All of SoerenMind's Comments + Replies
Thanks, we did look into the academic norms around this and concluded that including him was likely the standard choice. This choice was especially clear since (if I remember right) there was no further round of approval from the other authors either for the final edits after the relevant point in time.
1(I'm one of the authors but didn't contribute to experiments except for late stage discussion)
I absolutely think that our results are uniquely important for alignment [...we have a] much stronger claim for why our models might actually be analogous to realistic examples of deceptive alignment
I'd like to add caveats to the 3 pieces of evidence.
[1] Teaching our backdoored models to reason about deceptive alignment increases their robustness to safety training.
This is correct but it needs qualification. Currently the only control condition for this claim is h...
3So I'm imagining the agent doing reasoning like:
Misaligned goal --> I should get high reward --> Behavior aligned with reward function
The shortest description of this thought doesn't include "I should get high reward" because that's already implied by having a misaligned goal and planning with it.
In contrast, having only the goal "I should get high reward" may add description length like Johannes said. If so, the misaligned goal could well be equally simple or simpler than the high reward goal.
Interesting point. Though on this view, "Deceptive alignment preserves goals" would still become true once the goal has drifted to some random maximally simple goal for the first time.
To be even more speculative: Goals represented in terms of existing concepts could be simple and therefore stable by default. Pretrained models represent all kinds of high-level states, and weight-regularization doesn't seem to change this in practice. Given this, all kinds of goals could be "simple" as they piggyback on existing representations, requiring little additional description length.
See also: Your posts should be on Arxiv
I do agree we're leaving lots of value on the table and even causing active harm by not writing things up well, at least for Arxiv, for a bunch of reasons including some of the ones listed here.
I see. In that case, what do you think of my suggestion of inverting the LM? By default, it maps human reward functions to behavior. But when you invert it, it maps behavior to reward functions (possibly this is a one-to-many mapping but this ambiguity is a problem you can solve with more diverse behavior data). Then you could use it for IRL (with the some caveats I mentioned).
Which may be necessary since this:
The LM itself is directly mapping human behaviour (as described in the prompt) to human rewards/goals (described in the output of the LM).
...see...
Do I read right that the suggestion is as follows:
- Overall we want to do inverse RL (like in our paper) but we need an invertible model that maps human reward functions to human behavior.
- You use an LM as this model. It needs to take some useful representation of reward functions as input (it could do so if those reward functions are a subset of natural language)
- You observe a human's behavior and invert the LM to infer the reward function that produced the behavior (or the set of compatible reward functions)
- Then you train a new model using this reward f
Great to see this studied systematically - it updated me in some ways.
Given that the study measures how likeable, agreeable, and informative people found each article, regardless of the topic, could it be that the study measures something different from "how effective was this article at convincing the reader to take AI risk seriously"? In fact, it seems like the contest could have been won by an article that isn't about AI risk at all. The top-rated article (Steinhardt's blog series) spends little time explaining AI risk: Mostly just (part of) the last of...
Not sure if any of these qualify but: Military equipment, ingredients for making drugs, ingredients for explosives, refugees and travelers (being transferred between countries), stocks and certificates of ownership (used to be physical), big amounts of cash. Also I bet there was lots of registration of goods in planned economies.
Playing this game made me realize that humans aren't trainged to predict at the token-level. I don't know the token-level vocabulary; and made lots of mistakes by missing spaces and punctuation. Is it possible to convert the token-level prediction in to word-level prediction? This may get you a better picture of human ability.
Relevant: Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations.
They argue that the pre-trained network already learns some non-confused features but doesn't use them. And you just need to fine-tune the last layer to utilize them.
We’ll be able to fine-tune in the test environment so won’t experience OOD at deployment, and while changes will happen, continual fine-tuning will be good enough to stop the model from ever being truly OOD. We think this may apply in settings where we’re using the model for prediction, but it’s unclear whether continual fine-tuning will be able to help models learn and adapt to the rapid OOD shifts that could occur when the models are transferred from offline learning to online interaction at deployment.
Couldn't the model just fail at the start of fine-tu...
This distillation was useful for me, thanks for making it! As feedback, I got stuck at the bullet-point explanation of imitative generalization. There was not enough detail to understand it so I had to read Beth's post first and try connect it to your explanation. For example kind of changes are we considering? To what model? How do you evaluate if an change lets the human make better predictions?
A large amount of math describes the relations between agents at the same level of analysis: this is almost all of game theory. [...] our focus is on "vertical" relations, between composite agents and their parts.
This seems to be what is studied in the fields of organizational economics and to some extent in industrial organization / vertical integration. These fields have a great deal of game theory on vertical relationships, particularly rel...
Some minor feedback points: Just from reading the abstract and intro, this could be read as a non-sequitur: "It limits our ability to mitigate short-term harms from NLP deployments". Also, calling something a "short-term" problem doesn't seem necessary and it may sound like you think the problem is not very important.
Thanks!
On 2): Being overparameterized doesn't mean you fit all your training data. It just means that you could fit it with enough optimization. Perhaps the existence of some Savant people shows that the brain could memorize way more than it does.
On 3): The number of our synaptic weights is stupendous too - about 30000 for every second in our life.
On 4): You can underfit at the evolution level and still overparameterize at the individual level.
Overall you convinced me that underparameterization is less likely though. Especially on your definition of overparameterization, which is relevant for double descent.
Also interesting to see that all of these groups were able to coordinate to the disadvantage of less coordinates groups, but not able to reach peace among themselves.
One explanation might be that the more coordinated groups also have harder coordination problems to solve because their world is bigger and more complicated. Might be the same with AI?
If X is "number of paperclips" and Y is something arbitrary that nobody optimizes, such as the ratio of number of bicycles on the moon to flying horses, optimizing X should be equally likely to increase or decrease Y in expectation. Otherwise "1-Y" would go in the opposite direction which can't be true by symmetry. But if Y is something like "number of happy people", Y will probably decrease because the world is already set up to keep Y up and a misaligned agent could disturb that state.
Thanks for writing this! It always felt like a blind spot to me that we only have Goodhart's law that says "if X is a proxy for Y and you optimize X, the correlation breaks" but we really mean a stronger version: "if you optimize X, Y will actively decrease". Your paper clarifies that what we actually mean is an intermediate version: "if you optimize X, it becomes a harder to optimize Y". My conclusion would be that the intermediate version is true but the strong version false then. Would you say that's an accurate summary?
Costs don't really grow linearly with model size because utilization goes down as you spread a model across many GPUs. I. e. aggregate memory requirements grow superlinearly. Relatedly, model sizes increased <100x while compute increased 300000x on OpenAI's data set. That's been updating my views a bit recently.
People are trying to solve this with things like GPipe, but I don't know yet if there can be an approach that scales to many more TPUs than what they tried (8). Communication would be the next bottleneck.
...(also x-posted from https://arbital.com/p/goodharts_curse/#subpage-8s5)
Another, speculative point: If and were my utility function and my friend's, my intuition is that an agent that optimizes the wrong function would act more robustly. If true, this may support the theory that Goodhart's curse for AI alignment would be to a large extent a problem of defending against adversarial examples by learning robust features similar to human ones. Namely, the robust response may be because me and my friend have learned similar robust, high-level features; we ju
...(x-posted from Arbital ==> Goodhart's curse)
On "Conditions for Goodhart's curse":
It seems like with AI alignment the curse happens mostly when V is defined in terms of some high-level features of the state, which are normally not easily maximized. I.e., V is something like a neural network where is the state.
Now suppose U' is a neural network which outputs the AI's estimate of these features. The AI can then manipulate the state/input to maximize these features. That's just the standard problem of adversarial examples.
So it seems like the con
...
It seems likely that process supervision was used for o1. I'd be curious to what extent it addresses the concerns here, if a supervision model assesses that each reasoning step is correct, relevant, and human-understandable. Even with process supervision, o1 might give a final answer that essentially ignores the process or uses some self-prompting. But process supervision also feels helpful, especially when the supervising model is more human-like, similar to pre-o1 models.