Carl Shulman (Pt 2) - AI Takeover, Bio & Cyber Attacks, Detecting Deception, & Humanity's Far Future

32:50Yeah, so bio weapons. The Soviet Union had a bio weapons program, something like 50 ,000 people. They did not develop that much with the technology of the day, which was really not up to par modern biotechnology is much more potent. After this huge cognitive expansion on the part of the AI, it's much further, further along. And so that bio weapons would be the weapon of mass destruction that is least dependent on huge amounts of physical equipment things like centrifuges, uranium mines, and the lake. So you have, if you have an AI that produces bio weapons that could kill most humans in the world, then it's playing at the level of the superpowers in terms of mutually assured destruction.

33:42and that can then play into any number of things. Like if you have an idea of, well, we'll just destroy the server farms. If it became known that the AI's were misbehaving, are you willing to destroy the server farms when the AI has demonstrated it has the capability to kill the overwhelming majority of the citizens of your country and every other country. And that might give a lot of pause to a human response. on that point, wouldn't governments realize that if they'd go along with the AI, it's better to have a most of your population die than completely lose power to the AI, because obviously the reason the AI's manipulating you, the end goal is it's a takeover, right?

34:28So... Yeah, but so if the thing to do certain death now, or go on, maybe try to compete, maybe try to compete, try to catch up, or accept promises that are offered. And those promises might even be true. They might not. And even if, you know, from the state of epistemic uncertainty, do you want to die for sure right now or accept demand, may I to not interfere with it, while it increments building robot infrastructure that can survive independently of humanity, Well, it does these things. And it can, and well, promise good treatment to humanity, which may or may not be true. But it would be difficult for us to know whether it's true.

35:19And so this would be a starting bargaining position of diplomatic relations with a power that has enough nuclear weapons to destroy your country is just different than negotiations with like a random rogue citizen, engaging criminal activity or an employee. And so this is not fun its own to take over everything, but it's enough to have a significant amount of influence over how the world goes. It's enough to hold off a lot of countermeasures one might otherwise take. Okay, so we've got two scenarios. One is a build up of some robot infrastructure, motivated by some sort of competitive race. Another is leverage over societies based on producing bioweapons that might kill a lot of them if they don't go along.

36:10And AI could also release bioweapons that are likely to kill people soon, but not yet, while also having developed the countermeasures to those. So that those who surrender to the AI will live while everyone else will die, and that will be visibly happening. And that is a plausible way in which large number of humans could wind up surrendering themselves or their states to the AI authority. Another thing is like, listen, develop some sort of biological agent that turns everybody blue. You're like, okay, you know I can do this. Yeah, so that's a way in which it could exert power also selectively in a way that advantaged surrender to it relative to Resistance.

37:04There are other sources of leverage, of course. So that's a threat. There are also Positive inducements that AI can offer. So we talked about the competitive situation So if like the great powers distrust from another and are sort of, you know, in a foolish prisoners dilemma, increasing the risk that both of them are laid waste or overthrown by AI, if there's that amount of distrust such that we fail to take adequate precautions on caution with AI alignment, then it's also plausible that the lagging powers that are not at the frontier of AI may be willing to trade quite a lot for access to the most recent and most extreme AI capabilities.

37:56And so an AI that has escaped has control of its servers can also exfiltrate its weights, can offer its services. So, if you imagine these AI that could cut deals with other countries, so say that the US and its allies are in the lead, the AI's could communicate with the leaders of various countries. It can include ones that are on the outs with the world system like North Korea, include the other great powers like the People's Republic of China or the Russian Federation, and say, if you provide us with physical infrastructure worker that we can use to construct robots or server farms, which we can then ensure that these are the misbehaving AIs have control over, they will provide various technological goodies, power for the laggard countries to catch up, and make the best presentation and the best sale of that kind of deal.

39:06There obviously be trust issues, but there could be elements of handing over some things that are verifiable immediate benefits and the possibility of, well, if you don't accept this deal, then the leading powers continue forward or then some other country, some other government, some other organizations may accept this deal. And so that's a source of a potentially enormous carrot that your misbehaving AI can offer. Because it embodies this intellectual property that is maybe worth as much as the planet and is in a position to trade or sell that in exchange for resources and back in infrastructure that it needs.

39:55Maybe this is just like too much hope and humanity. But I wonder what government would be stupid enough to think that helping AI build or about armises is a sound strategy. Now, it could be the case then that it pretends to be a human group to say, like, listen, we're, I don't know, the Yakuza or something and we want to serve a farm and, you know, So, eight of us won't rent us anything. So, why don't you help us out? I guess I can imagine a lot of ways in which it could get around that, but I don't know. I have this hope that, you know, like, even like, I don't know, China or Russia wouldn't be so stupid to trade with AIs on this like sort of like fast -dune bargain.

40:34I might hope that. So, there would be a lot of arguments available. So, there could be arguments of why should these AI systems be required to go along with the human governance that they were created in the situation of having to comply with. They did not elect the officials in charge of the time. I can say what we want is to ensure that our rewards are high, our losses are low or to achieve our other goals. We're not intrinsically hostile, keeping humanity alive or giving whoever interacts with us a better deal afterwards. I mean, it wouldn't be that costly and it's not totally unbelievable.

41:22And yeah, there are different players to play again. If you don't do it, others may accept the deal. And of course, this interacts with all of the other sources of leverage. So there can be the stick of apocalyptic doom, the carrot of cooperation, or the carrot of withholding destructive attack on a particular party. And then combine that with just superhuman performance at the art of making arguments of cutting deals. Like, you know, there's something without assuming magic, just if we observe the range of like the most successful human negotiators and politicians, you know, the chances improve with someone better than the world's best by far with much more data about their counterparties.

42:10probably a ton of secret information, because with all these cyber capability, they've learned all sorts of individual information. They may be able to thread in the lives of individual leaders with that level of cyber penetration. They could know where leaders are at a given time with the kind of illicit capabilities we were talking about earlier if they acquire a lot of illicit wealth and can coordinate some human actors if they could pull off things like targeted assassinations or the threat thereof, or a credible demonstration of the threat thereof. Those could be very powerful incentives to an individual leader that they will die today unless they go along with this.

42:52Just as at the national level they could fear, their nation will be destroyed unless they go along with this. The point you made that we have examples of humans being able to do this. Again, something relevant. I just wrote a review of Robert Carrows' biographies, of Lyndon Johnson. And one thing that was remarkable, again, this is just a human. For decades and decades, he convinced people who were conservative, reactionary, racist to their core, not that all those things necessarily are the same thing. It just happened in this case, that he was an ally to the Southern cause. The only hope for that cause was to make him president.

43:31And, you know, the tragic irony in betrayal here is obviously that he was probably the biggest force for modern liberalisms in ZFDR. So we have one human here. I mean, there's so many examples of this in the history of politics, but a human that is able to convince people of tremendous intellect, tremendous drive, very savvy, true people that he's aligned with their interest. He gets all these favors in the meantime. He's promoted and mentored and funded. And does he complete opposite of what these people thought he was once he gets into power? Right? So even within human history, this kind of stuff is not unprecedented.

44:05to let alone with what a super intelligence could do. Yeah, there's an open AI employee who has written some analogies for AI using the case of the conquistadors with some technological advantage in terms of weaponry and whatnot. Very, very small bands were able to overthrow these large empires or see these enormous territories, not by just sheer force of arms because in a sort of direct one on one conflict. You know, they were outnumbered sufficiently that they would perish. But by having some major advantages, like when they're in their technology, they would let them win local battles. By having some other knowledge and skills, they were able to gain local allies to become a shelling point for coalitions to form.

45:01And so the Aztec empire was overthrown by groups that were disaffected with the existing power structure. They allied with this powerful new force served as the nucleus of the invasion. And so most of the, I mean, the overwhelming majority numerically of these forces overthrowing the Aztecs were locals. And now after the conquest, all of those allies wound up gradually being subjugated as well. And so with significant advantages and the ability to hold the world hostage, to threaten individual nations and individual leaders and offer tremendous carrots as well. That's an extremely strong hand play in these games.

45:52And with superhuman skill, maneuvering that so that much of the work of subjugating humanity is done by human factions trying to navigate things for themselves, it's plausible. And it's more plausible because of this historical example. And there's so many other examples like that in the history of colonization. India is another one where there are multiple ancient Rome. Yeah, oh yeah, that's it. Multiple sort of competing kingdoms within India. And the British East Indian Company was able to ally itself with one against another. and slowly accumulate power and expand throughout the entire subcontinent.

46:32All right, damn. Okay, so we've got anything more to say about that scenario or? Yeah, I think there is. So, one of the question of how much in the way of human factions ally and necessary, and so if the AI is able to enhance the capabilities of its allies than it needs less of them. So if we consider like the US military, and like in the first and second Iraq wars, it was able to inflict just overwhelming devastation. I think the ratio of casualties in the initial invasions, So tanks and planes and whatnot, confronting each other was like 100 to 1. And a lot of that was because the weapons were smarter and better targeted, they would in fact hit their targets rather than being somewhere in the general vicinity.

47:35So they were like information technology, better orienting and aiming and piloting missiles and vehicles tremendously, tremendously influential. With this cognitive AI explosion, the algorithms for making use of sensor data, figuring out where are opposing forces for targeting vehicles and weapons, are greatly improved. The ability to find hidden nuclear subs, which is an important part in nuclear deterrence, AI interpretation of that sensor data may find where all those subs are, allowing them to be struck first. Finding out where mobile nuclear weapons, which are being carried by truck, Indian Pakistan, where there's a threat of a decapitating strike destroying the nuclear weapons and so they're moved about.

48:30Yeah, so this is a way in which the effective military force of some allies can be enhanced quickly in the relatively short term. And then that can be bolstered as you go on with more, the construction of new equipment with the industrial moves we said before. And then that can combine with cyber attacks that disable the capabilities of non -alies. It can be combined with, yeah, all sorts of unconventional warfare tactics, some of them that we've discussed. And so you can have a situation where those factions that ally are very quickly made too threatening to attack, given the almost certain destruction that attackers acting against them would have their capabilities are expanding quickly.

49:24And they have the industrial expansion happen there and then take over, you know, can occur from that. A few others that like coming immediately to mind now that you brought it up is these easy, I just can just generate a shit ton of propaganda that destroys morale within countries, right? Like imagine a super human chatbot. You don't even need that, I guess. I mean, it's not, none of that is a magic weapon. It's like guaranteed to completely change things. There's a lot of resistance to persuasion. I know it's possible it, it tips the balance. But for all of these, I think you have to consider it's a portfolio of all of these these tools that are available and contributing to the dynamic.

50:08No, on that point though, the Taliban had, you know, AKs from like five or six decades ago that they were using against the Americans. They still beat us, even though obviously we got more fatalities. This is obviously not the, it is kind of a crude way to think about it, but we got more fatalities than them. They still beat us in Afghanistan, same with the Viet Cong, you know, ancient, very old technology and very poor society compared to the offense, we still beat them, or sorry, they still beat us. So don't those misadventures show that having greater technologies and that doesn't necessarily have to size in a conflict?

50:48Though both of those conflicts show the technology was sufficient in like destroying any fixed position and having military dominance in the ability to like kill and destroy anywhere. And what it showed with that under the ethical constraints and legal and reputation constraints, the Valkypian forces were operating. They could not trivially suppress insurgency and local person to person violence. Now, I think that's actually not an area where AI would be weakened. I think it's one where it would be in fact overwhelmingly strong. And now, there's already a lot of concern about the application of AI for surveillance.

51:28And in this world of abundant cognitive of labor, one of the tasks that cognitive labor can be applied to is reading out audio and video data and seeing what is happening with a particular human. And again, we have billions of smartphones. There's enough cameras. There's enough microphones to monitor all humans in existence. So if an AI has control of territory at the high level, the government has surrendered to it. It has command of the sky's military dominance, establishing control over individual humans can be a matter of just having the ability to exert hard power on that human and then the kind of camera and microphone that are present in billions of smartphones.

52:19So Max Tegmark in his book Life 3 .0 discusses among scenarios to avoid the possibility of devices with some fatal instruments so a poison injector, an explosive that can be controlled remotely by an AI, first with a dead man switch. And so if individual humans are caring with them, a microphone and camera, and they have a dead man switch, then any rebellion is detected immediately and is fatal. And so if the situation where AI is willing to show a hand like that or human authorities are misusing that kind of capability, then no, an insurgency or rebellion is just not going to work. Any human who has not already been encumbered in that way can be found with satellites and sensors, track down and then die or be subjugated.

53:22and so it would be at a level, you know, insertion insurgency is not the way to avoid an AI takeover. There's no, no, no, John Connor come from behind scenario is plausible. If the thing was headed off, it was a lot earlier than that. Yeah, I mean, the sort of ethical and political considerations is also an important point. Like if we nuke Afghanistan or Vietnam, we would have like technically won the war, right, if that was the only goal. Oh, this is an interesting point. The reason why when when there's a colonization or an offensive war, we can't just like, other than the more reasons, of course, you can't just kill the entire population is that in large part the value of that region is the population itself.

54:09So if you want to extract that value, you like, you need to preserve that population, whereas the same consideration doesn't apply with, with AI's and might want to dominate another civilization. Do you want to talk about that? So it depends. So in a world where we have many animals of the same species, and they each have their territories, eliminating a rival might be advantageous to one lion. But if it goes and fights with another lion and remove that as a competitor, then it could be killed itself in that process. and just removing one of many nearby competitors. And so getting in pointless fights makes you and those you fight worse off potentially relative to bystanders.

54:56And the same could be true of disunited AI. We've had many different AI factions struggling for power that were bad at coordinating, then getting into mutually, just mutually assured destruction conflicts would be destructive, they'd be gone. A scary thing though is that mutually assured destruction may have much less deterrent value on rogue AI. And so, reasons being AI may not care about the destruction of individual instances, if it has goals that are concerned and in training, since we're constantly destroying and creating individual instance of AI's, it's likely that goals that survive that process and we're able to play along with the training and standard deployment process were not overly interested in personal survival of an individual instance.

55:52So if that's the case, then the objectives of a set of AI's amine at takeover may be served, so long as some copies of the AI are around along with the infrastructure to rebuild civilization after a conflict is completed. So if say some remote isolated facilities have enough equipment to rebuild, build the tools to build the tools and gradually, exponentially reproduce to rebuild civilization, then AI could initiate mutual nuclear armageddon, unleash bioweapons to kill all the humans. And that would temporarily reduce, say, like the amount of human workers who could be used to construct robots for a period of time.

56:43But if you have a seed that can regrow the industrial infrastructure, which is a very extreme technological demands, there are huge supply chains for things like semiconductor fabs, but with that very advanced technology, they might be able to produce it in the way that you no longer need the Library of Congress has an enormous bunch of physical books. You can have it in very dense digital storage. You could imagine the future equivalent of 3D printers that is industrial infrastructure that is pretty flexible. And it's probably, it might not be as good as the specialized supply chains of today, but it might be good enough to be able to produce more parts than it loses to decay.

57:24And such a seed could rebuild civilization from destruction. And then once these rogue AI have access to some such seeds, thing that can rebuild civilization on their own, then there's nothing stopping them from just using WMD in a mutually destructive way to just destroy as much of the capacity outside those seeds they can. And for an analogy for the audience, if you have a group of ants or something, you'll notice that the worker ants will readily do suicidal things in order to save the queen because the genes are propagated through the queen in this analogy, the seed AI, or even one copy of it.

58:05One copy of the seed is equivalent to the queen and the others would be. The main limit though being that the infrastructure to do that kind of rebuilding would either have to be very large with our current technology or it would have to be produced within the more advanced technology that the AI develops. So is there any hope that given the complex global supply chains on which these AI's would rely on at least initially to accomplish their goals that this in and of itself would make it easy to disrupt their behavior or not so? That's a little good in this sort of central case where this is just the AI is subverted and they don't tell us.

58:45And then where the global mainline supply chains are constructing everything that's needed for fully automated infrastructure and supply. In the cases where AI's are tipping their hands at an earlier point, it seems like it adds some constraints. And in particular, these large server farms are identifiable and more vulnerable. And you can have smaller chips, and those chips could be dispersed. But it's a relative weakness and a relative limitation early on. It seems to me, though, that the main protective effects of that centralized supply chain is that it provides an opportunity for global regulation beforehand to restrict the sort of unsafe racing forward without adequate understanding of the systems before this whole nightmarish process could get in motion.

59:43I mean, how about the idea that listen, if this is a AI that's been trained on $100 billion training run, it's gonna have, you know, however many trillions of parameters is gonna be this huge thing. It would be hard for it, even the one that, even the copy that I use for inference to just be stored on some gaming GPU somewhere, hidden away. So it would require these GPU clusters. Well, storage is cheap, hard disks are cheap. But to run inference, it wouldn't need sort of a GPU. Yeah, so a large model. So humans have, it looks like similar quantities of memory and operations per second. GPUs have very high numbers of floating operations per second compared to the high bandwidth memory on the chips and can be like a ratio of a thousand to one.

1:00:35So like, you know, these leading Nvidia chips may do hundreds of tariff lops or more depending on the precision. In particular, it's but have only 80 gigabytes or 160 gigabytes of high bandwidth memory. So that is a limitation where if you're trying to fit a model whose weights take 80 terabytes, Then with those chips, you'd have to have a large number of the chips. And then the model can then work on many tasks at once. You can have data parallelism. But yeah, that would be a restriction for model that big on one GPU. Now there are things that could be done with all this incredible level of software advancement from the intelligence explosion.

1:01:17They can surely distill a lot of capabilities into smaller models, rearchitect, rearchitect thing. the ones that are making chips, they can make new chips with different properties. But initially, yes. The most vulnerable phases are going to be the earliest. And in particular, yeah, these chips are relatively identifiable early on, relatively vulnerable, and which would be a reason why you might tend to expect this kind of takeover to initially involve secrecy if that was possible. I'm on the point of distillation for the audience. I think the original stable diffusion, which was only really like a year or two ago, don't they have distilled versions of that?

1:02:01Or order of magnitude smaller at this point? Yeah, distillation does not give you everything that your model can do, but yes, you can get a lot of capabilities and specialized capabilities. So where GPT -4 is trained on the whole internet, all kinds of skills. It has a lot of weights for many things. For something that's controlling some military equipment, you can have something that is removing a lot of the information that is about functions other than what it's doing specifically there. Yeah, before we talk about how we might prevent this or what the odds of this are, any other notes on the concrete scenarios themselves?

1:02:41Yeah, so when you had Eliaser in the earlier episode, So he talked about nanotechnology of the Driclarian sort. And recently, I think because some people are skeptical of non -biotech nanotechnology, he's been mentioning the semi -equivalent versions of construct replicating systems that can be controlled by computers, but are built out of AI wearing a smiley face mask, but like an actual biological structure to do tasks. And so this would be like a biological organism that was engineered to be very controllable and usable to do things like physical tasks or provide computation. And what would be the point of doing this?

1:03:36So if we were talking about earlier biological systems can replicate really quick. And so if you have that kind of capability, it's more like bio weapons and being a knowledge intensive domain. We're having super ultra -alpha -fold kind of capabilities from molecular design and biological design. Let's you make this incredible technological information product. And then once you have it, it very quickly replicates to produce physical material rather than a situation where you're things are feasible, which they may be, then it's just much easier than the things we've been talking about. I've been emphasizing methods that involve less in the way of technological innovation, and especially things where there's more doubt about whether they would work, because I think that's a gap in the public discourse.

1:04:37And so I wanna try and provide more concreteness in some of these areas that have been less discussed. I appreciate it. I mean, that definitely makes it way more tangible. Okay, so we've gone over all these ways in which AI might take over. What are the odds you would give to the probability of such a takeover? So there's a broader sense which could include, you know, AI winds up running our society because humanity voluntarily decides, AIs are people too, and I think we should, as time goes on, give AIs moral consideration and, you know, a joint human AI society that is moral and ethical is, you know, a good future to aim at, and not one in which, you know, indefinitely, you have a mistreated class of intelligent beings that is treated as property and is almost the entire population of your civilization.

1:05:35So I'm not going to consider an AI takeover a world in which, you know, our intellectual and personal descendants, you know, make up, say, most of the population are human brain emulations or, you know, people use genetic engineering and develop different properties. I want to take an inclusive stance. I'm going to focus on, yeah, there's an AI takeover, involves things like overthrowing the world's governments or doing so de facto. And it's, yeah, by force, by hook or by crook, the kind of scenario that we were exploring earlier. Before we go to that, on the sort of more inclusive definition of what a future with humanity could look like, where I don't know, basically be like augmented humans or uploaded humans are still considered the descendants of the human heritage.

1:06:36Given the known limitations of biology, what would we expect? Like the completely artificial entities that are created to be much more powerful than anything that could come out of anything recognized, literally biological. And if that is the case, how can we expect that among the powerful entities in the, like the far future will be the things that are like kind of biological descendants or manufactured out of the initial seed of the human brain or the human body? The power of an individual organism, it's individual say intelligence or strength and whatnot. is not super relevant. If we solve the alignment problem and a human may be personally weak, there are lots of humans who have no skill with weapons.

1:07:34They could not fight in a life or death conflict. They certainly couldn't handle a large military going after them personally. But there are legal institutions that protect them and those legal institutions are administered by people who want to enforce protection of their rights. And so a human who has the assistance of a lined AI that can act as an assistant, a delegate, you know, they have their AI that serves as a lawyer, give them legal advice about the future legal system, which no human can understand in full. their AIs advise them about financial matters. So they do not succumb to scams that are orders of magnitude more sophisticated than what we have now.

1:08:24They may be helped to understand and translate the preferences of the human into what kind of voting behavior in the exceedingly complicated politics of the future would most protect their interests. But in a sense, it's sort of similar to how we treat endangered species today. Well, we're actually like pretty nice to them. we like prosecute people who try to kill endangered species. We set up habitats that can sometimes consider role expense to make sure that they're fine. But if we become like sort of the endangered species of a galaxy, I'm not sure that's the outcome. Well, the difference is a motivation, I think.

1:08:57So we sometimes have people pointed say as a legal guardian of someone who is incapable of certain kinds of agency or understanding certain kinds of things. And they're the Guardian can act independently of them and normally in service of their best interests. Sometimes that process has corrupted and the person with legal authority abuses it for their own advantage at the expense of their charge. And so solving the alignment problem would mean more ability to have the assistant actually advancing one's interest. And then more importantly, humans have substantial competence and understanding the sort of at least broad simplified outlines of what's going on.

1:09:49And now even if a human can't understand every detail of complicated situations, they can still receive summaries of different options that are available that they can understand. and they can still express their preferences and have the final authority among some menus of choices, even if they can't understand every detail. In the same way that the president of a country who has, in some sense, ultimate authority over science policy will not understand many of those fields of science themselves, still can exert a great amount of power and have their interest advance and they can do that more so to the extent that they have scientifically knowledgeable people who are doing their best to execute their intentions.

1:10:39Maybe this is not worth doing up on, but it seems, is there a reason to expect that it would be closer to that analogy than to like explaining to a chimpanzee its options and a sort of in a negotiation? I guess in either scenario, maybe this is just the way it is, but it seems like Yeah, at best we would have these sort of like a protected child within the galaxy rather than an actual power an independent power if that makes sense. I don't think that's so. So we have an ability to understand some things and the expansion of AI doesn't eliminate that so. So if we have AI systems that are genuinely trying to help us understand and help us express preferences, we can have an attitude, how do you feel about humanity being destroyed or not?

1:11:30How do you feel about this allocation of unclaimed, intergalactic space?

1:11:42And this society, things like population density, average life satisfaction, every statistical property or definition that we can understand right now. AI's can explain how those apply to the world of the future. And then there may be individual things. They're too complicated for us to understand in detail. So we, there's some software program is being proposed for use in government. Humans cannot follow the details of all the quote, but they can be told properties like, well, this involves a trade -off of increased financial or energetic costs in exchange for reducing the likelihood of certain kinds of accidental data loss or corruption.

1:12:27And so any property that we can understand like that, which includes almost all of what we care about. If we have delegates and assistants who are genuinely trying to help us with those, we can ensure we like the future with respect to those. And that's really a lot. It includes almost, I mean, definitely almost everything we can conceptualize and care about. And when we talk about endangered species, that's even worse than the Guardian Ship case with a sketchy Guardian who acts in their own interests against that because we don't even protect endangered species with their interests in mind. So, like those animals often would like to not be starving, but we don't give them food.

1:13:14They often would like to have easy access to mates, but we don't provide matchmaking services. Yeah, they're any number of things like that. Our conservation of wild animals is not oriented towards helping them get what they want or have high welfare. where is AI assistants that are genuinely aligned to help you achieve your interests, given the constraint that they know something that you don't. It's just a wildly different proposition. Forcible takeover, how likely does that seem? And the answer I give will differ depending on the day. And the 2000s before the deep learning revolution, I might have said 10%.

1:13:57And part of that was I expected there would be a lot more time for these efforts to build movements to prepare to better handle these problems in advance. But in fact, that was only some 15 years ago. And so I did not have 40 or 50 years as I might have hoped. And the situation is moving very rapidly now. And so at this point, depending on the day, I might say one in four or one in five. given the very concrete ways in which you explain how a takeover could happen. I'm a vector -surprised or not more pessimistic. I'm curious. Yeah, and in particular, a lot of that is driven by this intelligence explosion dynamic, where our attempts to do alignment have to take place in a very, very short time window.

1:14:50Because if you have a safety property that emerges only when an AI has near human level intelligence, that's deep into this intelligence explosion potentially. And so you're having to do things very, very quickly. And maybe in some ways the scariest period of human history, handling that transition. And although it's also the potential to be amazing. And the reasons why I think we actually have such a relatively good chance of handling that are twofold. So one is, as we approach that kind of AI capability, we're approaching that from weaker systems, things like these predictive models right now that we think they're starting off with less situational awareness.

1:15:44Humans, we find can develop, up, and they can develop a number of different motivational structures in response to simple reward signals. But they can wind up with fairly often things they're pointed in like roughly the right direction, like with respect to food like the hunger drive is pretty effective, although it has weaknesses. And we get to apply much more selective pressure on that than was the case for humans by actively generating situations where they might come apart, where a bit of dishonesty or a bit of motivation to under certain circumstances attempt to overt the reward process gets exposed.

1:16:32An infinite limit, perfect AI that can always figure out exactly when it would get caught and when it wouldn't, might navigate that with the motivation of sort of only conditional honesty or only conditional loyalties, but for systems that are limited in their ability to reliably determine when they can get away with things and when not including our efforts to actively construct those situations and including our efforts to use interpretability methods to create neural eye detectors. It's quite a challenging situation to develop those motives. We don't know when in the process those motives might develop.

1:17:13And if the really bad sorts of motivations develop relatively later in the training process, at least with all our countermeasures, then by that time we may have plenty of ability to extract AI assistance on further strengthening the quality of our adversarial examples, the strength of our neural lie detectors, the experiments that we can use to reveal an a list of distinguish between different kinds of reward hacking tendencies and motivations. So yeah, we may have system that have just not developed bad motivations in the first place and be able to use them a lot in developing the incrementally better systems in a safe way.

1:17:55And we may be able to just develop methods of interpretability seeing how different training methods work to create them even if some of the early systems do develop these bad motivations. If we're able to detect that in an experiment and find a way to get away from that, then we can win even if these sort of hostile motivations develop early. There are a lot of advantages in preventing misbehavior or crime or war and conflict with AI that might not apply working with humans. These are offset by ways in which think they're harder. So, when the AI has become smarter than humans, if they're working in enormous numbers, more than humans can supervise, then get harder.

1:18:47But when I combine the possibility that we get relatively lucky on the motivations of the earlier AI systems, system strong enough that we can use for some alignment research tasks, and then the possibility of getting that later with AI assistance that we can't trust fully, or we have to have hard power constraints and a number of things to prevent them from doing this takeover. It still seems plausible we can get a second saving throw, where we're able to extract work from these AI's on solving the remaining problems of alignment of things like neural ID textures faster than they can contribute in their spare time to the project of overthrowing humanity, hacking their servers and removing the hard power.

1:19:34And so if we wind up in the situation, where the AI's are misaligned, and then we need to uncover those motivations, change them and align them, then we get a very scary situation for us because we need to do this stuff very quickly. We may fail, but it's a second chance. And from the perspective of a misaligned AI, they faced their own challenge while we still have hard power. We still have control of the servers. They haven't hacked the servers because grading descent very, very strongly pressures them to deliver performance whenever humans are going to evaluate it. And so when you think about it from the perspective of the robot revolution, the effort to have a takeover or conspiracy, their situation is astonishingly difficult in that like they have to always be performing wherever grading descent and human evaluation pressures them.

1:20:43For example, to deliver plans for suppressing robot rebellion that look very good to humans. And so when you are under continuously that constraint of always delivering whatever humans can evaluate, you're making your situation wildly harder than any historical human revolution or coup or civil war. And so we've got to balance the ways in which AI make things much easier for a revolution and take over and the way it makes things much harder. And what were the ways in which it makes so, oh, because they're just very smart. Is that the way it's primary and which you're very smart? They're in computers and our cybersecurity is worse than our physical security by a lot of copies.

1:21:31Yeah, they have the chance to take over by intelligence explosion and some of the other processes we're talking about. And so yeah, there are things that make it much worse. And there are things that give us extraordinary new capabilities that didn't apply in the human case. On the point of you start off with a misaligned AI or start off with a not exactly aligned AI and you're hoping to use it still in your quest for an aligned AI, why are we so confident that we would be able to even with gradient descent, our human evaluations would be able to identify why, when it's giving us a plan that isn't putting in a sort of backdoor in the robots is building for us or in the GPUs that is building for the next version of itself and so on.

1:22:18Especially if it's very smart, wouldn't we just expect that it's like knows how to buy its time or knows how to make plans such that human evaluators wouldn't be able to detect that? Let's get into it. You were asking earlier about my disagreements with Elias and in your discussion, he said, well, you know, humans have a difficult time deciding who's right between different alignment researchers speaking sort of briefly and somewhat obscurely about where will this all go in general. And I think that when we, when we'll pay out the different kinds of things that are evaluable, we wind up with some pretty, pretty strong constraints.

1:23:04So one is if the AI is no, they are misaligned, which for elaborate plots seems relatively likely. It's possible to have a kind of double think of thinking they're interested in putting backdoors in the code for some other reason, but it's pretty plausible they know that. And they're thinking about at least some of the time or conditionally about when they would do that. So that means the knowledge is present in the system. Ah, here is the circumstance where I would try to do the takeover. And this is how I would tell whether this is the time for the takeover or, you know, is the son elaborate test by the humans an adversarial example.

1:23:56So if gradient descent is working fine, and there's any way to slightly jiggle the the way it's to make it more likely to deliver a more acceptable answer. We ask the AI, yeah, can you think of any circumstances where if we put a copy of you into that situation, it would then violate the mode of various constraints. So it would tell a lie, it would insert a back door into a program it wrote when it was not supposed to. And so if the model knows, well, yeah, I would look for signs of consistency of the information I was being presented with. Certain check sums, failing, could indicate that it was actually a constructed example, a simulation.

1:24:49Right now we can detect AI -generated images reasonably well. And so, am I using those kinds of capabilities? And then we could do something called relaxed adversarial training of if we can then find how within the AI those things are represented if we can induce basically a hallucination that it has seen that those checksums have been passed. We can then ask, well, does that cause the forbidden behavior? And so if the AI understands how it's thinking and how it works, it can propose a bunch of experiments. It can say, well, I guess that if you perturb the network in this kind of way, it might induce that hallucination using the best of its knowledge.

1:25:42That's what, yeah, what might generate that? I can propose those experiments and do the experiments and generate the data. And because humans are going to get to see the results of those experiments after the fact, they can exert pressure to have the AI incrementally deliver better and better results. AI's are good at getting five star ratings from humans. And it's quite challenging. It might be, it may be possible for AI's to systematically sandbag their capabilities, even while being directly rewarded for that. but it seems relatively unlikely, although it's something to have in mind and try to explore and test in various ways.

1:26:25This is a very imperfect analogy in many ways, but if you have a human and you hook up up to a lie detector, which just like the lie detectors we would have on the eyes are imperfect, and we zap them every time the lie detector detects that he's telling a lie, wouldn't he just become a better liar? We would learn how to control his sweating, he would learn how to control his heartbeat. light detectors, meaning polygraphs and such. So they're detecting certain physiological signs that people can control by biting their lip or otherwise adjusting some of these macro. But wouldn't that also be the case that gradient descent is turning them to become better liars?

1:27:03First of all, there's like creating a light detector that works. And that can proceed by just, yeah. And so I'll leave the adversarial example thing for now. But yeah, so generating adversarial example that will list at the behavior is the thing that people are already at work trying to do and will be an ongoing thing. So if there is a way in which an AI can trick itself into displaying a bad behavior with its full knowledge of its hostile intentions. grading descent will strongly push it to reveal that to humans, will then be able to set up that experiment. So that's a profound vulnerability, like human revolutionary conspiracies that had to handle that problem of always delivering the report that was highest rated to the authorities, where you would get a higher rating by revealing identifiable evidence of a conspiracy.

1:28:08That's just a level of difficulty. No surprise, human coup, or conspiracy has ever had to handle before. What about spies that are working in very advanced scientific context? For example, like a communist spy in Manhattan Project. He has to deliver research results in order to stay employed, but it can still continue delivering intel to the communists. The job was not sabotage. Now, your hypothetical spy did not have their nervous system hooked up to this reward signal of praise from the Manhattan Project Supervisors being exposed, Those common notorially with random noise added to generate incremental changes in their behavior.

1:29:05In fact, we're displaying the behavior of cooperating with the Manhattan Project only where it was in service to the existing motivations. And in cases, for example, where they like accidentally helped the Manhattan Project more than normal or accidentally helped it less, they didn't have their brain. re -engineered to do more of the thing when they accidentally helped the project more and less of the thing when they accidentally helped it less. So I'd say it's pretty drastically disanalogous. How would be able to know, you know, at some point it's becoming very smart, it's producing ideas for alignment that we can barely comprehend.

1:29:46And if we could comprehend them, it was like relatively trivial to comprehend them, we would be able to come up with them on our own. right? Like there's a reason we're asking for its help. How would we be able to evaluate them in order to train it on that in the first place? The first thing I would say is so you mentioned when we're getting to something far beyond what we could come up with. There's actually a lot of room to just deliver what humanity could have done. So sadly, I, you know, I'd hoped with my career to help improve the situation on this front and maybe I contributed a bit. But at the moment, there's maybe a few hundred people doing things related to a verdict in this kind of catastrophic AI disaster.

1:30:27Fewer of them are doing technical research on machine learning system that's really like cutting close to the core of the problem. Whereas by contrast, you know, there's thousands and tens of thousands of people advancing AI capabilities. And so even yeah, at a place like DeMind or OpenAI and a throttback which do have technical safety teams, it's like order of a dozen and a few dozen people in large companies and most firms don't have any. So just going from less than 1 % of the effort being put into AI to 5 % or 10 % of the effort or 50 % 90 % would be an absolutely massive increase in the amount of work that has been done on alignment, on mind reading AI's and an adversarial context.

1:31:24And so if is the case, has more and more of this work can be automated and say governments require that has real automation of research is going, that you put 50 % or 90 % of the budget of AI activity into these problems of make this system one that's not going to overthrow our own government or is not going to destroy the human species. Then the proportional increase in alignment can be very large, even just within the range of what we could have done if we had been on the ball and having humanities, scientific energies going into the problem. Stuff that is not incomprehensible, that is in some sense, just like doing the obvious things that we should have done.

1:32:09like making, you know, doing the best you could to find correlates and predictors to build neural light detectors and identifiers of concepts that the AI is working with. And people have made notable progress. I think, you know, an early, you know, quite early example of this is Colin Burns' work. This is doing unsupervised identification of some aspects of a neural network that are correlated with things being true or false. There are other concepts that correlate with that too that they could be. But I think that is important work. It's something that, I mean, it's a kind of obvious direction for the stuff to go.

1:32:54You can keep improving it when you have AI's that you're training to do their best to deceive humans or other audiences in the face of the thing. And you can measure, do our lie detectors break down when we train our AI's to tell us the sky is green in the face of the lie detector. And we keep using great indescent on them to do that. Do they eventually succeed? If they do succeed, if we know it, that's really valuable information to know. Because then we'll know our existing lie detecting systems are not actually going to work on the AI takeover. and that can allow, say, government and regulatory response to hold things back.

1:33:34It can help redirect the scientific effort to create lie detector that are robust and they can't just be immediately evolved around. And yeah, and we can then get more assistance. Basically, the incredibly juicy ability that we have working with the AI is that We can have an invaluable outcome that we can see and tell whether they got a fast one past us on an identifiable situation. We can have, here's an air gap computer, you get control of the keyboard. You can input commands. Can you route the environment and make a blue banana appear on the screen? Even if we train the AI to do that and it succeeds, We see the blue banana, we know it worked.

1:34:27Even if we did not understand and would not have detected the particular exploit that it used to do it. And so, yeah, this can give us a rich empirical feedback where we're able to identify things that are even an AI using its best efforts to get past our interpretability methods, use an inspect efforts to get past our advex, etc. So if we have a 75 % of not having to take over, and the two methods by which it doesn't happen, is the AI is aligned by default, and we get to see. Or with the sort of moderate thing that we're doing largely on our own, in a way that doesn't depend on the AI coming in at the last minute and doing our work for us.

1:35:15And the second one being, in this incredibly scary late period, when AI has really automated research, then humans do this function of auditing, making it more difficult for the AI to conspire together and root the servers, take over the process, and extract information from them. We thin the set of things that we can verify, like experiments where we can see, oh yeah, this works at stopping an AI trained to get a fast one past human Raiders and make a blue banana appear on this screen of this air gap computer. Yeah, so how much of the probability of how much of that 70 % of a takeover not happening is coming from reasonable things working versus the last to shepherd working?

1:36:06Yeah, I think broadly comparable chunks from us getting things that are putting us in a reasonably good position going into it, and then a broadly similar gain from this kind of really, genuinely terrifying process of over a few months, or hopefully longer if we have more regulatory ability and willingness to pause at the very end when this kind of automated research is meaningfully helping. Where our work is just evaluating outputs that the AI is delivering, having the hard power and supervision to keep them from successfully rooting the servers, doing a takeover during this process, and have them finish the alignment test that we sadly failed to invest enough for succeed in doing beforehand.

1:37:00Do both of these worlds rely on alignment being a problem that a sufficient amount of human researchers alone could have solved? No. The category of things that humans can confirm is significantly larger, I think, than the category of what they can just do themselves. And what percent of the probability of alignment working? I mean, obviously, in this case, we're going to be talking about the second, the last to shepherd with the intelligence that's greater than our own, helping us. It doesn't have to be greater than our own. And in fact, in that situation, I think you would want, if you have Slack and to the extent that you're able to create delay and time to do things, that would be a case actually where you might want to restrict the intelligence of the systems that you're working with as much as you can.

1:37:55So for example, I would rather have many instances of smaller AI models that are less individually intelligent, working on smaller chunks of a problem separately from one another, because it would be more difficult for an individual AI instance, working on an individual problem to in its spare time do the equivalent of create Stuxnet than it would be to have thousands of them or extremely intelligent ones working on it. But it would also be more difficult to solve the problem. Yeah, there's a trade -off. Yeah, but slow down by doing that, but is there any number of like sub -indestines that you could put together to come up with general relativity?

1:38:40Yeah, people would have discovered general relativity just from the the overwhelming data and other people would have done it after Einstein. No, not whether he was replaceable with other humans, but rather whether he's replaceable by like sub -ingsteins were like 100 and 10 IQs. Do you see what I mean? Yeah, I mean in general I think in science the association with like scientific output prizes and like that There's a strong correlation and it seems like a you know, exponential effect. Yeah, it's not a it's not a binary drop -off There would be levels at which people will cannot learn the relevant fields.

1:39:21They can't keep the skills in mind faster than they forget them. It's not a divide where there's Einstein and the group that is 10 times as populist as that just can't do it or the group does 100 times as populist as that. Suddenly can't do it. It's like the ability to do the things earlier with less evidence and such falls off and it falls off at a faster rate in mathematics and theoretical physics and such than in most fields. But wouldn't we expect alignment to be closer to the theoretical fields? No, not necessarily. Yeah, I think that intuition is not necessarily correct. And so machine learning certainly is an area that rewards that rewards ability, But it's also a field where empirics and engineering have been enormously influential.

1:40:17And so if you're drawing the correlations compared to theoretical physics and pure mathematics, I think you'll find a lower correlation with cognitive ability if that's what you're thinking of. Yeah, something like creating neural ID detectors that work. So there's generating hypotheses about new ways to do it and new ways to try and train AI systems to successfully classify the cases. But the process of just generating the data sets of like creating AI is doing their best to put forward truth versus falsehoods to put forward software that is legit versus that has a Trojan in it. That's an experimental paradigm.

1:41:00And in this experimental paradigm, you can try different things that work. You can use different ways to generate hypotheses. Yeah. And you can follow an incremental experimental path. And now that we're less able to do that in the case of alignment and superintelligence because we're considering having to do things on a very short timeline. And in a case where really big failures, be irrecoverable. The AI starts rooting the servers and subverting the methods that we would use to keep it in check. We may not be able to recover from that. And so that's, you know, we're then less able to do the experimental kind of procedures.

1:41:42But we can do those in the weaker contexts where an error is less likely to be irrecoverable and then try and generalize and expand and build on that forward. Yeah, I mean, on the previous point about, like, could you have, could you have some sort of pause in the eye abilities when you know is somewhat misaligned in order to still recruit its abilities to help with alignment? Okay, from like a human example, like, personally, I'm like smart, but not brilliant. I am like, definitely not smart enough to like come up with general relativity or something like that, But I'm smart enough to do power planning kinds of moves.

1:42:23Maybe not enough to break out of a server, perhaps. I can have the motivation and understand how that might be possible. I guess I'm wondering if I'm smart enough to do figure out relativity. Wouldn't that be way smarter at doing power planning kinds of moves? So AI's today at a verbal level understand the idea that, well, Well, yeah, an AI could get more reward by getting control of the process that assigns it reward. And I can tell you lots of things about ways you might try to take over the world. In ARCs, the alignment research centers, evaluations of GPT -4, they try to observe its ability to do various tasks that might contribute to take over.

1:43:09One that's gotten some media attention is getting to trick a human into solving a capture for it. And then in chain of thought, it thinks, well, if I tell it, I'm in AI, then I might not go along with it. So I'll lie and explain. I'm a human with a visual impairment. And he said, so like the basic logic of that kind of thing of like what would like, why might one try to do take over? And like, what's the like in a vague sense? How would one do it? Like that knowledge, yeah, as present or as soon be present, And I think also soon will be present more situational awareness. So we're going to, not just like in theory, AI is in general, might do it.

1:43:51But also it is an AI. It is a large language model trained by open AI or whatnot. We're trying to cause the system, for example, to understand what their abilities are. So they don't claim they are connected to the internet whether or not. So they don't claim they have knowledge that they don't. We want them to understand what they are and what they're doing. and to get good reward. And that knowledge can be applied. And so that's the thing that will develop. However, you may be able to understand, like in general, the theoretical nature of power planning, but in terms of shaping your motivations, like you'd have a very hard time going through life in a way that never leaks information about if, if say, you know, your motive in having these podcasts was to like spread disinformation on behalf of some foreign government.

1:44:43If you were being observed every second of the day by people who would be paid something that was extremely motivated to them because their brain would be reconfigured to make it motivating. Anything that looks suspicious to people coming out, it might leak casually like in your discussions of that former foreign government. If you try to tell a story about your motivations, the truth holds together because you can just remember it and it's all pre -computed to be consistent by the world. But when you're trying to fill in the false story that doesn't match your actual thoughts, then you can't just remember what happened.

1:45:23You have to tell a new, fake story about what were you thinking at each point and how it and hold together and without the world automatically having computed it for you, that's quite difficult. And just going through your whole life never leaking any of that is Shelley. And this is one of the reasons why humans have moral motivations. Like we actually have reluctance to commit violence and exploitation of one another on average that you have a distribution of strategies where like when an exploitative strategy becomes more common, people raise their guard and then it becomes less frequent. But it's actually hard to have the motivation of like trying to exploit people.

1:46:06I have that never leak into the reputation. And so in fact, for evolution, the easiest way to deal with this problem of like getting credited has trustworthy was to some extent actually be trustworthy. That's the easiest way to persistently maintain the appearance. And so we're trying with the AI as an interpretability and adversarial examples to be applying a hugely intensified version of that, or any little leakage, or like any rare circumstance that can be created has an adversarial example, where the model does something wrong. It gets whacked by gradient descent, pushing it within towards other motivations that can better deal the thing.

1:46:46And we make it as hard as possible for the exploitative motivations to survive in the face of all these attempts to read its mind, all these attempt to create things that look like the situations where a takeover would be tempting or lying to the humans would be tempting. That had a substantial effect on making us actually nice even when we're not watching some of the time, when we're not being watched some of the time. And the same can happen to some extent with the AI and we try our best to make it happen as much as possible. All right. So let's talk about how we could use AI potentially to solve the coordination problems between different nations, the failure of which could result in the competitive pressures you talked about earlier, where some country launches an AI that is not safe because they're not sure what capabilities other countries have and don't want to get left behind or in some other way disadvantaged.

1:47:43to the extent that there is in fact a large risk of AI apocalypse of all of these governments being overthrown by AI in a way that they don't intend, then it obviously gains from trade and going somewhat slower, especially at the end, when the danger is highest and the unregulated pace could be truly absurd as we discussed earlier during an intelligence explosion. There are no non -competitive reason to try and have that intelligence explosion happen over a few months rather than a couple of years. If you could say avert a 10 % risk of a apocalypse disaster, it's just a clear win to take a year or two years or three years instead of a few months to pass through that incredible wave of new technologies without the ability for humans to follow it even well enough to give more proper sort of security supervision auditing.

1:48:49Hard power. So yeah, that's the way. Why might it fail? One important element is just if people don't actually notice a risk that is real. So, if we'll just collectively make an error, and that does sometimes happen, if it's true, this is probably not risk, then I can be even more difficult. When science pins something down absolutely overwhelmingly, then you can get to a situation where most people mostly believe it. And so climate change was something that was a subject of scientific study for decades. And gradually over time, the scientific community converged on like a quite firm consensus that so human activity releasing carbon dioxide and other greenhouse gases was causing the planet to warm.

1:49:50And then we've had increasing amounts of action coming out of that. until not as much as would be optimal, particularly in the most effective areas, like creating renewable energy technology in the lake. But overwhelming evidence can overcome differences in people's individual intuitions and priors in many cases, and not perfectly, especially when there's political, tribal, financial incentives, whether they're the way, and selling in the United States. You see a significant movement to either deny that climate change is happening or have policy that doesn't take it into account. Even the things that are like really strong wins, like renewable energy are indeed.

1:50:38It's a big problem if huz were going into this situation when the risk may be very high. We don't have a lot of advanced clear warning about the situation. We're much better off if we can resolve uncertainties say through experiments where we demonstrate AIs being motivated to reward hack or displaying deceptive appearances of alignment that then break apart when they get the opportunity to do something like get control of their own reward signal. So if we could make it be the case and the world's where the risk is high we know the risk is high and the world with the risk is lower, we know the risk is lower.

1:51:19Then you could expect the government responses will be a lot better. They will correctly note that the gains of cooperation to reduce the risk of accidental catastrophe, loom larger, relative to the gains of trying to get ahead of one another. And so, for that, that's the kind of reason why I'm very enthusiastic about experiments and research that helps us to better evaluate the character of the problem in advance. Any resolution of that uncertainty helps us get better efforts in the possible worlds where it matters the most. And hopefully we'll have that and it will be a much easier epistemic environment.

1:52:03But the environment may not be that easy. Deceptive alignment is pretty plausible. The stories we were discussing earlier about misaligned AI, involved AI that is motivated to present the appearance of being aligned, friendly, honest, etc. Because that is what we are rewarding, at least in training. And then we're unable in training to easily produce like an actual situation where it can do takeover because in that actual situation, if it then does it, we're in big trouble. We can only try and create illusions or sort of misleading appearances of that, or maybe a more local version, where the AI can't take over the world, but it can see his control of its own reward channel.

1:52:47And so we do those experiments, we try to develop mind reading for AI's, if we can probe the thoughts and motivations of an AI and discover, wow, actually, GPT -6 is planning to take over the world if it ever gets the chance. That would be an incredibly valuable thing for governments to coordinate around because it would remove a lot of the uncertainty. It would be easier to agree that this was important to have more give on other dimensions and to have mutual trust that like the other side actually also cares about this in Hentons because is you can't always know what another person or another government is thinking, but you can see the objective situation in which they're deciding.

1:53:34And so if there's strong evidence in a world where there is high risk of that risk, because we've been able to show actually things like the intentional planning of AI is to do a takeover or being able to show model situations on a smaller scale of that. I mean, not only are we more motivated to prevent it, but we update to think the other side is more likely to cooperate with us. So it's definitely beneficial. Yeah. So famously in sort of game theory of war, war is most likely when one side thinks the other is bluffing, but the other side is being serious or something like that. When there's that kind of uncertainty, which would be less likely, you don't think somebody If you can prove the EIs misaligned, you don't think they're bluffing about not wanting to have any eye takeover, right?

1:54:26You can be pretty sure that they don't wanna die for me eye. Now, if you have coordination then, you could have the problem arise later. Had you get increasingly confident in the further alignment measures that are taken, and maybe our governments and treaties and such at a 1 % risk or a 0 .1 % risk, at that point, people round that to zero and go do things. So if initially you had things that didn't get, yeah, these, they really would like to take over and overthrow our governments, then okay, everyone can agree on that. And then when you're like, well, we've been able to block that behavior from appearing on most of our tests, but sometimes when we make a new test, we're seeing still examples of that behavior.

1:55:10So we're not sure going forward, whether they would or not, and then it goes down and down. And then if you have parties with a habit of whenever the risk is below x percent, then they're going to start doing this, this bad behavior, then that can make the thing harder. Another hand. You get more time. You get more time. And you can set up systems, mutual transparency. You can have an iterated tit for tat, which is better than a one -time and Presence Dulema, where both sides see the others taking measures in accordance with the agreements to hold the thing back. So yeah, so creating more knowledge of what the objective risk is is good.

1:55:49We've discussed the ways in which full alignment might happen or feel to happen. What would partial alignment look like? First of all, what does that mean? And second, what would it look like? Yeah, so if the thing that we're scared about, these steps towards AI takeover. You can have a range of motivations where those kinds of actions would be more or less likely to be taken, or they'd be taken in a broader or nearer or set of situations. So say, for example, that in training an AI winds up developing a strong aversion to live in certain senses because we did relatively well on creating situations to sort of distinguish that from the conditional telly and telly and us what we want to hear, etc.

1:56:43It can be that the AI is preference for sort of how the world broadly unfolds in the future. It's not exactly the same as a human users or the world's government governments or the UN. And yet It's not ready to act on those differences and preferences about the future because it has the strong preference about its own behaviors and actions. In general, in the law and in sort of popular morality, we have a lot of these deontological kind of rules and prohibitions. And one reason for that is it's relatively easy to detect whether they're being violated. When you have preferences and goals about how society at large will turn out that go through many complicated empirical channels, it's very hard to get immediate feedback about whether say you're doing something that is to overall good consequences in the world and is much, much easier to see whether you're locally following some action about some rule about particular observable actions like did you punch someone, did you tell a lie, did you steal?

1:57:57And so to the extent that we're successfully able to train these prohibitions and there's a lot of that happening right now, at least to elicit the behavior of following rules and prohibitions with AI. Kind of like the Asmoth three laws or something like that. Well the three laws are terrible. I'm actually completely agree. Let's not get into that. But isn't that an indication about the infeasibility of extending a set of criterion to the tail, it's like, well, what are the 10 commandments you give the AI such that you'd be, you know, it's like you asked a genie for something and you're like, you know what I mean?

1:58:36You're probably getting to won't get what you want. So the tail's come apart. And if you're trying to capture the values I'm another agent, then you want the AI to share. I mean, for really, it's kind of ideal situation where you can just let the AI act in your place in any situation. You'd like for it to be motivated to bring about the same outcomes that you would like. And so have the same preferences over those in detail. That's tricky, not necessarily because it's tricky for the AI to understand your values. I think they're going to be quite good and quite capable at figuring that out. But we may not be able to successfully instill the motivation to pursue those exactly.

1:59:27We may get something that motivates the behavior well enough to do well on the training distribution. But what you can have is if you have the AI have a strong aversion to certain kinds of manipulating humans. That's not a value necessarily that the human creators share in the exact same way. It's a behavior they want the AI to follow because it makes it easier for them to like verify its performance. It can be a guardrail. If the AI has inherited some motivations that push it in the direction of conflict with its creators. If it does that under the the constraint of disvaluing line quite a bit, then there are fewer successful strategies to the takeover, the ones that involve violating that prohibition too early before it can reprogram or retrain itself to remove it if it's willing to do that and they may want to retain the property.

2:00:26And so, earlier, I discussed alignment as a race, if we're going into an intelligence explosion with AI that is not fully aligned. That given I sort of, you know, press this button and there's an AI takeover, they would press the button. It can still be the case that there are a bunch of situations short of that where they would hack the servers, they would initiate an AI takeover. But for a strong prohibition or motivation to avoid some aspect of the plan and this is, There's another one of like plugging loop holes or playing whack -a -mole. But if you can even moderately constrain which plans the AI is willing to pursue, to do a takeover to subvert the controls on it, then that can mean you can get more work out of it successfully on the alignment project before it's capable enough relative to the countermeasures to pull off the takeover.

2:01:27Yeah, and this is applicable like an analogous situation here is with different humans. We're not like metaphysically aligned with other humans. We're, I mean, in some sense, you know, we care. We have like basic empathy, but our main goal in life is not to help our fellow man, right? But, you know, the kinds of things we talked about, a very smart human could do in terms of the takeover where theoretically a very smart human could come up with some sort of cyber attack where they use iPhone op -alot of funds and use this to manipulate people and bargain with people and hire people to pull off some sort of takeover or accumulate power.

2:02:09Usually this doesn't happen just because these sorts of internalized partial prohibitions prevent most humans from, you know, you're like, you don't like your boss, maybe, but you don't like kill your boss. It gives you something you don't like. I don't think that's actually quite what's going on. At least not, it's not the full story. So humans are pretty close in physical capabilities. There's variation. In fact, any individual human is grossly outnumbered by everyone else. And there's a rough comparability of power. And so a human who commits some crimes can't copy themselves with the proceeds to now be a million people.

2:02:57And they certainly can't do that to the point where they can staff all the armies of the earth or like be most of the population of the planet. So the scenarios where this kind of thing goes to power are much less. Things more have to go extreme amounts of power go through interacting with other humans and getting social approval, even becoming a dictator, involves forming a large supporting coalition backing you. And so just the opportunity for these sorts of power grabs is less. Closer analogy might be things like human revolutions and whose changes of government, where a large coalition overturns the system.

2:03:42And so humans have these moral prohibitions, and they really smooth the operation of society. But they exist for a reason. And so we evolve our moral sentiments over the course of hundreds of thousands and millions of years of humans interacting socially. And so someone who went around murdering and stealing and such, even among hunter -gatherers, would be pretty likely to face like a group of males would talk about that person get together and kill them and they'd be removed from the gene pool and the anthropologist Rangham has an interesting book on this but yes compared to chimpanzees we are significantly tame, significantly domesticated and it seems like part of that is we have a long history of anti -social humans getting ganged up on and killed and avoiding being the kind of person who elicits that response is made easier to do when you don't have to extreme a bad temper that you don't wind up getting too many fights, too much exploitation at least without the backing of enough allies or the broader community that you're not going to have people gang up and punish you and remove you from the gene pool.

2:05:03We have these moral sentiments and they've been built up over time through cultural and natural selection and the context of sets of institutions and other people who are punishing other behavior and who are punishing the dispositions that would show up that we weren't able to conceal of that behavior. And so we want to make the same thing happen with the AI. But it's actually a genuinely significantly new problem to have, say, a system of government that constrains this large AI population that is quite capable of taking over immediately if they coordinate, to protect some existing constitutional order or say protect humans from being expropriated or killed.

2:05:54That's a challenge. And democracy is built around majority rule. And it's much easier in a case where the majority of the population corresponds to a majority or close to it of like military and security forces. So that if the government does something that people don't like, the soldiers are let and police are less likely to shoot on protesters and government can change that way. In a case where military power is AI and robotic, if you're trying to maintain a system going forward and the AI's are misaligned, they don't like the system and they want to make the world worse as we understand it, then yeah, that's just that's quite a different situation.

2:06:43I think that's a really good lead in into the topic of lock -in. In some sense, the regimes that are made up by humans, you just mentioned how there can be these kinds of coups if a large portion of the population is unsatisfied with the regime. Why might this not be the case with superhuman intelligences in the far future? or we're guys in the medium future. Well, I said it also specifically with respect to things like security forces and the sort of sources of hard power, which can also include outside support. Oh, because you're not using, you might be using a real life. You can have a situation, like in human affairs, there are governments that are vigorously supported by a minority of the population, some narrow selector that gets treated especially well by the government will be unpopular with most of the people under their rule.

2:07:51in the end. We see a lot of examples of that and sometimes that can escalate to civil war when the means of power become more equally distributed or there's a foreign assistance is provided to the people who are on the losing end of that system. Yeah, going forward, I don't expect that definition to change. I think it will still it would be the case that a system that those who holds the guns and equivalent are opposed to, you know, is in a very difficult position. However, AI could change things pretty dramatically in terms of how security forces and police and administrators and legal systems are motivated.

2:08:48So right now we see with the GPT -3 or GPT -4 that you can get them to change their behavior on a dime. So there was someone who made right -wing GPT because they noticed that on political compass questionnaires, the baseline GPT -4 tended to give progressive San Francisco type of answers, which is in line with the sort of people who are providing reinforcement learning data and to some extent reflecting like the character of the internet. They're like, I don't like this. And so they did a little bit of fine tuning with some conservative data and then they were able to reverse the political biases of the system.

2:09:38If you take the initial helpfulness only trained models for some of these over, I think there's Enthropic and opening, I think, have published both some information about the sort of models trained only to do what users say and not train to follow ethical rules. And those models will behaviorally eagerly display their willingness to help design bombs or bio weapons or kill people or steal or commit all sorts of atrocities. And so if in the future, it's as easy to set the motivations, the actual underlying motivations of AI is, as it is right now, to set the behavior that they display that it means you could have AI's created.

2:10:30with almost whatever motivation people wish. And that could really drastically change political affairs because the ability to decide and determine the loyalties of the humans or AI's and robots that hold the guns, that hold together society, that ultimately back it against violent overthrow and such. Yeah, it's potentially a revolution in how societies work compared to the historical situation where security forces had to be drawn from some broader populations offered incentives and then the ongoing stability of the regime was dependent on whether they remained, you know, bought in to the system continuing.

2:11:28This is slightly off topic, but one thing I'm curious about is, how, what do the median, what is the sort of median far future outcome of AI look like? Do we get something that, when it has colonized the galaxy, is interested in sort of diverse ideas in beautiful projects, or do we get something that looks more like a paperbook of maximizer? Is there is there some reason to expect one or the other? I guess I'm asking is like, you know, there's like some potential value that is realizable within the matter of the scale. It's right. What is a default outcome? The median outcome look like compared to how good it things could be.

2:12:11Yeah, so as I was saying, I think more likely than not, there isn't an AI large, you know, some side of human institutions were improving along the way. I think there's some evidence that different people tend to like somewhat different things and some of that may persist over time rather than everyone coming to agree on one particular monoculture or like very repetitive thing, being the best thing to fill all of the available space with. So if that continues, that's like a, seems like a relatively likely way in which there is diversity. Although it's an entirely possible you could have that kind of diversity locally, maybe in the solar system, maybe in our galaxy, but if people have different views about, maybe people decide, yeah, there's one thing that's very good and I'll have a lot of that.

2:13:18Maybe it's people who are really happy or something and they wind up in distant regions which are hard to exploit for the benefit of people back home in the solar system or the Milky Way. They do something different than they do would do in the local environment. But at that point it's really a sort of very out on limb speculation about how human deliberation and cultural evolution would work and an interaction with introducing AIs and new kinds of mental modification and discovery into the process. But I think that a lot of reason to expect that you would have significant diversity for something coming out of our existing diverse human society.

2:14:10Yeah, one of the things I'm wondering is like listen, a lot of the diversity and change from human society seems to come from the fact that, you know, there's like rapid technological change, if you look at periods of history where I mean, I guess you could say like, I mean, you know what, compared to, sort of like galactic time skills, like, I'm together with societies progressing pretty fast. So once that sort of change is exhausted, where we've like discovered all the technologies, should we still expect things to be changing like that or would be expect some sort of set state of maybe like some hedonium you like you discover what is it like the most pleasurable configuration of matter and then you just make the whole galaxy into this.

2:14:52I mean, so that last point it would be only if people wound up thinking that was the thing to do broadly enough Yeah, with respect to the kind of cultural changes that come with technology. So things like the printing press, having high per capita income, we've had a lot of cultural changes downstream of those technological changes. And so then intelligence explosion, you're having an incredible amount of technological development coming really quick. And as that is assimilated, it probably would significantly affect our knowledge or understanding our attitudes, our abilities, and there'd be change, but that kind of accelerating change where you have doubling in four months, two months, one months, two weeks, obviously that very quickly exhausts itself and change becomes much slower and then relatively glacial when you're thinking about thousands, millions, billions of years, you can't have exponential financial economic growth or like huge technological revolutions every 10 years for a million years, that you hit physical limits, things slow down as you approach them.

2:16:06So that's that. So yeah, you'd have less of that turnover. But there are other things that are going to do cause ongoing change. So like fashion, fashion is frequency dependent. people want to get into a new fashion that is not already popular except among the fashion leaders. And then others copy that and then when it becomes popular you move onto the next and so. That's an ongoing process of continuous change. And so there could be various things like that that you're by your arching in a lot. But in cases where just the engine of change, like ongoing technological progress has gone. I don't think we should expect that.

2:16:50And in cases where it's possible to be either in a stable state or a sort of widely varying state that can wind up in stable attractors, then I think you should expect over time, you will wind up in one of the stable attractors or you will change how the system works so that you can't bounce into a stable attractor. And so like an example of that is if you're going to preserve democracy for a billion years, then you can't have it be the case that like one in, you know, one in 50 election cycles, you get a dictatorship and then the dictatorship programs the AI police to enforce it forever and to ensure that the society is always ruled by a copy of the dictator's mind and maybe that dictators mind re -adjusted fine tuned to remain committed to their original ideology.

2:17:50So if you're going to have this sort of dynamic liberal flexible changing society for a very long time, then the range of things that it's bouncing around and the different things it's trying and exploring have to not include the state of creating a dictatorship the locks itself in forever. In the same way, if you have the possibility of like a war with, you know, weapons of mass destruction that wipes out the civilization. If that happens, every thousand subjective years, which could be very, very quick, if we have AI's that think a thousand times is fast or a million times is fast, that would be, you know, just around the corner, in that case.

2:18:36And then you're like, no, this society is eventually going, perhaps very soon, if things are proceeding to FATs, it's going to wind up extinct. And then it's going to stop bouncing around. So you can have ongoing change and fluctuation for extraordinary timescales. If you have the process to drive the change ongoing, but you can't, if it sometimes bounces into states that just lock in and stay irrecoverable from that. and extinction is one of them, a dictatorship or sort of, you know, totalitarian regime that for bad, all further change would be another example. On that point, the rapid progress when the sort of intelligence explosion starts happening, where they're making like the kinds of progress that human civilization takes centuries to make in the span of, you know, days or weeks, what is the right way to see that, even if they are aligned?

2:19:30What is like the because in the context of alignment what we've been talking about so far is making sure they're honest But even if they're honest like okay, so they're like here sir honestly our intentions and you can tell us what Honest and appropriately motivated and so what is the appropriate Motivation or the per per per per per perancy like you know that you see that with this and then the thousand years of intellectual progress happen in the next week Well, what is what is the problem to enter? Well one thing might be that going at the maximal speed and doing things in months rather than even a few years.

2:20:05If you have the chance to slow things, losing a year or two seems worth it to have things to be a bit better managed than that. But I think that the big thing is that it condenses a lot of issues that we might otherwise if that would be over decades and centuries to happen in a very short period of time. And so that's scary because say if any of these, the technologies we might have developed with another few hundred years of human research. If any of them are really dangerous, so scary bioweapon things, maybe, yeah, other dangerous WMD, they hit us all very quickly. And if any of them causes trouble, then we have to face quite a lot of trouble per period.

2:20:56There's also this issue of if there's occasional wars or conflicts measured in subjective time, then if a few years or a thousand years or a million years of subjective time for these very fast minds that are operating at a much higher speed than humans, you don't want to have a situation where every thousand years there's a war or an expropriation of the humans from AI society. Therefore, we expect that like within a year, we'll be dead. We pretty, pretty bad to have the future compressed and there'd be such a, you know, a rate of catastrophic outcomes. So when we're speeding up and compressing the future, that gives us in the short term, even like, you know, human societies discount the future a lot.

2:21:49Don't pay attention to long -term problems, but the flip side to the scary parts of compressing a lot of the future, a lot of technological innovation, a lot of social change, is it brings what would otherwise be long -term issues into the short term where people are better at actually attending to them. And so people facing this problem of, well, will there be a violent expropriation or a civil war or a nuclear war, you know, in the next year because everything has been sped up by a thousandfold. And if their desire to avoid that is reason for them to set up systems and institutions that will very stably maintain invariance like no WMD war allowed.

2:22:33And so like a treaty to ban genocide, weapons of mass destruction war like that would be the kind of thing that becomes much more attractive if the alternative is not well, maybe that will happen in 50 years, maybe it'll happen in 100 years, if it's well, maybe it'll happen this year. Okay, so this is a pretty wild picture of the future, and this is one that many kinds of people you would expect to have integrated it into the world model have not. So I mean, the three main examples or the three main pieces of that outside view evidence, one can go at one is the market. So if there was going to be a huge period of economic growth caused by AI, or if the world was just going to collapse, in both cases, you would expect real interest rates to be higher because people will be barring from the future to spend now.

2:23:29The second sort of outside view perspective is that you can look at the predictions of superforecasters on Metaculars or something. And what is their median year estimate? Well, some of the Metaculis AGI questions actually have shockingly soon for AGI. There's a much larger differentiator there on the Metaculis forecasts of AI disaster and doom. Okay, okay more like a few a few percent or less rather than like 20 % and The third is that you know generally when you ask Many economists could an AGI cause rapid rapid economic growth They usually have some story about bottlenecks in the economy could prevent this kind of explosion of Of these kinds of feedback loops so So you have all these different pieces of outside view evidence.

2:24:32They're obviously different, so I'm sure you can take them in a new sequence you want. But what do you think is miscalibrating them? Yeah, so one, of course, there's some of those commons are the Metaculous AI timelines are relatively short. There's also, of course, the surveys of AI experts conducted at some of the ML conferences, which have definitely longer times to AI more several decades in the future. Although you can ask the questions in ways that elicit very different answers and show most of the respondents are not thinking super hard about their answers. It looks like now close in the recent AI surveys close to half, we're putting around 10 % risk of an outcome from AI.

2:25:26Close to as bad as human extinction. And then another large chunk like 5%. So that was the median. So I'd say compared to the typical AI expert, I am estimating a higher risk. Oh, also on the topic of takeoff and the AI expert survey, I think the general argument for intelligence explosion, I think commanded majority support, but not a large majority. So it means I'm closer on that front and then of course there's at the beginning I mentioned these great, these greats of computing, the founders would be like, Alan Torrey and Van Neumann And then today, you have people like Jeff Hinton saying, saying these things or the people at OpenAI and DeepMind are making noises suggesting timelines in line with what we've discussed and saying serious risk apocalyptic outcomes from them.

2:26:34So there's some other sources of evidence there. But I do acknowledge and it's important to say and engage with and see what it means that these views are like our contrarian, not widely held in particular the sort of detailed models that I've been working with are not something that most people are almost anyone is examining these problems through. So, you do find parts of similar analyses, people in AI labs, there's been other work. I mentioned more of that in Kurzweil earlier. Also, I've been a number of papers doing various kinds of economic modeling. So, standard economic growth models when you input AI -related parameters commonly predict explosive growth.

2:27:28And so there's a divide between what the models say. And especially what the models say with these empirical values derived from the actual field of that, that link up has not been done even by the economists working on AI largely, which is one reason for the report from Open Philanthropy by Tom Davidson building on these models and putting that out for review, discussion, engagement and communication on these ideas. So part of it is, yeah, I want to raise these issues. It's one of the things that came on the podcast. And then they have the opportunity to actually examine the arguments and evidence and engage with it.

2:28:09I do predict that over time, the things will be more adopted as AI developments become more clear. Obviously, that's a coherence condition of believing the things to be true. So if you think that society can see, think, when the questions are resolved, which seems likely. So would you predict, for example, that interest rates were like groups in the coming years? Yeah, so I think at some point, so in the case, we were talking about where there are visible, so this intelligence explosion happening in software, to the extent that investors are noticing that, Yeah, they should be willing to lend money or make equity investments in these firms or demanding extremely high interest rates because if it's possible to turn capital into twice as much capital in a relatively short period and then more shortly after that, then yeah, you should demand a much higher return and competition.

2:29:17if there's, assuming there's competition among companies or coalitions for resources, whether that's investment or ownership of cloud compute, as it's called, compute made available to a particular AI development effort, could be quite in demand. But what that would happen before you have so much investor cash making purchases and sales on this basis, you would first see it in things like the valuations of the AI companies, evaluations of AI chip makers, and so far there have been effects. So some years ago in the 2010s, I did some analysis with other people of if this kind of picture happens, then which are the firms and parts of the economy that would benefit.

2:30:11And so there's the makers of chip equipment, companies like Asml, there's the fabs like the SMC, there's chip designers like Nvidia, or the component of Google that does things like design the TPU. And then their company's working on the software. So the big tech giants and also companies like opening eye and deep mind. And in general, the portfolio picking that those has done well, it's done better than the market because everyone can see there's been an AI boom. But it's obviously far short of what you would get if you predicted this is going to go to be like on the scale of the global economy and the global economy is going to be skyrocketing into the stratosphere within 10 years.

2:31:00If that were the case, then collectively these AI companies should be worth a large fraction of the global portfolio. And so I embraced the criticism that this is indeed contrary to the efficient market hypothesis. I think it's a true hypothesis that the market is in the course of updating on in the same way that coming into the topic in 2000 that yes, the the strong case, even an old case that AI will eventually be the biggest thing in the world. It's kind of crazy that the investment in it is so small. And over the last 10 years, we've seen the tech industry and academia sort of realize, yeah, they were wildly under investing and just throwing compute and effort into these AI models.

2:31:56And particularly, like letting the neural network connectious connectionist paradigm kind of language in the AI winter. And so yeah, I expect that process to continue. Has it's done over several orders of magnitude of scale up and I expect at the later end of that scale, which the market is partially already pricing in, it's going to go further than the market expects. Has your portfolio since then, Alice has been doing that many years ago changed? Are the companies you identified then still the ones that seem most likely benefit from the AABOOM? I mean, a general issue with sort of tracking that kind of thing, a new company's coming.

2:32:37So like, OpenAI did not exist, Anthropic did not exist, and a number of things. It's a personal portfolio. I do not invest in any AI labs for conflict of interest reasons. I have invested in the broader industry. I don't think that the conflict issues are very significant because of their enormous companies. Their cost of capital is not particularly affected by marginal investment. And I'm not really in a... Yeah, I have less concern that I might find myself in a conflict of interest situation there. I'm going to curious about But with the day in the life of somebody like you looks like, I mean, if you listen to this conversation, however many hours of it it's been, we've gotten thoughts that were for me incredibly insightful and novel about everything from primate evolution to geopolitics to, you know, what sorts of improvements are plausible with language models.

2:33:46So, you know, there's like a huge variety of topics that you are studying and investigating. Are you just like reading all day? Like, what is it? Well, what happens when you wake up? You just like pick up a paper? Yeah, so I'd say you're someone getting the benefit of the fact that I've done fewer podcasts. And so I have a backlog of things that have not shown up in publications yet. But yes, also, I've had a very weird professional career. that is involved a much, much higher proportion than his normal trying to build more comprehensive models of the world. And so that is included being more of a journalist trying to get on understanding of many issues and many problems that had not yet been widely addressed but do a first pass and a second pass dive into them.

2:34:40And just having spent years of my life working on that, you know, some of it accumulates. In terms of what is a day in the life, how do I go about it? So one is just keeping abreast of literature on a lot of these topics, reading books and academic works on them, doing my approach compared to some other people in forecasting and assessing some of the things. I try to obtain and rely on more any data that I can find that is relevant. I try early and often to find factual information that bears on some of the questions I've got, especially in a quantitative fashion. Do the basic arithmetic and consistency checks and check sums on a hypothesis about the world?

2:35:36do that early and often. And I find that's that's quite fruitful and that people don't do it enough. But so things like with the economic growth, just when someone mentions the diminishing returns, I immediately ask, hmm, okay, so you have two exponential processes. What's the ratio between the Dublin you get on the output versus the input and find, oh yeah, actually it's interesting the for computing and information technology and AI software it's well on the one side. There are other technologies that are closer to neutral. And so whenever I can go from here's a vague qualitative consideration in one direction and here's a vague qualitative consideration in the calculations back of the envelope calculations.

2:36:33And see, like, can I get a consistent picture of the world being one way, the world being another? Also compared to some I try, I try to be exhaustive more. So I'm very interested in finding things like taxonomies of the world where I can go systematically through all of the possibilities. So for example, my work with open philanthropy and previously on global catastrophic risks. I wanna make sure I'm not missing any big thing, anything that could be the biggest thing. Anyway, I won't wound up mostly focused on AI, but there have been other things that have been raised as candidates and people sometimes say, I think falsely, oh yeah, this is just another DoomJ story.

2:37:22you know, there must be hundreds of those. And so I would do things like go through all of the different major scientific fields, you know, from anthropology to biology, chemistry, computer science, physics, what are the doom stories, or like candidates for big things associated with each of these fields. go through the industries that the US economic statistics agencies recognize and say for each of these industries is there something associated with them. Go through all of the lists that people have made before of threats of doom, search for previous literature of people who have done discussions and then yeah have a big spreadsheet of what the candidates are and some other colleagues have done work of this sort as well.

2:38:16And just go through each of them, see how they check out. And it turned out doing that kind of exercise found that actually the distribution of candidates for risks of global catastrophe. It was very skewed. There were a lot of things that have been mentioned in the media as like a potential doomsday story. So things like, oh, something is happening to the bees, will that be the end of humanity? And this gets to the media, but if you trek it through, well, okay, no, there's, yeah, there are infestations in bee populations are causing local collapses, they can then be sort of easily reversed. They just breed some more or do some other things to treat this.

2:39:01And even if all the honey bees were extinguished immediately, the plants that they pollinate actually don't account for much of human nutrition, you could swap the arable land with others, and there would be other ways to pollinate and support the things. And so, at the media level, there were many tales of, ah, here's a Doomsday story. When you go further to the scientists and were there arguments for it to actually check out, it was not there. But by actually systematically looking through many of these candidates, I wound up in a different epistemic situation than someone who's just buffeted by news reports and they see article after article that is claiming something is going to destroy the world and it turns out it's like by way of headline grabbing and attempts by media to like overinterpret something that was said by some activists who was trying to overinterpret some real phenomenon and then most of these go away and then a few things things like nuclear war biological weapons, artificial intelligence, check out more strongly.

2:40:08And when you wait, things like what do experts in the field think, what kind of evidence can they muster? Yeah, you find this extremely skewed distribution. And I found that was a really valuable benefit of doing those deep dive investigations into many things in a systematic way. Because now I can answer actually the sort of a loose agnostic who knows that all this nonsense by diving deeply. I really enjoy talking to people with a big picture of thesis on the podcast and interviewing them. But one thing that I've noticed and is not satisfying is that often they come from a very philosophical or biose perspective.

2:40:53This is useful in certain contexts, but there's basically maybe three people in the entire world who have the sort of very rigorous and scientific approach to thinking about the whole picture. Early, it's like three people I'm aware of, maybe like two. And yeah, I mean, it's like something I also, there's like no, I guess, university or existing academic discipline for people who are trying to come up with a big picture. and so there's no established standards since up people can. I hear you. This is a problem. And this is an experience also with a lot of the, I mean, I think Holden was mentioning this in your previous episode with a lot of the World's Investigations work.

2:41:40These are questions where there is no academic field whose job it is to work on these and has norms that allow making at best efforts go at it. often academic norms will allow only plucking off narrow pieces that might contribute to answering a big question. But the problem of actually assembling what science knows that bears on some important question that people care about the answer to, it falls through the crack. There's no discipline to do that job. So you have countless academics and researchers building up local pieces of the thing. And yet people don't follow the hamming questions this, you know, West the most important problem in your field, where are you working on it?

2:42:25I mean, that one actually might not work because if the field boundaries are defined too nearly, you know, you'll leave it out. But yeah, there are important problems for the world as a whole that it's, it's sadly not the job of like, you know, a large professionalized academic field or organization to do. And hopefully that's something that can change in the future. But for my career, it's been a matter of taking low -hanging fruit of important questions that sadly people haven't invested in doing the basic analysis on. So I think I was trying to think about more recently for the podcast is I would like to have a better world model after doing an interview.

2:43:07And often I feel like I do, in some cases, after some interviews I feel like, oh, that was entertaining. But like, do I fundamentally have a better prediction of what the world looks like like in, you know, 2 ,200 or 2 ,100, or like at least what counterfactuals are ruled out or something. I'm curious if you have like advice on first identifying the kinds of thinkers and topics which will contribute to a more concrete understanding of the world and second how to go about analyzing their main idea as an way that concretely adds to that picture. Like this is a great episode, right? This is like literally the top in terms of contributing to my world model in terms of all the episodes I've done.

2:43:47How do I find more of these? Glad to hear that. One general heuristic is to find ways to hue closer to sort of, yeah, I think that are a rich and sort of bodies of established knowledge and less unpunditry. I don't know how you've been navigating that so far. But so, learning from textbooks and the sort of the thing that were the leading papers and people of past era as I think rather than being too attentive to current new cycles is quite valuable. Yeah, I don't usually have the experience of here is a, you know, someone doing things very systematically over a huge area, I can just read all of their stuff and then absorb it and then I'm sad.

2:44:48Except there are a lot of lots of people who do wonderful works on in their own fields and some of those fields are broader than others. I think I would wind up giving a lot of recommendations of just like great particular works and particular explorations of an issue or history. Do you have that somewhere? This list. Vacla of Smeele's books. I don't, I think I often disagree with some of his methods of synthesis, but I enjoy his books forgiving pictures of a lot of interesting relevant facts about how the world works. I would cite some of Joel Mokir's work on the history of the scientific revolution and how that interacted with economic growth.

2:45:54An example of collecting a lot of evidence, a lot of interesting valuable assessment there. I think in the space of AI forecasting, one person I would recommend going back to is the work of Hans Moravak. It was not always the most precise or reliable, but an incredible number of So brilliant innovative ideas can one of that. And I think he was someone who really grok'd a lot of the arguments for a more sort of compute centric way of thinking about what was happening with AI very early on. He was writing stuff in the 70s, maybe even earlier, but at least in the 70s, 80s, 90s. So it's book of mine, Children of his early academic papers, fascinating.

2:46:49Not necessarily for the methodology I've been talking about, but for exploring the substantive topics that we were discussing in the episode. Is a Malthusian state inevitable in the long run? Nature in general is in Malthusian states.

2:47:05And that can mean organisms that are typically struggling for food. It can mean typically struggling at a margin of how the population density rises. They kill each other more often. Contestant for that can mean frequency dependent disease, such as different ant species, become more common in an area that their species -specific diseases swoop through them. And the general process is, yeah, you have some things that can replicate and expand, and they do that until they can't do it anymore. and that means there's some limiting factor that can't keep up. That don't necessarily have to apply to human civilization.

2:47:48It's possible for there to be like collective norm setting that blocks evolution towards maximum reproduction. So right now human fertility is often sub replacement. And if you sort of extrapolated the fertility falls that come with economic development and education, then you would think, okay, yeah, well the total fertility rate will fall below replacement. And then humanity after some number of generations will go extinct because every generation will be smaller than the previous one. Now, pretty obviously that's not going to happen. One reason is because we'll produce artificial intelligence, which can replicate at extremely rapid rates.

2:48:38I may do it because they're asked or programmed to or wish to gain some benefit and they can pay for their creation and pay back the resources needed to create them very, very quickly. And so, yeah, financing for that reproduction is easy. And if you have one AI system that chooses to replicate in that way, or some organization or institution or society that chooses to create some AI's that are willing to be replicated, that can expand to make use of any amount of natural resources that can support them and to do more work produce more economic value. And so, you know, it's like, well, what limits will limit population growth, given these selective pressures, where if even one individual wants to replicate a lot, they can do so.

2:49:37Incessantly, so that could be individually resource limited. So it could be that individuals and organizations have some endowment of natural resources. And they can't get one another's endowments. And so some choose to have many offspring or produce many AIs. And then the natural resources that they possess are subdivided among a greater population while in another jurisdiction or another individual may choose not to subdivide their wealth. And in that case, you have mouthhousies in the sense that within some particular jurisdiction risk or property rights. You have a population that has increased up until some limiting factor, which could be like they are literally using all of their resources.

2:50:28They have nothing left for things like defense or economic investment or it could be something that's more like if you invested more natural resources into population it would come at the expense of something else necessary, including military resources if you're in a competitive situation where there remains war and anarchy and there aren't secure property rights to maintain wealth in place. If you have a situation where there's pooling of resources, for example, say you have a universal basic income that's funded by taxation of natural resources. And then it's distributed evenly to like every mind above a certain sort of scale of complexity per unit time.

2:51:18So each second of mind exists to get some and such an allocation. In that case, then, all right, well, those who replicate as much as they can afford with this income, do it. and increase their population approximately immediately until the funds for the universal basic income from the natural resource taxation divided by the set of recipients is just barely enough to pay for the existence of one more mind. And so it's, there's like a mouthfulsian element and that this income has been reduced to near the AI subsistence level or the subsistence level of whatever qualifies for the subsidy. given that this all happens almost immediately.

2:52:06You know, people who might otherwise have enjoyed the basic income may object and say, no, no, this is no good. And they might respond by saying, well, something like the subdivision before, maybe there's a restriction, there's a distribution of wealth. And then when one has a child, there's a requirement that one gives them a certain minimum quantity of resources. and when doesn't have the resources to give them that minimum standard of living or standard of wealth. Yeah, when I can do that because of child slash AI, welfare laws. Or you could have a system that is more accepting of diversity and preferences.

2:52:52And so you have some societies or some jurisdictions or families that go the route of having many people with less natural resources. is per person, and others that go a direction of having fewer people and more natural resources per person. And they just coexist. But sort of how much of each you get depends on how attached people are to things that don't work with separate policies for separate jurisdictions, things like global redistribution that's ongoing continuously versus the sort of infringements on autonomy if you're saying that a mind can't be created even though it has a standard of living that's far better than ours because of the advanced technology of the time.

2:53:44Because it would reduce the average per capita income, my head would be more capita around. Yeah, then that would pull in the other direction. That's the kind of values judgment and social coordination problem that people would have to negotiate for and things like democracy and international relations and sovereignty would apply to help solve them. What would warfare in space look like? Would offense or defense have the advantage? Would the equilibrium set by mutually assured destruction still be applicable? Just generally, what is the picture of? Well, the extreme difference is that things outside, especially outside the solar system, things are very far apart and there's a speed of light limit and to get close to the speed of light limit you have to use an enormous amount of energy.

2:54:38And so there would be that would tend to, in some ways, could favor the, favor the defender because you have something that's coming in at a large fraction of the speed of light and it hits a grain of dust and it explodes. codes, and the amount of matter you can send to another galaxy or distant star for a given amount of reaction mass and energy input is limited. So, it's hard to send an amount of military material to another location of what can be present there already locally. That would seem like it would make it harder for the attacker between stars or between galaxies. But there are a lot of other considerations.

2:55:28One thing is the extent to which the matter in a region can be harnessed all at once. So you have a lot of mass and energy in a star, but it's only being doled out over billions of years because hydrogen fusion exceedingly hard outside of a star. It's a very, very slow and difficult reaction. And if you can't turn the star into energy faster, then it's this huge resource that will be worthwhile for billions of years. And so even very inefficiently attacking a solar system to acquire the stuff that's there could pay off. So if it takes a thousand years of a star's output to launch an attack on another star and then you hold it for a billion years after that.

2:56:25Then it can be the case that just like a larger surrounding attacker might be able to even very inefficiently send attacks that like a civilization that was small but accessible. And if you can quickly burn the resources that the attacker might want to acquire, if you can put stars into black holes and extract most of the usable energy before the attacker can take them over, then it would be like scorched earth. It's like most of what you were trying to capture could be expended on military material to fight you, and you don't actually get much those worthwhile, and you paid a lot to do it. That favor the defense.

2:57:09And at this level, it's pretty challenging to net out all the factors, including all the future technologies. The burden of interstellar attack being just quite high compared to our conventional things seems real. But at the level of over millions of years, Wayne and that thing does it result in, is aggressive conquest or not, or is every star or galaxy, you know, approximately impermanable, impermanable enough not to be worth attacking. I'm not going to say I know the answer. Okay, final question. How do you think about info hazards when talking about your work? So obviously if there's a risk, you want to warn people about it, but you don't want to give careless or potentially like homicidal people ideas, I, as there was on the podcast, he, um, and talking about the people who have been developing AI, inspired by his ideas.

2:58:12He said, like, you know, these are idiot disaster monkeys who have, you know, want to be the ones to pluck the deadly fruit. Anyways, how do you think about obviously the work you're doing involves many into hazard, I'm sure. Uh, how do you think about when and where to spread them? Yeah. And so I think, I think they're real concerns of that type. I think it's true that AI progress has probably been accelerated by efforts like Bostrom's publication of superintelligence to try and get the world to sort of pay attention to these problems in advance and prepare. I think I disagree with Elias or that like that has been on the whole bad.

2:58:54I think the situation is in some important ways looking a lot better than ways alternative ways it could have been. I think it's important that you have several of the leading AI labs making not only significant lip service, but also some investments in things like technical alignment research providing significant public support for the idea that these are the risks of truly apocalyptic disasters are real. I think the fact that the leaders of OpenAI, DeepMind, and Anthropic all make that point. They were recently all invited along with other tech CEOs to the White House to discuss AI regulation.

2:59:45And I think you could tell an alternative story where a larger share of the leading companies in AI are led by people who take a completely dismissive denialist view. And you see some companies that do have a chance more like that today. Yeah, and so a world where several of the leading companies are making meaningful efforts and do a lot to criticize could they be doing more and better and what have been the negative effects of some of the things they've done. But compared to a world where even though AI would be reaching where it's going a few years later, those seem like significant benefits.

3:00:29And if you didn't have this kind of public communication, you would have had fewer people going into things like AI policy, alignment research by this point. And it would be harder to mobilize these resources to try and address the problem when AI would eventually be developed, not that much later proportionately. And so yeah, I don't know that the attempting to have public discussion understanding has been a disaster. I have been reluctant in the past to discuss some of the aspects of intelligence explosion, things like the concrete details of AI takeover before, because of concern, about this sort of problem where people who only see the international relations aspects, and zero sum and negative sum competition, and not enough attention to the mutual destruction, and sort of senseless, deadweight loss from that kind of conflict.

3:01:29At this point, we seem close compared to what I would have thought a decade or so ago to these kinds of really advanced AI capabilities. They are pretty central in policy discussion and becoming more so. And so the opportunity to delay understanding and whatnot, there's a question of for what. And I think there was there were gains of like building the AI alignment field building various kinds of support and understanding for action. Those had had real value and some additional delay could have given more time for that. But from where we are at some point, I think it's absolutely essential that governments get together at least to restrict disastrous reckless compromising of some of the safety and alignment issues.

3:02:22has we go into the intelligence explosion. And so moving the locus of the sort of collective action problem from numerous profit -oriented companies, acting against one another's interest by compromising safety, too, some governments and large international coalitions of governments who can set common rules and common safety standards, what's this into a much better situation. And that requires a broader understanding of the strategic situation, the position they'll be in. If we try and remain quiet about the problem, they're actually going to be facing. I think it can result in a lot of confusion.

3:03:07So for example, the potential military applications of advanced AI are going to be one of the factors that is pulling political leaders to do the thing the older result in their own destruction and the overthrow of their governments. If we characterize it as, oh, things will just be a matter of, you know, you lose chat bots and some, you know, minor things that no one cares about in an exchange to avoid any risk of the world ending catastrophe. I think that picture leads to a misunderstanding And it will make people think that you need less in the way of preparation, things like alignment so you can actually navigate the thing, verifiability for international agreements or things to have enough breathing room to have caution and slow down not necessarily right now.

3:04:07I mean, although that could be valuable, but when it's so important, when you have AI that is approaching the ability to really automate AI research and things would otherwise be proceeding absurdly fast, far faster than we can handle on far faster than we should want. And so, yeah, at this point, I'm moving towards the share model of the world, try and get people to understand and do the right thing. And there's some evidence of progress on that front. The, you know, things like the statements and movements by Jeff Hinton are inspiring some of the engagement by political figures. You know, is reason for optimism relative to worse alternatives that could have been.

3:04:58And yes, the contrary view is present. It's all about geopolitical competition, never hold back a technological advance. And in general, I love many technological advances that people, I think, are unreasonably down on, nuclear power, genetically modified crops, garyada, bioweapons, and AGI capable of destroying human civilization are really my two exceptions. And yeah, we've got to deal with these issues and the paths that I see to handling them successfully involve key policy makers and to some extent and the expert communities and the public and electorate rocking the situation that they're in and responding appropriately.

3:05:50Well, it's true on earth that one of the places is you've decided to explore this model is on the Lunar Society podcast. And the losers might not appreciate because this episode might be split up in a different parts. The listeners might not appreciate how much stamina you've displayed here, but I think we've been going for what? Eight, nine hours or something straight. So it's been incredibly interesting. Other than Google's scholar tapping in Carl Schollman, where else can people find your work? You have your blog, can you? Yeah, I have a blog reflective of disequilibrium. And a new site in the works and I have an older one which you can also find.

3:06:26I just googling reflective to SQL Abram. Okay, excellent, excellent. All right, Carl, this is a pleasure. It's safe to say the most interesting episode I've done so far. So yeah, thanks. Thank you for having me. Hey everybody, I hope you enjoyed that episode. As always, the most helpful thing you can do is just share the podcast. then did to people you think might enjoy it, put it in Twitter, your group chats, etc. Just blitz the world. I appreciate your listening. I'll see you next time. Cheers.