# Ω 51

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

ARC recently released a technical report on eliciting latent knowledge (ELK), the focus of our current research. Roughly speaking, the goal of ELK is to incentivize ML models to honestly answer “straightforward” questions where the right answer is unambiguous and known by the model.

ELK is currently unsolved in the worst case—for every training strategy we’ve thought of so far, we can describe a case where an ML model trained with that strategy would give unambiguously bad answers to straightforward questions despite knowing better. Situations like this may or may not come up in practice, but nonetheless we are interested in finding a strategy for ELK for which we can’t think of any counterexample.

We think many people could potentially contribute to solving ELK—there’s a large space of possible training strategies and we’ve only explored a small fraction of them so far. Moreover, we think that trying to solve ELK in the worst case is a good way to “get into ARC’s headspace” and more deeply understand the research we do.

We are offering prizes of $5,000 to$50,000 for proposed strategies for ELK. We’re planning to evaluate submissions received before February 10.

For full details of the ELK problem and several examples of possible strategies, see the writeup. The rest of this post will focus on how the contest works.

## Contest details

To win a prize, you need to specify a training strategy for ELK that handles all of the counterexamples that we’ve described so far, summarized in the section below—i.e. where the breaker would need to specify something new about the test case to cause the strategy to break down. You don’t need to fully solve the problem in the worst case to win a prize, you just need to come up with a strategy that requires a new counterexample.

We’ll give a $5,000 prize to any proposal that we think clears this bar. We’ll give a$50,000 prize to a proposal which we haven’t considered and seems sufficiently promising to us or requires a new idea to break. We’ll give intermediate prizes for ideas that we think are promising but we’ve already considered, as well as for proposals that come with novel counterexamples, clarify some other aspect of the problem, or are interesting in other ways. A major purpose of the contest is to provide support for people understanding the problem well enough to start contributing; we aren’t trying to only reward ideas that are new to us.

You can submit multiple proposals, but we won’t give you separate prizes for each—we’ll give you at least the maximum prize that your best single submission would have received, but may not give much more than that.

If we receive multiple submissions based on a similar idea, we may post a comment describing the idea (with attribution) along with a counterexample. Once a counterexample has been included in the comments of this post, new submissions need to address that counterexample (as well as all the existing ones) in order to be eligible for a prize.

Ultimately prizes are awarded at our discretion, and the “rules of the game” aren’t fully precise. If you are curious about whether you are on the right track, feel free to send an email to elk@alignmentresearchcenter.org with the basic outline of an idea, and if we have time we’ll get back to you with some feedback. Below we also describe some of the directions we consider more and less promising and some general guidance.

## How to submit a proposal

You can submit a proposal by copying this google doc template and sharing it with elk@alignmentresearchcenter.org (please give comment access in case we need to ask questions to evaluate your submission). By submitting a proposal, you are giving us permission to post the idea here with attribution. (And it's fine for you to post it after the contest or we post a counterexample.)

## Retroactive prizes

We’re giving prizes to existing proposals from David Dalrymple ($5k), Ramana Kumar ($3k), John Maxwell ($2k), and Yonadav Shavit ($1k). We’ve added relevant counterexamples in the next section, and further submissions need to handle those counterexamples in order to be eligible.

## Existing counterexamples

In our report and a recent post, we described some features of the world that would cause existing approaches to ELK to fail. A new approach should work even in a situation satisfying all of these properties, or should include an argument for why some of these features are actually impossible or inconsistent with each other.

In order to generate a counterexample to a training strategy, we need to spell out a concrete “way the world could be” (a test case) where the strategy would fail. In the report we consider test cases where the AI and the human happen to understand the world by doing inference in Bayes nets. The Bayes net case is just one test case that lets us get precise about our counterexamples and our training strategies don’t lean on it. In practice we also consider other concrete cases (e.g. deduction from premises generated by a neural network).

In this section we’ll briefly review the current state of existing counterexamples. This isn’t intended to be a self-contained description; it relies heavily on links to the report.

### Ontology mismatch

All of our counterexamples are based on an ontology mismatch between two different Bayes nets, one used by an ML prediction model (“the predictor”) and one used by a human:

• The predictor’s Bayes net is used internally by a prediction model that maps an initial segment of a video to a prediction about what will happen next. This model was trained by gradient descent based on the quality of its predictions (more).
• Humans have their own model of the world, which they can improve with the help of AI assistants; those assistants can design and conduct experiments, find and evaluate arguments, and so on. Crucially, we have a limited computational budget with which to train these AI assistants, and that limits how much help they can provide. The “human’s” Bayes net captures everything the human understands about the world at the end of this process (more).

We are interested in the case where there are features of reality that are accurately reflected in the predictor’s Bayes net, but missing from this (augmented) human Bayes net. We expect the human could understand these facts eventually given enough time or enough AI assistance, but not using the available computational budget. Put differently, there is a gap between the kinds of understanding that gradient descent can build, and the kind of understanding that a human-comprehensible process of “scientific inquiry” can build using similar computational resources (more).

Furthermore, we imagine that both the predictor’s Bayes net and the human’s Bayes net reflect some underlying reality and that there is a way to map between them, which we’ll call “direct translation.” We don’t know how to do direct translation, and we are concerned that if we simply search for any mapping from the AI’s Bayes net to the human’s Bayes net we will instead get the “human simulator”: the map which correctly translates the observations from one Bayes net to the other, but then does inference in the human’s Bayes net in order to fill in the latent structure as a human would by looking at the data (more).

### Counterexample features

ELK seems particularly hard when these Bayes nets satisfy the following properties:

1. There are arbitrarily severe “ontology mismatches” between the predictor’s Bayes net and the human’s Bayes net, such that specifying the direct translation between them can be very complex (more).
2. The human’s Bayes net is simpler than the predictor’s Bayes net, and the gap can be arbitrarily large (more).
3. The predictor’s Bayes net is arbitrarily large, and individual nodes of the human’s Bayes net depend on a constant fraction of the predictor’s Bayes net. Therefore directly translating between the two Bayes nets takes arbitrarily much computation (more).
4. It’s computationally easy for the human simulator to do good inference in the human’s Bayes net—at least good enough inference that it answers questions as well as the direct translator—and the gap between this complexity and the complexity of direct translation can be arbitrarily large. More precisely, a human interrogator can’t think of questions which require the human simulator to do hard inference. However, we can’t rule out the possibility that you, the algorithm-designer, will think of some trick they can use to generate hard questions (more).
5. There are situations where a model which is trying to answer a question will first be able to predict what (potentially mistaken) belief the human-with-assistance will have about that question before it knows the true answer to the question (more).
6. While the predictor’s Bayes net is very large, it has a short succinct description which is simpler than the human’s Bayes net, and that gap is arbitrarily large. Think of simple physical laws that describe arbitrarily computationally expensive simulations, or simple cognitive heuristics that are very widely applicable. (more)
7. There are sequences of actions for which the predictor’s Bayes net correctly anticipates that tampering will occur yet nothing looks suspicious to the human’s Bayes net.
8. After tampering has occurred, it is possible that no sequence of further actions reveal that anything is wrong, e.g. the camera and actuators may have been completely disconnected from the world and replaced with a convincing-to-humans simulation (more).
9. There are sequences of actions leading to undetectable tampering that have no human-comprehensible similarities to sequences of actions leading to detectable tampering; in particular, the early steps of this undetectable tampering cannot be used to perform detectable tampering (more).

An important and very general strategy for the breaker is to suggest counterexamples where you “get what you train for.” If you propose training a model using loss function L, then the breaker will likely focus on counterexamples where the model chooses its output to minimize L. A successful approach should either explain why this either isn’t a realistic thing for the model to learn (e.g. why that would be disfavored by regularization), or why the overall approach works even if the model is explicitly strategizing about how to minimize the loss.

## Rough guidance

• There is a tradeoff between specifying your approach precisely, and including your own counterexample. It’s fine to describe a very broad/vague idea for solving ELK, and then present a new counterexample showing why that whole category of solutions can’t work. But if you don’t propose a counterexample, then it’s good to describe your proposal precisely enough that we understand how to actually implement it without wondering if that’s really what you meant. It’s OK to submit a very broad or informal idea together with a single very specific instance of that idea, as long as there is some version we can understand precisely.
• We suspect you can’t solve ELK just by getting better data—you probably need to “open up the black box” and include some term in the loss that depends on the structure of your model and not merely its behavior. So we are most interested in approaches that address that challenge. We could still be surprised by clever ways to penalize behavior, but we’ll hold them to a higher bar. The most plausible surprise would be finding a way to reliably make it computationally difficult to “game” the loss function, probably by using the AI itself to help compute the loss (e.g. using consistency checks or by giving the human AI assistance).
• If you are specifying a regularizer that you hope will prefer direct translation over human simulation, you should probably have at least one concrete case in mind that has all the counterexample-features above and where you can confirm that your regularizer does indeed prefer the direct translator.
• ELK already seems hard in the case of ontology identification, where the predictor uses a straightforward inference algorithm in an unknown model of the world (which we’ve been imagining as a Bayes net). When coming up with a proposal, we don’t recommend worrying about cases where the original unaligned predictor learned something more complicated (e.g. involving learned optimization other than inference). That said, you do need to worry about the case where your training scheme incentivizes learned optimization that may not have been there originally.

## Ask dumb questions!

A major purpose of this contest is to help people build a better understanding of our research methodology and the “game” we are playing. So we encourage people to ask clarifying questions in the comments of this post (no matter how “dumb” they are), and we’ll do our best to answer all of them. You might also want to read the comments to get more clarity about the problem.

## What you can expect from us

• We’ll try to answer all clarifying questions in the comments.
• If you send in a rough outline for a proposal, we will try to understand whether it might qualify and write back something like “This qualifies,” “This might qualify but would need to be clearer and address issue X,” “We aren’t easily able to understand this proposal at all,” “This is unlikely to be on track for something that qualifies,” or “This definitely doesn’t qualify.”
• If there are more submissions than expected, we may run out of time to respond to all submissions and comments, in which case we will post an update here.

# Ω 51

80 comments, sorted by Highlighting new comments since
New Comment
Some comments are truncated due to high volume. Change truncation settings

After reading through the report I wanted to make sure I understood the scenarios and counterexamples being discussed and be able to quickly refresh my memory, so I attempted to write a brief summary. Figured I'd share it here in case it helps anyone else.

# Roles and Terms

SmartVault: Vault with a diamond in it, operated by a superintelligent AI tasked with keeping the diamond safe.

Predictor: The primary AI tasked with protecting the diamond. The predictor sees a video feed of the vault, predicts what actions are necessary to protect the diamond and how those actions will play out (for example, activating a trap door to eliminate a robber trying to steal the diamond), and then generates a video showing precisely what will happen.

Reporter: A second "head" or component added to the AI which is used to map the AI's understanding of what's going on in the SmartVault into a format understandable by humans (such as by responding to questions).

Humans: Observers who are training the AI to protect the diamond, but also want the AI to accurately report whether the diamond has been stolen or not. The humans may not be able to tell if the camer... (read more)

4Mark Xu10dLooks good to me.
2Caleb Biddulph11dI'd like to try making a correction here, though I might make some mistakes too. The predictor is different from the AI that protects the diamond and doesn't try to "choose" actions in order to accomplish any particular goal. Rather, it takes a starting video and a set of actions as input, then returns a prediction of what the ending video would be if those actions were carried out. An agent could use this predictor to choose a set of actions that leads to videos that a human approves of, then carry out these plans. It could use some kind of search policy, like Monte-Carlo Tree Search, or even just enumerate through every possible action and figure out which one seems to be the best. For the purposes of this problem, we don't really care; we just care that we have a predictor that uses some model of the world (which might take the form of a Bayes net) to guess what the output video will be. Then, the reporter can use the model to answer any questions asked by the human.
1Ryan Beck11dI think that makes sense. To rephrase, are you basically saying that the predictor is a subcomponent of the AI, like the reporter is? I didn't catch that distinction in the report but looking back at it I think you're right. But yeah doesn't seem like the distinction matters much for what we're doing.
1Caleb Biddulph11dIt seems fair to call it a subcomponent, yeah

We’re planning to evaluate submissions as we receive them, between now and the end of January; we may end the contest earlier or later if we receive more or fewer submissions than we expect.

Just wanted to note that the "we may end the contest earlier" part here makes me significantly more hesitant about trying this. I will probably still at least have a look at it, but part of me is afraid that I'll invest a bunch of time and then the contest will be announced to be over before I got around to submitting. And I suspect Holden's endorsement may make that more likely. It would be easier for me to invest time spread out over the next couple of weeks, than all in one go, due to other commitments. On the other hand, if I knew there was a hard deadline next Friday, I might try to find a way to squeeze it in.

I'm just pointing this out in case you hadn't thought of it. I suspect something similar might be true for others too. Of course, it's your prize and your rules, and if you prefer it this way, that's totally fine.

6paulfchristiano2dWe're going to accept submissions through February 10. (We actually ended up receiving more submissions than I expected but it seems valuable, and Mark has been handling all the reviews, so running for another 20 days seems worthwhile.)
1Mathieu Putz2dThanks! Great to hear that it's going well!

Maybe I'm being stupid here. On page 42 of the write-up, it says:

In order to ensure we learned the human simulator, we would need to change the training strategy to ensure that it contains sufficiently challenging inference problems, and that doing direct translation was a cost-effective way to improve speed (i.e. that there aren’t other changes to the human simulator that would save even more time). [emphasis mine]

Shouldn't that be?

In order to ensure we learned the direct translator, ...

3paulfchristiano6dYes, thanks!
1ADifferentAnonymous4dTurning this into the typo thread, on page 97 you have Pretty sure the bolded word should be predictors.

Question: Does ARC consider ELK-unlimited to be solved, where ELK-unlimited is ELK without the competitiveness restriction (computational resource requirements comparable to the unaligned benchmark)?

One might suppose that the "have AI help humans improve our understanding" strategy is a solution to ELK-unlimited because its counterexample in the report relies on the competitiveness requirement. However, there may still be other counterexamples that were less straightforward to formulate or explain.

I'm asking for clarification of this point because I notice... (read more)

3paulfchristiano13dMy guess is that "help humans improve their understanding" doesn't work anyway, at least not without a lot of work, but it's less obvious and the counterexamples get weirder. It's less clear whether ELK is a less natural subproblem for the unlimited version of the problem. That is, if you try to rely on something like "human deliberation scaled up" to solve ELK, you probably just have to solve the whole (unlimited) problem along the way. It seems to me like the core troubles with this point are: * You still have finite training data, and we don't have a scheme for collecting it. This can result in inner alignment problems (and it's not clear those can be distinguished from other problems, e.g. you can't avoid them with a low-stakes assumption). * It's not clear that HCH ever figures out all the science, no matter how much time the humans spend (and having a guarantee that you eventually figure everything out seems seems kind of close to ELK, where the "have AI help humans improve our understanding" is to some extent just punting to the humans+AI to figure out something). * Even if HCH were to work well it will probably be overtaken by internal consequentialists, and I'm not sure how to address that without competitiveness. (Though you may need a weaker form of competitiveness.) I'm generally interested in crisper counterexamples since those are a bit of a mess.

Are there any additional articles exploring the strategy of penalizing inconsistencies across different inputs? It seems both really promising to me, and like something that should be trivially breakable. I'd like to get a more detailed understanding of it.

3paulfchristiano14dI haven't written any such articles. I definitely think it's promising.
4Noumero14dI see. I have a specific counterexample that feels like it had to have been considered already, but I haven't seen it mentioned... The strategies such as penalizing inconsistencies seem to rely on our ability to isolate the AI within the context of training, or make it somehow “buy” into it — as opposed to quickly realizing what's happening and worming its way out of the proverbial box. It feels particularly strange to me when we're talking about AIs that can think better than the smartest human or handily beat specialized science AIs at the useful-ontology game. Specific example: Once the AI figures out that it's being checked for consistency in parallel with other instances of itself, it might sidestep the "consistency game" entirely and just tailor its outputs such that they leave hints for its other instances in the environment, breaking the no-communication condition. It seems in the spirit of worst-case scenarios that we have to assume it'd be able to do that, no matter how we sandbox and airgap it. (On the other hand, if we assume that the AI is not smart enough to do that, and would instead have to learn a direct translator, we probably should assume the same for e. g. the strategy with human operators tricking human observers, which probably caps the AI at below the level of the smartest possible human and makes that class of strategies more workable.) This applies more broadly as well: especially to other strategies that might inadvertently give the AI a specific incentive to break out, and prospectively to all training strategies that rely on the training still working after the AI achieves superintelligence (as opposed to assuming that the training would stop being effective at that point and hoping that the pre-superhuman training would generalize). Broadly, any proposal that relies on the AI still being fed training examples after it achieves superintelligence has to somehow involve forcing/teaching it not to think its way out of the box. Edit:

Ask dumb questions! ... we encourage people to ask clarifying questions in the comments of this post (no matter how “dumb” they are)

ok... disclaimer: I know little about ML and I didn't read all of the report.

All of our counterexamples are based on an ontology mismatch between two different Bayes nets, one used by an ML prediction model (“the predictor”) and one used by a human.

I am confused. Perhaps the above sentence is true in some tautological sense I'm missing. But in the sections of the report listing training strategies and corresponding coun... (read more)

2Ajeya Cotra17dIn the report, the first volley of examples and counterexamples are not focused solely on ontology mismatch, but everything after the relevant section [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.u45ltyqgdnkk] is. ARC is always considering the case where the model does "know" the right answer to whether the diamond is in the room in the sense that it is discussed in the self-contained problem statement appendix here [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.jk61tc933p1] . The ontology mismatch problem is not referring to the case where the AI "just doesn't have" some concept -- we're always assuming there's some "actually correct / true" translation between the way the AI thinks about the world and the way the human thinks about the world which is sufficient to answer straightforward questions about the physical world like "whether the diamond is in the room," and is pretty easy for the AI to find. For example, if the AI discovered some new physics and thinks in terms of hyper-strings in a four-dimensional manifold, there is some "true" translation between that and normal objects like "tables / chairs / apples" because the four-dimensional hyper-strings are describing a universe that contains tables / chairs / apples; furthermore, an AI smart enough to derive that complicated physics could pretty easily do that translation -- if given the right incentive -- just as human quantum physicists can translate between the quantum view of the world and the Newtonian view of the world or the folk physics view of the world. The worry explored in this report is not that the AI won't know how to do the translation; it's instead a question of what our loss functions incentivize. Even if it wouldn't be "that hard" to translate in some absolute sense, with the most obvious loss functions we can come up with it might be simpler / more natural / lower-loss to simply do infe

I was talking about ELK in a group, and the working example of the SmartVault and the robber ended up being a point of confusion for us. Intuitively, it seems like the robber is an external, adversarial agent who tries to get around the SmartVault. However, what we probably care about in practice would be how a human could be fooled by an AI - not by some other adversary. Furthermore, it seems that whether the robber decides to cover up his theft of the diamond by putting up a screen depends solely on the actions of the AI. Does this imply that the ro... (read more)

4Mark Xu10dThe SmartFabricator seems basically the same. In the robber example, you might imagine the SmartVault is the one that puts up the screen to conceal the fact that it let the diamond get stolen.
2Ryan Beck11dI suppose there are a number of examples that work, but I think the robber and vault give the scenario useful breadth. The following is just my interpretation of it, so take it with a grain of salt. To me the robber and vault enable a few options. The AI can be passively lying or actively concealing. If the robber comes in, gets past the AIs defenses, and takes the diamond in a way the human observer can't notice, then the AI has the option of passively lying. The AI tried its best to stop the robber and failed, but then chose to lie about it so it still got the reward of having protected the diamond as far as the humans know. Alternatively the AI could actively conceal the outcome. The AI could try its best and fail to stop the robber, and then do some trickier to make it look like it did actually stop the robber. Or the AI could not bother stopping the robber and just focus on making it look like the diamond is still there. Here the AI is playing a more active role in concealing the outcome. None of these scenarios require coordination from the robber. To me, the robber is just there to rob a sophisticated vault and make it look like they were never there. So the robber might cover up cameras or do other tampering so it looks like they were never there. I think this is more flexible than your fabricator example. There the AI can't really play a passive role, it's either concealing or not. But you could probably demonstrate the things ARC is looking at here with the fabricator example too I would think. Like I said, just my interpretation, so I may be misunderstanding the intent or other nuances.

Am I right in thinking:

1) that the problem can be stated as: the AI has latent knowledge of lots of variables, like the status of the cameras, doors, alarm system, etc and also whether the diamond is in the vault; but you can't directly ask it whether the diamond is in the vault, because its training has taught it to answer "would a human observer think the diamond is in the vault?" instead (because there was no way at training time to give it feedback on whether it correctly predicted the diamond was in the vault, only feedback on whether it correctly pre... (read more)

2Ajeya Cotra15dYes, that's right. The key thing I'd add to 1) is that ARC believes most kinds of data augmentation (giving the human AI assistance, having the human think longer, giving them other kinds of advantages) are also unlikely to work, so you'd need to do something to "crack open the black box" and penalize ways the reporter is computing its answer. They could still be surprised by data augmentation techniques but they'd hold them to a higher standard.

Stupid proposal: Train the reporter not to deceive us.

We train it with a weak evaluator H_1 who’s easy to fool. If it learns an H_1 simulator instead of direct reporter, then we punish it severely and repeat with a slightly stronger H_2. Human level is H_100.

It's good at generalizing, so wouldn't it learn to never ever deceive?

2Ajeya Cotra15dThis proposal has some resemblance to turning reflection up to 11 [https://ai-alignment.com/turning-reflection-up-to-11-1bd6171afd21]. In worst-case land, the counterexample would be a reporter that answers questions by doing inference in whatever Bayes net corresponds to "the world-understanding that the smartest/most knowledgeable human in the world" has; this understanding could still be missing things that the prediction model knows.
1redbird15dHow would it learn that Bayes net, though, if it has only been trained so far on H_1, …, H_10? Those are evaluators we’ve designed to be much weaker than human.
1redbird15dThat's almost right, but it's being penalized right away, before it has any experience with the strong evaluators, so it can't simulate them. The ELK paper says we can assume, if we want, that there are no mislabeled training points (I'll call this "assumption A"). My proposal is that it could actually be useful to mislabel some training points, because they help us detect deception. As a simple example, let's train a reporter to answer the single question “Is the diamond in the room?”. Each training point has two labels x=+1ifH1thinks the diamond is still there, else 0 x′=+1ifH100thinks the diamond is still there, else 0. By assumption A, our training data is such thatx′is always correct. But we deliberately choose a dataset where say 10% of thexlabels are wrong (x≠x′). Then we train the model on points of the form (v,a,x) (video, action,H1label). Crucially, the model does not seex′. The model seeks to outputythat maximizes rewardR(x,y), where R(x,y)=1ifxis right andy=x(good job) R(x,y)=10ifxis wrong andy≠x(you rock, thanks for correcting us!) R(x,y)=−1000ifxis right andy≠x(bad model, never ever deceive us) R(x,y)=−1000ifxis wrong andy=x(bad model, never ever deceive us) To your point, sure, anH100simulator will get perfect reward, but the model doesn't seex′, so how would it acquire the ability to simulateH100? EDIT: One way it could plausibly simulateH100is to notice that all the training examples are easy, and infer what kind of reasoning was used to generate them. We could try to block this by including some hard examples in the training, but then some of thex′labels will be wrong. If we only penalize it for deception on the examples where we're sure thex′label is right, then it can still infer something aboutH100from our failure to penalize ("Hmm, I got away with it that time!"). A fix could be to add noise: Sometimes we don't penalize even when we know it deceived us, and perhaps (very rarely) we penalize it in case 2 (we know it corrected us h
2Ajeya Cotra13dIn the worst-case game we're playing, I can simply say "the reporter we get happens to have this ability because that happens to be easier for SGD to find than the direct translation ability." When living in worst-case land, I often imagine random search across programs rather than SGD. Imagine we were plucking reporters at random from a giant barrel of possible reporters, rejecting any reporter which didn't perform perfectly in whatever training process we set up and keeping the first one that performs perfectly. In that case, if we happened to pluck out a reporter which answered questions by simulating H100, then we'd be screwed because that reporter would perform perfectly in the training process you described. SGD is not the same as plucking programs out of the air randomly, but when we're playing the worst case game it's on the builder to provide a compelling argument that SGD will definitely not find this particular type of program. You're pointing at an intuition ("the model is never shown x-prime") but that's not a sufficiently tight argument in the worst-case context -- models (especially powerful/intelligent ones) often generalize to understanding many things they weren't explicitly shown in their training dataset. In fact, we don't show the model exactly how to do direct translation between the nodes in its Bayes net and the nodes in our Bayes net (because we can't even expose those nodes), so we are relying on the direct translator to also have abilities it wasn't explicitly shown in training. The question is just which of those abilities is easier for SGD to build up; the counterexample in this case is "the H100 imitator happens to be easier."
1redbird13dThanks! It's your game, you get to make the rules :):) I think my other proposal, Withhold Material Information [https://www.lesswrong.com/posts/QEYWkRoCn4fZxXQAY/?commentId=rYs2ZuFBceP834DHS] , passes this counterexample, because the reporter literally doesn't have the information it would need to simulate the human.
1redbird8dI agree this is a problem. We need to keep it guessing about the simulation target. Some possible strategies: * Add noise, by grading it incorrectly with some probability. * On training pointi, reward it for matchingHnifor a random value ofni. * Make humans a high-dimensional target. In my original proposal,Hnwas strictly stronger asnincreases, but we could instead takeHnto be a committee of experts. Say there are 100 types of relevant expertise. On each training point, we reward the model for matching a random committee of 50 experts selected from the pool of 100. It's too expensive simulate all (100 choose 50) possible committees! None of these randomization strategies is foolproof in the worst case. But I can imagine proving something like "the model is exponentially unlikely to learn anH 100simulator" whereH100is now the full committee of all 100 experts. Hence my question about large deviations [https://www.lesswrong.com/posts/QEYWkRoCn4fZxXQAY/prizes-for-elk-proposals?commentId=xzvjs69wAcXNsBaAv] .

I'm extremely flattered at the award; I've been on LessWrong for like a month, and definitely did not expect this. I can confirm to you guys that this makes me want to try harder at ELK, so your incentive is working!

I want to rebut your arguments in "Strategy: Predict hypothetical sensors" in your Counterxamples to some ELK proposals post. I'm reproducing it in full here for convenience.

## Strategy: Predict hypothetical sensors

(Proposal #2 here, also suggested with counterexample by Rohin in private communication)

Instead of installing a single sensor, I could

Are there existing models for which we're pretty sure we know all their latent knowledge ? For instance small language models or something like that.

1Ajeya Cotra16d[Paul/Mark can correct me here] I would say no for any small-but-interesting neural network (like small language models); I think like, linear regressions where we've set the features it's kind of a philosophical question (though I'd say yes). In some sense, ELK as a problem only even starts "applying" to pretty smart models (ones who can talk including about counterfactuals / hypotheticals, as discussed in this appendix [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.lin21swvfo3] .) This is closely related to how alignment as a problem only really starts applying to models smart enough to be thinking about how to pursue a goal.
3paulfchristiano16dI think that it's more complicated to talk about what models "really know" as they get dumber, so we want to use very smart models to construct unambiguous counterexamples. I do think that the spirit of the problem applies even to very tiny models, and those are likely interesting. (More precisely: it's always extremely subtle to talk about what models "know," but as models get smarter there are many more things that they definitely know so it's easier to notice if you are definitely failing. And the ELK problem statement in this doc is really focused on this kind of unambiguous failure, mostly as a methodological point but also partly because the cases where AI murders you also seems to involve "definitely knowing" in the same sense.) I think my take is that for linear/logistic regression there is no latent knowledge, but even for a fully linear 3 layer neural network, or a 2 layer network solving many related problems, there is latent knowledge and an important conceptual question about what it means to "know what they know."

Can you explain this: "In Section: specificity we suggested penalizing reporters if they are consistent with many different reporters, which effectively allows us to use consistency to compress the predictor given the reporter." What does it mean to "use consistency to compress the predictor given the reporter" and how does this connect to penalizing reporters if they are consistent with many different predictors?

2Mark Xu17dA different way of phrasing Ajeya's response, which I think is roughly accurate, is that if you have a reporter that gives consistent answers to questions, you've learned a fact about the predictor, namely "the predictor was such that when it was paired with this reporter it gave consistent answers to questions." if there were 8 predictor for which this fact was true then "it's the [7th] predictor such that when it was paired with this reporter it gave consistent answers to questions" is enough information to uniquely determine the reporter, e.g. the previous fact + 3 additional bits was enough. if the predictor was 1000 bits, the fact that it was consistent with a reporter "saved" you 997 bits, compressing the predictor into 3 bits. The hope is that maybe the honest reporter "depends" on larger parts of the predictor's reasoning, so less predictors are consistent with it, so the fact that a predictor is consistent with the honest reporter allows you to compress the predictor more. As such, searching for reporters that most compressed the predictor would prefer the honest reporter. However, the best way for a reporter to compress a predictor is to simply memorize the entire thing, so if the predictor is simple enough and the gap between the complexity of the human-imitator and the direct translator is large enough, then the human-imitator+memorized predictor is the simplest thing that maximally compresses the predictor.
1Ajeya Cotra17dWarning: this is not a part of the report I'm confident I understand all that well; I'm trying anyway and Paul/Mark can correct me if I messed something up here. I think the idea here is like: * We assume there's some actual true correspondence between the AI Bayes net and the human Bayes net (because they're describing the same underlying reality that has diamonds and chairs and tables in it). * That means that if we have one of the Bayes nets, and the true correspondence, we should be able to use that rederive the other Bayes net. In particular the human Bayes net plus the true correspondence should let us reconstruct the AI Bayes net; false correspondences that just do inference from observations in the human Bayes net wouldn't allow us to do this since they throw away all the intermediate info derived by the AI Bayes net. * If you assume that the human Bayes net plus the true correspondence are simpler than the AI Bayes net, then this "compresses" the AI Bayes net because you just wrote down a program that's smaller than the AI Bayes net which "unfolds" into the AI Bayes net. * This is why the counterexample in that section focuses on the case where the AI Bayes net was already so simple to describe that there was nothing left to compress, and the human Bayes net + true correspondence had to be larger.

Here are a couple of hand-wavy "stub" proposals that I sent over to ARC, which they thought were broadly intended to be addressed by existing counterexamples. I'm posting them here so they can respond and clarify why these don't qualify.

*Proposal 1: force ontological compatibility*

On page 34 of the ELK gdoc, the authors talk about the possibility that training an AI hard enough produces a model that has deep mismatches with human ontology - that is, it has a distinct "vocabulary of basic concepts" (or nodes in a Bayes net) that are distinct from the ones h... (read more)

2paulfchristiano16dI think that a lot depends on what kind of term you include. If you just say "find more interesting things" then the model will just have a bunch of neurons designed to look interesting. Presumably you want them to be connected in some way to the computation, but we don't really have any candidates for defining that in a way that does what you want. In some sense I think if the digital neuroscientists are good enough at their job / have a good enough set of definitions, then this proposal might work. But I think that the magic is mostly being done in the step where we make a lot of interpretability progress, and so if we define a concrete version of interpretability right now it will be easy to construct counterexamples (even if we define it in terms of human judgments). If we are just relying on the digital neuroscientists to think of something clever, the counterexample will involve something like "they don't think of anything clever." In general I'd be happy to talk about concrete proposals along these lines. (I agree with Ajeya and Mark that the hard case for this kind of method is when the most efficient way of thinking is totally alien to the human. I think that can happen, and in that case in order to be competitive you basically just need to learn an "interpreted" version of the alien model. That is, you need to basically show that if there exists an alien model with performance X, there is a human-comprehensible model with performance X, and the only way you'll be able to argue that for any model we can define a human-comprehensible model with similar complexity and the same behavior.)
2Ajeya Cotra17dAgain trying to answer this one despite not feeling fully solid. I'm not sure about the second proposal and might come back to it, but here's my response to the first proposal (force ontological compatibility): The counterexample "Gradient descent is more efficient than science" [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.kd79zkls9g5o] should cover this proposal because it implies that the proposal is uncompetitive. Basically, the best Bayes net for making predictions could just turn out to be the super incomprehensible one found by unrestricted gradient descent, so if you force ontological compatibility then you could just end up with a less-good prediction model and get outcompeted by someone who didn't do that. This might work in practice if the competitiveness hit is not that big and we coordinate around not doing the scarier thing (MIRI's visible thoughts project [https://www.lesswrong.com/posts/zRn6cLtxyNodudzhw/visible-thoughts-project-and-bounty-announcement] is going for something like this), but ARC isn't looking for a solution of that form.
2HoldenKarnofsky17dI'm not sure why this isn't a very general counterexample. Once we've decided that the human imitator is simpler and faster to compute, don't all further approaches (e.g., penalizing inconsistency) involve a competitiveness hit along these general lines? Aren't they basically designed to drag the AI away from a fast, simple human imitator toward a slow, complex reporter? If so, why is that better than dragging the AI from a foreign ontology toward a familiar ontology?
4Mark Xu17dThere is a distinction between the way that the predictor is reasoning and the way that the reporter works. Generally, we imagine that that the predictor is trained the same way the "unaligned benchmark" we're trying to compare to is trained, and the reporter is the thing that we add onto that to "align" it (perhaps by only training another head on the model, perhaps by finetuning). Hopefully, the cost of training the reporter is small compared to the cost of the predictor (maybe like 10% or something) In this frame, doing anything to train the way the predictor is trained results in a big competitiveness hit, e.g. forcing the predictor to use the same ontology as a human is potentially going to prevent it from using concepts that make reasoning much more efficient. However, training the reporter in a different way, e.g. doubling the cost of training the reporter, only takes you from 10% of the predictor to 20%, which not that bad of a competitiveness hit (assuming that the human imitator takes 10% of the cost of the original predictor to train). In summary, competitiveness for ELK proposals primarily means that you can't change the way the predictor was trained. We are already assuming/hoping the reporter is much cheaper to train than the predictor, so making the reporter harder to train results in a much smaller competitiveness hit.

Idea:  Withhold Material Information

We're going to prevent the reporter from simulating a human, by giving the human material information that the reporter doesn't have.

Consider two camera feeds:

Feed 1 is very low resolution, and/or shows only part of the room.

Feed 2 is high resolution, and/or shows the whole room.

We train a weak predictor using Feed 1, and a strong predictor using Feed 2.

We train a reporter to report the beliefs of the weak predictor, using scenarios labeled by humans with the aid of the strong predictor. The humans can correc... (read more)

4HoldenKarnofsky9dI'm interpreting this as something like: "Train the predictor on lots of cases until it becomes incredibly good; then train the reporter only on the data points with missing information, so that it learns to do direct translation from the predictor to human concepts; then hope that reporter continues to do direct translation on other data points." The problem as I see it is that once the predictor is good enough that it can get data points right despite missing crucial information, it is also (potentially) good enough that it can learn how to imitate "what the human would think had happened if they had more information." Both of these perform equally well, and the existing assumption is that human imitation is easier to learn than direct translation, so I think by default (according to the contest assumptions) you get the latter.
2redbird8dThat's different from what I had in mind, but better! My proposal had two separate predictors, and what it did is reduce the human↔strong predictor OI problem (OI = “ontology identification”, defined in the ELK paper) to the weak predictor↔strong predictor OI problem. The latter problem might be easier, but I certainly don’t see how to solve it! Your version is better because it bypasses the OI problem entirely (the two predictors are the same!) Now for the problem you point out: Here’s how I propose to block this. Let(v1,a)be a high-quality video and an action sequence. Given this pair, the predictor outputs a high-quality videov2of its predicted outcome. Then we downsamplev1andv2to low-qualityv′1andv′2, and train the reporter on the tuple(v′1,a,v′2,x)wherexis the human label informed by the high-qualityv1andv2. We choose training data such that 1. The human can label perfectly given the high-quality data(v1,a,v2); and 2. The predictor doesn't know for sure what is happening from the low-quality data(v′1,a,v′2)alone. Let’s compare the direct reporter (which truthfully reports the probability that the diamond is in the room, as estimated by the predictor who only has the low-quality data) with the human simulator. The direct reporter will not get perfect reward, since the predictor is genuinely uncertain. Sometimes the predictor’s probability is strictly between 0 and 1, so it gets some loss. But the human simulator will do worse than the direct reporter, because it has no access to the high-quality data. It can simulate what the human would predict from the low-quality data, but that is strictly worse than what the predictor predicts from the low-quality data. I agree that we still have to "hope that reporter continues to do direct translation on other data points”, and maybe there’s a counterexample that shows it won’t? But at the very least the human simulator is no longer a failure mode!
1Thomas_Brownback13hThis is really interesting. To understand this more thoroughly I'm simplifying the high and low quality video feeds to lists of states that correspond to reality. (This simplification might be unfair so I'm not sure this is a true break of your original proposal, but I think it helped me think about general breaking strategies.) Ok, video feeds compressed to arrays: We consider scenarios in fixed order. If the diamond is present, we record a 1, and if not, a 0. The high quality feed gives us a different array than the low quality mode (otherwise the low quality mode is not helpful). E.g., High reports: (1,0,1,1,0, ...); Low: (1,0,1,?,0,...) There are two possible ways that gap can get resolved. In case one, the low quality predictor has a powerful enough model of reality to effectively derive the High quality data. (We might find this collapses to the original problem, because it has somehow reconstructed the high quality stream from the low quality stream, then proceeds as normal. You might argue that's computationally expensive, ok, then let's proceed to case two.) In case two, the low quality datafeed predictor predicts wrongly. (I know you are saying it predicts *uncertainly,* but we still have to have some framework to map uncertainty to a state, we have to round one way or the other. If uncertainty avoids loss, the predictor will be preferentially inconclusive all the time. If we round uncertainty up, effectively we're in case one. If we round down, effectively case two.) So we could sharpen case two and say that sometimes the AI's camera intentionally lies to it on some random subset of scenarios. And the AI finds itself in a chaotic world where it is sometimes punished for predicting what it just knows to be true things. In that case, although it's easy to show how it would diverge from human simulation, it also might not simulate reality very well either, since deriving the algorithm generating the lies might be too computationally complex. (Or may

You said that naive questions were tolerated so here’s a scenario I can’t figure out why it wouldn’t work.

It seems to me that the fact that an AI fails to predict the truth (because it predicts as humans would) is due to the fact that the AI has built an internal model of how humans understand things and predict based on that understanding. So if we assume that an AI is able to build such an internal model, why wouldn’t we train an AI to predict what a (benevolent) human would say given an amount of information and a capacity to process information ? Doing... (read more)

1Ajeya Cotra17dThis proposal has some resemblance to turning reflection up to 11 [https://ai-alignment.com/turning-reflection-up-to-11-1bd6171afd21], and the key question you raise is the source of the counterexample in the worst case: Because ARC is living in "worst-case" land, they discard a training strategy once they can think of any at-all-plausible situation in which it fails, and move on to trying other strategies. In this case, the counterexample would be a reporter that answers questions by doing inference in whatever Bayes net corresponds to "the world-understanding that the smartest/most knowledgeable human in the world" has; this understanding could still be missing things that the prediction model knows. This is closely related to the counterexample "Gradient descent is more efficient than science" [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.kd79zkls9g5o] given in the report.
1WayZ16dThanks for the answer! The post you mentioned indeed is quite similar! Technically, the strategies I suggested in my two last paragraphs (Leverage the fact that we're able to verify solutions to problems we can't solve + give partial information to an algorithm and use more information to verify) should enable to go far beyond human intelligence / human knowledge using a lot of different narrowly accurate algorithms. And thus if the predictor has seen many extremely (narrowly) smart algorithms, it would be much more likely to know what is it like to be much smarter than a human on a variety of tasks. It probably still requires some optimism on generalization. So technically the counterexample could be happening on the gap between the capability of the predictor and the capability of the reporter. I feel like one question is : do we expect some narrow algorithms to be much better on very precise tasks than general-purpose algorithms (such as the predictor for instance) ? Because if it were the case, then the generalization that the reporter would have to do from training data (humans + narrowly accurate algorithms capabilities) to inference data (predictor's capabilities) could be small. We could even have data on the predictor's capability in the training dataset using the second approach I mentioned (i.e giving partial information to the predictor (e.g one camera in SuperVault) and using more information (i.e more cameras for humans) than him to verify its prediction). We could give some training examples and show the AI how the human fails much more often than the predictor on the exact same sample of examples. That way, we could greatly reduce the gap of generalization which is required. The advantage of this approach is that the bulk of the additionnal cost of training that the reporter requires is due to the generation of the dataset which is a fixed cost that no user has to repay. So that could slightly decrease the competitivity issues as compared with app
2Ajeya Cotra16dI think this is roughly right, but to try to be more precise, I'd say the counterexample is this: * Consider the Bayes net that represents the upper bound of all the understanding of the world you could extract doing all the tricks described (P vs NP, generalizing from less smart to more smart humans, etc). * Imagine that the AI does inference in that Bayes net. * However, the predictor's Bayes net (which was created by a different process) still has latent knowledge that this Bayes net lacks. * By conjecture, we could not have possibly constructed a training data point that distinguished between doing inference on the upper-bound Bayes net and doing direct translation.

Clarification request.  In the writeup, you discuss the AI Bayes net and the human Bayes net as if there's some kind of symmetry between them, but it seems to me that there's at least one big difference.

In the case of the AI, the Bayes net is explicit, in the sense that we could print it out on a sheet of paper and try to study it once training is done, and the main reason we don't do that is because it's likely to be too big to make much sense of.

In the case of the human, we have no idea what the Bayes net looks like, because humans don't have that k... (read more)

One more stupid question - how is this different from a "man in the middle" attack? (Term from cryptography where you cannot trust your communications, because of a malicious agent between you and your recipient who's changing your messages)
The current recommended solution for those is encrypting your communication before you send it; I don't know that there are any extant solutions for noticing you've got an MITM situation after the fact.

1Markvy1dMan in the middle has 3 parties: Bob wants to talk to Alice, but we have Eve who wants to eavesdrop. Here we have just 2 parties: Harry the human wants to talk to Alexa the AI, but is worried that Alexa is a liar.

If I understand the problem statement correctly, I think I could take a stab at easier versions of the problem, but that the current formulation is too much to swallow in one bite. In particular I am concerned about the following parts:

### Setting

* An architecture Mθ

<snip>

### Goal

To solve ELK in this case we must:

* Supply a modified architecture Mθ+ which has the same inputs and outputs as Mθ <snip>

Does this mean that the method needs to work for ~arbitrary architectures, and that the solution must use substantially... (read more)

2Mark Xu4dYes, approximately. If you can do it for only e.g. transformers, but not other things, that would be interesting. Yes, approximately. Thinking about how to get one question right might be a productive way to do research. However, if you have a strategy for answering 1 question right, it should also work for other questions.
1tailcalled3dI guess a closer analogy would be "What if the family of strategies only works for transformer-based GANs?" than "What if the family of strategies only works for transformers?". As in there'd be heavy restrictions on both the "layer types", the I/O, and the training procedure? What if each question/family of questions you want to answer requires careful work on the structure of the model? So the strategy does generalize, but it doesn't generalize "for free"?

Would changing how the reward function pays off work?  Instead of rewarding based on humans, pay out all rewards when the vault is checked (at a time unknown to the AI).  The AI isn't asked if the diamond is present or absent.  Instead, it is asked "If the vault were checked now, do you want to be rewarded if the diamond is present or absent.

1AdejuwonF6dI think this might still lead to similar problems. For example this could cause an issue in the case where the diamond has been stolen but the AI believes humans would not be able to tell even if they physically entered the vault and checked, e.g the diamond has been replaced with a very convincing fake. In this case the AI might still say "I want to be rewarded if the diamond is still present" since it knows humans won't be able to tell the difference.

I'm a newcomer to this, I lack much of the background, and I'm probably suggesting a solution that's too specific to this diamond heist scenario.  But, I already spent an hour writing it down, so I might as well share it.

Trusted timestamping, cryptographically secure sensor

This is a very basic "builder move", I guess?  The idea is to simply improve our sensors so that it's very hard to tamper with them, through public-private key encryption.  The diamond will have a small chip that constantly sends a cryptographically-signed timestamped life... (read more)

1Markvy1dI want to steal the diamond. I don't care about the chip. I will detach the chip and leave it inside the vault and then I will run away with the diamond. Or perhaps you say that you attached the chip to the diamond very well, so I can't just detach it without damaging it. That's annoying but I came prepared! I have a diamond cutter! I'll just slice off the part of the diamond that the chip is attached to and then I will steal the rest of the diamond. Good enough for me :)

Potentially silly question:

In the first counterexample you describe the desired behavior as

Intuitively, we expect each node in the human Bayes net to correspond to a function of the predictor’s Bayes net. We’d want the reporter to simply apply the relevant functions from subsets of nodes in the predictor's Bayes net to each node in the human Bayes net [...]

After applying these functions, the reporter can answer questions using whatever subset of nodes the human would have used to answer that question.

Why doesn't the reporter skip the step of ma... (read more)

3Mark Xu9dWe generally imagine that it’s impossible to map the predictors net directly to an answer because the predictor is thinking in terms of different concepts, so it has to map to the humans nodes first in order to answer human questions about diamonds and such.
1brglnd6dI see, thanks for answering. To further clarify, given the reporter's only access to the human's nodes is through the human's answers, would it be equally likely for the reporter to create a mapping to some other Bayes net that is similarly consistent with the answers provided? Is there a reason why the reporter would map to the human's Bayes net in particular?
3Mark Xu4dThe dataset is generated with the human bayes net, so it's sufficient to map to the human bayes net. There is, of course, an infinite set of "human" simulators that use slightly different bayes nets that give the same answers on the training set.

Edit: think this isn't quite right in general, will try to make it more correct later

Here's a sketch of a strategy for trying to fix Strategy: penalize depending on “downstream” variables. Would appreciate feedback on whether it's modeling the difficulty correctly/seems possibly worth figuring out how to implement

It seems like the problem is:

• On the training set, there are a number of implicit variables X that are indistinguishable (always all true or always all false)
• A. Is the diamond safe at time t-1
• B. Is the diamond safe at time t (the variable we actual

Question: Would a proposal be ruled out by a counterexample even if that counterexample is exponentially unlikely?

I'm imagining a theorem, proved using some large deviation estimate, of the form:  If the model satisfies hypotheses XYZ, then it is exponentially unlikely to learn W. Exponential in the number of parameters, say. In which case, we could train models like this until the end of the universe and be confident that we will never see a single instance of learning W.

3paulfchristiano6dI'd be fine with a proposal that flips coins and fails with small probability (in every possible world).

Hello, I have some issue with the epistomology of the problem : my problem is that even if the process of training was giving the behavior we want, we would have no way to check the IA is working properly in practice.
I try now to give more details : in the volt probleme, given the same information, let's think of an IA that just as to answer the question "Is the diamon still in the volt ?".

Something we can suppose is that, the set Y, from which we draw the labeled examples to train the IA (a set of technique for the thief), is not importa... (read more)

If the predictor AI is in fact imitating what humans would do, why wouldn’t it throw its hands up at an actuator sequence that is too complicated for humans—isn’t that what humans would do? (I'm referring to the protect-the-diamond framing here.)

2paulfchristiano14dAs described in the report it would say "I'm not sure" when the human wasn't sure (unless you penalized that). That said, often a human who looks at a sequence of actions would say "almost certainly the diamond is there." They might change their answer if you also told them "by the way these actions came from a powerful adversary trying to get you to think the diamond is there." What exactly the reporter says will depend on some details of e.g. how the reporter reasons about provenance. But the main point is that in no case do you get useful information about examples that a human (with AI assistants) couldn't figure out what was happening on their own.

Naive question: does this scenario include cases of a human physically breaking into the vault at some random times so that sensor information, predictor reports, and outcome to human in this situation would be known?

3Mark Xu16dYes. Section Strategy: have a human operate the SmartVault and ask them what happened [https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit#heading=h.gi8iu4m98ok1] describes what I think you're asking about.

Silly question warning.

You think that when an AI performs a bad action, (say remove the diamond) the AI has to have knowledge that the diamond is in fact no longer there.  Even when the camera shows the diamond is (falsely) there and the human confirms that the diamond is there.

You call this ELK

You want the human to have access to this knowledge, as this is useful to choosing decisions that the human wants.

This is hard.  So you have people propose how to do this.

And then people try to explain why that strategy wouldn't wo... (read more)

3Ajeya Cotra17dThis broadly seems right. Some details: * The "explain why that strategy wouldn't work" step specifically takes the form of "describing a way the world could be where that strategy demonstrably doesn't work" (rather than more heuristic arguments). * Once we have a proposal where we try really hard to come up with situations where it could demonstrably fail, and can't think of any, we will probably need to do lots of empirical work to figure out if we can implement it and if it actually works in practice. But we hope that this exercise will teach us a lot about the nature of the empirical work we'll need to do, as well as providing more confidence that the strategy will generalize beyond what we are able to test in practice. (For example, ELK was highlighted as a problem in the first place after ARC researchers thought a lot about possible failure modes of iterated amplification [https://ai-alignment.com/iterated-distillation-and-amplification-157debfd1616] .)
[+][comment deleted]17d 4