Rubi Hudson

Wiki Contributions


I don't find goal misgeneralization vs schemers to be as much as a dichotomy as this comment is making it out to be. While they may be largely distinct for the first period of training, the current rollout method for state of the art seems to be "give a model situational awareness and deploy it to the real world, use this to identify alignment failures, retrain the model, repeat steps 2 and 3". If you consider this all part of the training process (and I think that's a fair characterization),  model that starts with goal misgeneralization quickly becomes a schemer too.

I think this part uses an unfair comparison:

Supposes that  and  are small finite sets. A task  can be implemented as dictionary whose keys lie in  and whose values lie in , which uses  bits. The functional  can be implemented as a program which receives input of type  and returns output of type . Easy!

In the subjective account, by contrast, the task  requires infinite bits to specify, and the functional  must somehow accept a representation of an arbitrary function . Oh no! This is especially troubling for embedded agency, where the agent's decision theory must run on a physical substrate.

If X and W+ are small finite sets, then any behavior can be described with a utility function requiring only a finite number of bits to specify. You only need to use R as the domain when W+ is infinite, such as when outcomes are continuous, in which case the dictionaries require infinite bits to specify too.

I think this is representative of an unease I have with the framing of this sequence. It seems to be saying that the more general formulation allows for agents that behave in ways that utility maximizers cannot, but most of these behaviors exist for maximizers of certain utility functions. I'm still waiting for the punchline of what AI safety relevant aspect requires higher order game theory rather than just maximizing agents, particularly if you allow for informational constraints.

I think, from an alignment perspective, having a human choose their action while being aware of the distribution over outcomes it induces is much safer than having it effectively chosen for them by their specification of a utility function. This is especially true because probability distributions are large objects. A human choosing between them isn't pushing in any particular direction that can make it likely to overlook negative outcomes, while choosing based on the utility function they specify leads to exactly that. This is all modulo ELK, of course.

I'm not sure I understand the variant you proposed. How is that different than the Othman and Sandholm MAX rule?

Thanks for the comment. I agree that, ideally, we would find a way not to have two wholly separate models and instead somehow train a model against itself. I think a potential issue with your proposal is that small perturbations could have discontinuous effects, the anticipation of which distorts predictions. However, it would be interesting to think about further to see if there's some way to avoid that issue.

Thanks Caspar, your comments here and on earlier drafts are appreciated. We'll expand more on the positioning within the related literature as we develop this into a paper.

As for your work on Decision Scoring Rules and the proposal in your comment, the biggest distinction is that this post's proposal does not require specifying the decision maker's utility function in order to reward one of the predictors and shape their behavior into maximizing it. That seems very useful to me, as if we were able to properly specify the desired utility function, we could skip using predictive models and just train an AI to maximize that instead (modulo inner alignment). 

For the first point, I agree that the SGD pushes towards closing any gaps. My concern is that at the moment, we don't know how small the gaps need to be to get the desired behavior (and this is what we are working on modelling now). On top of that, depending on how the models are initialized, the starting gap may be quite large, so the dynamics of how gaps close throughout the training process seems important to study further.

For the second point, I think we are also in agreement. If the training process leads the AI to learning "If I predict that this action will destroy the world, the humans won't choose it", which then leads to dishonest predictions. However, I also find the training process converging to a mesa-optimizer for the training objective (or something sufficiently close) to be somewhat more plausible.

It sounds like you have a number of ideas as to why robustness was not achieved and how to correct those issues. Why is the project over now, rather than continuing having made those updates?