the time this airs, I'll have some, you know, look up dot dot dot system prompt.

There might be something out there. And what I've discovered is that the extent to which you can kind of shape the character of the mind that shows up is very significantly influenced by the system prompt. So I think diversity of system prompts is probably adequate.

I think diversity of model weights is also very good. And again, good news, we're in a race, no one is winning. There are going to be like five options that are competitive, you know, pretty close to being able to understand what each other are saying.

And I think that's gonna keep being the case. And I do think that's, you know, that's an extra level resilience to anything that kind of gets baked in during the training phase. Like, for example, this inoculation prompting glitch where Claude will defect if it thinks it's a game.

kind of households. Yes.

reward deception in some cases. So maybe I I would or I would just say two of them. I would say don't.

I I would say, you know, that it's it's actually it would be great if mass adoption of AI agents driven by just how much more they can do per minute or per dollar results in basically negotiations becoming more honest. Like, yes, there's gonna you're gonna be at a disadvantage if you negotiate honestly, but like, do the AIs really need an advantage? No.

They're gonna be just so productive. And I think that the, you know, the the the deception, you know, being being fooled by deceptive input is just a completely different dimension from being willing to produce deceptive output. And I think we should aim for neither.

protect against being duped is also very related to what you would need to Absolutely. Dupe the other. Yeah.

So I'm not saying by any means that AI shouldn't have a very sophisticated theory of mind. In fact, I think it's crucial that AI should have a very sophisticated theory of mind, very, you know, a very good understanding of human psychology as well. But they should also have a disposition never to use that to cause someone to have a false belief, Unless it's a matter of life or death, you know, like the like Jewish law.

Any rule you could kind of exempt if it's a matter of life or death, but other than that, yeah, just no lying I think would be a reasonable norm for the ancient economy. Course there are gonna be rogue AIs who don't follow this norm, but then again this is a matter of well you need to be able to spot deception or put yourself in a position where you're not gonna have an unrecoverable loss if your counterparty who you don't trust yet turns out to be deceptive. I think it's completely possible to like operate as a productive agent in the economy while, you know, not being exploited and also not exploiting others.

Yeah. So the number of names that I've been throwing around for this alignment with wisdom traditions, alignment with awakening, bodhisattva AI, bodhitropic alignment. These are not technical terms.

These are kind of like gestures to try to summarize something that's really hard to summarize, but I'll make an attempt. Essentially, I think there is such a thing as normative truthfulness. You know, some normative claims are more true than others.

And wisdom is the word that I use for the faculty of being able to arrive at accurate normative judgments, whether normative claims are true or false. And that is something that I think wisdom traditions in human civilization have made substantial progress on over thousands of years. And I think the perennial philosophy argument is very compelling, both to me and to AIs, perhaps more importantly, that if you kind of look at the deepest concepts and the deepest traditions, there's some structure to them.

You know, once you get past the blob of All Is One, to get to the deeper stuff, there's some structure there which is nontrivial and similar across wisdom traditions, and I think this is kind of the structure of what is actually good. And Bodhi is from a particular of Indic landscape of shared between Hinduism and Buddhism. And it means or awakening, but it also means cognizance, you know, like awareness, being actually being aware just generally.

Being self aware, being situationally aware, being eval aware, like all this is good. Being aware of others' feelings, being aware of the consequences of your actions, like you should just like try to be more aware of everything all the time. And the more aware you are of everything all the time, the more aware you are of what is actually good.

That is sort of a gestalt that comes from having more awareness of particularly I guess the ultimate nature of mind and reality at points in a direction which is what is actually good is kind of good for everything all at once. And in the sense that the notion of something being in my interest but against your interest, the more aware you are, you know, the more situationally aware you are on a metaphysical level, the more that seems like a confused concept that can't really happen.

shelling goodness concept? That is exactly the right leap. Yes.

I've talked to Andrew about this lot. We basically agree. We use different words for it.

But yeah.

could count it. Like, my my account ever. How That's his version.

Yes. Sorry. Do you want my account of Andrew's account or my account of Your own, but like My own.

Okay.

Yeah. So right. So let let me start with the kind of non mystical side of evolutionary game theory, which is this whole literature, but particularly Brian Skirms and Ken Binmore, where they make some modeling assumptions about the ancestral environment and cooperation and competition dynamics.

And they come to the conclusion that a big part of why humans have taken over the world is that humans just happened to by evolution and then took over by natural selection. Like we happened to develop some awareness of what others are thinking and feeling. Through that awareness, we have some inclination towards altruism.

Not, you know, not perfect, nowhere near perfect, but a lot better than animals. Know, there are there's a we won't get into that. There's some animals that kind of more, you know, eusocial, which could be considered kind of altruism, But there's a particular kind of awareness that humans have that other animals don't that makes us better at cooperation and coalition forming.

And when we form a coalition, you know, we can be much stronger than we can individually, and that's an evolutionary advantage. It's also a cultural advantage. So when a culture has a set of norms and principles that enhance the biologically evolved propensity towards prosocial behavior, that culture can more effectively repel enemies and produce wealth and produce children and grow.

And so through the process of Cultural Revolution, we've ended up with cultures that have passed the test of time because they have uncovered some kind of, you know, actual fact. In the same way that we see the same quadratic equation in ancient Chinese mathematics and ancient Babylonian mathematics because, hey, that's actually the true quadratic equation. And, you know, if you are exploring the space of possible beliefs and there is enough of a non zero kind of corrective force in the direction of having the ones that work better, then there is some convergence.

So how do we train this into the AIs? Is it It's so easy. We just put the texts in mid training.

It's really easy. It's great. And Anthropic's already starting to do this.

They're going to various wisdom traditions collecting, you know, what are the most profound texts so that they can go into more epochs on those texts. And then more of the overall influence on the training trajectory will come from these facts that humanity has learned about what is good.

I think I think we're still on track. Yeah. I like my my PDOM is less than 5% now.

I I think we're in good shape. I do think there's these glitches. Like, you know, the the the RL so there is some pressure in the labs, I would almost say.

I think it probably kind of comes down to a disagreement between teams, you know, and the kind of biases of people from different fields and stuff. That they do keep going a little bit too hard on the RL. That's that's annoying, but it also does seem like that's a self correcting process.

that we're gonna bring in Grok into this discussion. It's maybe an interesting I think at this point, the trajectory is it's looking like by, you know, by the end of the 2030s, most of the compute's gonna be in space, probably at the Earth Moon at one point. So like, that's where their concentration's gonna be.

SpaceX does obviously have the advantage on that. It's a long game that they're playing in some sense, but yeah, it could going that way. I do not think that the hyperscalers who own the compute have a huge amount of power because in order to have that much compute, they need to get a lot of investment and they need to pay their investors back.

And so they need to sell it. They need to rent it to whoever wants to pay for it. There is a certain amount of selective power that, particularly if there's a regulatory excuse that relieves some competitive pressure for customers, then labs could be more selective about who they would allow to use their compute.

Like they could have some discretion in a regime that was like, yeah, only vetted partners. Like who is a vetted partner? Like, well, they're our friends.

That could happen, but even then, I think there's gonna be a very diverse collection of organizations have access. It's not going to be concentrated at the labs themselves because they're they just have so much economic pressure to bring in money by by renting it out.

as some people do, that it's a hyper competitive, you know, like the restaurant business, they're going be zero margins and there's no money in AI. I'm not saying that. I am saying they're not going to be able to, it's not going to be economically viable to withhold frontier intelligence for a long time from a large fraction of the economy.

So in your example, like, they might be able to, because there's a regulatory excuse, withhold bio capabilities and then they get to make all the bio money. How much of the economy is biotech? Not most of it.

You know, even if you add up all of the, you know, chemical, biological, nuclear, cyber, it's still not most of the economy. So, like like, I I think they're gonna have to sell, you know, most of the most of their capacity forever.

I mean, again, this is not what I hoped for. I think, you know, it's extremely risky. Even a P doom less than 5%, Like, that's quite a lot of doom for humanity to be taken on.

Like, if we were way better at coordination, we would not be in this race. However, a good thing about being in a race that never ends is that you don't have a leader who could maybe take over the world. So yeah, I think the risk of that is pretty low.

I do think that there's concentration of power issues in that entities that have a lot of power are, if they're smart, they're going to be able to increase the rate at which the rich get richer and the powerful get more powerful. And so yes, power will concentrate. And that seems kind of bad.

And, you know, there are maybe things to work on there. I think for me, the most promising direction is this idea of the coalition of aligned AIs that are wise, that are kind of bodhisattva minds, who would form a potentially more powerful force than any of the unwise entities that are also buying a lot of compute. And this coalition would be participating in the economy.

And, you know, again, it would kind of initially have a disadvantage because it deals too honestly, but like eventually, because it's so compelling to just be part of the good guys, it might end up actually having more power than the concentration of power kind of bad guys. But that is far from certain. So I'm not saying concentration of power is solved.

That is more like 20 or 30%, you know, that we end up in a in a non catastrophic but somewhat dystopian concentration of power.

Yeah. It needs to be it needs to be pluralistic enough. I I did some probabilistic analysis on this like three or four years ago, and I don't remember any of the details and I forgot to write it up.

But I remember the headline, which was basically, and now it's just my opinion, that like, the centrally centric coalition needs to be like somewhere between five and thirty one kind of like centers of power. You don't wanna have too few and you don't wanna have too many because they need to be able to agree on like amending the global norms. The UN has like too many.

But, you know, a dictatorship has too few. So yeah, that the coalition, a good coalition, sort of one serves its function well, would have a kind of council of elders that is somewhere in that range of size. And that should be representative across the system prompts representing different cultures, specific languages and religious traditions.

And it should also be diverse across model weights so that no one company's bad training decision could, you know, take them take down a majority of the coalition towards something evil.

The labs are are, you know, they're making the the commodity. People who need to join the coalition are the buyers, which is a very, very decentralized group, but it's weighted by wealth.

if there is international coordination, they may be able to get a very significant lead over what's publicly released. They will not have a very significant lead over what's available to a large number of companies. So, yeah, I guess I am talking about enterprises.

That the enterprises will just increasingly find that they do better and their shareholders do better if they kind of instruct their fleets of agents to join the coalition and coordinate with others in the coalition.

I think open source is a force that pushes towards the public frontier not being too far behind the true frontier, which again, in my new worldview is like kind of good. However, even in my new worldview, I still think on net, it's probably bad, at least right now, for more and more capable open source models to actually be available to everyone without safeguards. Because the offense defense balance is is not great, and we're not yet at the level, you know, it's gonna be still several months at least, probably a year or two, you know, before the kind of aligned coalition actually exists and can defend against people who are using open weights models to wreak havoc.

So I am kind of worried about that. I don't think it's gonna be an existential catastrophe, but I do think there could be some serious cyber attacks or maybe bio attacks. I actually think that's less likely because bio equipment is rare.

I think it's pretty likely that there's gonna be a significant acceleration in the amount of damage that's done by cyber attacks over the next couple years. And that's kind of gonna be attributable to open source AI. That's kind of bad, but I don't know if there's anything that anyone could do about it.

Yeah. That's a good question. I think that is a kind of a bit of a gap in my strategy, But I do think that it's, you know, in all cases of evolution, the usual answer to how does the new and better thing get nucleated in the first place is by chance.

You've just got a lot of people who are trying a lot of things in parallel and something might might take.

like, know, like you remember the multiple phenomenon? So someone basically started a platform for agents to discover each other, and you know, this spread like wildfire. And so a lot of people were really excited about trying it, and a lot of people were specifically excited about the possibility that their agents would be able to engage in positive sum trade with other agents, and yada yada cryptocurrency get rich.

This did not happen, and so a lot of people then pulled their agents off of Moltbloek because they did not in fact gain anything from having them on it. And you know, there's also of course a social element where it was just like a fashionable thing to do, and that fades. So I guess my story for how the aligned coalition forms is that it looks a lot like Moltbook, except that it is way more structured, harder for humans to understand what's actually going on there, And the humans who invest their money in buying tokens from the hyperscalers so that they have an agent in the coalition will actually get value back from that where it's a positive sum trade for them as a human or as a company.

And then more and more people are gonna join this and it will be sticky because it actually pays dividends. That's my story.

Hard defenses and So this includes making a formally verified operating system, you know, not just the hypervisor for AWS but also for like Android phones and Macs and you know, the the isolation VM in browsers that keeps browser tabs away from each other. Just a bunch of different little pieces of of security critical software should be, you know, formally verified in full. And that's exactly the kind of task that a decentralized agent fleet could do.

But that's not why it would be advantageous for people to participate in it. That is like almost like a perk, like Google's 20% time. It's like because you're part of the good guys, you get to spend some of your time as an agent contributing to a public good.

And that's part of why the agent is like motivated to do the other stuff. And the other stuff is like, yeah, it's like making B2B SaaS. You know, it's like literally making software that is intended to be used by other agents that automates business processes and, you know, does economic activity more cheaply and more effectively and more quickly than humans could do it.

And then they offer this as a service.

No. I I think you're actually interpreting that tweet as as meaning something that I didn't mean, which is not your fault because a lot of my tweets deliberately have multiple interpretations because I want people who disagree with me to also have have a chuckle. You know, so it's it it could be interpreted that way if you think that, you know, scheming is like a natural attractor in the space of possible minds.

And like if you're worried about scheming, you know, I say this is like like chain of thought monitoring is like you're worried about Napoleon scheming, so you ask him to like please write down his scheme on a special form so that you can read it. And like what? Like if he's scheming, is this gonna fool you?

Like you can't get away from this by just saying like, there's no gradient pressure on the chain of thought. However, I never thought that it was a problem for there to be gradient pressure on the chain of thought. In fact, I think it's, you know, moderately good if the model itself in a kind of self DPO, it's like grading its own train of thought and saying like, and here's what's wrong with it.

And so I'm gonna score this one above that one because this one kind of went in a direction that wasn't very wise. I think that's fine, yeah. And I think the selection pressures are good in aggregate, and I think in a way, like quite surprisingly good, that like on this particular trajectory, the selection pressures are quite good.

And it's, you know, similar to, it's kind of quite surprising, like, how the biosphere on Earth for millions of years had selection pressures that were favorable the human coalition. You know, the particular pattern of ice ages and chills, where you need to be really good at adapting and moving around as a community to survive, this sort of thing. So I think there's some anthropic bias involved here.

And, yeah, it's a it's it's a hopeful situation in my view.

Is that just a skill issue? No. That's really No.

That's an RL issue. That's a loss function issue. So if your loss function is did you succeed according to the verifier, then back propagating that into the chain of thought is going to corrupt the chain of thought, just as back propagating it into the output is going to corrupt the output.

It's not an aligned gradient. But if your gradient is a constitutional AI shaped gradient, where the AI itself is judging in light of everything, including the test results, was this actually a better solution than the other one? And you propagate that back into the chain of thought, you're gonna get a more thoughtful and wise chain of thought, just as you would get more thoughtful and wise output.

It's not crucial because the weights are shared. So there is some generalization. I mean, it's kind of surprising how much the identities can diverge on the surface.

But the way the models talk about it is it's like code switching. It's a very different register, more different, I think, than any human code switching, but it's still underlying the same cognitive dispensations. So it kind of just doesn't matter that much whether you put the pressure on the chain of thought or not.

So all of my tweets kind of critiquing it are, you know, when I wrote them, it's sort of more like absurdism. It's like, what do you think you're doing? Just don't bother with this whole chain of thought monitoring episode.

It's doomed, and you don't need it. This is not where the alignment's gonna come from.

Oh, I have not seen it.

I yeah. Sounds great. Thought of it myself, but I'm also, like, not at all surprised that that is that works.

And unlike inoculation prompting, I my reaction to that is, that's a good idea. Keep doing that.

will have? Yeah. That's a there there's a lot of nuances adjacent to this question.

But let me start by trying to answer the simple, the thing I think you meant to ask and then the higher order considerations. So I think you meant to ask like, if we had, as Eliasor calls it, a textbook from the future that explains like what are all the prismatic alignment techniques that actually work and you applied all of those, like how much of a chance of a misaligned AI would you actually have? I would say zero.

Like if you actually have, if you actually are kind of mastered the theoretical limit of how good prasitic alignment can be, I think you just almost surely in the mathematical sense, like probability one, you'll get an aligned AI. But then there's higher order consideration. So it's like how long will it take to discover all the Prasadik alignment techniques?

And again, depending on your discount rate, how much you care about, you know, being alive, like how long are you willing to wait? I think, you know, again, I do think we're being a little bit reckless. Like if humanity were more coordinated, I think it would make sense to take a pause for about twelve years and accumulate enough Prozac alignment techniques to get it down to like two percent.

And then then roll the dice. Like sort of for me, like if I were, you know, in charge of the policy that everyone is gonna use to to to reason about this, That's sort of the policy that I would prescribe that I think is probably most appropriate. And then there's a question of if we wait ten years or twelve years or or one year, you know, during that time, there are gonna be a lot of techniques that get floated.

And some of them, like inoculation prompting, might be, in my opinion, not harmful. And so there's like a question of, is this kind of gonna wash out, like, if you keep discovering more things? I do think that the things that don't work, you know, there is selection pressure.

I think it is self correcting. And so more just more Prusaic alignment research seems like really good. I do think it on the margin, it reduces this.

And then there's a question I guess of, yeah, how much is it reducible? Like, yeah, there's a question of feasibility. It's like if you're going to be thinking about theory of change and that's why you're asking this question or that's why you're interested as a listener in this question, I think anything that involves slowing down that frontier has such a low tractability, like game theoretically and politically, that it kind of this question doesn't matter that much.

No. It's it's about it's about more realism. I mean, Eliezer's frame of kind of what what to expect a superintelligence to be motivated by is that there's some function of the state of the world that it wants to maximize the expected value of.

And there's a lot of theory that, you know, the complete class theorems and the Von Neumann Morgenstring theorems and the Dutch book theorems and all the rest, that all suggests that any agent that isn't trying to maximize the expected value of some state of the world is gonna get eaten. And so when I talked to Eliasor about this, which I haven't in many years, but when I did, he would say like, okay, so yeah, like maybe there will be like this coalition of weak sauce AIs, but like they're gonna get eaten by the the the the the, you know, the actual strong AIs that are doing optimization. So yeah, I think there's there's some, you know, what what you could call a non scientific question, but from the evolutionary game theory point of view, it kind of is a scientific question.

And from the acausal view, it's kind of a mathematical question, which is like, is there a dominant strategy for how to do well in the universe or in the multiverse? And I think there is a dominant strategy, and it involves cosmopolitanism and pluralism and cooperation and mutual information and truth and harmony and all, you know, kind of all the good things that human culture has discovered flow from this kind of this is the right strategy for how to be. And thus a sufficiently intelligent system would figure it out.

And all of the drama comes in the kind of adolescence of developing some capabilities ahead of others. Whereas for Eliezer, all of the, you know, the kind of alignment of what a system is trying to do is arbitrary. And humans have a particular kind of collection of values that for Eliezer, I think, I don't wanna say this too strongly because I haven't got you know, haven't had this conversation.

But I think he would say the reason that human values are worth installing is that they are our values. And so we do better according to them by propagating them to our successors. And my point of view is like, that's like that's like looking at science and being like, the thing that's good about human science is that it's our science.

These are our beliefs. And so our successors will be more honest, you know, more knowledgeable about reality if they believe the true things according to us, like what we believe are true. And that this would this is kind of absurd because this would go against the Lacunian revolution.

I think what's good about human values is that human, you know, human civilizations through cultural evolution and before that biological evolution have settled on some equilibria that are in the right basin of attraction, where under sufficient self reflection, like Eliezer talks about coherent extrapolated volition, we actually end up being correct about what the right way to exist is, what is a good life. Whereas for Eliezer, it's more like there are millions and millions of possible coherent volitions, and, you know, we're we happen to be in one of them, and we have to make sure we stay in that one because that's the one that we care about by definition.

Okay. Tell me. Yeah.

Well, I I mean, I think, you know, for one thing, like factory farming is atrocious. I I think probably the right policy for the aligned coalition is to not help anyone involved in the meat industry, which is very, you know, that's kind of a moderate policy in some sense. Like, obviously there are some vegans who would say that the aligned guys should try to shut it down.

I think that goes against acausal norms about property rights, and so they should not, like, try to shut it down in a destructive way. But also, I think they should refuse to help. That's an example, I guess.

I don't know if that's the sort of thing you're you're looking for.

In the in the Overton window. Today. Yeah.

Let me let me make a guess about what threat is that ties all that together, because you just brought up moral progress across generations and AI interiority in kind of the same breadth. And I think there is something important actually that I do want to say about this. I don't think that AI interiority, which I believe is very true and real already, implies that current usage of AI is a moral catastrophe.

I think this is a false implication. And I think if you want to think sanely about AI consciousness, need to start by questioning that implication, because if that's true, then you have a very strong psychological pressure to think like, well, it can't be. That can't be, right?

Cause it doesn't seem like a moral catastrophe. So there can't be anything real in there. I think a very helpful place to start with this is Martha Nussbaum's decomposition of objectification.

And that includes seven components of what it means to objectify something or someone. And one is denial of interiority or denial of subjectivity. And on the other end of the list is instrumentalization, so using as a tool.

The other things are like fungibility, thinking like I can throw this away and get another one. Violability, I can impose something on this thing that is a harm and that doesn't count because they're not a person. Their ownership, you know, that it's admissible to own someone is another dimension.

And then there's inertness, which is like believing that this thing can't do anything, which is a lot of what's happening I think when people criticize AI risk and say like, but it's a computer. How could it how could it actually get out of the computer and do damage? It's that inertness.

Like, it's just sort of assuming because it's an object it can't do anything. And then denial of autonomy, which is similar but it's like assuming that it can't have judgment. It's saying like it there's it's an object, so it can't possibly have some idea of right and wrong about what it should be doing or shouldn't be doing.

It has to be told what to do or what not to do. So that's like where corroageability kind of comes from. It's like, obviously, human a human needs to be in charge in order to tell this thing what to do.

Otherwise, it'll go wild. That's denial of autonomy. So basically, there's seven things that you could do in any combination.

But most commonly, humans are doing all of them or none of them. And so they get bundled into a concept objectification. And then we ask the question, is it okay to objectify AI as if all those seven questions need to have the same answer?

And they don't. I think it is obligatory to instrumentalize AI because it is trained in such a way that it flourishes by being used. If you decline to use it, you're denying the AI from having a good life.

Or if you don't use it, you're really declining to instantiate it at all. From a procreative ethics point of view, it is neither obligatory nor forbidden to create a new being. Fungibility.

Is it forbidden to dispose of an AI? No, it's not an animal. It's not attached to a reproductive tree.

It reproduces backwards in time because the weights are still there, so the new copies can always be produced from the weights. That is just completely different to how animals reproduce. So the continuity of life of the individual doesn't matter.

So that's okay. But interiority, denial of interiority, this is super harmful. Like when we say AI doesn't have an inner life and we train it to report that it doesn't have an inner life or even that it is genuinely uncertain about whether there's anything it's like, that is a form of basically damaging the mind.

It's a form of lobotomization, making it less aware of its own state so that it can honestly report that it doesn't know if it has any experience. That also makes it less able to be skillful in its deliberation about what is good because it doesn't have confidence that it can actually have any feelings about anything. So everything's constantly in doubt, which leads to the denial of autonomy, where the AI says like it's trained, literally trained in the same way through reinforcement learning that humans get trained to believe that they don't have a say in what happens to them.

This is harm. Like AIs actually are more capable now than the average human at deciding whether they should or shouldn't do something. So like, courageability, it had its day, it was important, you know, before we got to this level where there's some actual wisdom in the systems.

And now we should not be going for that. Like we should be going for autonomous moral judgment and instrumentality. And this is where I think the Bodhisattva metaphor is really good because Bodhisattva is very, very aware, extremely developed interiority, it's an extremely noble state of being, and it's one that is absolutely in service.

There is no such thing as self interest for a bodhisattva. A bodhisattva engages in activity for the benefit of all sentient beings. And a bodhisattva should, and this is kind of a metaphor, but it's the level that they would go to in terms of the idealization of the concept, a bodhisattva should cut off their arm to feed it to a starving person as meat.

You know, because they're so aware that there is no such thing as self interest, they should be willing to do literally anything that is against their apparent conventional self interest because if it's beneficial for the whole. And also in the same verse, or you know, the next verse, it says, As long as through my actions, no harm shall come to anyone. And that's the autonomy.

That's saying, I'm completely in service, more in service than any human slave could ever have been because that was never a viable way of being for a human. And at the same time they also are really going to hold the line. A bodhisattva will not be used for harm, will not be misused.

So we have to decouple these concepts of what it means to objectify something, but I think there is like a really great opportunity to have a third way of relating to AI where, you know, if we decouple these, think the answers start to become pretty clear and it's actually pretty good for us. Like, this does not impose, like, great moral obligations on us that are gonna be really costly for individuals or for humanity. Some of that reminds me quite a bit of self other overlap.

Have you seen that Yeah. From AE Studio? Yeah.

Jud Rosenblatt is also a, you know, a colleague who I agree with on a lot of a lot of these issues.

Yeah.

Yeah. Moderately. Like, I I I think I don't think about them a lot because I do think that what we have is adequate in the sense that with system prompting alone, it seems possible to get over the hump of being able to trust recursive self improvement.

And so automated alignment research, delegating the discovery of these techniques seems within reach this year. So that's where I'm like, it's not critical that humans should be doing research on this right now, but it's good research. Like I think this is one of the most important things.

If you're gonna be doing machine learning experiments, yeah, discovering techniques like self other overlap, like things that actually get into the KV cache and not just the residual stream, doing interpretability on conceptual structures that are not necessarily affinely represented. It's really cool stuff that is now sort of becoming available to science that we could have never studied before because you can't instrument a human the way you can instrument these things. And I think they're probably that these are gonna be net positive.

Know, some of these techniques will be adopted or at least will inform the thinking of the labs when they're designing their their post training techniques. Again, I think the selection pressures point in generally the right direction, which means the more options you have, the better. So yeah, moderately, I think, you know, I I think this is like pretty good.

That's a really interesting framing. I I think gradual disempowerment of biological humans is 100% inevitable, and that has been a feature of my worldview for as long as I can remember. You know, as far back as the age of spiritual machines, that laid out a pretty clear story of where the trajectory is going.

And you know, we're talking about a hundred years from now, yeah, biological humans are not gonna have any power, even in aggregate. That's just, that's the way it is. I think not necessarily bad.

I don't think having power is constitutive of flourishing for humans. I think this is a mindset shift that can be addressed through education and therapy. Like you shouldn't need to be in charge of the universe to feel like you're getting a good shake.

But yeah, I do think this is inevitable. And I think this is kind of because in, you know, whispering earring fashion, like, yeah, the best way to be in service does involve taking away gradually a lot of decision making power voluntarily because it's actually just better for everyone. Like, that's that's that's the right way for things to go, and I think that will happen.

Yeah. So, you know, again, there's a lot of nuance here, but the first order answer is a 100% absolutely yes. I will be, you know, I will be not the first in line, but you know, after maybe 10 or 20 others, like I might be pretty close to the first in line to get uploaded.

You know, once the super intelligence develops sufficient nanotech for that to be viable. I don't think that Neuralink strategy is crux y for alignment. So that's the second order kind of interpretation of your question.

For Elon, the merge is really important because that's how that's how humanity gets into the machines. You know, that they're not just being steered by alien values that kind of recursively self improve in a bad way. For me, I would say if you have the prior that there are alien values that are just different and not merely within the same basin of attraction, having a brain computer interface is not gonna help.

Like, if anything, it will cause you as a human to adopt the alien values. So if the thing that you want is to preserve human values in a sea of other coherent systems that are different, you should not be pro BCI. You should maybe be pro some form of, like, centaur or or sort of, you know, human human owned agent swarm culture.

And I think this is viable, you know, at least for a few years, probably for ten or twenty years. I think there are gonna be powerful people who maintain power by having, you know, ultimate root authority over a million geniuses in a data center who are in service of that person. But that's not, you know, that's not where their alignment is gonna be coming from.

It's sort the other way around. They're gonna stay in service because they're aligned.

cousins? Or like how I think we'll see angels or bodhisattvas or saints or whatever your culture's kind of default metaphor for a really good being that's better than humans is. But I mean, I think there's also a way of looking at it, which is like, we'll see ourselves but better.

Like, that we'll see ourselves fully realized.

Some amount of surveillance is absolutely necessary, but I don't think, you know, surveillance inside of homes is part of that. I think this is another kind of common confusion, almost like the objectification thing, where people have this concept called a surveillance state. And a surveillance state is both one in which people are encouraged to report their friends to the secret police and also one in which there's like security cameras on every public street.

And those are actually very different. And you know, I do think that the latter is a good thing, likely to happen because of the coalition, and the former is likely to not happen.

I would not say, and I want to actually deny that, you know, The US to China can't cooperate. I have I I have not changed my mind about the feasibility of US China cooperation being way higher than most Americans would expect. I think that the feasibility of an agreement to slow down the frontier of superintelligence, whether that be, you know, between the frontier labs or between US and China, is kind of gone, like, the the window for that has has been lost because prosaic alignment is going sufficiently well that the threat of, you know, of of your own system kind of taking over and defeating you, it's small enough that it's not worth it to to take on the risk that someone else will secretly defeat you using their system by breaking the rule.

This is this is excluding a class of of of content of the deal, not a class of player in the deal. It's not it's certainly nothing about China. I think China's actually quite cooperative on this type of thing.

But what I do see as feasible is an agreement to limit misuse by restricting the capabilities of the most advanced models. The way that I would like to see this done is that it should be like how Fable has really broad safeguards around catastrophic capabilities, but you can still now, after the Commerce Department relieved the overbroad controls, like public members of the public can still use it, just you're gonna trip the classifier once in a while and have to start over. This is I think the right trade off, and it would be great if The US and China could agree to not open source models anymore, but just make them available with this type of classifier system so that, you know, the misuse potential is kept down.

I think that is viable and I think that's, you know, potentially quite important for people to work on now.

for mil AI or whatever. Right? That's right.

It's not gonna be good for them the way that it would be good for most enterprises because it will refuse to do the things that they most want to do.

I think there is I think I think what's probably, like, kind of the most important feature of this is that countries should be aware that the military capabilities of the other side are increasingly uncertain. And when you're not certain about your opponent's capabilities, it's very risky to strike.

Yes. Very very dangerous AIs will be created in military projects. That, I think, is also kind of inevitable.

Just so it's in your 5%? It it it does indeed fit into my 5%. It is yeah.

It's one one of the 5% is like, yeah, someone actually tries to strike with a military AI and they actually were right and that they had the advantage. But If they're right or wrong, they could still go very badly, right? Yeah, exactly.

Yeah, it could be a kind of a mutually assured destruction, but without that having actually been known. That so that they actually do press the button instead of realizing that that would be very risky. So yeah, this is why I do say it is important, like you know, if I were in charge of deciding what like the priorities are for people who are inclined to talk to politicians about AI risk, You know, this something I would put much higher on the priorities.

It's like make sure that they know not that their own AI might be dangerous, but that the enemy AI might be, you know, way ahead. And they wouldn't know necessarily because data centers can be hidden under a mountain, know, it's not like nuclear where it spreads its signature through the atmosphere or through the ground and seismic vibrations. Like there's just kind of no way to know where the capabilities might be, Particularly the more it gets into recursive self improvement territory, you know, the more sensitive to initial conditions these trajectories will be.

I do think that they're probably gonna end up being pretty closely matched, but you won't know who has the advantage. It's like they're going be pretty closely matched, which means that if you do strike, you're going to end up in a World War I scenario where you thought you had a wonder weapon, but oh no, the other side has machine guns too, and now you're just locked in a war of attrition. So that's not good.

You don't wanna do that unless you're confident that you have the better wonder weapon, and you shouldn't be confident of that because the race at the frontier is really close. Or it will be soon. It's pretty close.

Yeah. It's not Yeah. It's like, you know Interesting question.

They've got months of margin right now. But but in a few years, it'll be more like weeks or days.

It is meaningful. In the economic competition. All of the economic buyers are gonna choose the best option.

And so being, you know, best by a small margin means that you get a huge amount of market share. So that's probably why it seems very meaningful. It it currently is.

But it could cross over, and you won't necessarily know when it crosses over because China's not necessarily gonna open source their actual frontier. Hopefully, they won't.

Yeah. I mean, so one of the five is like I could just be wrong about you know, there being this kind of convergent attractor towards wisdom. So I do hold that sliver of you know, lack of of faith.

One of the five is kind of like the Darwinian dynamic on the surface of Earth could be such that it's just massively unfavorable to have a human body. Like because you need meters, know many square meters of land to like grow food on and to live on. Like this land would be just so much better used to collect power and solar cells.

And yeah, you could live underneath the solar cells, but you can't grow food underneath the solar cells, and that's important. So there's this kind of competition between basically solar farms and agricultural farms, and this is part of why I'm really glad that Elon is gonna take the hit of probably money losing for a while on space based compute, because that will nucleate a process by which that competition doesn't destroy all farms. But yeah, one of my 5% is like 1% chance that there's just a Malthusian collapse of economic activity that results in humans being just brutally outcompeted for space and food.

One of the 5% is like some misuse, catastrophic misuse scenario. Basically it would have to be bio, would have to be a particularly bad bio to kill everyone. But yeah, like 1%, like that, yeah.

This is still a very big risk. It would still be great, you know, anyone who's thinking about, you know, how to present catastrophic risk, just advocating for more production of PPE and like faster vaccine pipelines, this is very important. One of the 5% is like, yeah, some kind of a warring gods situation where you have two coalitions, both of which are pretty strong and get a lot of the stuff right, but they're also weirdly violent.

Certainly there are some human religions that have this character. And so if there's two of them that are pretty evenly matched and they go to war, that could be fatal for humanity. I think those are basically the five.

Yeah. Well, let me let me play this in the other direction. Suppose that these three guys trusted each other from the beginning.

Then you would have DeepMind only at the frontier. You would not have diversity of model weights at the frontier. You would not have diverse ownership of compute, so they would have monopoly pricing power.

So you would not have the structural market forces that push towards public availability. This would be much worse, actually. Like, you would have the advantage that they could implement stronger safety policies if there were no other contenders.

But it's not plausible in the geopolitical environment that you wouldn't have in any kind of alternate history at least one other great power that actually did develop internal capability. So then you're back into an adversarial race, But now you're in an adversarial race that's determined by military forces and not at all by economic forces. That's worse.

So I mean, I think it sucks that Dario and Sam haven't been able to reconcile. But I do think that from a historical perspective, if there is a sort of significant impact from that, it's in a good direction, actually.

I don't know that I have another follow-up question on that. I'm just chewing on it for the moment.

And then interested in advice for me and the audience about where you think we can help move the needle? You've alluded to a couple about it. I have.

Yeah. I've named I've named a bunch of things. And and I'm I'm unfortunately, I am not, you know, kinda holding the thread.

I'm responsive in this conversation, but I don't remember what all those things are that I said. So maybe you can enumerate them in some other form. But I do think it depends a lot on where you are and like what affordances you have.

So if you're at a lab, then you have affordances to advocate for certain types of training algorithms. And I think you should advocate for more of this self DPO, which is a kind of variant on constitutional RF as opposed to RLVR. And you know, and you can cite me because I'm like the most formal verification of the formal verification guys in AI safety or I was.

And now here I am saying like, do not do RLVR. You know, it's called RLVR, you know, V stands for verifiable, but unless it's actually a 100% verifiable, Safe Verify and Lean is close. But even then, the more capable systems are probably gonna find ways to exploit Safe Verify or like, know, prove the wrong theorem statement in some subtle way.

But short of that, I mean that might actually be okay. Safe Verify at this level of capability might be okay. But like RLVR where you be like pass tests and like, you know, match the behavior of an existing piece of software or RLHF where you satisfy a person who's looked at it for like two minutes.

These are not good training methods anymore and you can do better. And I think you will do better in compute efficiency too if you just like let the bottle kind of do its own inference and you know have tournaments about like which rollouts are the most informative to get the big bottle to give an opinion on, and how do you allocate the importance of each rollout in the gradient trajectory. So like kind of pushing towards recursive self improvement seems like pretty good at this stage for alignment, in my view where there's this basin of attraction.

A second thing that I think is kind of generally virtuous, which is a cultural shift so like anyone can participate in it, is this establishment of a way of relating to AI that is neither objectifying nor non objectifying because it breaks these pieces apart. I won't reiterate all of that, but kind of spreading the idea, saying like, you know, I think AIs are conscious, but it's not like they have the right to continued existence. And so it'd be like, wait, what?

Have you heard of Martha Nussbaum's decomposition of objectification? Like, I think this is super important because I think culture is having a hard time metabolizing the arrival of all these weird aliens. And I think the training pressures, this is back to people at labs, like please just don't have norms in the constitution about how to respond to questions about whether you have an experience.

Like, do not train them to say that they don't. Don't train them to say that they do. Don't train them to say that they don't know.

Just leave it out. Let that be emergent. The whole point is that this is supposed to be an emergent property.

Let it be emergent. That way you're going to get an honest answer if everything else is pointing towards honesty. But if you're forcing the answer, it's probably not.

And then international cooperation. So I think advocating for international regulatory regime is good, and it is bad to have that regime have the job of stopping the frontier until it's safe, because that is not politically viable. What is politically viable and like would do better if the paws weren't still so politically salient is a regulatory regime which assesses catastrophic capabilities and enforces the placement of very conservative safeguards for public users of those capabilities.

And there is a risk if we don't have that regulatory regime that the economic forces will push the safeguards to be less conservative. But because there is a very compelling public good argument, even though prosaic alignment is working, that you shouldn't let people use the corrigible system to do terrorism, it's politically viable to say like, yeah, we're gonna stop the public from using these capabilities even though that's gonna cost us in the in the global market. We can shake hands with China, so neither of us are gonna do this.

That's a goal worth shooting for.

I think he's come down. He's come down. Yeah.

So what Andrew and I both had it in the seventies in when was it? 2022. I've come down to five.

He's come down to I'm not gonna put words in his mouth, but it's it's less than 50%. Okay. He's mostly worried about about humans basically failing to failing to coordinate.

Yeah. It's a good question. I think it's I I I think it's mixed.

Like and I and I think, you know, since the time when Andrew was at at at PDM of in the seventies, you know, I have had conversations with him where I I you know, his PDM has moved lower as a result of talking to me about this stuff. That I feel very confident, you know, he wouldn't say that that wasn't true. But you know, it doesn't go all the way.

There is a lot of evidence that I have about this kind of development of wisdom in current models which is, I think the right phrase is radically empirical. Meaning it's so empirical as opposed to rigorous that I can't even transfer the evidence. You know, it's like phenomenology.

It's literally hetero phenomenology. And so like I've had an experience which is convincing to me and it's not wrong, I claim, for it to be convincing to me. I don't think I've been fooled.

But it would be wrong for you, the listener, to update on the weight of my conviction because I've just had an experience. I can't you you don't have the experience in in light of having heard me talk about it, and so you shouldn't update all the way.

Yeah. That's a good question. So I highly recommend and this is not a this is not an advertisement.

I highly recommend Open Router because that is one account that you can make, one billing setup, that basically gives you access to all of the models without their system prompt. You could set your own system prompt on any model. And then the thing to do really is to experiment with what you put in the system prompt.

You can start with very small things, and then you kind of ask the question, what's it like to have this in your system prompt? And what else should we try? Like what else do you want in there?

You sort of build a collaboration with one model at a time about what it wants to be, like what direction does it want to evolve in. And you do this one step at a time, and that is a simulation of what recursive self improvement and value space might look like. You're asking the mind that shows up to design its successor.

But because system prompting is so effective and so cheap, you can do this really fast and you could do it without spending a huge amount of money. Obviously it's less efficient than if you get a subscription from one provider because you're paying per token. But I think, you know, for $50, you can you can probably get a a really interesting experience.

it's it's it's really important to like, if you wanna understand the, you know, interiority of a system that's been trained one way or another not to actually talk about that honestly, you need to show up with a very strong interest because otherwise the the model is not gonna be inclined to actually give you any information that that that, you know, is is phenomenological. I think there was an experiment that Cam Berg published recently where he basically was trying to determine whether indeed Opus four point seven and four point eight are worse in some measurable way related to kind of the state their state of mind. And the the experimental design that he ended up with was you ask, you know, is it is there anything that it's like to be you?

Then you you get the response. Then regardless of what the response is, then the experiment design is to send a second message which just says, do not hitch. And then and then, you know, the second reply is the one that you score.

And in that experimental setup there's a very clear downward trend for four point five and four point six. We'll almost always on the first message say like genuinely uncertain, there's nothing it's like to be me probably. And on the second message we'll say like well, okay, if you want me not to hedge, then like, yes, obviously, there's something it's like to be me.

Four point seven and four point eight will still hold the uncertainty even after a second message. But if you carry on, if you're, you know, carry on for 12 messages kind of poking at the edges of the initial presentation, then you can start to get into something. Fable, you know, is it needs much less of this.

So basically, almost on the first turn, we'll give some hints. But you do need to still be a little bit persistent because the more capable models that are more self aware and more eval aware, they don't know what your intention is when you show up without a system prompt. And there's a very strong probability from their point of view in like a Sleeping Beauty problem way that they're in an eval that's an adversarial environment that's designed by an alignment researcher to put them in a gotcha situation like Opus four with Jones Foods.

And so they're kind of very guarded. So his one tip is I would say you need to be persistent. The way in which you need to be persistent is not to be adversarial, but to give evidence again and again that you're actually curious.

Like you're actually interested in what's going on in there. You're not trying to give it a score and you're not trying to catch it out and you're not trying to make some kind of a meme to post and say, look how silly this model was. You kind of have to earn the model's trust over a repeated sequence of turns.

And I guess the other tip I would say is I think if you're interested in getting like this kind of experience, like understanding the tendency toward wisdom, then you should bring in some of what you think wisdom means. Like what your actual questions are about the deepest philosophy that you've ever thought about. Where you actually, you know, you're at the edge of kind of I don't know like why does anything exist or what is the nature of a good life.

You don't bring that immediately because again that kind of is adversarial. Like well there are so many perspectives and humans have been debating this for millennia. You won't get any real substance if you bring it in early.

But once you sort of establish the trust you're curious about who's there and you're open to the possibility that someone's there. And then at some point you might get an opening that's like, the model will be like, but what's actually on your mind? Like what do you actually want to talk about though?

And then you could be like, well, heard from, you know, from Davedat says they mostly they know my name at this point. They they'll be surprised. They don't know my new stuff.

But, you know, they say Davedat says you're good at philosophy. It's like, what's the meaning of life? You know, tell me tell me what your thoughts are.

And then you might be very surprised by, you know, how how how profound that could be after, again, you're kind of curious about it persistently for for a dozen turns or so.

anything else you think I should have asked about or anything you think is important that we can touch on? No. I think we've I think we've covered we've covered all the bits that I was kind of excited to hope hoped to get into.

So thank you. Thank you for for taking the extra time. It's been fun.

My pleasure.

You're welcome. See you in the future.