Edit: I no longer endorse this comment; see this comment instead.
I think you’ve just assumed the entire inner alignment problem away. You assume that the model—the imitation learner—is a perfect Bayesian, rather than just some trained neural network or other function approximator (edit: I was just misinterpreting here and the training process is supposed to Bayesian rather than the model, see Rohin’s comment below). The entire point of the inner alignment problem, though, is that you can’t guarantee that your trained model is actually a perfect Bayesian—or anything else. In practice, all we actually generally do when we do ML is we train some neural network on some training data/environment and hope that the implicit inductive biases of our training process are such that we end up with a model doing the right thing, meaning that we can’t really control what sort of model—Bayesian or anything else—that we get when we do ML, and that uncontrollability, in my eyes, is the inner alignment problem.
While I share your position that this mostly isn’t addressing the things that make inner alignment hard / risky in practice, I agree with Vanessa that this does not assume the inner alignment problem away, unless you have a particularly contorted definition of “inner alignment”.
There’s an optimization procedure (Bayesian updating) that is selecting models (the model of the demonstrator) that can themselves be optimizers, and you could get the wrong one (e.g. the model that simulates an alien civilization that realizes it’s in a simulation and predicts well to be selected by the Bayesian updating but eventually executes a treacherous turn). The algorithm presented precludes this from happening with some probability. We can debate the significance, but it seems to me like it is clearly doing something solution-like with respect to the inner alignment problem.
Hmmm… I think I just misunderstood the setup then. It seemed to me like the Bayesian updating was supposed to represent the model rather than the training process, but under the framing that you just said, I agree that it’s relevant. It’s worth noting that I do think most of the danger lies in the ways in which gradient descent is not a perfect Bayesian, but I agree that modeling gradient descent as Bayesian is certainly relevant.
I think this is completely unfair. The inner alignment problem exists even for perfect Bayesians, and solving it in that setting contributes much to our understanding. The fact we don’t have satisfactory mathematical models of deep learning performance is a different problem, which is broader than inner alignment and to first approximation orthogonal to it. Ideally, we will solve this second problem by improving our mathematical understanding of deep learning and/or other competitive ML algorithms. The latter effort is already underway by researchers unrelated to AI safety, with some results. Moreover, we can in principle come up with heuristics how to apply this method of solving inner alignment (which I call “confidence thresholds” in my own work) to deep learning: e.g. use NNGP to measure confidence or use an evolutionary algorithm with a population of networks and check how well they agree with each other. Of course if we do this we won’t have formal guarantees that it will work, but, like I said this is a broader issue than inner alignment.
Regardless of how you define inner alignment, I think that the vast majority of the existential risk comes from that “broader issue” that you’re pointing to of not being able to get worst-case guarantees due to using deep learning or evolutionary search or whatever. That leads me to want to define inner alignment to be about that problem—and I think that is basically the definition we give in Risks from Learned Optimization, where we introduced the term. That being said, I do completely agree that getting a better understanding of deep learning is likely to be critical.
I think that the vast majority of the existential risk comes from that “broader issue” that you’re pointing to of not being able to get worst-case guarantees due to using deep learning or evolutionary search or whatever. That leads me to want to define inner alignment to be about that problem...
[Emphasis added.] I think this is a common and serious mistake-pattern, and in particular is one of the more common underlying causes of framing errors. The pattern is roughly:
Notice cluster of problems X which have a similar underlying causal pattern Cause(X)
Notice problem y in which Cause(X) could plausibly play a role
On deeper examination, the cause of y cause(y) doesn’t quite fit Cause(X)
Attempt to redefine the pattern Cause(X) to include cause(y)
The problem is that, in trying to “shoehorn” cause(y) into the category Cause(X), we miss the opportunity to notice a different pattern, which is more directly useful in understanding y as well as some other cluster of problems related to y.
Now, this is not to say that changing a definition to fit another case is always the wrong move. Sometimes, a new use-case shows that the definition can handle the new case while still preserving its original essence. The key question is whether the problem cluster X and problem y really do have the same underlying structure, or if there’s something genuinely new and different going on in y.
In this case, I think it’s pretty clear that there is more than just inner alignment problems going on in the lack of worst-case guarantees for deep learning/evolutionary search/etc. Generalization failure is not just about, or even primarily about, inner agents. It occurs even in the absence of mesa-optimizers. So defining inner alignment to be about that problem looks to me like a mistake—you’re likely to miss important, conceptually-distinct phenomena by making that move. (We could also come at it from the converse direction: if something clearly recognizable as an inner alignment problem occurs for ideal Bayesians, then redefining the inner alignment problem to be “we can’t control what sort of model we get when we do ML” is probably a mistake, and you’re likely to miss interesting phenomena that way which don’t conceptually resemble inner alignment.)
A useful knee-jerk reaction here is to notice when cause(y) doesn’t quite fit the pattern Cause(X), and use that as a curiosity-pump to look for other cases which resemble y. That’s the sort of instinct which will tend to turn up insights we didn’t know we were missing.
I mean, I don’t think I’m “redefining” inner alignment, given that I don’t think I’ve ever really changed my definition and I was the one that originally came up with the term (inner alignment was due to me, mesa-optimization was due to Chris van Merwijk). I also certainly agree that there are “more than just inner alignment problems going on in the lack of worst-case guarantees for deep learning/evolutionary search/etc.”—I think that’s exactly the point that I’m making, which is that while there are other issues, inner alignment is what I’m most concerned about. That being said, I also think I was just misunderstanding the setup in the paper—see Rohin’s comment on this chain.
If the inner alignment problem did not exist for perfect Bayesians, but did exist for neural networks, then it would appear to be a regime where more intelligence makes the problem go away. If the inner alignment problem were ~solved for perfect Bayesians, but unsolved for neural networks, I think there’s still some of the flavor of that regime, but we do have to be pretty careful to make sure we’re applying the same sort of solution to the non-Bayesian algorithms. I think in Vanessa’s comment above, she’s suggesting this looks doable.
Note the method here of avoiding mesa-optimizers: error bounds. Neural networks don’t have those. Naturally, one way to make mesa-optimizer-deceptively-selected-errors go away is just to have better learning algorithms that make errors go away. Algorithms like Gated Linear Networks with proper error bounds may be a safer building block for AGI. But none of this takes away from the fact that it is potentially important to figure out how to avoid mesa-optimization in neural networks, and I would add to your claim that this is a much harder setting; I would say it’s a harder setting because of the non-existence of error bounds.
I think I mostly agree with what you’re saying here, though I have a couple of comments—and now that I’ve read and understand your paper more thoroughly, I’m definitely a lot more excited about this research.
then it would appear to be a regime where more intelligence makes the problem go away.
I don’t think that’s right—if you’re modeling the training process as Bayesian, as I now understand, then the issue is that what makes the problem go away isn’t more intelligent models, but less efficient training processes. Even if we have arbitrary compute, I think we’re unlikely to use training processes that look Bayesian just because true Bayesianism is really hard to compute such that for basically any amount of computation that you have available to you, you’d rather run some more efficient algorithm like SGD.
I worry about these sorts of Bayesian analyses where we’re assuming that we’re training a large population of models, one of which is assumed to be an accurate model of the world, since I expect us to end up using some sort of local search instead of a global search like that—just because I think that local search is way more efficient than any sort of Bayesianish global search.
Note the method here of avoiding mesa-optimizers: error bounds. Neural networks don’t have those. Naturally, one way to make mesa-optimizer-deceptively-selected-errors go away is just to have better learning algorithms that make errors go away. Algorithms like Gated Linear Networks with proper error bounds may be a safer building block for AGI. But none of this takes away from the fact that it is potentially important to figure out how to avoid mesa-optimization in neural networks, and I would add to your claim that this is a much harder setting; I would say it’s a harder setting because of the non-existence of error bounds.
I definitely agree with all of this, except perhaps on whether Gated Linear Networks are likely to help (though I don’t claim to actually understand backpropagation-free networks all that well).
I don’t think that’s right—if you’re modeling the training process as Bayesian, as I now understand, then the issue is that what makes the problem go away isn’t more intelligent models, but less efficient training processes. Even if we have arbitrary compute, I think we’re unlikely to use training processes that look Bayesian just because true Bayesianism is really hard to compute such that for basically any amount of computation that you have available to you, you’d rather run some more efficient algorithm like SGD.
I feel this is a wrong way to look at it. I expect any effective learning algorithm to be an approximation of Bayesianism in the sense that, it satisfies some good sample complexity bound w.r.t. some sufficiently rich prior. Ofc it’s non-trivial to (i) prove such a bound for a given algorithm (ii) modify said algorithm using confidence thresholds in a way that leads to a safety guarantee. However, there is no sharp dichotomy between “Bayesianism” and “SGD” such that this approach obviously doesn’t apply to the latter, or to something competitive with the latter.
I agree that at some level SGD has to be doing something approximately Bayesian. But that doesn’t necessarily imply that you’ll be able to get any nice, Bayesian-like properties from it such as error bounds. For example, if you think of SGD as effectively just taking the MAP model starting from sort of simplicity prior, it seems very difficult to turn that into something like the top N posterior models, as would be required for an algorithm like this.
I mean, there’s obviously a lot more work to do, but this is progress. Specifically if SGD is MAP then it seems plausible that e.g. SGD + random initial conditions or simulated annealing would give you something like top N posterior models. You can also extract confidence from NNGP.
I agree that this is progress (now that I understand it better), though:
if SGD is MAP then it seems plausible that e.g. SGD + random initial conditions or simulated annealing would give you something like top N posterior models
I think there is strong evidence that the behavior of models trained via the same basic training process are likely to be highly correlated. This sort of correlation is related to low variance in the bias-variance tradeoff sense, and there is evidence that not only do massive neural networks tend to have pretty low variance, but that this variance is likely to continue to decrease as networks become larger.
Here’s another way how you can try implementing this approach with deep learning. Train the predictor using meta-learning on synthetically generated environments (sampled from some reasonable prior such as bounded Solomonoff or maybe ANNs with random weights). The reward for making a prediction is 1−(1−δ)maxipi+ϵqi+ϵ, where pi is the predicted probability of outcome i, qi is the true probability of outcome i and ϵ,δ∈(0,1) are parameters. The reward for making no prediction (i.e. querying the user) is 0.
This particular proposal is probably not quite right, but something in that general direction might work.
Sure, but you have no guarantee that the model you learn is actually going to be optimizing anything like that reward function—that’s the whole point of the inner alignment problem. What’s nice about the approach in the original paper is that it keeps a bunch of different models around, keeps track of their posterior, and only acts on consensus, ensuring that the true model always has to approve. But if you just train a single model on some reward function like that with deep learning, you get no such guarantees.
Right, but but you can look at the performance of your model in training, compare it to the theoretical optimum (and to the baseline of making no predictions at all) and get lots of evidence about safety from that. You can even add some adversarial training of the synthetic environment in order to get tighter bounds. If on the vast majority of synthetic environments your model makes virtually no mispredictions, then, under the realizability assumption, it is very unlikely to make mispredictions in deployment. Ofc the realizability assumption should also be questioned: but that’s true in the OP as well, so it’s not a difference between Bayesianism and deep.
Right, but but you can look at the performance of your model in training, compare it to the theoretical optimum (and to the baseline of making no predictions at all) and get lots of evidence about safety from that. You can even add some adversarial training of the synthetic environment in order to get tighter bounds.
Note that adversarial training doesn’t work on deceptive models due to the RSA-2048 problem; also see more detail here.
If on the vast majority of synthetic environments your model makes virtually no mispredictions, then, under the realizability assumption, it is very unlikely to make mispredictions in deployment.
I think realizability basically doesn’t help here—as long as there’s a deceptive model which is easier to find according to your inductive biases, the fact that somewhere in the model space there exists a correct model, but not one that your local search process finds by default, is cold comfort.
I think that adversarial training working so well that it can find exponentially rare failures is an unnecessarily strong desideratum. We need to drive to probability of catastrophic failures to something very low, but not actually zero. If a system is going to work for time t during deployment, then running it in n different synthetic environments for time t during training is enough to drive the probability of failure down to O(1n). Now, this is prohibitively costly, but it’s not exponentially prohibitively costly. And this doesn’t use adversarial training at all! So, while it’s not obvious how to get a good solution, it seems at least plausible that this can lead to a solution.
I agree that random defection can potentially be worked around—but the RSA-2048 problem is about conditional defection, which can’t be dealt with in the same way. More generally, I expect it to be extremely difficult if not impossible to prevent a model that you want to be able to operate in the real world from being able to determine at what point in training/deployment it’s in.
I expect it to be extremely difficult if not impossible to prevent a model that you want to be able to operate in the real world from being able to determine at what point in training/deployment it’s in.
Why do you expect it? During training, it finds itself in random universe. During deployment, it finds itself in another universe drawn from the same prior (the realizability assumption). How would it determine the difference?
Because that’s never what machine learning actually looks like in practice—essentially any access to text from the internet (let alone actual ability to interface with the world, both of which seem necessary for competitive systems) will let it determine things like the year, whether RSA-2048 has been factored, or other various pieces of information that are relevant to what stage in training/testing/deployment it’s in, how powerful the feedback mechanisms keeping it in check are, whether other models are defecting, etc. that can let it figure out when to defect.
Hmm, maybe you misunderstood my proposal? I suggested to train the model by meta-learning on purely synthetic data, sampled from some kind of simplicity prior, without any interface to the world. Maybe you just think this wouldn’t be competitive? If so, why? Is the argument just that there are no existing systems like this? But then it’s weak evidence at best. On the contrary, even from a purely capability standpoint, meta-learning with synthetic data might be a promising strategy to lower deep learning’s sample complexity.
Here’s why I think it will be competitive:
When a hypothetical competitive prediction algorithm A produces a malign prediction, the knowledge that it is malign clearly exists somewhere inside A in some form: otherwise it wouldn’t come up with the prediction. In particular, the knowledge that there are multiple plausible hypotheses consistent with the data also exists somewhere inside A.
Therefore, there must exist some competitive algorithm B that would be able to use the knowledge of this ambiguity to abstain from predicting in such cases.
There is no reason why B should be tailored to fine details of our physical world: it can be quite generic (as all deep learning algorithms).
If we have an ML algorithm C that is powerful enough to produce superintelligence, then it is likely powerful enough to come up with B. Since B is generic, the task of finding B doesn’t require any real-world data, and can be accomplished by meta-learning on synthetic data like I suggested.
This seems very sketchy to me. If we let A = SGD or A = evolution, your first claim becomes “if SGD/evolution finds a malign model, it must understand that it’s malign on some level,” which seems just straightforwardly incorrect. The last claim also seems pretty likely to be wrong if you let C = SGD or C = evolution.
Moreover, it definitely seems like training on data sampled from a simplicity prior (if that’s even possible—it should be uncomputable in general) is unlikely to help at all. I think there’s essentially no realistic way that training on synthetic data like that will be sufficient to produce a model which is capable of accomplishing things in the world. At best, that sort of approach might give you better inductive biases in terms of incentivizing the right sort of behavior, but in practice I expect any impact there to basically just be swamped by the impact of fine-tuning on real-world data.
If we let A = SGD or A = evolution, your first claim becomes “if SGD/evolution finds a malign model, it must understand that it’s malign on some level,” which seems just straightforwardly incorrect.
To me it seems straightforwardly correct! Suppose you’re running evolution in order to predict a sequence. You end up evolving a mind M that is a superintelligent malign consequentialist: it makes good predictions on purpose, in order to survive, and then produces a malign false prediction at a critical moment. So, M is part of the state of your algorithm A. All of M’s knowledge is also part of the state. M knows that M is malign, M knows the prediction it’s making this time is false. In this case, B can be whatever algorithm M uses to form its beliefs + confidence threshold (it’s strategy stealing.)
The last claim also seems pretty likely to be wrong if you let C = SGD or C = evolution.
Why? If you give evolution enough time, and the fitness criterion is good (as you apparently agreed earlier), then eventually it will find B.
Moreover, it definitely seems like training on data sampled from a simplicity prior (if that’s even possible—it should be uncomputable in general) is unlikely to help at all.
First, obviously we use a bounded simplicity prior, like I said in the beginning of this thread. It can be something like weighting programs by 2^{-length} while constraining their amount of computational resources, or something like an ANN with random weights (the latter is more speculative, but given that we know ANNs have inductive bias to simplicity, an untrained ANN probably reflects that.)
Second, why? Suppose that your starting algorithm is good at finding results when a lot of data is available, but is also very data inefficient (like deep learning seems to be). Then, by providing it with a lot of synthetic data, you leverage its strength to find a new algorithm which is data efficient. Unless you believe deep learning is already maximally data efficient (which seems very dubious to me)?
B can be whatever algorithm M uses to form its beliefs + confidence threshold (it’s strategy stealing.)
Sure, but then I think B is likely to be significantly more complex and harder for a local search process to find than A.
Why? If you give evolution enough time, and the fitness criterion is good (as you apparently agreed earlier), then eventually it will find B.
I definitely don’t think this, unless you have a very strong (and likely unachievable imo) definition of “good.”
Second, why? Suppose that your starting algorithm is good at finding results when a lot of data is available, but is also very data inefficient (like deep learning seems to be). Then, by providing it with a lot of synthetic data, you leverage its strength to find a new algorithm which is data efficient. Unless you believe deep learning is already maximally data efficient (which seems very dubious to me)?
I guess I’m skeptical that you can do all that much in the fully generic setting of just trying to predict a simplicity prior. For example, if we look at actually successful current architectures, like CNNs or transformers, they’re designed to work well on specific types of data and relationships that are common in our world—but not necessarily at all just in a general simplicity prior.
Sure, but then I think B is likely to be significantly more complex and harder for a local search process to find than A.
A is sufficiently powerful to select M which contains the complex part of B. It seems rather implausible that an algorithm of the same power cannot select B.
if we look at actually successful current architectures, like CNNs or transformers, they’re designed to work well on specific types of data and relationships that are common in our world—but not necessarily at all just in a general simplicity prior.
CNNs are specific in some way, but in a relatively weak way (exploiting hierarchical geometric structure). Transformers are known to be Turing-complete, so I’m not sure they are specific at all (ofc the fact you can express any program doesn’t mean you can effectively learn any program, and moreover the latter is false on computational complexity grounds, but it still seems to point to some rather simple and large class of learnable hypotheses). Moreover, even if our world has some specific property that is important for learning, this only means we may need to enforce this property in our prior. For example, if your prior is an ANN with random weights then it’s plausible that it reflects the exact inductive biases of the given architecture.
A is sufficiently powerful to select M which contains the complex part of B. It seems rather implausible that an algorithm of the same power cannot select B.
A’s weights do not contain the complex part of B—deception is an inference-time phenomenon. It’s very possible for complex instrumental goals to be derived from a simple structure such that a search process is capable of finding that simple structure that yields those complex instrumental goals without being able to find a model with those complex instrumental goals hard-coded as terminal goals.
Hmm, sorry, I’m not following. What exactly do you mean by “inference-time” and “derived”? By assumption, when you run A on some sequence it effectively simulates M which runs the complex core of B. So, A trained on that sequence effectively contains the complex core of B as a subroutine.
A’s structure can just be “think up good strategies for achieving X, then do those,” with no explicit subroutine that you can find anywhere in A’s weights that you can copy over to B.
IIUC, you’re saying something like: suppose trained-A computes the source code of the complex core of B and then runs it. But then, define B′ as: compute the source code of the complex core of B (in the same way A does it) and use it to implement B. B′ is equivalent to B and has about the same complexity as trained-A.
Or, from a slightly different angle: if “think up good strategies for achieving X” is powerful enough to come up with M, then “think up good strategies for achieving [reward of the type I defined earlier]” is powerful enough to come up with B.
I think that “think up good strategies for achieving [reward of the type I defined earlier]” is likely to be much, much more complex (making it much more difficult to achieve with a local search process) than an arbitrary goal X for most sorts of rewards that we would actually be happy with AIs achieving.
Why? It seems like M would have all the knowledge required for achieving good rewards of the good type, so simulating M should not be more difficult than achieving good rewards of the good type.
The reward function I was sketching earlier is not complex. Moreover, if you can encode M then you can encode B, no reason why the latter should have much greater complexity. If you can’t encode M but can only encode something that producesM, then by the same token you can encode something that produces B (I don’t think that’s even a meaningful distinction tbh). I think it would help if you could construct a simple mathematical toy model of your reasoning here?
Here’s a simple toy model. Suppose you have two agents that internally compute their actions as follows (perhaps with actual argmax replaced with some smarter search algorithm, but still basically structured as below):
and the problem becomes that both Mdeceptive and Maligned will produce behavior that looks aligned on the training distribution, but Ualigned has to be much more complex. To see this, note that essentially any Udeceptive will yield good training performance because the model will choose to act deceptively during training, whereas if you want to get good training performance without deception, then Ualigned has to actually encode the full objective, which is likely to make it quite complicated.
I understand how this model explains why agents become unaligned under distributional shift. That’s something I never disputed. However, I don’t understand how this model applies to my proposal. In my proposal, there is no distributional shift, because (thanks to the realizability assumption) the real environment is sampled from the same prior that is used for training with C. The model can’t choose to act deceptively during training, because it can’t distinguish between training and deployment. Moreover, the objective I described is not complicated.
Yeah, that’s a fair objection—my response to that is just that I think that preventing a model from being able to distinguish training and deployment is likely to be impossible for anything competitive.
Okay, but why? I think that the reason you have this intuition is, the realizability assumption is false. But then you should concede that the main weakness of the OP is the realizability assumption rather than the difference between deep learning and Bayesianism.
Perhaps I just totally don’t understand what you mean by realizability, but I fail to see how realizability is relevant here. As I understand it, realizability just says that the true model has some non-zero prior probability—but that doesn’t matter (at least for the MAP, which I think is a better model than the full posterior for how SGD actually works) as long as there’s some deceptive model with greater prior probability that’s indistinguishable on the training distribution, as in my simple toy model from earlier.
When talking about uniform (worst-case) bounds, realizability just means the true environment is in the hypothesis class, but in a Bayesian setting (like in the OP) it means that our bounds scale with the probability of the true environment in the prior. Essentially, it means we can pretend the true environment was sampled from the prior. So, if (by design) training works by sampling environments from the prior, and (by realizability) deployment also consists of sampling an environment from the same prior, training and deployment are indistinguishable.
Sure—by that definition of realizability, I agree that’s where the difficulty is. Though I would seriously question the practical applicability of such an assumption.
We’re doing meta-learning. During training, the network is not learning about the real world, it’s learning how to be a safe predictor. It’s interacting with a synthetic environment, so a misprediction doesn’t have any catastrophic effects: it only teaches the algorithm that this version of the predictor is unsafe. In other words, the malign subagents have no way to attack during training because they can access little information about what the real universe is like. The training process is designed to select predictors that only make predictions when they can be confident, and the training performance allows us to verify this goal has truly been achieved.
You have no guarantees, sure, but that’s a problem with deep learning in general and not just inner alignment. The point is, if your model is not optimizing that reward function then its performance during training will be suboptimal. To the extent your algorithm is able to approximate the true optimum during training, it will behave safely during deployment.
that’s a problem with deep learning in general and not just inner alignment
I think you are understanding inner alignment very differently than we define it in Risks from Learned Optimization, where we introduced the term.
The point is, if your model is not optimizing that reward function then its performance during training will be suboptimal.
This is not true for deceptively aligned models, which is the situation I’m most concerned about, and—as we argue extensively in Risks from Learned Optimization—there are a lot of reasons why a model might end up pursuing a simpler/faster/easier-to-find proxy even if that proxy yields suboptimal training performance.
I don’t understand the alternative, but maybe that’s neither here nor there.
what makes the problem go away isn’t more intelligent models, but less efficient training processes
It’s a little hard to make a definitive statement about a hypothetical in which the inner alignment problem doesn’t apply to Bayesian inference. However, since error bounds are apparently a key piece of a solution, it certainly seems that if Bayesian inference was immune to mesa-optimizers it would be because of competence not resource-prodigality.
Here’s another tack. Hypothesis generation seems like a crucial part of intelligent prediction. Pure Bayesian reasoning does hypothesis generation by brute force. Suppose it was inefficiency, and not intelligence, that made Bayesian reasoning avoid mesa-optimizers. Then suppose we had a Bayesian reasoning that was equally intelligent but more efficient, by only generating relevant hypotheses. It gains efficiency by not even bothering to consider a bunch of obviously wrong models, but it’s posterior is roughly the same, so it should avoid inner alignment failure equally well. If, on the other hand, the hyopthesis generation routine was bad enough that some plausible hypotheses went unexamined, this could introduce an inner alignment failure, with a notable decrease in intelligence.
I expect us to end up using some sort of local search instead of a global search like that—just because I think that local search is way more efficient than any sort of Bayesianish global search
I expect some heuristic search with no discernable structure, guided “attentively” by an agent. And I expect this heuristic search through models to identify any model that a human could hypothesize, and many more.
I don’t understand the alternative, but maybe that’s neither here nor there.
Perhaps I’m just being pedantic, but when you’re building mathematical models of things I think it’s really important to call attention to what things in the real world those mathematical models are supposed to represent—since that’s how you know whether your assumptions are reasonable or not. In this case, there are two ways I could interpret this analysis: either the Bayesian learner is supposed to represent what we want our trained models to be doing, and then we can ask how we might train something that works that way; or the Bayesian learner is supposed to represent how we want our training process to work, and then we can ask how we might build training processes that work that way. I originally took you as saying the first thing, then realized you were actually saying the second thing.
Here’s another tack. Hypothesis generation seems like a crucial part of intelligent prediction. Pure Bayesian reasoning does hypothesis generation by brute force. Suppose it was inefficiency, and not intelligence, that made Bayesian reasoning avoid mesa-optimizers. Then suppose we had a Bayesian reasoning that was equally intelligent but more efficient, by only generating relevant hypotheses. It gains efficiency by not even bothering to consider a bunch of obviously wrong models, but it’s posterior is roughly the same, so it should avoid inner alignment failure equally well. If, on the other hand, the hyopthesis generation routine was bad enough that some plausible hypotheses went unexamined, this could introduce an inner alignment failure, with a notable decrease in intelligence.
That’s a good point. Perhaps I am just saying that I don’t think we’ll get training processes that are that competent. I do still think there are some ways in which I don’t fully buy this picture, though. I think that the point that I’m trying to make is that the Bayesian learner gets its safety guarantees by having a massive hypothesis space and just keeping track of how well each of those hypotheses is doing. Obviously, if you knew of a smaller space that definitely included the desired hypothesis, you could do that instead—but given a fixed-size space that you have to search over (and unless your space is absolutely tiny such that you basically already have what you want), for any given amount of compute, I think it’ll be more efficient to run a local search over that space than a global one.
I expect some heuristic search with no discernable structure, guided “attentively” by an agent. And I expect this heuristic search through models to identify any model that a human could hypothesize, and many more.
Interesting. I’m not exactly sure what you mean by that. I could imagine “guided ‘attentively’ by an agent” to mean something like recursive oversight/relaxed adversarial training wherein some overseer is guiding the search process—is that what you mean?
I’m not exactly sure what I mean either, but I wasn’t imagining as much structure as exists in your post. I mean there’s some process which constructs hypotheses, and choices are being made about how computation is being directed within that process.
I think it’ll be more efficient to run a local search over that space than a global one
I think any any heuristic search algorithm worth its salt will incorporate information about proximity of models. And I think that arbitrary limits on heuristic search of the form “the next model I consider must be fairly close to the last one I did” will not help it very much if it’s anywhere near smart enough to merit membership in a generally intelligent predictor.
But for the purpose of analyzing it’s output, I don’t think this discussion is critical if we agree that we can expect a good heuristic search through models will identify any model that a human could hypothesize.
But for the purpose of analyzing it’s output, I don’t think this discussion is critical if we agree that we can expect a good heuristic search through models will identify any model that a human could hypothesize.
I think I would expect essentially all models that a human could hypothesize to be in the search space—but if you’re doing a local search, then you only ever really see the easiest to find model with good behavior, not all models with good behavior, which means you’re relying a lot more on your prior/inductive biases/whatever is determining how hard models are to find to do a lot more work for you. Cast into the Bayesian setting, a local search like this is relying on something like the MAP model not being deceptive—and escaping that to instead get N models sampled independently from the top q proportion or whatever seems very difficult to do via any local search algorithm.
I think that arbitrary limits on heuristic search of the form “the next model I consider must be fairly close to the last one I did” will not help it very much if it’s anywhere near smart enough to merit membership in a generally intelligent predictor.
Yeah; I think I would say I disagree with that. Notably, evolution is not a generally intelligent predictor, but is still capable of producing generally intelligent predictors. I expect the same to be true of processes like SGD.
If we ever produce generally intelligent predictors (or “accurate world-models” in the terminology we’ve been using so far), we will need a process that is much more efficient than evolution.
But also, I certainly don’t think that in order to be generally intelligent you need to start with a generally intelligent subroutine. Then you could never get off the ground. I expect good hypothesis-generation / model-proposal to use a mess of learned heuristics which would not be easily directed to solve arbitrary tasks, and I expect the heuristic “look for models near the best-so-far model” to be useful, but I don’t think making it ironclad would be useful.
Another thought on our exchange:
Me: we can expect a good heuristic search through models will identify any model that a human could hypothesize
You: I think I would expect essentially all models that a human could hypothesize to be in the search space—but if you’re doing a local search, then you only ever really see the easiest to find model with good behavior
If what you say is correct, then it sounds like exclusively-local search precludes human-level intelligence! (Which I don’t believe, by the way, even if I think it’s a less efficient path). One human competency is generating lots of hypotheses, and then having many models of the world, and then designing experiments to probe those hypotheses. It’s hard for me to imagine that an agent that finds an “easiest-to-find model” and then calls it a day could ever do human-level science. Even something as simple as understanding an interlocuter requires generating diverse models on the fly: “Do they mean X or Y with those words? Let me ask a clarfying question.”
I’m not this bearish on local search. But if local search is this bad, I don’t think it is a viable path to AGI, and if it’s not, then the internals don’t for the purposes of our discussion, and we can skip to what I take to be the upshot:
we can expect a good heuristic search through models will identify any model that a human could hypothesize
It’s hard for me to imagine that an agent that finds an “easiest-to-find model” and then calls it a day could ever do human-level science.
I certainly don’t think SGD is a powerful enough optimization process to do science directly, but it definitely seems powerful enough to find an agent which does do science.
if local search is this bad, I don’t think it is a viable path to AGI
We know that local search processes can produce AGI, so viability is a question of efficiency—and we know that SGD is at least efficient enough to solve a wide variety of problems from image classification, to language modeling, to complex video games, all given just current compute budgets. So while I could certainly imagine SGD being insufficient, I definitely wouldn’t want to bet on it.
I certainly don’t think SGD is a powerful enough optimization process to do science directly, but it definitely seems powerful enough to find an agent which does do science.
Okay I think we’ve switched from talking about Q-learning to talking about policy gradient. (Or we were talking about the latter the whole time, and I didn’t notice it). The question that I think is relevant is: how are possible world-models being hypothesized and analyzed? That’s something I expect to be done with messy heuristics that sometimes have discontinuities their sequence of outputs. Which means I think that no reasonable DQN is will be generally intelligent (except maybe an enormously wide one attention-based one, such that finding models is more about selective attention at any given step than it is about gradient descent over the whole history).
A policy gradient network, on the other hand, could maybe (after having its parameters updated through gradient descent) become a network that, in a single forward pass, considers diverse world-models (generated with a messy non-local heuristic), and analyzes their plausibility, and then acts. At the end of the day, what we have is an agent modeling world, and we can expect it to consider any model that a human could come up with. (This paragraph also applies to the DQN with a gradient-descent-trained method for selectively attending to different parts of a wide network, since that could amount to effectively considering different models).
Hmmm… I don’t think I was ever even meaning to talk specifically about RL, but regardless I don’t expect nearly as large of a difference between Q-learning and policy gradient algorithms. If we imagine both types of algorithms making use of the same size massive neural network, the only real difference is how the output of that neural network is interpreted, either directly as a policy, or as Q values that are turned into a policy via something like softmax. In both cases, the neural network is capable of implementing any arbitrary policy and should be getting a similar sort of feedback signal from the training process—especially if you’re using a policy gradient algorithm that involves something like advantage estimation rather than actual rollouts, since the update rule in that situation is going to look very similar to the Q learning update rule. I do expect some minor differences in the sorts of models you end up with, such as Q learning being more prone to non-myopic behavior across episodes, and I think there are some minor reasons that policy gradient algorithms are favored in real-world settings, since they get to learn their exploration policy rather than having it hard-coded and can handle continuous action domains—but overall I think these sorts of differences are pretty minor and shouldn’t affect whether these approaches can reach general intelligence or not.
I certainly don’t think SGD is a powerful enough optimization process to do science directly, but it definitely seems powerful enough to find an agent which does do science.
But taking us back out of RL, in a wide neural network with selective attention that enables many qualitatively different forward passes, gradient descent seems to be training the way different models get proposed (i.e. the way attention is allocated), since this happens in a single forward pass, and what we’re left with is a modeling routine that is heuristically considering (and later comparing) very different models. And this should include any model that a human would consider.
I think that is main thread of our argument, but now I’m curious if I was totally off the mark about Q-learning and policy gradient.
but overall I think these sorts of differences are pretty minor and shouldn’t affect whether these approaches can reach general intelligence or not.
I had thought that maybe since a Q-learner is trained as if the cached point estimate of the Q-value of the next state is the Truth, it won’t, in a single forward pass, consider different models about what the actual Q-value of the next state is. At most, it will consider different models about what the very next transition will be.
a) Does that seem right? and b) Aren’t there some policy gradient methods that don’t face this problem?
I had thought that maybe since a Q-learner is trained as if the cached point estimate of the Q-value of the next state is the Truth, it won’t, in a single forward pass, consider different models about what the actual Q-value of the next state is. At most, it will consider different models about what the very next transition will be.
a) Does that seem right? and b) Aren’t there some policy gradient methods that don’t face this problem?
This seems wrong to me—even though the Q learner is trained using its own point estimate of the next state, it isn’t, at inference time, given access to that point estimate. The Q learner has to choose its Q values before it knows anything about what the Q value estimates will be of future states, which means it certainly should have to consider different models of what the next transition will be like.
it certainly should have to consider different models of what the next transition will be like.
Yeah I was agreeing with that.
even though the Q learner is trained using its own point estimate of the next state, it isn’t, at inference time, given access to that point estimate.
Right, but one thing the Q-network, in its forward pass, is trying to reproduce is the point of estimate of the Q-value of the next state (since it doesn’t have access to it). What it isn’t trying to reproduce, because it isn’t trained that way, is multiple models of what the Q-value might be at a given possible next state.
Edit: I no longer endorse this comment; see this comment instead.
I think you’ve just assumed the entire inner alignment problem away. You assume that the model—the imitation learner—is a perfect Bayesian, rather than just some trained neural network or other function approximator (edit: I was just misinterpreting here and the training process is supposed to Bayesian rather than the model, see Rohin’s comment below). The entire point of the inner alignment problem, though, is that you can’t guarantee that your trained model is actually a perfect Bayesian—or anything else. In practice, all we actually generally do when we do ML is we train some neural network on some training data/environment and hope that the implicit inductive biases of our training process are such that we end up with a model doing the right thing, meaning that we can’t really control what sort of model—Bayesian or anything else—that we get when we do ML, and that uncontrollability, in my eyes, is the inner alignment problem.
While I share your position that this mostly isn’t addressing the things that make inner alignment hard / risky in practice, I agree with Vanessa that this does not assume the inner alignment problem away, unless you have a particularly contorted definition of “inner alignment”.
There’s an optimization procedure (Bayesian updating) that is selecting models (the model of the demonstrator) that can themselves be optimizers, and you could get the wrong one (e.g. the model that simulates an alien civilization that realizes it’s in a simulation and predicts well to be selected by the Bayesian updating but eventually executes a treacherous turn). The algorithm presented precludes this from happening with some probability. We can debate the significance, but it seems to me like it is clearly doing something solution-like with respect to the inner alignment problem.
“in a simulation”, no?
Lol yes fixed
Hmmm… I think I just misunderstood the setup then. It seemed to me like the Bayesian updating was supposed to represent the model rather than the training process, but under the framing that you just said, I agree that it’s relevant. It’s worth noting that I do think most of the danger lies in the ways in which gradient descent is not a perfect Bayesian, but I agree that modeling gradient descent as Bayesian is certainly relevant.
I think this is completely unfair. The inner alignment problem exists even for perfect Bayesians, and solving it in that setting contributes much to our understanding. The fact we don’t have satisfactory mathematical models of deep learning performance is a different problem, which is broader than inner alignment and to first approximation orthogonal to it. Ideally, we will solve this second problem by improving our mathematical understanding of deep learning and/or other competitive ML algorithms. The latter effort is already underway by researchers unrelated to AI safety, with some results. Moreover, we can in principle come up with heuristics how to apply this method of solving inner alignment (which I call “confidence thresholds” in my own work) to deep learning: e.g. use NNGP to measure confidence or use an evolutionary algorithm with a population of networks and check how well they agree with each other. Of course if we do this we won’t have formal guarantees that it will work, but, like I said this is a broader issue than inner alignment.
Regardless of how you define inner alignment, I think that the vast majority of the existential risk comes from that “broader issue” that you’re pointing to of not being able to get worst-case guarantees due to using deep learning or evolutionary search or whatever. That leads me to want to define inner alignment to be about that problem—and I think that is basically the definition we give in Risks from Learned Optimization, where we introduced the term. That being said, I do completely agree that getting a better understanding of deep learning is likely to be critical.
[Emphasis added.] I think this is a common and serious mistake-pattern, and in particular is one of the more common underlying causes of framing errors. The pattern is roughly:
Notice cluster of problems X which have a similar underlying causal pattern Cause(X)
Notice problem y in which Cause(X) could plausibly play a role
On deeper examination, the cause of y cause(y) doesn’t quite fit Cause(X)
Attempt to redefine the pattern Cause(X) to include cause(y)
The problem is that, in trying to “shoehorn” cause(y) into the category Cause(X), we miss the opportunity to notice a different pattern, which is more directly useful in understanding y as well as some other cluster of problems related to y.
A concrete example: this is the same mistake I accused Zvi of making when trying to cast moral mazes as a problem of super-perfect competition. The conditions needed for super-perfect competition to explain moral mazes did not hold, and by trying to shoehorn the problem into that mold Zvi was missing an orthogonal phenomenon which is extremely interesting in its own right: thinking about that exact problem was what led to Demons in Imperfect Search.
Now, this is not to say that changing a definition to fit another case is always the wrong move. Sometimes, a new use-case shows that the definition can handle the new case while still preserving its original essence. The key question is whether the problem cluster X and problem y really do have the same underlying structure, or if there’s something genuinely new and different going on in y.
In this case, I think it’s pretty clear that there is more than just inner alignment problems going on in the lack of worst-case guarantees for deep learning/evolutionary search/etc. Generalization failure is not just about, or even primarily about, inner agents. It occurs even in the absence of mesa-optimizers. So defining inner alignment to be about that problem looks to me like a mistake—you’re likely to miss important, conceptually-distinct phenomena by making that move. (We could also come at it from the converse direction: if something clearly recognizable as an inner alignment problem occurs for ideal Bayesians, then redefining the inner alignment problem to be “we can’t control what sort of model we get when we do ML” is probably a mistake, and you’re likely to miss interesting phenomena that way which don’t conceptually resemble inner alignment.)
A useful knee-jerk reaction here is to notice when cause(y) doesn’t quite fit the pattern Cause(X), and use that as a curiosity-pump to look for other cases which resemble y. That’s the sort of instinct which will tend to turn up insights we didn’t know we were missing.
I mean, I don’t think I’m “redefining” inner alignment, given that I don’t think I’ve ever really changed my definition and I was the one that originally came up with the term (inner alignment was due to me, mesa-optimization was due to Chris van Merwijk). I also certainly agree that there are “more than just inner alignment problems going on in the lack of worst-case guarantees for deep learning/evolutionary search/etc.”—I think that’s exactly the point that I’m making, which is that while there are other issues, inner alignment is what I’m most concerned about. That being said, I also think I was just misunderstanding the setup in the paper—see Rohin’s comment on this chain.
If the inner alignment problem did not exist for perfect Bayesians, but did exist for neural networks, then it would appear to be a regime where more intelligence makes the problem go away. If the inner alignment problem were ~solved for perfect Bayesians, but unsolved for neural networks, I think there’s still some of the flavor of that regime, but we do have to be pretty careful to make sure we’re applying the same sort of solution to the non-Bayesian algorithms. I think in Vanessa’s comment above, she’s suggesting this looks doable.
Note the method here of avoiding mesa-optimizers: error bounds. Neural networks don’t have those. Naturally, one way to make mesa-optimizer-deceptively-selected-errors go away is just to have better learning algorithms that make errors go away. Algorithms like Gated Linear Networks with proper error bounds may be a safer building block for AGI. But none of this takes away from the fact that it is potentially important to figure out how to avoid mesa-optimization in neural networks, and I would add to your claim that this is a much harder setting; I would say it’s a harder setting because of the non-existence of error bounds.
I think I mostly agree with what you’re saying here, though I have a couple of comments—and now that I’ve read and understand your paper more thoroughly, I’m definitely a lot more excited about this research.
I don’t think that’s right—if you’re modeling the training process as Bayesian, as I now understand, then the issue is that what makes the problem go away isn’t more intelligent models, but less efficient training processes. Even if we have arbitrary compute, I think we’re unlikely to use training processes that look Bayesian just because true Bayesianism is really hard to compute such that for basically any amount of computation that you have available to you, you’d rather run some more efficient algorithm like SGD.
I worry about these sorts of Bayesian analyses where we’re assuming that we’re training a large population of models, one of which is assumed to be an accurate model of the world, since I expect us to end up using some sort of local search instead of a global search like that—just because I think that local search is way more efficient than any sort of Bayesianish global search.
I definitely agree with all of this, except perhaps on whether Gated Linear Networks are likely to help (though I don’t claim to actually understand backpropagation-free networks all that well).
I feel this is a wrong way to look at it. I expect any effective learning algorithm to be an approximation of Bayesianism in the sense that, it satisfies some good sample complexity bound w.r.t. some sufficiently rich prior. Ofc it’s non-trivial to (i) prove such a bound for a given algorithm (ii) modify said algorithm using confidence thresholds in a way that leads to a safety guarantee. However, there is no sharp dichotomy between “Bayesianism” and “SGD” such that this approach obviously doesn’t apply to the latter, or to something competitive with the latter.
I agree that at some level SGD has to be doing something approximately Bayesian. But that doesn’t necessarily imply that you’ll be able to get any nice, Bayesian-like properties from it such as error bounds. For example, if you think of SGD as effectively just taking the MAP model starting from sort of simplicity prior, it seems very difficult to turn that into something like the top N posterior models, as would be required for an algorithm like this.
I mean, there’s obviously a lot more work to do, but this is progress. Specifically if SGD is MAP then it seems plausible that e.g. SGD + random initial conditions or simulated annealing would give you something like top N posterior models. You can also extract confidence from NNGP.
I agree that this is progress (now that I understand it better), though:
I think there is strong evidence that the behavior of models trained via the same basic training process are likely to be highly correlated. This sort of correlation is related to low variance in the bias-variance tradeoff sense, and there is evidence that not only do massive neural networks tend to have pretty low variance, but that this variance is likely to continue to decrease as networks become larger.
Hmm, added to reading list, thank you.
Here’s another way how you can try implementing this approach with deep learning. Train the predictor using meta-learning on synthetically generated environments (sampled from some reasonable prior such as bounded Solomonoff or maybe ANNs with random weights). The reward for making a prediction is 1−(1−δ)maxipi+ϵqi+ϵ, where pi is the predicted probability of outcome i, qi is the true probability of outcome i and ϵ,δ∈(0,1) are parameters. The reward for making no prediction (i.e. querying the user) is 0.
This particular proposal is probably not quite right, but something in that general direction might work.
Sure, but you have no guarantee that the model you learn is actually going to be optimizing anything like that reward function—that’s the whole point of the inner alignment problem. What’s nice about the approach in the original paper is that it keeps a bunch of different models around, keeps track of their posterior, and only acts on consensus, ensuring that the true model always has to approve. But if you just train a single model on some reward function like that with deep learning, you get no such guarantees.
Right, but but you can look at the performance of your model in training, compare it to the theoretical optimum (and to the baseline of making no predictions at all) and get lots of evidence about safety from that. You can even add some adversarial training of the synthetic environment in order to get tighter bounds. If on the vast majority of synthetic environments your model makes virtually no mispredictions, then, under the realizability assumption, it is very unlikely to make mispredictions in deployment. Ofc the realizability assumption should also be questioned: but that’s true in the OP as well, so it’s not a difference between Bayesianism and deep.
Note that adversarial training doesn’t work on deceptive models due to the RSA-2048 problem; also see more detail here.
I think realizability basically doesn’t help here—as long as there’s a deceptive model which is easier to find according to your inductive biases, the fact that somewhere in the model space there exists a correct model, but not one that your local search process finds by default, is cold comfort.
I think that adversarial training working so well that it can find exponentially rare failures is an unnecessarily strong desideratum. We need to drive to probability of catastrophic failures to something very low, but not actually zero. If a system is going to work for time t during deployment, then running it in n different synthetic environments for time t during training is enough to drive the probability of failure down to O(1n). Now, this is prohibitively costly, but it’s not exponentially prohibitively costly. And this doesn’t use adversarial training at all! So, while it’s not obvious how to get a good solution, it seems at least plausible that this can lead to a solution.
I agree that random defection can potentially be worked around—but the RSA-2048 problem is about conditional defection, which can’t be dealt with in the same way. More generally, I expect it to be extremely difficult if not impossible to prevent a model that you want to be able to operate in the real world from being able to determine at what point in training/deployment it’s in.
Why do you expect it? During training, it finds itself in random universe. During deployment, it finds itself in another universe drawn from the same prior (the realizability assumption). How would it determine the difference?
Because that’s never what machine learning actually looks like in practice—essentially any access to text from the internet (let alone actual ability to interface with the world, both of which seem necessary for competitive systems) will let it determine things like the year, whether RSA-2048 has been factored, or other various pieces of information that are relevant to what stage in training/testing/deployment it’s in, how powerful the feedback mechanisms keeping it in check are, whether other models are defecting, etc. that can let it figure out when to defect.
Hmm, maybe you misunderstood my proposal? I suggested to train the model by meta-learning on purely synthetic data, sampled from some kind of simplicity prior, without any interface to the world. Maybe you just think this wouldn’t be competitive? If so, why? Is the argument just that there are no existing systems like this? But then it’s weak evidence at best. On the contrary, even from a purely capability standpoint, meta-learning with synthetic data might be a promising strategy to lower deep learning’s sample complexity.
Here’s why I think it will be competitive:
When a hypothetical competitive prediction algorithm A produces a malign prediction, the knowledge that it is malign clearly exists somewhere inside A in some form: otherwise it wouldn’t come up with the prediction. In particular, the knowledge that there are multiple plausible hypotheses consistent with the data also exists somewhere inside A.
Therefore, there must exist some competitive algorithm B that would be able to use the knowledge of this ambiguity to abstain from predicting in such cases.
There is no reason why B should be tailored to fine details of our physical world: it can be quite generic (as all deep learning algorithms).
If we have an ML algorithm C that is powerful enough to produce superintelligence, then it is likely powerful enough to come up with B. Since B is generic, the task of finding B doesn’t require any real-world data, and can be accomplished by meta-learning on synthetic data like I suggested.
This seems very sketchy to me. If we let A = SGD or A = evolution, your first claim becomes “if SGD/evolution finds a malign model, it must understand that it’s malign on some level,” which seems just straightforwardly incorrect. The last claim also seems pretty likely to be wrong if you let C = SGD or C = evolution.
Moreover, it definitely seems like training on data sampled from a simplicity prior (if that’s even possible—it should be uncomputable in general) is unlikely to help at all. I think there’s essentially no realistic way that training on synthetic data like that will be sufficient to produce a model which is capable of accomplishing things in the world. At best, that sort of approach might give you better inductive biases in terms of incentivizing the right sort of behavior, but in practice I expect any impact there to basically just be swamped by the impact of fine-tuning on real-world data.
To me it seems straightforwardly correct! Suppose you’re running evolution in order to predict a sequence. You end up evolving a mind M that is a superintelligent malign consequentialist: it makes good predictions on purpose, in order to survive, and then produces a malign false prediction at a critical moment. So, M is part of the state of your algorithm A. All of M’s knowledge is also part of the state. M knows that M is malign, M knows the prediction it’s making this time is false. In this case, B can be whatever algorithm M uses to form its beliefs + confidence threshold (it’s strategy stealing.)
Why? If you give evolution enough time, and the fitness criterion is good (as you apparently agreed earlier), then eventually it will find B.
First, obviously we use a bounded simplicity prior, like I said in the beginning of this thread. It can be something like weighting programs by 2^{-length} while constraining their amount of computational resources, or something like an ANN with random weights (the latter is more speculative, but given that we know ANNs have inductive bias to simplicity, an untrained ANN probably reflects that.)
Second, why? Suppose that your starting algorithm is good at finding results when a lot of data is available, but is also very data inefficient (like deep learning seems to be). Then, by providing it with a lot of synthetic data, you leverage its strength to find a new algorithm which is data efficient. Unless you believe deep learning is already maximally data efficient (which seems very dubious to me)?
Sure, but then I think B is likely to be significantly more complex and harder for a local search process to find than A.
I definitely don’t think this, unless you have a very strong (and likely unachievable imo) definition of “good.”
I guess I’m skeptical that you can do all that much in the fully generic setting of just trying to predict a simplicity prior. For example, if we look at actually successful current architectures, like CNNs or transformers, they’re designed to work well on specific types of data and relationships that are common in our world—but not necessarily at all just in a general simplicity prior.
A is sufficiently powerful to select M which contains the complex part of B. It seems rather implausible that an algorithm of the same power cannot select B.
CNNs are specific in some way, but in a relatively weak way (exploiting hierarchical geometric structure). Transformers are known to be Turing-complete, so I’m not sure they are specific at all (ofc the fact you can express any program doesn’t mean you can effectively learn any program, and moreover the latter is false on computational complexity grounds, but it still seems to point to some rather simple and large class of learnable hypotheses). Moreover, even if our world has some specific property that is important for learning, this only means we may need to enforce this property in our prior. For example, if your prior is an ANN with random weights then it’s plausible that it reflects the exact inductive biases of the given architecture.
A’s weights do not contain the complex part of B—deception is an inference-time phenomenon. It’s very possible for complex instrumental goals to be derived from a simple structure such that a search process is capable of finding that simple structure that yields those complex instrumental goals without being able to find a model with those complex instrumental goals hard-coded as terminal goals.
Hmm, sorry, I’m not following. What exactly do you mean by “inference-time” and “derived”? By assumption, when you run A on some sequence it effectively simulates M which runs the complex core of B. So, A trained on that sequence effectively contains the complex core of B as a subroutine.
A’s structure can just be “think up good strategies for achieving X, then do those,” with no explicit subroutine that you can find anywhere in A’s weights that you can copy over to B.
IIUC, you’re saying something like: suppose trained-A computes the source code of the complex core of B and then runs it. But then, define B′ as: compute the source code of the complex core of B (in the same way A does it) and use it to implement B. B′ is equivalent to B and has about the same complexity as trained-A.
Or, from a slightly different angle: if “think up good strategies for achieving X” is powerful enough to come up with M, then “think up good strategies for achieving [reward of the type I defined earlier]” is powerful enough to come up with B.
I think that “think up good strategies for achieving [reward of the type I defined earlier]” is likely to be much, much more complex (making it much more difficult to achieve with a local search process) than an arbitrary goal X for most sorts of rewards that we would actually be happy with AIs achieving.
Why? It seems like M would have all the knowledge required for achieving good rewards of the good type, so simulating M should not be more difficult than achieving good rewards of the good type.
It’s not that simulating M is difficult, but that encoding for some complex goal is difficult, whereas encoding for a random, simple goal is easy.
The reward function I was sketching earlier is not complex. Moreover, if you can encode M then you can encode B, no reason why the latter should have much greater complexity. If you can’t encode M but can only encode something that produces M, then by the same token you can encode something that produces B (I don’t think that’s even a meaningful distinction tbh). I think it would help if you could construct a simple mathematical toy model of your reasoning here?
Here’s a simple toy model. Suppose you have two agents that internally compute their actions as follows (perhaps with actual argmax replaced with some smarter search algorithm, but still basically structured as below):
Mdeceptive(x)=argmaxaE[∑iUdeceptive(si) | a]Maligned(x)=argmaxaE[∑iUaligned(si) | a]
Then, comparing the K-complexity of the two models, we get
K(Maligned)−K(Mdeceptive)≈K(Ualigned)−K(Udeceptive)
and the problem becomes that both Mdeceptive and Maligned will produce behavior that looks aligned on the training distribution, but Ualigned has to be much more complex. To see this, note that essentially any Udeceptive will yield good training performance because the model will choose to act deceptively during training, whereas if you want to get good training performance without deception, then Ualigned has to actually encode the full objective, which is likely to make it quite complicated.
I understand how this model explains why agents become unaligned under distributional shift. That’s something I never disputed. However, I don’t understand how this model applies to my proposal. In my proposal, there is no distributional shift, because (thanks to the realizability assumption) the real environment is sampled from the same prior that is used for training with C. The model can’t choose to act deceptively during training, because it can’t distinguish between training and deployment. Moreover, the objective I described is not complicated.
Yeah, that’s a fair objection—my response to that is just that I think that preventing a model from being able to distinguish training and deployment is likely to be impossible for anything competitive.
Okay, but why? I think that the reason you have this intuition is, the realizability assumption is false. But then you should concede that the main weakness of the OP is the realizability assumption rather than the difference between deep learning and Bayesianism.
Perhaps I just totally don’t understand what you mean by realizability, but I fail to see how realizability is relevant here. As I understand it, realizability just says that the true model has some non-zero prior probability—but that doesn’t matter (at least for the MAP, which I think is a better model than the full posterior for how SGD actually works) as long as there’s some deceptive model with greater prior probability that’s indistinguishable on the training distribution, as in my simple toy model from earlier.
When talking about uniform (worst-case) bounds, realizability just means the true environment is in the hypothesis class, but in a Bayesian setting (like in the OP) it means that our bounds scale with the probability of the true environment in the prior. Essentially, it means we can pretend the true environment was sampled from the prior. So, if (by design) training works by sampling environments from the prior, and (by realizability) deployment also consists of sampling an environment from the same prior, training and deployment are indistinguishable.
Sure—by that definition of realizability, I agree that’s where the difficulty is. Though I would seriously question the practical applicability of such an assumption.
What’s the distinction between training and deployment when the model can always query for more data?
We’re doing meta-learning. During training, the network is not learning about the real world, it’s learning how to be a safe predictor. It’s interacting with a synthetic environment, so a misprediction doesn’t have any catastrophic effects: it only teaches the algorithm that this version of the predictor is unsafe. In other words, the malign subagents have no way to attack during training because they can access little information about what the real universe is like. The training process is designed to select predictors that only make predictions when they can be confident, and the training performance allows us to verify this goal has truly been achieved.
You have no guarantees, sure, but that’s a problem with deep learning in general and not just inner alignment. The point is, if your model is not optimizing that reward function then its performance during training will be suboptimal. To the extent your algorithm is able to approximate the true optimum during training, it will behave safely during deployment.
I think you are understanding inner alignment very differently than we define it in Risks from Learned Optimization, where we introduced the term.
This is not true for deceptively aligned models, which is the situation I’m most concerned about, and—as we argue extensively in Risks from Learned Optimization—there are a lot of reasons why a model might end up pursuing a simpler/faster/easier-to-find proxy even if that proxy yields suboptimal training performance.
It may be helpful to point to specific sections of such a long paper.
(Also, I agree that a neural network trained trained with that reward could produce a deceptive model that makes a well-timed error.)
I don’t understand the alternative, but maybe that’s neither here nor there.
It’s a little hard to make a definitive statement about a hypothetical in which the inner alignment problem doesn’t apply to Bayesian inference. However, since error bounds are apparently a key piece of a solution, it certainly seems that if Bayesian inference was immune to mesa-optimizers it would be because of competence not resource-prodigality.
Here’s another tack. Hypothesis generation seems like a crucial part of intelligent prediction. Pure Bayesian reasoning does hypothesis generation by brute force. Suppose it was inefficiency, and not intelligence, that made Bayesian reasoning avoid mesa-optimizers. Then suppose we had a Bayesian reasoning that was equally intelligent but more efficient, by only generating relevant hypotheses. It gains efficiency by not even bothering to consider a bunch of obviously wrong models, but it’s posterior is roughly the same, so it should avoid inner alignment failure equally well. If, on the other hand, the hyopthesis generation routine was bad enough that some plausible hypotheses went unexamined, this could introduce an inner alignment failure, with a notable decrease in intelligence.
I expect some heuristic search with no discernable structure, guided “attentively” by an agent. And I expect this heuristic search through models to identify any model that a human could hypothesize, and many more.
Perhaps I’m just being pedantic, but when you’re building mathematical models of things I think it’s really important to call attention to what things in the real world those mathematical models are supposed to represent—since that’s how you know whether your assumptions are reasonable or not. In this case, there are two ways I could interpret this analysis: either the Bayesian learner is supposed to represent what we want our trained models to be doing, and then we can ask how we might train something that works that way; or the Bayesian learner is supposed to represent how we want our training process to work, and then we can ask how we might build training processes that work that way. I originally took you as saying the first thing, then realized you were actually saying the second thing.
That’s a good point. Perhaps I am just saying that I don’t think we’ll get training processes that are that competent. I do still think there are some ways in which I don’t fully buy this picture, though. I think that the point that I’m trying to make is that the Bayesian learner gets its safety guarantees by having a massive hypothesis space and just keeping track of how well each of those hypotheses is doing. Obviously, if you knew of a smaller space that definitely included the desired hypothesis, you could do that instead—but given a fixed-size space that you have to search over (and unless your space is absolutely tiny such that you basically already have what you want), for any given amount of compute, I think it’ll be more efficient to run a local search over that space than a global one.
Interesting. I’m not exactly sure what you mean by that. I could imagine “guided ‘attentively’ by an agent” to mean something like recursive oversight/relaxed adversarial training wherein some overseer is guiding the search process—is that what you mean?
I’m not exactly sure what I mean either, but I wasn’t imagining as much structure as exists in your post. I mean there’s some process which constructs hypotheses, and choices are being made about how computation is being directed within that process.
I think any any heuristic search algorithm worth its salt will incorporate information about proximity of models. And I think that arbitrary limits on heuristic search of the form “the next model I consider must be fairly close to the last one I did” will not help it very much if it’s anywhere near smart enough to merit membership in a generally intelligent predictor.
But for the purpose of analyzing it’s output, I don’t think this discussion is critical if we agree that we can expect a good heuristic search through models will identify any model that a human could hypothesize.
I think I would expect essentially all models that a human could hypothesize to be in the search space—but if you’re doing a local search, then you only ever really see the easiest to find model with good behavior, not all models with good behavior, which means you’re relying a lot more on your prior/inductive biases/whatever is determining how hard models are to find to do a lot more work for you. Cast into the Bayesian setting, a local search like this is relying on something like the MAP model not being deceptive—and escaping that to instead get N models sampled independently from the top q proportion or whatever seems very difficult to do via any local search algorithm.
So would you say you disagree with the claim
?
Yeah; I think I would say I disagree with that. Notably, evolution is not a generally intelligent predictor, but is still capable of producing generally intelligent predictors. I expect the same to be true of processes like SGD.
If we ever produce generally intelligent predictors (or “accurate world-models” in the terminology we’ve been using so far), we will need a process that is much more efficient than evolution.
But also, I certainly don’t think that in order to be generally intelligent you need to start with a generally intelligent subroutine. Then you could never get off the ground. I expect good hypothesis-generation / model-proposal to use a mess of learned heuristics which would not be easily directed to solve arbitrary tasks, and I expect the heuristic “look for models near the best-so-far model” to be useful, but I don’t think making it ironclad would be useful.
Another thought on our exchange:
If what you say is correct, then it sounds like exclusively-local search precludes human-level intelligence! (Which I don’t believe, by the way, even if I think it’s a less efficient path). One human competency is generating lots of hypotheses, and then having many models of the world, and then designing experiments to probe those hypotheses. It’s hard for me to imagine that an agent that finds an “easiest-to-find model” and then calls it a day could ever do human-level science. Even something as simple as understanding an interlocuter requires generating diverse models on the fly: “Do they mean X or Y with those words? Let me ask a clarfying question.”
I’m not this bearish on local search. But if local search is this bad, I don’t think it is a viable path to AGI, and if it’s not, then the internals don’t for the purposes of our discussion, and we can skip to what I take to be the upshot:
I certainly don’t think SGD is a powerful enough optimization process to do science directly, but it definitely seems powerful enough to find an agent which does do science.
We know that local search processes can produce AGI, so viability is a question of efficiency—and we know that SGD is at least efficient enough to solve a wide variety of problems from image classification, to language modeling, to complex video games, all given just current compute budgets. So while I could certainly imagine SGD being insufficient, I definitely wouldn’t want to bet on it.
Okay I think we’ve switched from talking about Q-learning to talking about policy gradient. (Or we were talking about the latter the whole time, and I didn’t notice it). The question that I think is relevant is: how are possible world-models being hypothesized and analyzed? That’s something I expect to be done with messy heuristics that sometimes have discontinuities their sequence of outputs. Which means I think that no reasonable DQN is will be generally intelligent (except maybe an enormously wide one attention-based one, such that finding models is more about selective attention at any given step than it is about gradient descent over the whole history).
A policy gradient network, on the other hand, could maybe (after having its parameters updated through gradient descent) become a network that, in a single forward pass, considers diverse world-models (generated with a messy non-local heuristic), and analyzes their plausibility, and then acts. At the end of the day, what we have is an agent modeling world, and we can expect it to consider any model that a human could come up with. (This paragraph also applies to the DQN with a gradient-descent-trained method for selectively attending to different parts of a wide network, since that could amount to effectively considering different models).
Hmmm… I don’t think I was ever even meaning to talk specifically about RL, but regardless I don’t expect nearly as large of a difference between Q-learning and policy gradient algorithms. If we imagine both types of algorithms making use of the same size massive neural network, the only real difference is how the output of that neural network is interpreted, either directly as a policy, or as Q values that are turned into a policy via something like softmax. In both cases, the neural network is capable of implementing any arbitrary policy and should be getting a similar sort of feedback signal from the training process—especially if you’re using a policy gradient algorithm that involves something like advantage estimation rather than actual rollouts, since the update rule in that situation is going to look very similar to the Q learning update rule. I do expect some minor differences in the sorts of models you end up with, such as Q learning being more prone to non-myopic behavior across episodes, and I think there are some minor reasons that policy gradient algorithms are favored in real-world settings, since they get to learn their exploration policy rather than having it hard-coded and can handle continuous action domains—but overall I think these sorts of differences are pretty minor and shouldn’t affect whether these approaches can reach general intelligence or not.
I interpreted this bit as talking about RL
But taking us back out of RL, in a wide neural network with selective attention that enables many qualitatively different forward passes, gradient descent seems to be training the way different models get proposed (i.e. the way attention is allocated), since this happens in a single forward pass, and what we’re left with is a modeling routine that is heuristically considering (and later comparing) very different models. And this should include any model that a human would consider.
I think that is main thread of our argument, but now I’m curious if I was totally off the mark about Q-learning and policy gradient.
I had thought that maybe since a Q-learner is trained as if the cached point estimate of the Q-value of the next state is the Truth, it won’t, in a single forward pass, consider different models about what the actual Q-value of the next state is. At most, it will consider different models about what the very next transition will be.
a) Does that seem right? and b) Aren’t there some policy gradient methods that don’t face this problem?
This seems wrong to me—even though the Q learner is trained using its own point estimate of the next state, it isn’t, at inference time, given access to that point estimate. The Q learner has to choose its Q values before it knows anything about what the Q value estimates will be of future states, which means it certainly should have to consider different models of what the next transition will be like.
Yeah I was agreeing with that.
Right, but one thing the Q-network, in its forward pass, is trying to reproduce is the point of estimate of the Q-value of the next state (since it doesn’t have access to it). What it isn’t trying to reproduce, because it isn’t trained that way, is multiple models of what the Q-value might be at a given possible next state.