Jacob_Hilton(Jacob Hilton)

• Jacob_Hilton 4 Feb 2023 19:50 UTC

  3 points

  in reply to: gwern’s comment on: Pro­posal: Scal­ing laws for RL generalization

  You might find this work interesting, which takes some small steps in this direction. It studies the effect of horizon length inasmuch as it makes credit assignment harder, showing that the number of samples required is an affine function of horizon length in a toy context.

• Jacob_Hilton 1 Feb 2023 17:42 UTC

  LW: 2 AF: 2

  0 ∶ 0

  AF

  in reply to: cfoster0’s comment on: The effect of hori­zon length on scal­ing laws

  I think the direction depends on what your expectations were – I’ll try to explain.

  First, some terminology: the term “horizon length” is used in the paper to refer to the number of timesteps over which the algorithm pays attention to rewards, as governed by the discount rate. In the biological anchors framework, the term “effective horizon length” is used to refer to a multiplier on the number of samples required to train the model, which is influenced by the horizon length and other factors. For clarity, I’ll using the term “scaling multiplier” instead of “effective horizon length” in this comment. The paper studies the effect of the horizon length on the scaling multiplier in a toy MNIST setting.

  One key takeaway is that the scaling multiplier is not simply proportional to the horizon length, as one might have naively expected. Instead, the number of samples required is the sum of two components, one that is inherent to the task and independent of the horizon length, and one that is proportional to the horizon length. Compared to the naive expectation, this means that training compute requirements are lower. On the other hand, this ignores reward sparsity, so you might expect training compute requirements to be higher once both horizon length and reward sparsity are accounted for.

  The paper also lends some support to the modeling assumptions of the neural network anchor, by validating the hypotheses that (a) training compute requirements still scale as a power law in model size for reinforcement learning, and with a similar exponent, and (b) the scaling multiplier can indeed vary a lot between environments. This might make you put more weight on the neural network anchor, which could again have either directional effect.

  The other takeaways are more methodological and I don’t think have much of a directional effect.

The effect of hori­zon length on scal­ing laws

• Jacob_Hilton 5 Dec 2022 0:58 UTC

  7 points

  0 ∶ 0

  in reply to: Wei_Dai’s comment on: Jailbreak­ing ChatGPT on Re­lease Day

  I would wildly speculate that “simply” scaling up RLHF ~100x, while paying careful attention to rewarding models appropriately (which may entail modifying the usual training setup, as discussed in this comment), would be plenty to get current models to express calibrated uncertainty well. However:

  • In practice, I think we’ll make a lot of progress in the short term without needing to scale up this much by using various additional techniques, some that are more like “tricks” (e.g. teaching the model to generally express uncertainty when answering hard math problems) and some more principled (e.g. automating parts of the evaluation).

  • Even ~100x is still much less than pre-training (e.g. WebGPT used ~20k binary comparisons, compared to ~300b pre-training tokens for GPT-3). The difficulty of course is that higher-quality data is more expensive to collect. However, most of the cost of RLHF is currently employee hours and compute, so scaling up data collection ~100x might not be as expensive as it sounds (although it would of course be a challenge to maintain data quality at this scale).

  • Even though scaling up data collection will help, I think it’s more important for labs to be prioritizing data quality (i.e. “reducing bias” rather than “reducing variance”): data quality issues are in some sense “scarier” in the long run, since they lead to the model systematically doing the wrong thing (e.g. deceiving the evaluators) rather than defaulting to the “safer” imitative pre-training behavior.

  • It’s pretty unclear how this picture will evolve over time. In the long run, we may end up needing much less extremely high-quality data, since larger pre-trained models are more sample efficient, and we may get better at using techniques like automating parts of the evaluation. I’ve written more about this question here, and I’d be excited to see more people thinking about it.

  In short, sample efficiency is a problem right now, but not the only problem, and it’s unclear how much longer it will continue to be a problem for.

• Jacob_Hilton 3 Dec 2022 7:04 UTC

  30 points

  0 ∶ 0

  in reply to: Wei_Dai’s comment on: Jailbreak­ing ChatGPT on Re­lease Day

  My understanding of why it’s especially hard to stop the model making stuff up (while not saying “I don’t know” too often), compared to other alignment failures:

  • The model inherits a strong tendency to make stuff up from the pre-training objective.

  • This tendency is reinforced by the supervised fine-tuning phase, if there are examples of answers containing information that the model doesn’t know. (However, this can be avoided to some extent, by having the supervised fine-tuning data depend on what the model seems to know, a technique that was employed here.)

  • In the RL phase, the model can in theory be incentivized to express calibrated uncertainty by rewarding it using a proper scoring rule. (Penalizing the model a lot for saying false things and a little for saying “I don’t know” is an approximation to this.) However, this reward signal is noisy and so is likely much less sample-efficient than teaching the model simple rules about how to behave.

  • Even if the model were perfectly calibrated, it would still make legitimate mistakes (e.g., if it were incentivized to say “I’m not sure” whenever it was <95% confident, it would still be wrong 5% of the time). In other words, there is also an inherent trade-off at play.

  • Labelers likely make some mistakes when assessing correctness, especially for more complex topics. This is in some sense the most pernicious cause of failure, since it’s not automatically fixed by scaling up RL, and leads to deception being directly incentivized. That being said, I suspect it’s currently driving a minority of the phenomenon.

  In practice, incorporating retrieval should help mitigate the problem to a significant extent, but that’s a different kind of solution.

  I expect that making the model adversarially robust to “jailbreaking” (enough so for practical purposes) will be easier than stopping the model making stuff up, since sample efficiency should be less of a problem, but still challenging due to the need to generate strong adversarial attacks. Other unwanted behaviors such as the model stating incorrect facts about itself should be fairly straightforward to fix, and it’s more a matter of there being a long list of such things to get through.

  (To be clear, I am not suggesting that aligning much smarter models will necessarily be as easy as this, and I hope that once “jailbreaking” is mostly fixed, people don’t draw the conclusion that it will be as easy.)

• Jacob_Hilton 8 Nov 2022 0:05 UTC

  1 point

  0 ∶ 0

  in reply to: Raphaël S’s comment on: Don’t you think RLHF solves outer al­ign­ment?

  I just meant that the usual RLHF setup is essentially RL in which the reward is provided by a learned model, but I agree that I was stretching the way the terminology is normally used.

• Jacob_Hilton 6 Nov 2022 0:21 UTC

  13 points

  0 ∶ 0

  in reply to: habryka’s comment on: Don’t you think RLHF solves outer al­ign­ment?

  I would estimate that the difference between “hire some mechanical turkers and have them think for like a few seconds” and the actual data collection process accounts for around ¹⁄₃ of the effort that went into WebGPT, rising to around ²⁄₃ if you include model assistance in the form of citations. So I think that what you wrote gives a misleading impression of the aims and priorities of RLHF work in practice.

  I think it’s best to err on the side of not saying things that are false in a literal sense when the distinction is important to other people, even when the distinction isn’t important to you—although I can see why you might not have realized the importance of the distinction to others from reading papers alone, and “a few minutes” is definitely less inaccurate.

• Jacob_Hilton 5 Nov 2022 18:31 UTC

  4 points

  0 ∶ 0

  in reply to: habryka’s comment on: Don’t you think RLHF solves outer al­ign­ment?

  However, I do think in-practice, the RLHF that has been implemented has mostly been mechanical turkers thinking about a problem for a few minutes

  I do not consider this to be accurate. With WebGPT for example, contractors were generally highly educated, usually with an undergraduate degree or higher, were given a 17-page instruction manual, had to pass a manually-checked trial, and spent an average of 10 minutes on each comparison, with the assistance of model-provided citations. This information is all available in Appendix C of the paper.

  There is RLHF work that uses lower-quality data, but it tends to be work that is more experimental, because data quality becomes important once you are working on a model that is going to be used in the real world.

  Annoyingly almost none of the papers and blogposts speak straightforwardly about who they used as the raters

  There is lots of information about rater selection given in RLHF papers, for example, Appendix B of InstructGPT and Appendix C of WebGPT. What additional information do you consider to be missing?

• Jacob_Hilton 5 Nov 2022 8:42 UTC

  4 points

  0 ∶ 0

  in reply to: habryka’s comment on: Don’t you think RLHF solves outer al­ign­ment?

  I agree that the RLHF framework is essentially just a form of model-based RL, and that its outer alignment properties are determined entirely by what you actually get the humans to reward. But your description of RLHF in practice is mostly wrong. Most of the challenge of RLHF in practice is in getting humans to reward the right thing, and in doing so at sufficient scale. There is some RLHF research that uses low-quality feedback similar to what you describe, but it does so in order to focus on other aspects of the setup, and I don’t think anyone currently working on RLHF seriously considers that quality of feedback to be at all adequate outside of an experimental setting.

  The RLHF work I’m most excited by, and which constitutes a large fraction of current RLHF work, is focused on getting humans to reward the right thing, and I’m particularly excited about approaches that involve model assistance, since that’s the main way in which we can hope for the approach to scale gracefully with model capabilities. I’m also excited by other RLHF work because it supports this work and has other practical benefits.

  I don’t think RLHF directly addresses inner alignment, but I think that an inner alignment solution is likely to rely on us doing a good enough job at outer alignment, and I also have a lot of uncertainty about how much of the risk comes from outer alignment failures directly.

  What links here?

  • Com­pendium of prob­lems with RLHF by Raphaël S (29 Jan 2023 11:40 UTC; 85 points)
  • Com­pendium of prob­lems with RLHF by Raphaël S (EA Forum; 30 Jan 2023 8:48 UTC; 13 points)

• Jacob_Hilton 29 Oct 2022 5:01 UTC

  LW: 2 AF: 2

  0 ∶ 0

  AF

  in reply to: Adam Jermyn’s comment on: Scal­ing Laws for Re­ward Model Overoptimization

  1. We are just observing that the gold RM score curves in Figure 9 overlap. In other words, the KL penalty did not affect the relationship between KL and gold RM score in this experiment, meaning that any point on the Pareto frontier could be reached using only early stopping, without the KL penalty. As mentioned though, we’ve observed this result to be sensitive to hyperparameters, and so we are less confident in it than other results in the paper.

  2. I don’t have this data to hand unfortunately.

  3. I don’t have this data to hand, but entropy typically falls roughly linearly over the course of training, sometimes slightly faster towards the start, and typically moving around more than KL. So I’d expect the graph to look somewhat similar, but for it to be noisier and for the functional form to not fit as well.

Scal­ing Laws for Re­ward Model Overoptimization

• Jacob_Hilton 15 Sep 2022 16:03 UTC

  LW: 3 AF: 3

  0 ∶ 0

  AF

  in reply to: tailcalled’s comment on: Co­or­di­nate-Free In­ter­pretabil­ity Theory

  Agreed. Likewise, in a transformer, the token dimension should maintain some relationship with the input and output tokens. This is sometimes taken for granted, but it is a good example of the data preferring a coordinate system. My remark that you quoted only really applies to the channel dimension, across which layers typically scramble everything.

• Jacob_Hilton 15 Sep 2022 5:26 UTC

  LW: 24 AF: 16

  0 ∶ 0

  AF

  on: Co­or­di­nate-Free In­ter­pretabil­ity Theory

  The notion of a preferred (linear) transformation for interpretability has been called a “privileged basis” in the mechanistic interpretability literature. See for example Softmax Linear Units, where the idea is discussed at length.

  In practice, the typical reason to expect a privileged basis is in fact SGD – or more precisely, the choice of architecture. Specifically, activation functions such as ReLU often privilege the standard basis. I would not generally expect the data or the initialization to privilege any basis beyond the start of the network or the start of training. The data may itself have a privileged basis, but this should be lost as soon as the first linear layer is reached. The initialization is usually Gaussian and hence isotropic anyway, but if it did have a privileged basis I would also expect this to be quickly lost without some other reason to hold onto it.

• Jacob_Hilton 27 Aug 2022 15:26 UTC

  32 points

  0 ∶ 0

  in reply to: gadyp’s comment on: Com­mon mis­con­cep­tions about OpenAI

  Thank you for causing me to reconsider. I should have said “other OpenAI employees”. I do not intend to disengage from the alignment community because of critical rhetoric, and I apologize if my comment came across as a threat to do so. I am concerned about further breakdown of communication between the alignment community and AI labs where alignment solutions may need to be implemented.

  I don’t immediately see any other reason why my comment might have been inappropriate, but I welcome your clarification if I am missing something.

• Jacob_Hilton 27 Aug 2022 8:30 UTC

  9 points

  0 ∶ 0

  in reply to: lc’s comment on: Com­mon mis­con­cep­tions about OpenAI

  I obviously think there are many important disanalogies, but even if there weren’t, rhetoric like this seems like an excellent way to discourage OpenAI employees from ever engaging with the alignment community, which seems like a pretty bad thing to me.

  What links here?

  • Adam Scholl's comment on Com­mon mis­con­cep­tions about OpenAI by Jacob_Hilton (27 Aug 2022 15:54 UTC; 170 points)

• Jacob_Hilton 26 Aug 2022 20:34 UTC

  LW: 3 AF: 3

  0 ∶ 0

  AF

  in reply to: Neel Nanda’s comment on: Com­mon mis­con­cep­tions about OpenAI

  For people viewing on the Alignment Forum, there is a separate thread on this question here. (Edit: my link to LessWrong is automatically converted to an Alignment Forum link, you will have to navigate there yourself.)

• Jacob_Hilton 26 Aug 2022 14:51 UTC

  LW: 6 AF: 1

  0 ∶ 0

  AF

  in reply to: habryka’s comment on: Com­mon mis­con­cep­tions about OpenAI

  Without commenting on the specifics, I have edited to the post to mitigate potential confusion: “this fact alone is not intended to provide a complete picture of the Anthropic split, which is more complicated than I am able to explain here”.

• Jacob_Hilton 25 Aug 2022 21:19 UTC

  LW: 28 AF: 13

  0 ∶ 0

  AF

  in reply to: habryka’s comment on: Com­mon mis­con­cep­tions about OpenAI

  I was the project lead on WebGPT and my motivation was to explore ideas for scalable oversight and truthfulness (some further explanation is given here).

  What links here?

  • Richard_Ngo's comment on Com­mon mis­con­cep­tions about OpenAI by Jacob_Hilton (29 Aug 2022 23:55 UTC; 11 points)

• Jacob_Hilton 25 Aug 2022 19:24 UTC

  LW: 13 AF: 8

  0 ∶ 0

  AF

  in reply to: Larks’s comment on: Com­mon mis­con­cep­tions about OpenAI

  It includes the people working on the kinds of projects I listed under the first misconception. It does not include people working on things like the mitigation you linked to. OpenAI distinguishes internally between research staff (who do ML and policy research) and applied staff (who work on commercial activities), and my numbers count only the former.

• Jacob_Hilton 25 Aug 2022 18:54 UTC

  LW: 2 AF: 2

  0 ∶ 0

  AF

  in reply to: Joe_Collman’s comment on: Com­mon mis­con­cep­tions about OpenAI

  I don’t think I understand your question about Y-problems, since it seems to depend entirely on how specific something can be and still count as a “problem”. Obviously there is already experimental evidence that informs predictions about existential risk from AI in general, but we will get no experimental evidence of any exact situation that occurs beforehand. My claim was more of a vague impression about how OpenAI leadership and John tend to respond to different kinds of evidence in general, and I do not hold it strongly.