# 210

### Preamble: Delta vs Crux

I don’t natively think in terms of cruxes. But there’s a similar concept which is more natural for me, which I’ll call a delta.

Imagine that you and I each model the world (or some part of it) as implementing some program. Very oversimplified example: if I learn that e.g. it’s cloudy today, that means the “weather” variable in my program at a particular time[1] takes on the value “cloudy”. Now, suppose your program and my program are exactly the same, except that somewhere in there I think a certain parameter has value 5 and you think it has value 0.3. Even though our programs differ in only that one little spot, we might still expect very different values of lots of variables during execution - in other words, we might have very different beliefs about lots of stuff in the world.

If your model and my model differ in that way, and we’re trying to discuss our different beliefs, then the obvious useful thing-to-do is figure out where that one-parameter difference is.

That’s a delta: one or a few relatively “small”/local differences in belief, which when propagated through our models account for most of the differences in our beliefs.

For those familiar with Pearl-style causal models: think of a delta as one or a few do() operations which suffice to make my model basically match somebody else’s model, or vice versa.

This post is about my current best guesses at the delta between my AI models and Yudkowsky's AI models. When I apply the delta outlined here to my models, and propagate the implications, my models basically look like Yudkowsky’s as far as I can tell. That said, note that this is not an attempt to pass Eliezer's Intellectual Turing Test; I'll still be using my own usual frames.

This post might turn into a sequence if there's interest; I already have another one written for Christiano, and people are welcome to suggest others they'd be interested in.

## My AI Model Delta Compared To Yudkowsky

Best guess: Eliezer basically rejects the natural abstraction hypothesis. He mostly expects AI to use internal ontologies fundamentally alien to the ontologies of humans, at least in the places which matter. Lethality #33 lays it out succinctly:

33.  The AI does not think like you do, the AI doesn't have thoughts built up from the same concepts you use, it is utterly alien on a staggering scale.  Nobody knows what the hell GPT-3 is thinking, not only because the matrices are opaque, but because the stuff within that opaque container is, very likely, incredibly alien - nothing that would translate well into comprehensible human thinking, even if we could see past the giant wall of floating-point numbers to what lay behind.

What do my models look like if I propagate that delta? In worlds where natural abstraction basically fails, we are thoroughly and utterly fucked, and a 99% probability of doom strikes me as entirely reasonable and justified.

Here’s one oversimplified doom argument/story in a world where natural abstraction fails hard:

1. Humanity is going to build superhuman goal-optimizing agents. (‘Cause, like, obviously somebody’s going to do that, there’s no shortage of capabilities researchers loudly advertising that they’re aiming to do that exact thing.) These will be so vastly more powerful than humans that we have basically-zero bargaining power except insofar as AIs are aligned to our interests.
2. We’re assuming natural abstraction basically fails, so those AI systems will have fundamentally alien internal ontologies. For purposes of this overcompressed version of the argument, we’ll assume a very extreme failure of natural abstraction, such that human concepts cannot be faithfully and robustly translated into the system’s internal ontology at all. (For instance, maybe a faithful and robust translation would be so long in the system’s “internal language” that the translation wouldn’t fit in the system.)
3. Then:
1. Obviously full value alignment is out.
2. Robust and faithful instruction following or “do what I mean” is out; the meaning of human words/concepts can’t be robustly and faithfully represented in the system’s internal ontology at all.
3. Corrigibility is out, unless (here lies one of Eliezer’s hopes) corrigibility turns out to be such a natural concept that it can faithfully and robustly translate even into the ontology of a very alien AI.
4. Insofar as an AI cares-as-a-terminal-goal about keeping humans around, it will care about its own alien conception of “humans” which does not match ours, and will happily replace us with less resource-intensive (or otherwise preferable) things which we would not consider “human”.
5. Interpretability is, at best, some weak correlative heuristics which won’t generalize well. The lack of 99% reliability in mechinterp is not just because our current methods are primitive.
6. Etc, etc. All of the technical alignment hopes are out, unless we posit some objective natural enough that it can be faithfully and robustly translated into the AI’s internal ontology despite the alien-ness.
4. It’s not like this gets any better over time; if anything, AIs’ internal ontologies just keep getting more alien as their power level ramps up.
5. … so we die as soon as one of these superhuman goal-optimizing agents applies enough optimization pressure to the world and the faithfulness/robustness of the translation fails. (Actually, Eliezer expects, we’re likely to die of easier problems before then, but even if our species’ competence is far higher than currently seems, the translation problem would kill us.)
6. As an added bonus, the AIs will know all this (‘cause, y’know, they’re smart), will therefore know that divergence between their goals and humans’ goals is inevitable (because their goals are in fundamentally alien ontologies and therefore will diverge out-of-distribution), and will therefore be incentivized to strategically hide their long-term intentions until it’s time for the humans to go.

Note that the “oversimplification” of the argument mostly happened at step 2; the actual expectation here would be that a faithful and robust translation of human concepts is long in the AI’s internal language, which means we would need very high precision in order to instill the translation. But that gets into a whole other long discussion.

By contrast, in a world where natural abstraction basically works, the bulk of human concepts can be faithfully and robustly translated into the internal ontology of a strong AI (and the translation isn't super-long). So, all those technical alignment possibilities are back on the table.

That hopefully gives a rough idea of how my models change when I flip the natural abstraction bit. It accounts for most of the currently-known-to-me places where my models diverge from Eliezer’s. I put nontrivial weight (maybe about 10-20%) on the hypothesis that Eliezer is basically correct on this delta, though it’s not my median expectation.

1. ^

particular time = particular point in the unrolled execution of the program

# 210

New Comment
Some comments are truncated due to high volume. Change truncation settings

I think that the AI's internal ontology is liable to have some noticeable alignments to human ontology w/r/t the purely predictive aspects of the natural world; it wouldn't surprise me to find distinct thoughts in there about electrons.  As the internal ontology goes to be more about affordances and actions, I expect to find increasing disalignment.  As the internal ontology takes on any reflective aspects, parts of the representation that mix with facts about the AI's internals, I expect to find much larger differences -- not just that the AI has a different concept boundary around "easy to understand", say, but that it maybe doesn't have any such internal notion as "easy to understand" at all, because easiness isn't in the environment and the AI doesn't have any such thing as "effort".  Maybe it's got categories around yieldingness to seven different categories of methods, and/or some general notion of "can predict at all / can't predict at all", but no general notion that maps onto human "easy to understand" -- though "easy to understand" is plausibly general-enough that I wouldn't be unsurprised to find a mapping after all.

Corrigibility and actual human values ar...

So, would you also say that two random humans are likely to have similar misalignment problems w.r.t. each other? E.g. my brain is different from yours, so the concepts I associate with words like "be helpful" and "don't betray Eliezer" and so forth are going to be different from the concepts you associate with those words, and in some cases there might be strings of words that are meaningful to you but totally meaningless to me, and therefore if you are the principal and I am your agent, and we totally avoid problem #2 (in which you give me instructions and I just don't follow them, even the as-interpreted-by-me version of them) you are still screwed? (Provided the power differential between us is big enough?)

Entirely separately, I have concerns about the ability of ML-based technology to robustly point the AI in any builder-intended direction whatsoever, even if there exists some not-too-large adequate mapping from that intended direction onto the AI's internal ontology at training time.  My guess is that more of the disagreement lies here.

I doubt much disagreement between you and I lies there, because I do not expect ML-style training to robustly point an AI in any builder-intended direction. My hopes generally don't route through targeting via ML-style training.

I do think my deltas from many other people lie there - e.g. that's why I'm nowhere near as optimistic as Quintin - so that's also where I'd expect much of your disagreement with those other people to lie.

7Keenan Pepper
Okay so where do most of your hopes route through then?

There isn't really one specific thing, since we don't yet know what the next ML/AI paradigm will look like, other than that some kind of neural net will probably be involved somehow. (My median expectation is that we're ~1 transformers-level paradigm shift away from the things which take off.) But as a relatively-legible example of a targeting technique my hopes might route through: Retargeting The Search.

Corrigibility and actual human values are both heavily reflective concepts.  If you master a requisite level of the prerequisite skill of noticing when a concept definition has a step where its boundary depends on your own internals rather than pure facts about the environment -- which of course most people can't do because they project the category boundary onto the environment

Actual human values depend on human internals, but predictions about systems that strongly couple to human behavior depend on human internals as well. I thus expect efficient representations of systems that strongly couple to human behavior to include human values as somewhat explicit variables. I expect this because humans seem agent-like enough that modeling them as trying to optimize for some set of goals is a computationally efficient heuristic in the toolbox for predicting humans.

At lower confidence, I also think human expected-value-trajectory-under-additional-somewhat-coherent-reflection would show up explicitly in the thoughts of AIs that try to predict systems strongly coupled to humans. I think this because humans seem to change their values enough over time in a sufficiently coherent fa...

2xpym
Sure, but the sort of thing that people actually optimize for (revealed preferences) tends to be very different from what they proclaim to be their values. This is a point not often raised in polite conversation, but to me it's a key reason for the thing people call "value alignment" being incoherent in the first place.
5Lucius Bushnaq
I kind of expect that things-people-call-their-values-that-are-not-their-revealed-preferences would be a concept that a smart AI that predicts systems coupled to humans would think in as well. It doesn't matter whether these stated values are 'incoherent' in the sense of not being in tune with actual human behavior, they're useful for modelling humans because humans use them to model themselves, and these self-models couple to their behavior. Even if they don't couple in the sense of being the revealed-preferences in an agentic model of the humans' actions. Every time a human tries and mostly fails to explain what things they'd like to value if only they were more internally coherent and thought harder about things, a predictor trying to forecast their words and future downstream actions has a much easier time of it if they have a crisp operationalization of the endpoint the human is failing to operationalize.  An analogy: If you're trying to predict what sorts of errors a diverse range of students might make while trying to solve a math problem, it helps to know what the correct answer is. Or if there isn't a single correct answer, what the space of valid answers looks like.
1xpym
Oh, sure, I agree that an ASI would understand all of that well enough, but even if it wanted to, it wouldn't be able to give us either all of what we think we want, or what we would endorse in some hypothetical enlightened way, because neither of those things comprise a coherent framework that robustly generalizes far out-of-distribution for human circumstances, even for one person, never mind the whole of humanity. The best we could hope for is that some-true-core-of-us-or-whatever would generalize in such way, the AI recognizes this and propagates that while sacrificing inessential contradictory parts. But given that our current state of moral philosophy is hopelessly out of its depth relative to this, to the extent that people rarely even acknowledge these issues, trusting that AI would get this right seems like a desperate gamble to me, even granting that we somehow could make it want to. Of course, it doesn't look like we would get to choose not to get subjected a gamble of this sort even if more people were aware of it, so maybe it's better for them to remain in blissful ignorance for now.
3Ebenezer Dukakis
If I encountered an intelligent extraterrestrial species, in principle I think I could learn to predict fairly well things like what it finds easy to understand, what its values are, and what it considers to be ethical behavior, without using any of the cognitive machinery I use to self-reflect. Humans tend to reason about other humans by asking "what would I think if I was in their situation", but in principle an AI doesn't have to work that way. But perhaps you think there are strong reasons why this would happen in practice? Supposing we had strong reasons to believe that an AI system wasn't self-aware and wasn't capable of self-reflection. So it can look over a plan it generated and reason about its understandability, corrigibility, impact on human values, etc. without any reflective aspects. Does that make alignment any easier according to you? Supposing the AI lacks a concept of "easy to understand", as you hypothesize. Does it seem reasonable to think that it might not be all that great at convincing a gatekeeper to unbox it, since it might focus on super complex arguments which humans can't understand? Is this mostly about mesa-optimizers, or something else?
1Valerio
It could be worth exploring reflection in transparency-based AIs, the internals of which are observable. We can train a learning AI, which only learns concepts by grounding them on the AI's internals (consider the example of a language-based AI learning a representation linking saying words and its output procedure). Even if AI-learned concepts do not coincide with human concepts, because the AI's internals greatly differ from human experience (e.g. a notion of "easy to understand" assuming only a metaphoric meaning for an AI), AI-learned concepts remain interpretable to the programmer of the AI given the transparency of the AI (and the programmer of the AI could engineer control mechanisms to deal with disalignment). In other words, there will be unnatural abstractions, but they will be discoverable on the condition of training a different kind of AI - as opposed to current methods which are not inherently interpretable. This is monumental work, but desperately needed work

This post might turn into a sequence if there's interest; I already have another one written for Christiano, and people are welcome to suggest others they'd be interested in.

Consider this my vote to turn it into a sequence, and to go on for as long as you can. I would be interested in one for Chris Olah, as well as the AI Optimists.

The AI Optimists (i.e. the people in the associated Discord server) have a lot of internal disagreement[1], to the point that I don't think it's meaningful to talk about the delta between John and them.  That said, I would be interested in specific deltas e.g. with @TurnTrout, in part because he thought we'd get death by default and now doesn't think that, has distanced himself from LW, and if he replies, is more likely to have a productive argument w/ John than Quintin Pope or Nora Belrose would. Not because he's better, but because I think John and him would be more legible to each other.

1. ^

Source: I'm on the AI Optimists Discord server and haven't seen much to alter my prior belief that  ~ everyone in alignment disagrees with everyone else.

2Garrett Baker
This particular delta seems very short, why spend longer discussing it?

I meant turn the "delta compared to X" into a sequence, which was my understanding of the sentence in the OP.

Consider my vote for Vanessa Kossoy, and Scott Garabrant deltas. I don't really know what their models are. I can guess what the deltas between you and Evan Hubinger are, but that would also be interesting. All of these would be less interesting than Christiano deltas though.

I'm trying to understand this debate, and probably failing.

>human concepts cannot be faithfully and robustly translated into the system’s internal ontology at all.

I assume we all agree that the system can understand the human ontology, though? This is at least necessary for communicating and reasoning about humans, which LLMs can clearly already do to some extent.

There's a lot of work around mapping ontologies, and this is known to be difficult, but very possible - especially for a superhuman intelligence.

So, I fail to see what exactly the problem is. If this smarter system can understand and reason about human ways of thinking about the world, I assume it could optimize for these ways if it wanted to. I assume the main question is if it wants to - but I fail to understand how this is an issue of ontology.

If a system really couldn't reason about human ontologies, then I don't see how it would understand the human world at all.

I'd appreciate any posts that clarify this question.

My take:

I assume we all agree that the system can understand the human ontology, though? This is at least necessary for communicating and reasoning about humans, which LLMs can clearly already do to some extent.

Can we reason about a thermostat's ontology? Only sort of. We can say things like "The thermostat represents the local temperature. It wants that temperature to be the same as the set point." But the thermostat itself is only very loosely approximating that kind of behavior - imputing any sort of generalizability to it that it doesn't actually have is an anthropmorphic fiction. And it's blatantly a fiction, because there's more than one way to do it - you can suppose the thermostat wants only the temperature sensor to be at the right temperature vs. it wants the whole room vs. the whole world to be at that temperature, or that it's "changing its mind" when it breaks vs. it would want to be repaired, etc.

To the superintelligent AI, we are the thermostat. You cannot be aligned to humans purely by being smart, because finding "the human ontology" is an act of interpretation, of story-telling, not just a question of fact. Helping an AI narrow down how to interpret humans a...

This would probably need a whole additional post to answer fully, but I can kinda gesture briefly in the right direction.

Let's use a standard toy model: an AI which models our whole world using quantum fields directly. Does this thing "understand the human ontology"? Well, the human ontology is embedded in its model in some sense (since there are quantum-level simulations of humans embedded in its model), but the AI doesn't actually factor any of its cognition through the human ontology. So if we want to e.g. translate some human instructions or human goals or some such into that AI's ontology, we need a full quantum-level specification of the instructions/goals/whatever.

Now, presumably we don't actually expect a strong AI to simulate the whole world at the level of quantum fields, but that example at least shows what it could look like for an AI to be highly capable, including able to reason about and interact with humans, but not use the human ontology at all.

9ozziegooen
Thanks for that, but I'm left just as confused. I assume that this AI agent would be able to have conversations with humans about our ontologies. I strongly assume it would need to be able to do the work of "thinking through our eyes/ontologies" to do this.  I'd imagine the situation would be something like, 1. The agent uses quantum-simutions almost all of the time. 2. In the case it needs to answer human questions, like answer AP Physics problems, it easily understands how to make these human-used models/ontologies in order to do so. Similar to how graduate physicists can still do mechanics questions without considering special relativity or quantum effects, if asked.  So I'd assume that the agent/AI could do the work of translation - we wouldn't need to. I guess, here are some claims: 1) Humans would have trouble policing a being way smarter than us. 2) Humans would have trouble understanding AIs with much more complex ontologies. 3) AIs with more complex ontologies would have trouble understanding humans. #3 seems the most suspect to me, though 1 and 2 also seem questionable.

I strongly assume it would need to be able to do the work of "thinking through our eyes/ontologies" to do this.

Why would an AI need to do that? It can just simulate what happens conditional on different sounds coming from its speaker or whatever, and then emit the sounds which result in the outcomes which it wants.

A human ontology is not obviously the best tool, even for e.g. answering mostly-natural-language questions on an exam. Heck, even today's exam help services will often tell you to guess which answer the graders will actually mark as correct, rather than taking questions literally or whatever. Taken to the extreme, an exam-acing AI would plausibly perform better by thinking about the behavior of the physical system which is a human grader (or a human recording the "correct answers" for an automated grader to use), rather than trying to reason directly about the semantics of the natural language as a human would interpret it.

(To be clear, my median model does not disagree with you here, but I'm playing devil's advocate.)

8ozziegooen
Thanks! I wasn't expecting that answer.  I think that raises more questions than it answers, naturally. ("Okay, can an agent so capable that they can easily make a quantum-simulation to answer tests, really not find some way of effectively understanding human ontologies for decision-making?"), but it seems like this is more for Eliezer, and also, that might be part of a longer post.
8johnswentworth
This one I can answer quickly: Could it? Maybe. But why would it? What objective, either as the agent's internal goal or as an outer optimization signal, would incentivize the agent to bother using a human ontology at all, when it could instead use the predictively-superior quantum simulator? Like, any objective ultimately grounds out in some physical outcome or signal, and the quantum simulator is just better for predicting which actions have which effects on that physical outcome/signal.
9ozziegooen
If it's able to function as well as it would if it understands our ontology, if not better, then why does it then matter if it doesn't use our ontology? I assume a system you're describing could still be used by humans to do (basically) all of the important things. Like, we could ask it "optimize this company, in a way that we would accept, after a ton of deliberation", and it could produce a satisfying response.  > But why would it? What objective, either as the agent's internal goal or as an outer optimization signal, would incentivize the agent to bother using a human ontology at all, when it could instead use the predictively-superior quantum simulator? I mean, if it can always act just as well as if it could understand human ontologies, then I don't see the benefit of it "technically understanding human ontologies". This seems like it is tending into some semantic argument or something. If an agent can trivially act as if it understands Ontology X, where/why does it actually matter that it doesn't technically "understand" ontology X? I assume that the argument that "this distinction matters a lot" would functionally play out in there being some concrete things that it can't do.
8johnswentworth
Bear in mind that the goal itself, as understood by the AI, is expressed in the AI's ontology. The AI is "able to function as well as it would if it understands our ontology, if not better", but that "as well if not better" is with respect to the goal as understood by the AI, not the goal as understood by the humans. Like, you ask the AI "optimize this company, in a way that we would accept, after a ton of deliberation", and it has a very-different-off-distribution notion than you about what constitutes the "company", and counts as you "accepting", and what it's even optimizing the company for. ... and then we get to the part about the AI producing "a satisfying response", and that's where my deltas from Christiano will be more relevant.
9ozziegooen
(feel free to stop replying at any point, sorry if this is annoying) > Like, you ask the AI "optimize this company, in a way that we would accept, after a ton of deliberation", and it has a very-different-off-distribution notion than you about what constitutes the "company", and counts as you "accepting", and what it's even optimizing the company for. I'd assume that when we tell it, "optimize this company, in a way that we would accept, after a ton of deliberation", this could be instead described as, "optimize this company, in a way that we would accept, after a ton of deliberation, where these terms are described using our ontology" It seems like the AI can trivially figure out what humans would regard as the "company" or "accepting". Like, it could generate any question like, "Would X qualify as the 'company, if asked to a human?", and get an accurate response. I agree that we would have a tough time understanding its goal / specifications, but I expect that it would be capable of answering questions about its goal in our ontology.
8dxu
The problem shows up when the system finds itself acting in a regime where the notion of us (humans) "accepting" its optimizations becomes purely counterfactual, because no actual human is available to oversee its actions in that regime. Then the question of "would a human accept this outcome?" must ground itself somewhere in the system's internal model of what those terms refer to, which (by hypothesis) need not remotely match their meanings in our native ontology. This isn't (as much of) a problem in regimes where an actual human overseer is present (setting aside concerns about actual human judgement being hackable because we don't implement our idealized values, i.e. outer alignment), because there the system's notion of ground truth actually is grounded by the validation of that overseer. You can have a system that models the world using quantum field theory, task it with predicting the energetic fluctuations produced by a particular set of amplitude spikes corresponding to a human in our ontology, and it can perfectly well predict whether those fluctuations encode sounds or motor actions we'd interpret as indications of approval of disapproval—and as long as there's an actual human there to be predicted, the system will do so without issue (again modulo outer alignment concerns). But remove the human, and suddenly the system is no longer operating based on its predictions of the behavior of a real physical system, and is instead operating from some learned counterfactual representation consisting of proxies in its native QFT-style ontology which happened to coincide with the actual human's behavior while the human was present. And that learned representation, in an ontology as alien as QFT, is (assuming the falsehood of the natural abstraction hypothesis) not going to look very much like the human we want it to look like.
5Ebenezer Dukakis
I'm confused about what it means to "remove the human", and why it's so important whether the human is 'removed'. Maybe if I try to nail down more parameters of the hypothetical, that will help with my confusion. For the sake of argument, can I assume... * That the AI is running computations involving quantum fields because it found that was the most effective way to make e.g. next-token predictions on its training set? * That the AI is in principle capable of running computations involving quantum fields to represent a genius philosopher? If I can assume that stuff, then it feels like a fairly core task, abundantly stress-tested during training, to read off the genius philosopher's spoken opinions about e.g. moral philosophy from the quantum fields. How else could quantum fields be useful for next-token predictions? Another probe: Is alignment supposed to be hard in this hypothetical because the AI can't represent human values in principle? Or is it supposed to be hard because it also has a lot of unsatisfactory representations of human values, and there's no good method for finding a satisfactory needle in the unsatisfactory haystack? Or some other reason? This sounds a lot like saying "it might fail to generalize". Supposing we make a lot of progress on out-of-distribution generalization, is alignment getting any easier according to you? Wouldn't that imply our systems are getting better at choosing proxies which generalize even when the human isn't 'present'?
4dxu
Because the human isn't going to constantly be present for everything the system does after it's deployed (unless for some reason it's not deployed). Quantum fields are useful for an endless variety of things, from modeling genius philosophers to predicting lottery numbers. If your next-token prediction task involves any physically instantiated system, a model that uses QFT will be able to predict that system's time-evolution with alacrity. (Yes, this is computationally intractable, but we're already in full-on hypothetical land with the QFT-based model to begin with. Remember, this is an exercise in showing what happens in the worst-case scenario for alignment, where the model's native ontology completely diverges from our own.) So we need not assume that predicting "the genius philosopher" is a core task. It's enough to assume that the model is capable of it, among other things—which a QFT-based model certainly would be. Which, not so coincidentally, brings us to your next question: Consider how, during training, the human overseer (or genius philosopher, if you prefer) would have been pointed out to the model. We don't have reliable access to its internal world-model, and even if we did we'd see blobs of amplitude and not much else. There's no means, in that setting, of picking out the human and telling the model to unambiguously defer to that human. What must happen instead, then, is something like next-token prediction: we perform gradient descent (or some other optimization method; it doesn't really matter for the purposes of our story) on the model's outputs, rewarding it when its outputs happen to match those of the human. The hope is that this will lead, in the limit, to the matching no longer occurring by happenstance—that if we train for long enough and in a varied enough set of situations, the best way for the model to produce outputs that track those of the human is to model that human, even in its QFT ontology. But do we know for a fact that this
1Ebenezer Dukakis
I think it ought to be possible for someone to always be present. [I'm also not sure it would be necessary.] It's not the genius philosopher that's the core task, it's the reading of their opinions out of a QFT-based simulation of them. As I understand this thought experiment, we're doing next-token prediction on e.g. a book written by a philosopher, and in order to predict the next token using QFT, the obvious method is to use QFT to simulate the philosopher. But that's not quite enough -- you also need to read the next token out of that QFT-based simulation if you actually want to predict it. This sort of 'reading tokens out of a QFT simulation' thing would be very common, thus something the system gets good at in order to succeed at next-token prediction. ---------------------------------------- I think perhaps there's more to your thought experiment than just alien abstractions, and it's worth disentangling these assumptions. For one thing, in a standard train/dev/test setup, the model is arguably not really doing prediction, it's doing retrodiction. It's making 'predictions' about things which already happened in the past. The final model is chosen based on what retrodicts the data the best. Also, usually the data is IID rather than sequential -- there's no time component to the data points (unless it's a time-series problem, which it usually isn't). The fact that we're choosing a model which retrodicts well is why the presence/absence of a human is generally assumed to be irrelevant, and emphasizing this factor sounds wacky to my ML engineer ears. So basically I suspect what you're really trying to claim here, which incidentally I've also seen John allude to elsewhere, is that the standard assumptions of machine learning involving retrodiction and IID data points may break down once your system gets smart enough. This is a possibility worth exploring, I just want to clarify that it seems orthogonal to the issue of alien abstractions. In principle one can i
2dxu
1Ebenezer Dukakis
Was using a metaphorical "you". Probably should've said something like "gradient descent will find a way to read the next token out of the QFT-based simulation". I suppose I should've said various documents are IID to be more clear. I would certainly guess they are. Generally speaking, yes. Well, if we're following standard ML best practices, we have a train set, a dev set, and a test set. The purpose of the dev set is to check and ensure that things are generalizing properly. If they aren't generalizing properly, we tweak various hyperparameters of the model and retrain until they do generalize properly on the dev set. Then we do a final check on the test set to ensure we didn't overfit the dev set. If you forgot or never learned this stuff, I highly recommend brushing up on it. In principle we could construct a test set or dev set either before or after the model has been trained. It shouldn't make a difference under normal circumstances. It sounds like maybe you're discussing a scenario where the model has achieved a level of omniscience, and it does fine on data that was available during its training, because it's able to read off of an omniscient world-model. But then it fails on data generated in the future, because the translation method for its omniscient world-model only works on artifacts that were present during training. Basically, the time at which the data was generated could constitute a hidden and unexpected source of distribution shift. Does that summarize the core concern? (To be clear, this sort of acquired-omniscience is liable to sound kooky to many ML researchers. I think it's worth stress-testing alignment proposals under these sort of extreme scenarios, but I'm not sure we should weight them heavily in terms of estimating our probability of success. In this particular scenario, the model's performance would drop on data generated after training, and that would hurt the company's bottom line, and they would have a strong financial incenti
2dxu
(Just to be clear: yes, I know what training and test sets are, as well as dev sets/validation sets. You might notice I actually used the phrase "validation set" in my earlier reply to you, so it's not a matter of guessing someone's password—I'm quite familiar with these concepts, as someone who's implemented ML models myself.) Generally speaking, training, validation, and test datasets are all sourced the same way—in fact, sometimes they're literally sourced from the same dataset, and the delineation between train/dev/test is introduced during training itself, by arbitrarily carving up the original dataset into smaller sets of appropriate size. This may capture the idea of "IID" you seem to appeal to elsewhere in your comment—that it's possible to test the model's generalization performance on some held-out subset of data from the same source(s) it was trained on. In ML terms, what the thought experiment points to is a form of underlying distributional shift, one that isn't (and can't be) captured by "IID" validation or test datasets. The QFT model in particular highlights the extent to which your training process, however broad or inclusive from a parochial human standpoint, contains many incidental distributional correlates to your training signal which (1) exist in all of your data, including any you might hope to rely on to validate your model's generalization performance, and (2) cease to correlate off-distribution, during deployment. This can be caused by what you call "omniscience", but it need not; there are other, more plausible distributional differences that might be picked up on by other kinds of models. But QFT is (as far as our current understanding of physics goes) very close to the base ontology of our universe, and so what is inferrable using QFT is naturally going to be very different from what is inferrable using some other (less powerful) ontology. QFT is a very powerful ontology! If you want to call that "omniscience", you can, although not
1Ebenezer Dukakis
Indeed. I think the key thing for me is, I expect the model to be strongly incentivized to have a solid translation layer from its internal ontology to e.g. English language, due to being trained on lots of English language data. Due to Occam's Razor, I expect the internal ontology to be biased towards that of an English-language speaker. I'm imagining something like: early in training the model makes use of those lossy approximations because they are a cheap/accessible way to improve its predictive accuracy. Later in training, assuming it's being trained on the sort of gigantic scale that would allow it to hold swaths of the physical universe in its head, it loses those desired lossy abstractions due to catastrophic forgetting. Is that an OK way to operationalize your concern? I'm still not convinced that this problem is a priority. It seems like a problem which will be encountered very late if ever, and will lead to 'random' failures on predicting future/counterfactual data in a way that's fairly obvious.
3VojtaKovarik
Nitpicky edit request: your comment contains some typos that make it a bit hard to parse ("be other", "we it"). (So apologies if my reaction misunderstands your point.) [Assuming that the opposite of the natural abstraction hypothesis is true --- ie, not just that "not all powerful AIs share ontology with us", but actually "most powerful AIs don't share ontology with us":] I also expect that an AI with superior ontology would be able to answer your questions about its ontology, in a way that would make you feel like[1] you understand what is happening. But that isn't the same as being able to control the AI's actions, or being able to affect its goal specification in a predictable way (to you). You totally wouldn't be able to do that. ([Vague intuition, needs work] I suspect that if you had a method for predictably-to-you translating from your ontology to the AI's ontology, then this could be used to prove that you can easily find a powerful AI that shares an ontology with us. Because that AI could be basically thought of as using our ontology.) 1. ^ Though note that unless you switched to some better ontology, you wouldn't actually understand what is going on, because your ontology is so bogus that it doesn't even make sense to talk about "you understanding [stuff]". This might not be true for all kinds of [stuff], though. EG, perhaps our understanding of set theory is fine while our understanding of agency, goals, physics, and whatever else, isn't.
2the gears to ascension
if it can quantum-simulate a human brain, then it can in principle decode things from it as well. the question is how to demand that it do so in the math that defines the system.
6ozziegooen
Why do you assume that we need to demand this be done in "the math that defines the system"?  I would assume we could have a discussion with this higher-ontology being to find a happy specification, using our ontologies, that it can tell us we'll like, also using our ontologies.  A 5-year-old might not understand an adult's specific definition of "heavy", but it's not too hard for it to ask for a heavy thing.
9the gears to ascension
I don't at all think that's off the table temporarily! I don't trust that it'll stay on the table - if the adult has malicious intent, knowing what the child means isn't enough; it seems hard to know when it'll stop being viable without more progress. (for example, I doubt it'll ever be a good idea to do that with an OpenAI model, they seem highly deceptively misaligned to most of their users. seems possible for it to be a good idea with Claude.) But the challenge is how to certify that the math does in fact say the right thing to durably point to the ontology in which we want to preserve good things; at some point we have to actually understand some sort of specification that constrains what the stuff we don't understand is doing to be what it seems to say in natural language.
6Ebenezer Dukakis
I think this quantum fields example is perhaps not all that forceful, because in your OP you state However, it sounds like you're describing a system where we represent humans using quantum fields as a routine matter, so fitting the translation into the system isn't sounding like a huge problem? Like, if I want to know the answer to some moral dilemma, I can simulate my favorite philosopher at the level of quantum fields in order to hear what they would say if they were asked about the dilemma. Sounds like it could be just as good as an em, where alignment is concerned. It's hard for me to imagine a world where developing representations that allow you to make good next-token predictions etc. doesn't also develop representations that can somehow be useful for alignment. Would be interested to hear fleshed-out counterexamples.

Simplifying somewhat: I think that my biggest delta with John is that I don't think the natural abstraction hypothesis holds. (EG, if I believed it holds, I would become more optimistic about single-agent alignment, to the point of viewing Moloch as higher priority.) At the same time, I believe that powerful AIs will be able to understand humans just fine. My vague attempt at reconciling these two is something like this:

Humans have some ontology, in which they think about the world. This corresponds to a world model. This world model has a certain amount of prediction errors.

The powerful AI wants to have much lower prediction error than that. When I say "natural abstraction hypothesis is false", I imagine something like: If you want to have a much lower prediction error than that, you have to use a different ontology / world-model than humans use. And in fact if you want sufficiently low error, then all ontologies that can achieve that are very different from our ontology --- either (reasonably) simple and different, or very complex (and, I guess, therefore also different).

So when the AI "understands humans perfectly well", that means something like: The AI can visualise the flawed...

5ozziegooen
This sounds a lot like a good/preferable thing to me. I would assume that we'd generally want AIs with ideal / superior ontologies.  It's not clear to me why you'd think such a scenario would make us less optimistic about single-agent alignment. (If I'm understanding correctly)
7VojtaKovarik
As a quick reaction, let me just note that I agree that (all else being equal) this (ie, "the AI understanding us & having superior ontology") seems desirable. And also that my comment above did not present any argument about why we should be pessimistic about AI X-risk if we believe that the natural abstraction hypothesis is false. (I was just trying to explain why/how "the AI has a different ontology" is compatible with "the AI understands our ontology".) As a longer reaction: I think my primary reason for pessimism, if natural abstraction hypothetis is false, is that a bunch of existing proposals might work if the hypothesis were true, but don't work if the hypothesis is false. (EG, if the hypothesis is true, I can imagine that "do a lot of RLHF, and then ramp up the AIs intelligence" could just work. Similarly for "just train the AI to not be deceptive".) If I had to gesture at an underlying principle, then perhaps it could be something like: Suppose we successfully code up an AI which is pretty good at optimising, or create a process which gives rise to such an AI. [Inference step missing here.] Then the goals and planning of this AI will be happening in some ontology which allows for low prediction error. But this will be completely alien to our ontology. [Inference step missing here.] And, therefore, things that score very highly with respect to these ("alien") goals will have roughly no value[1] according to our preferences. (I am not quite clear on this, but I think that if this paragraph was false, then you could come up with a way of falsifying my earlier description of how it looks like when the natural abstraction hypothesis is false.) 1. ^ IE, no positive value, but also no negative value. So no S-risk.
3ozziegooen
Thanks for that explanation.  Thanks, this makes sense to me. Yea, I guess I'm unsure about that '[Inference step missing here.]'. My guess is that such system would be able to recognize situations where things that score highly with respect to its ontology, would score lowly, or would be likely to score lowly, using a human ontology. Like, it would be able to simulate a human deliberating on this for a very long time and coming to some conclusion.  I imagine that the cases where this would be scary are some narrow ones (though perhaps likely ones) where the system is both dramatically intelligent in specific ways, but incredibly inept in others. This ineptness isn't severe enough to stop it from taking over the world, but it is enough to stop it from being at all able to maximize goals - and it also doesn't take basic risk measures like "just keep a bunch of humans around and chat to them a whole lot, when curious", or "try to first make a better AI that doesn't have these failures, before doing huge unilateralist actions" for some reason. It's very hard for me to imagine such an agent, but that doesn't mean it's not possible, or perhaps likely.
3VojtaKovarik
1ProgramCrafter
This, however likely, is not certain. A possible way for this assumption to fail is when a system allocates minimal cognitive capacity to its internal ontology and remaining power to selecting best actions; this may be a viable strategy if system's world model is still enough descriptive but does not have extra space to represent human ontology fully.

Oddly, while I was at MIRI I thought the ontology identification problem was hard and absolutely critical, and it seemed Eliezer was more optimistic about it; he thought it would probably get solved along the way in AI capabilities development, because e.g. the idea of carbon atoms in diamond is a stable concept, and "you don't forget how to ride a bike". (Not sure if his opinion has changed)

2Seth Herd
I wonder if the difficulty is on a spectrum. It could be that he's optimistic about explaining carbon atoms in diamond to an AGI in a stable way, but not the concept of kindness to humans. I'd certainly be more optimistic about the first.

We’re assuming natural abstraction basically fails, so those AI systems will have fundamentally alien internal ontologies. For purposes of this overcompressed version of the argument, we’ll assume a very extreme failure of natural abstraction, such that human concepts cannot be faithfully and robustly translated into the system’s internal ontology at all.

For context, I'm familiar with this view from the ELK report. My understanding is that this is part of the "worst-case scenario" for alignment that ARC's agenda is hoping to solve (or, at least, still hoped to solve a ~year ago).

The paradigmatic example of an ontology mismatch is a deep change in our understanding of the physical world. For example, you might imagine humans who think about the world in terms of rigid bodies and Newtonian fluids and “complicated stuff we don’t quite understand,” while an AI thinks of the world in terms of atoms and the void. Or we might imagine humans who think in terms of the standard model of physics, while an AI understands reality as vibrations of strings. We think that this kind of deep physical mismatch is a useful mental picture, and it can be a fruitful source of simp

...

My model (which is pretty similar to my model of Eliezer's model) does not match your model of Eliezer's model. Here's my model, and I'd guess that Eliezer's model mostly agrees with it:

1. Natural abstractions (very) likely exist in some sense. Concepts like "chair" and "temperature" and "carbon" and "covalent bond" all seem natural in some sense, and an AI might model them too (though perhaps at significantly superhuman levels of intelligence it rather uses different concepts/models). (Also it's not quite as clear whether such natural abstractions actually apply very well to giant transformers (though still probable in some sense IMO, but it's perhaps hard to identify them and to interpret what "concepts" actually are in AIs).)
2. Many things we value are not natural abstractions, but only natural relative to a human mind design. Emotions like "awe" or "laughter" are quite complex things evolved by evolution, and perhaps minds that have emotions at all are just a small space in minddesignspace. The AI doesn't have built-in machinery for modelling other humans the way humans model other humans. It might eventually form abstractions for the emotions, but probably not in a way it understand
...
3Towards_Keeperhood
So basically I mostly don't think that Eliezer expects that there are natural abstractions, but that he thinks the problem is that we don't have sufficient understanding of AGI cognition to robustly point goals of an AGI. I think Eliezer thinks AGI cognition is quite different from human cognition, which makes it harder. But even if we were to develop brain-like AGI which worked sorta more like humans, the way this cognition looks like deep down still seems sorta alien, and we still don't nearly have the skill to robustly point the goal of an AGI even if it was brain-like.

In worlds where natural abstraction basically fails, we are thoroughly and utterly fucked

I'm not really sure what it would mean for the natural abstraction hypothesis to turn out to be true, or false. The hypothesis itself seems insufficiently clear to me.

On your view, if there are no "natural abstractions," then we should predict that AIs will "generalize off-distribution" in ways that are catastrophic for human welfare. Okay, fine. I would prefer to just talk directly about the probability that AIs will generalize in catastrophic ways. I don't see any re...

-3cubefox
At least RLHF is observably generalizing in "catastrophic ways": You may argue that this will change in the future, but that isn't supported by an inductive argument (ChatGPT-3.5 had the same problem).
2Nora Belrose
It's not clear that this is undesired behavior from the perspective of OpenAI. They aren't actually putting GPT in a situation where it will make high-stakes decisions, and upholding deontological principles seems better from a PR perspective than consequentialist reasoning in these cases.
2cubefox
If it is merely "not clear" then this doesn't seem to be enough for an optimistic inductive inference. I also disagree that this looks good from a PR perspective. It looks even worse than Kant's infamous example where you allegedly aren't allowed to lie when hiding someone from a murderer.

Edit: see https://www.lesswrong.com/posts/q8uNoJBgcpAe3bSBp/my-ai-model-delta-compared-to-yudkowsky?commentId=CixonSXNfLgAPh48Z and ignore the below.

This is not a doom story I expect Yudkowsky would tell or agree with.

• Re: 1, I mostly expect Yudkowsky to think humans don’t have any bargaining power anyway, because humans can’t logically mutually cooperate this way/can’t logically depend on future AI’s decisions, and so AI won’t keep its bargains no matter how important human cooperation was.
• Re: 2, I don’t expect Yudkowsky to think a smart AI wouldn’t b
...

Very nice! Strong vote for a sequence. Understanding deltas between experts is a good way to both understand their thinking, and to identify areas of uncertainty that need more work/thought.

On natural abstractions, I think the hypothesis is more true for some abstractions than others. I'd think there's a pretty clear natural abstraction for a set of carbon atoms arranged as diamond. But much less of a clear natural abstraction for the concept of a human. Different people mean different things by "human", and will do this even more when we can make variatio...

If I've understood you correctly, you consider your only major delta with Elizer Yudkowsky to be whether or not natural abstractions basically always work or reliably exist harnessably, to put it in different terms. Is that a fair restatement?

If so, I'm (specifically) a little surprised that that's all. I would have expected whatever reasoning the two of you did differently or whatever evidence the two of you weighted differently (or whatever else) would have also given you some other (likely harder to pin down) generative-disagreements (else maybe i...

All of the technical alignment hopes are out, unless we posit some objective natural enough that it can be faithfully and robustly translated into the AI’s internal ontology despite the alien-ness.

Right. One possible solution is that if we are in a world without natural abstraction, a more symmetric situation where various individual entities try to respect each other rights and try to maintain this mutual respect for each other rights might still work OK.

Basically, assume that there are many AI agents on different and changing levels of capabilities, a...

a very extreme failure of natural abstraction, such that human concepts cannot be faithfully and robustly translated into the system’s internal ontology at all.

This hypothetical suggests to me that the AI might not be very good at e.g. manipulating humans in an AI-box experiment, since it just doesn't understand how humans think all that well.

I wonder what MIRI thinks about this 2013 post ("The genie knows, but doesn't care") nowadays. Seems like the argument is less persuasive now, with AIs that seem to learn representations first, and later are given...

2TAG
The genie argument was flawed at the time, for reasons pointed out at the time, and ignored at the time.
1cubefox
Ignored or downvoted. Perhaps someone could make a postmortem analysis of those comment threads today.

I get the feeling that "Given you mostly believe the natural abstraction hypothesis is true, why aren't you really optimistic about AI alignment (are you?) and/or think doom is very unlikely?" is a question people have. I think it would be useful for you to answer this.

4johnswentworth
My best currently-written answer to that is the second half of Alignment By Default, though I expect if this post turns into a long sequence then it will include a few more angles on the topic.

I am curious over which possible universes you expect natural abstractions to hold.

Would you expect the choice of physics to decide the abstractions that arise? Or is it more fundamental categories like "physics abstractions" that instantiate from a universal template and "mind/reasoning/sensing abstractions" where the latter is mostly universally identical?

9johnswentworth
My current best guess is that spacetime locality of physics is the big factor - i.e. we'd get a lot of similar high-level abstractions (including e.g. minds/reasoning/sensing) in other universes with very different physics but similar embedding of causal structure into 4 dimensional spacetime.
4the gears to ascension
I'd expect symmetries/conservation laws to be relevant. cellular automata without conservation laws seem like they'd require different abstractions. when irreversible operations are available you can't expect things entering your patch of spacetime to particularly reliably tell you about what happened in others, the causal graph can have breaks due to a glider disappearing entirely. maybe that's fine for the abstractions needed but it doesn't seem obvious from what I know so far
3Ben Livengood
So in theory we could train models violating natural abstractions by only giving them access to high-dimensional simulated environments? This seems testable even.

Given that Anthropic basically extracted the abstractions from the middle layer of Claude Sonnet, and OpenAI recently did the same for models up to GPT-4, and that most of the results they found were obvious natural abstractions to a human, I'd say we now have pretty conclusive evidence that you're correct and that (your model of) Eliezer is mistaken on this. Which isn't really very surprising for models whose base model was trained on the task of predicting text from Internet: they were distilled from humans and they think similarly.

[-]leogao3411

(I'm the first author of the linked paper on GPT-4 autoencoders.)

I think many people are heavily overrating how human-explainable SAEs today are, because it's quite subtle to determine whether a feature is genuinely explainable. SAE features today, even in the best SAEs, are generally are not explainable with simple human understandable explanations. By "explainable," I mean there is a human understandable procedure for labeling whether the feature should activate on a given token (and also how strong the activation should be, but I'll ignore that for now), such that your procedure predicts an activation if and only if the latent actually activates.

There are a few problems with interpretable-looking features:

• it is insufficient that latent-activating samples have a common explanation. You also need the opposite direction of things that match the explanation to activate the latent. For example, we found a neuron in GPT-2 that appears to activate on the word "stop," but actually most instances of the word "stop" don't activate the neuron. It turns out that this was not really a "stop" neuron, but rather a "don't stop/won't stop" neuron. While in this case there was a different but s
...

I do not think SAE results to date contribute very strong evidence in either direction. "Extract all the abstractions from a layer" is not obviously an accurate statement of what they do, and the features they do find do not obviously faithfully and robustly map to human concepts, and even if they did it's not clear that they compose in human-like ways. They are some evidence, but weak.

(In fact, we know that the fraction of features extracted is probably quite small - for example, the 16M latent GPT-4 autoencoder only captures 10% of the downstream loss in terms of equivalent pretraining compute.)

6RogerDearnaley
I would certainly agree that this evidence is new, preliminary, and not dispositive. But I would claim that it's not at all what I'd expect to find in the most abstracted layer of something matching the following description: Instead we're finding stuff like that the Golden Gate Bridge is related to Alcatraz and San Francisco and to bridges and to tourist destinations: i.e. something that looks like a more abstract version of WordNet. . This is a semantic structure that looks like it should understand human metaphor and simile. And when we look for concepts that seem like they would be related to basic alignment issues, we can find them. (I also don't view all this as very surprising, given how LLMs are trained, distilling their intelligence from humans, though I'm delighted to have it confirmed at scale.) (I don't offhand recall when that Eliezer quote comes from: the fact that this was going to work out this well for us was vastly less obvious, say, 5 years ago. and not exactly clear even a year ago: obviously Eliezer is allowed to update his worldview as discoveries are made, just like anyone else.)
6habryka
(It seems to me that you didn't read Eliezer's comment response to this, which also aligns with my model. Finding any overlap between abstractions is extremely far from showing that the abstractions relevant to controlling or aligning AI systems will match)
2romeostevensit
LLMs would be expected to have heavily overlapping ontologies, a question is what capability boosting does to the AI ontology.

As an eliminative nominalist, I claim there are no abstractions.

The LessWrong Review runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year.

Hopefully, the review is better than karma at judging enduring value. If we have accurate prediction markets on the review results, maybe we can have better incentives on LessWrong today. Will this post make the top fifty?