All of Sam Marks's Comments + Replies

Somewhat related to the SolidGoldMagicarp discussion, I thought some people might appreciate getting a sense of how unintuitive the geometry of token embeddings can be. Namely, it's worth noting that the tokens whose embeddings are most cosine-similar to a random vector in embedding space tend not to look very semantically similar to each other. Some examples:

v_1                 v_2             v_3
 characterized       Columb          determines
 Stra                1900           conserv
... (read more)

This, broadly-speaking, is also my best guess, but I'd rather phrase it as: larger LMs are better at making the personas they imitate "realistic" (in the sense of being more similar to the personas you encounter when reading webtext). So doing RLHF on a larger LM results in getting an imitation of a more realistic useful persona. And for the helpful chatbot persona that Anthropic's language model was imitating, one correlate of being more realistic was preferring not to be shut down.

(This doesn't obviously explain the results on sycophancy. I think for tha... (read more)

Regarding your points on agentic simulacra (which I assume means "agentic personas the language model ends up imitating"):

1) My best guess about why Anthropic's model expressed self-preservation desires is the same as yours: the model was trying to imitate some relatively coherent persona, this persona was agentic, and so it was more likely to express self-preservation desires.

2) But I'm pretty skeptical about your intuition that RLHF makes the "imitating agentic personas" problem worse. When people I've spoken to talk about conditioning-based alternatives... (read more)

4Arun Jose2mo
I wasn't really focusing on the RL part of RLHF in making the claim that it makes the "agentic personas" problem worse, if that's what you meant. I'm pretty on board with the idea that the actual effects of using RL as opposed to supervised fine-tuning won't be apparent until we use stronger RL or something. Then I expect we'll get even weirder effects, like separate agentic heads or the model itself becoming something other than a simulator (which I discuss in a section of the linked post []). My claim is pretty similar to how you put it - in RLHF as in fine-tuning of the kind relevant here, we're focusing the model onto outputs that are generated by better agentic persona. But I think that the effect is particuarly salient with RLHF because it's likely to be scaled up more in the future, where I expect said effect to be exacerbated. I agree with the rest of it, that prompt engineering is unlikely to produce the same effect, and definitely not the same qualitative shift of the world prior.

In terms of being able to sample from the conditional, I don't think that the important constraint here is . Rather, it seems that the important constraint is that our architecture can only sample from distributions of the form ; even allowing  to be arbitrary real numbers, this will never be the same as either (a) the distribution produced by conditioning the base model on high persuasiveness, or (b) the distribution which maximizes expected persuasiveness - KL divergence from the base model.... (read more)

3Paul Christiano3mo
I'm also most nervous about this way of modeling limitation (2)/(3), since it seems like it leads directly to the conclusion "fine-tuning always trades off truthfulness and persuasion, but conditioning can improve both."

(The worked example in this comment was a joint effort with Eric Neyman and Drake Thomas.)

Here's a toy example in which we get worse Goodharting for RL than for filtering: suppose that our model has three submodules

  • A, which tries to produce outputs which are both true and persuasive
  • B, which tries to produce outputs which are true, but have no effect on persuasiveness
  • C, which tries to produce outputs which are persuasive, but with no effect on truthiness.

Our model has parameters  summing to 1 which determine how much to listen to each of thes... (read more)

3Paul Christiano3mo
Note that in this example your model is unable to sample from the conditional you specified, since it is restricted to α+β+γ=1. In this regime truthfulness and persuasiveness are anticorrelated because of a capability constraint of your model, it just literally isn't able to increase both at the same time, and conditioning can do better because you are generating lots of samples and picking the best. (You point this out in your comment, but it seems worth emphasizing. As you say, if you do RL with a KL penalty, then the capability limit is the only way you can get this kind of mismatch. Without a KL penalty the exact behavior of RL vs conditioning will depend on details of gradient descent, though it seems quite similar in practice and I'm not sure which way this comparison goes.)

The paper is frustratingly vague about what their context lengths are for the various experiments, but based off of comparing figures 7 and 4, I would guess that the context length for Watermaze was 1-2 times as long as an episode length(=50 steps). (It does indeed look like they were embedding the 2d dark room observations into a 64-dimensional space, which is hilarious.)

I'm not sure I understand your second question. Are you asking about figure 4 in the paper (the same one I copied into this post)? There's no reward conditioning going on. They're also no... (read more)

My recent post on generative models has some related discussion; see especially remark 1 on the satisficer, quantilizer, and optimizer approaches to making agents with generative models.

Two interesting differences between the approaches discussed here and in my linked post:

  • In my post, I assumed that the generative model was trained on a data set which included rewards (for example, humans playing Breakout, where the reward is provided by the environment; or a setting in which rewards can be provided by a reward model trained with human feedback). In contra
... (read more)
2Adam Jermyn8mo
This is helpful, thanks for summarizing the differences! I definitely agree on the first one.  On the second one, my concern is basically that all the safety guarantees that quantilizers provide have an inherent power/safety tradeoff (modulo whatever I'm missing from the "Targeted Impact" section). That said, it's possible that your nested approach may avoid the 'simulate a deceptive AGI' failure mode. At least, if it's a continuous trajectory of improvement from median human performance up to very superhuman performance you might hope that that trajectory doesn't involve suddenly switching from human-like to AGI-like models. I don't personally find this very comforting (it seems totally plausible to me that there's a continuous path from "median human" to "very dangerous misaligned model" in model-space), but it does at least seem better than directly asking for a superhuman model.

When "List of Lethalities" was posted, I privately wrote a list of where I disagreed with Eliezer, and I'm quite happy to see that there's a lot of convergence between my private list and Paul's list here. 

I thought it would be a useful exercise to diff my list with Paul's; I'll record the result in the rest of this comment without the expectation that it's useful to anyone else.

Points on both lists:

  • Eliezer's "first critical try" framing downplays the importance of trial-and-error with non-critical tries.
  • It's not clear that a "pivotal act" by an align
... (read more)

When "List of Lethalities" was posted, I privately wrote a list of where I disagreed with Eliezer

Why privately?!  Is there a phenomenon where other people feel concerned about the social reception of expressing disagreement until Paul does?  This is a phenomenon common in many other fields - and I'd invoke it to explain how the 'tone' of talk about AI safety shifted so quickly once I came right out and was first to say everybody's dead - and if it's also happening on the other side then people need to start talking there too.  Especially if people think they have solutions.  They should talk.

Hmm, I'm not sure I understand -- it doesn't seem to me like noisy observations ought to pose a big problem to control systems in general.

For example, suppose we want to minimize the number of mosquitos in the U.S., and we access to noisy estimates of mosquito counts in each county. This may result in us allocating resources slightly inefficiently (e.g. overspending resources on counties that have fewer mosquitos than we think), but we'll still always be doing the approximately correct thing and mosquito counts will go down. In particular, I don't see a se... (read more)

0G Gordon Worley III10mo
"Error" here is all sources of error, not just error in the measurement equipment. So bribing surveyors is a kind of error in my model.

This paper gives a mathematical model of when Goodharting will occur. To summarize: if

(1) a human has some collection  of things which she values,

(2) a robot has access to a proxy utility function which takes into account some strict subset of those things, and

(3) the robot can freely vary how much of  there are in the world, subject only to resource constraints that make the  trade off against each other,

then when the robot optimizes for its proxy utility, it will minimize all 's which its proxy utility... (read more)

1G Gordon Worley III10mo
I actually don't think that model is general enough. Like, I think Goodharting is just a fact of control system's observing. Suppose we have a simple control system with output X and a governor G. G takes a measurement m(X) (an observation) of X. So long as m(X) is not error free (and I think we can agree that no real world system can be actually error free), then X=m(X)+ϵ for some error factor ϵ. Since G uses m(X) to regulate the system to change X, we now have error influencing the value of X. Now applying the standard reasoning for Goodhart, in the limit of optimization pressure (i.e. G regulating the value of X for long enough), ϵ comes to dominate the value of X. This is a bit handwavy, but I'm pretty sure it's true, which means in theory any attempt to optimize for anything will, under enough optimization pressure, become dominated by error, whether that's human values or something else. The only interesting question is can we control the error enough, either through better measurement or less optimization pressure, such that we can get enough signal to be happy with the output.

It seems to me that the meaning of the set  of cases drifts significantly from when it is first introduced and the "Implications" section. It further seems to me that clarifying what exactly  is supposed to be resolves the claimed tension between the existence of iterably improvable ontology identifiers and difficulty of learning human concept boundaries.

Initially,  is taken to be a set of cases such that the question  has an objective, unambiguous answer. Cases where the meaning of  are ambiguous are ... (read more)