All of Vlad Mikulik's Comments + Replies

FWIW I agree with you and wouldn't put it the way it is in Roger's post. Not sure what Roger would say in response.

The reasoning for the indistinguishability criterion is as a precaution against a model sandbagging when used as the red team attack model. If the model can tell it’s in a control eval it could pretend to be worse at attacking, making us think the control measures are better than they actually are. If the red team elicitation is robust to this, I agree this isn’t necessary. (See the note below [P2.4]).

Ah, yep, I think you're right -- it should be pretty easy to add support for and in selectors then.

You're right that accounting for the softmax could be used to get around the argument in the appendix.  We'll mention this when we update the paper.

The scheme as you described it relies on an always-on dummy token, which would conflict with our implementation of default values in aggregates: we fix the BOS token attention to 0.5, so at low softmax temp it's attended to iff nothing else is; however with this scheme we'd want 0.5 to always round off to zero after softmax. This is plausibly surmountable but we put it out of scope for the pilot release si... (read more)

Nice work! 

This section in Anthropic's work on Induction heads seems highly relevant -- I would be interested in seeing an extension of your analysis that looks at what induction heads do in these tasks.

If we believe the claims in that paper, then in-context learning of any kind seems to driven by a fairly simple mechanism not unlike kNN -- induction attention heads. Since it's pretty tractable to locate induction heads in an automated way, we could potentially take a look at the actual mechanism being used to implement these predictions and verify/fa... (read more)

Thanks for the link. This has been on my reading list for a little bit and your recco tipped me over.

Mostly I agree with Paul's concerns about this paper. 

However, I did find the "Transformer Feed-Forward Layers Are Key-Value Memories" paper they reference more interesting -- it's more mechanistic, and their results are pretty encouraging. I would personally highlight that one more, as it's IMO stronger evidence for the hypothesis, although not conclusive by any means.

Some experiments they show:

• Top-k activations of individual 'keys' do seem like coher

Thanks for a great post.

---

One nice point that this post makes (which I suppose was also prominent in the talk, but I can only guess, not being there myself) is that there's a kind of progression we can draw (simplifying a little):

- Human specifies what to do (Classical software)
- Human specifies what to achieve (RL)
- Machine infers a specification of what to achieve (IRL)
- Machine collaborates with human to infer and achieve what the human wants (Assistance games)

Towards the end, this post describes an extrapolation of this trend,

- Machine and human colla... (read more)

Thanks for the post and writeup, and good work! I especially appreciate the short, informal explanation of what makes this work.

Given my current understanding of the proposal, I have one worry which makes me reluctant to share your optimism about this being a solution to inner alignment:

The scheme doesn't protect us if somehow all top-n demonstrator models have correlated errors. This could happen if they are coordinating, or more prosaically if our way to approximate the posterior leads to such correlations. The picture I have in my head for the latter is... (read more)

More than a year since writing this post, I would still say it represents the key ideas in the sequence on mesa-optimisation which remain central in today's conversations on mesa-optimisation. I still largely stand by what I wrote, and recommend this post as a complement to that sequence for two reasons:

First, skipping some detail allows it to focus on the important points, making it better-suited than the full sequence for obtaining an overview of the area. 

Second, unlike the sequence, it deemphasises the mechanism of optimisation, and explicitly cas... (read more)

Not Abram, and I have only skimmed the post so far, and maybe you're pointing to something more subtle, but my understanding is this:

In Stuart's original use, 'No Indescribable Hellwords' is the hypothesis that in any possible world in which a human's values are violated, the violation is describable: one can point out to the human how her values are violated by the state of affairs.

Analogously, debate as an approach to alignment could be seen as predicated on a similar hypothesis: that in any possible flawed argument, the flaw is describable: one can poin... (read more)

Thanks for writing this. 

I wish you included an entry for your definition of 'mesa-optimizer'. When you use the term, do you mean the definition from the paper* (an algorithm that's literally doing search using the mesa objective as the criterion), or you do speak more loosely (e.g., a mesa-optimizer is an optimizer in the same sense as a human is an optimizer)? 

A related question is: how would you describe a policy that's a bag of heuristics which, when executed, systematically leads to interesting (low-entopy) low-base-objective states?

*inciden... (read more)

Good point -- I think I wasn't thinking deeply enough about language modelling. I certainly agree that the model has to learn in the colloquial sense, especially if it's doing something really impressive that isn't well-explained by interpolating on dataset examples -- I'm imagining giving GPT-X some new mathematical definitions and asking it to make novel proofs.

I think my confusion was rooted in the fact that you were replying to a section that dealt specifically with learning an inner RL algorithm, and the above sense of 'learni... (read more)

I am quite confused. I wonder if we agree on the substance but not on the wording, but perhaps it’s worthwhile talking this through.

I follow your argument, and it is what I had in mind when I was responding to you earlier. If approximating ${\pi }^{\ast }\left(o_t\right)$ within the constraints requires computing $f\left(o_t\right)$, then any policy that approximates ${\pi }^{\ast }$ must compute $f\left(o_t\right)$. (Assuming appropriate constraints that preclude the policy from being a lookup table precomputed by SGD; not sure if that’s what you meant by “other similar”, though this may be trickier to do formally than we... (read more)

I interpreted your previous point to mean you only take updates off-policy, but now I see what you meant. When I said you can update after every observation, I meant that you can update once you have made an environment transition and have an (observation, action, reward, observation) tuple. I now see that you meant the RL algorithm doesn't have the ability to update on the reward before the action is taken, which I agree with. I think I still am not convinced, however.

And can we taboo the word 'learning' for this discussion, or keep it to t... (read more)

I've thought of two possible reasons so far.

Perhaps your outer RL algorithm is getting very sparse rewards, and so does not learn very fast. The inner RL could implement its own reward function, which gives faster feedback and therefore accelerates learning. This is closer to the story in Evan's mesa-optimization post, just replacing search with RL.

More likely perhaps (based on my understanding), the outer RL algorithm has a learning rate that might be too slow, or is not sufficiently adaptive to the situation. The inner RL algorithm adjusts its

I would propose a third reason, which is just that learning done by the RL algorithm happens after the agent has taken all of its actions in the episode, whereas learning done inside the model can happen during the episode.

This is not true of RL algorithms in general -- If I want, I can make weight updates after every observation. And yet, I suspect that if I meta-train a recurrent policy using such an algorithm on a distribution of bandit tasks, I will get a 'learning-to-learn' style policy.

So I think this is a less fundamental reason, though it is true in off-policy RL.

I had a similar confusion when I first read Evan's comment. I think the thing that obscures this discussion is the extent to which the word 'learning' is overloaded -- so I'd vote taboo the term and use more concrete language.

You might want to look into NMF, which, unlike PCA/SVD, doesn't aim to create an orthogonal projection. It works well for interpretability because its components cannot cancel each other out, which makes its features more intuitive to reason about. I think it is essentially what you want, although I don't think it will allow you to find directly the 'larger set of almost orthogonal vectors' you're looking for.

I think we basically agree. I would also prefer people to think more about the middle case. Indeed, when I use the term mesa-optimiser, I usually intend to talk about the middle picture, though strictly that’s sinful as the term is tied to Optimisers.

Re: inner alignment

I think it’s basically the right term. I guess in my mind I want to say something like, “Inner Alignment is the problem of aligning objectives across the Mesa≠Base gap”, which shows how the two have slightly different shapes. But the difference isn’t really important.

Inner alignment gap? Inner objective gap?

I’m not talking about finding on optimiser-less definition of goal-directedness that would support the distinction. As you say, that is easy. I am interested in a term that would just point to the distinction without taking a view on the nature of the underlying goals.

As a side note I think the role of the intentional stance here is more subtle than I see it discussed. The nature of goals and motivation in an agent isn’t just a question of applying the intentional stance. We can study how goals and motivation work in the brain neuroscientifically (or at le

I understand that, and I agree with that general principle. My comment was intended to be about where to draw the line between incorrect theory, acceptable theory, and pre-theory.

In particular, I think that while optimisation is too much theory, goal-directedness talk is not, despite being more in theory-land than empirical malign generalisation talk. We should keep thinking of worries on the level of goals, even as we’re still figuring out how to characterise goals precisely. We should also be thinking of worries on the level of what we could observe empirically.

We’re probably in agreement, but I’m not sure what exactly you mean by “retreat to malign generalisation”.

For me, mesa-optimisation’s primary claim isn’t (call it Optimisers) that agents are well-described as optimisers, which I’m happy to drop. It is the claim (call it Mesa≠Base) that whatever the right way to describe them is, in general their intrinsic goals are distinct from the reward.

That’s a specific (if informal) claim about a possible source of malign generalisation. Namely, that when intrinsic goals differ arbitrarily from the reward, then system

I’m sympathetic to what I see as the message of this post: that talk of mesa-optimisation is too specific given that the practical worry is something like malign generalisation. I agree that it makes extra assumptions on top of that basic worry, which we might not want to make. I would like to see more focus on inner alignment than on mesa-optimisation as such. I’d also like to see a broader view of possible causes for malign generalisation, which doesn’t stick so closely to the analysis in our paper. (In hindsight our analysis could also have benefitted f

By that I didn’t mean to imply that we care about mesa-optimisation in particular. I think that this demo working “as intended” is a good demo of an inner alignment failure, which is exciting enough as it is. I just also want to flag that the inner alignment failure doesn’t automatically provide an example of a mesa-optimiser.

I have now seen a few suggestions for environments that demonstrate misaligned mesa-optimisation, and this is one of the best so far. It combines being simple and extensible with being compelling as a demonstration of pseudo-alignment if it works (fails?) as predicted. I think that we will want to explore more sophisticated environments with more possible proxies later, but as a first working demo this seems very promising. Perhaps one could start even without the maze, just a gridworld with keys and boxes.

I don’t know whether observing key-collection beha

Ah; this does seem to be an unfortunate confusion.

I didn’t intend to make ‘utility’ and ‘reward’ terminology – that’s what ‘mesa-‘ and ‘base’ objectives are for. I wasn’t aware of the terms being used in the technical sense as in your comment, so I wanted to use utility and reward as friendlier and familiar words for this intuition-building post. I am not currently inclined to rewrite the whole thing using different words because of this clash, but could add a footnote to clear this up. If the utility/reward distinction in your sense becomes accepted termi

You’re completely right; I don’t think we meant to have ‘more formally’ there.

I’ve been meaning for a while to read Dennett with reference to this, and actually have a copy of Bacteria to Bach. Can you recommend some choice passages, or is it significantly better to read the entire book?

P.S. I am quite confused about DQN’s status here and don’t wish to suggest that I’m confident it’s an optimiser. Just to point out that it’s plausible we might want to call it one without calling PPO an optimiser.

P.P.S.: I forgot to mention in my previous comment that I enjoyed the objective graph stuff. I think there might be fruitful overlap betwee

Thanks for an insightful comment. I think your points are good to bring up, and though I will offer a rebuttal I’m not convinced that I am correct about this.

What’s at stake here is: describing basically any system as an agent optimising some objective is going to be a leaky abstraction. The question is, how do we define the conditions of calling something an agent with an objective in such a way to minimise the leaks?

Distinguishing the “this system looks like it optimises for X” from “this system internally uses an evaluation of X to make decisions” is us

I think humans are fairly weird because we were selected for an objective that is unlikely to be what we select for in our AIs.

That said, if we model AI success as driven by model size and compute (with maybe innovations in low-level architecture), then I think that the way humans represent objectives is probably fairly close to what we ought to expect.

If we model AI success as mainly innovative high-level architecture, then I think we will see more explicitly represented objectives.

My tentative sense is that for AI to be interpretable (and safer) we want

Yes, it probably doesn’t apply to most objectives. Though it seems to me that the closer the task is to something distinctly human, the more probable it is that this kind of consideration can apply. E.g., making judgements in criminal court cases and writing fiction are domains where it’s not implausible to me that this could apply.

I do think this is a pretty speculative argument, even for this sequence.

The main benefit I see of hardcoding optimisation is that, assuming the system's pieces learn as intended (without any mesa-optimisation happening in addition to the hardcoded optimisation) you get more access and control as a programmer over what the learned objective actually is. You could attempt to regress the learned objective directly to a goal you want, or attempt to enforce a certain form on it, etc. When the optimisation itself is learned*, the optimiser is more opaque, and you have fewer ways to affect what goal is learned: which weights of... (read more)

The section on human modelling annoyingly conflates two senses of human modelling. One is the sense you talk about, the other is seen in the example:

For example, it might be the case that predicting human behavior requires instantiating a process similar to human judgment, complete with internal motives for making one decision over another.

The idea there isn't that the algorithm simulates human judgement as an external source of information for itself, but that the actual algorithm learns to be a human-like reasoner, with human-like goals (because tha... (read more)

to what extent are mesa-controllers with simple behavioural objectives going to be simple?

I’m not sure what “simple behavioural objective” really means. But I’d expect that for tasks requiring very simple policies, controllers would do, whereas the more complicated the policy required to solve a task, the more one would need to do some kind of search. Is this what we observe? I’m not sure. AlphaStar and OpenAI Five seem to do well enough in relatively complex domains without any explicit search built into the architecture. Are they using their recurrenc

(I am unfortunately currently bogged down with external academic pressures, and so cannot engage with this at the depth I’d like to, but here’s some initial thoughts.)

I endorse this post. The distinction explained here seems interesting and fruitful.

I agree with the idea to treat selection and control as two kinds of analysis, rather than as two kinds of object – I think this loosely maps onto the distinction we make between the mesa-objective and the behavioural objective. The former takes the selection view of the learned algorithm; the latter takes the

The goal that the agent is selected to score well on is not necessarily the goal that the agent is itself pursuing. So, unless the agent’s internal goal matches the goal for which it’s selected, the agent might still seek influence because its internal goal permits that. I think this is in part what Paul means by “Avoiding end-to-end optimization may help prevent the emergence of influence-seeking behaviors (by improving human understanding of and hence control over the kind of reasoning that emerges)”

I agree. That’s what I meant when I wrote there will be TMs that artificially promote S itself. However, this would still mean that most of S’s mass in the prior would be due to these TMs, and not due to the natural generator of the string.

Furthermore, it’s unclear how many TMs would promote S vs S’ or other alternatives. Because of this, I don’t now whether the prior would be higher for S or S’ from this reasoning alone. Whichever is the case, the prior no longer reflects meaningful information about the universe that generates S and whose inhabitants are using the prefix to choose what to do; it’s dominated by these TMs that search for prefixes they can attempt to influence.

I agree that this probably happens when you set out to mess with an arbitrary particular S, I.e. try to make some S’ that shares a prefix with S as likely as S.

However, some S are special, in the sense that their prefixes are being used to make very important decisions. If you, as a malicious TM in the prior, perform an exhaustive search of universes, you can narrow down your options to only a few prefixes used to make pivotal decisions, selecting one of those to mess with is then very cheap to specify. I use S to refer to those strings that are the ‘natu... (read more)

The trigger sequence is a cool idea.

I want to add that the intended generator TM also needs to specify a start-to-read time, so there is symmetry there. Whatever method a TM needs to use to select the camera start time in the intended generator for the real world samples, it can also use in the simulated world with alien life, since for the scheme to work only the difference in complexity between the two matters.

There is additional flex in that unlike the intended generator, the reasoner TM can sample its universe simulation at any cheaply computable interval, giving the civilisation the option of choosing any amount of thinking they can perform between outputs, if they so choose.