Was on Vivek Hebbar's team at MIRI, now working with Adrià Garriga-Alonso on various empirical alignment projects.
I'm looking for projects in interpretability, activation engineering, and control/oversight; DM me if you're interested in working with me.
The model ultimately predicts the token two positions after B_def. Do we know why it doesn't also predict the token two after B_doc? This isn't obvious from the diagram; maybe there is some way for the induction head or arg copying head to either behave differently at different positions, or suppress the information from B_doc.
I talked about this with Lawrence, and we both agree on the following:
You should update by +-1% on AI doom surprisingly frequently
This is just a fact about how stochastic processes work. If your p(doom) is Brownian motion in 1% steps starting at 50% and stopping once it reaches 0 or 1, then there will be about 50^2=2500 steps of size 1%. This is a lot! If we get all the evidence for whether humanity survives or not uniformly over the next 10 years, then you should make a 1% update 4-5 times per week. In practice there won't be as many due to heavy-tailedness in the distribution concentrating the updates in fewer events, and the fact you don't start at 50%. But I do believe that evidence is coming in every week such that ideal market prices should move by 1% on maybe half of weeks, and it is not crazy for your probabilities to shift by 1% during many weeks if you think about it often enough. [Edit: I'm not claiming that you should try to make more 1% updates, just that if you're calibrated and think about AI enough, your forecast graph will tend to have lots of >=1% week-to-week changes.]
I'm not so sure that shards should be thought of as a matter of implementation. Contextually activated circuits are a different kind of thing from utility function components. The former activate in certain states and bias you towards certain actions, whereas utility function components score outcomes. I think there are at least 3 important parts of this:
The first two are behavioral. We can say an agent is likely to be shardful if it displays these types of incoherence but not others. Suppose an agent is dynamically inconsistent and we can identify features in the environment like cheese presence that cause its preferences to change, but mostly does not suffer from the Allais paradox, tends to spend resources on actions proportional to their importance for reaching a goal, and otherwise generally behaves rationally. Then we can hypothesize that the agent has some internal motivational structure which can be decomposed into shards. But exactly what motivational structure is very uncertain for humans and future agents. My guess is researchers need to observe models and form good definitions as they go along, and defining a shard agent as having compositionally represented motivators is premature. For now the most important thing is how steerable agents will be, and it is very plausible that we can manipulate motivational features without the features being anything like compositional.
I now think the majority of impact of AI pause advocacy will come from the radical flank effect, and people should study it to decide whether pause advocacy is good or bad.
If SAE features are the correct units of analysis (or at least more so than neurons), should we expect that patching in the feature basis is less susceptible to the interpretability illusion than in the neuron basis?
Maybe related: A paper likely to get an oral at ICLR 2024. I haven't read it, but I think it substantially improves on the Good Regulator Theorem. I think their Theorem 1 shows that from an optimal policy, you can identify (deduce) the exact causal model of the data generating process, and Theorem 2 shows that from a policy satisfying regret bounds, you can identify an approximate causal model. The assumptions are far weaker and more realistic than being the simplest policy that can perfectly regulate some variable.
Robust agents learn causal world models
[...]
We prove that agents that are capable of adapting to distributional shifts must have learned a causal model of their environment, establishing a formal equivalence between causality and transfer learning.
I think that interpretability research isn't going to be able to produce explanations that are very faithful explanations of what's going on in non-toy models (e.g. I think that no such explanation has ever been produced). Since I think faithful explanations are infeasible, measures of faithfulness of explanations don't seem very important to me now.
By "explanations" you mean labeled high-level causal graphs right? Do you also think it's infeasible to identify sparse, unlabeled circuits as "the part of the model that's doing the task", like in ACDC, in a way that gets good performance on some downstream task?
I started a dialogue with @Alex_Altair a few months ago about the tractability of certain agent foundations problems, especially the agent-like structure problem. I saw it as insufficiently well-defined to make progress on anytime soon. I thought the lack of similar results in easy settings, the fuzziness of the "agent"/"robustly optimizes" concept, and the difficulty of proving things about a program's internals given its behavior all pointed against working on this. But it turned out that we maybe didn't disagree on tractability much, it's just that Alex had somewhat different research taste, plus thought fundamental problems in agent foundations must be figured out to make it to a good future, and therefore working on fairly intractable problems can still be necessary. This seemed pretty out of scope and so I likely won't publish.
Now that this post is out, I feel like I should at least make this known. I don't regret attempting the dialogue, I just wish we had something more interesting to disagree about.