All of Ben Cottier's Comments + Replies

AI learns betrayal and how to avoid it

I'm excited about this project. I've been thinking along similar lines about inducing a model to learn deception, in the context of inner alignment. It seems really valuable to have concrete (but benign) examples of a problem to poke at and test potential solutions on. So far there seem to be less concrete examples of deception, betrayal and the like to work with in ML compared to say, distributional shift, or negative side effects.

AI learns betrayal and how to avoid it

Previous high level projects have tried to define concepts like "trustworthiness" (or the closely related "truthful") and motivated the AI to follow them. Here we will try the opposite: define "betrayal", and motivate the AIs to avoid it.

Why do you think the betrayal approach is more tractable or useful? It's not clear from the post.

Do mesa-optimizer risk arguments rely on the train-test paradigm?

Thanks. I think I understand, but I'm still confused about the effect on the risk of catastrophe (i.e. not just being pseudo-aligned, but having a catastrophic real-world effect). It may help to clarify that I was mainly thinking of deceptive alignment, not other types of pseudo-alignment. And I'll admit now that I phrased the question stronger than I actually believe, to elicit more response :)

I agree that the probability of pseudo-alignment will be the same, and that an unrecoverable action could occur despite the threat of modification. I'm interested i... (read more)

3Evan Hubinger1yI agree with all of this—online learning doesn't change the probability of pseudo-alignment but might make it harder for a deceptively aligned model to defect. That being said, I don't think that deceptive models defecting later is necessarily a good thing—if your deceptive models start defecting sooner, but in recoverable ways, that's actually good because it gives you a warning shot. And once you have a deceptive model, it's going to try to defect against you at some point, even if it just has to gamble and defect randomly with some probability [] . First, I do think that worst-case guarantees are achievable if we do relaxed adversarial training with transparency tools [] . Second, I actually have done a bunch of probabilistic risk analysis on exactly this sort of situation here [] . Note, however, that the i.i.d. situation imagined in that analysis is extremely hard to realize in practice as there are fundamental distributional shifts [] that are very difficult to overcome—such as the distributional shift from a situation where the model can't defect profitably to a situation where it can.
Deceptive Alignment

In the limit of training on a diverse set of tasks, we expect joint optimization of both the base and mesa- objectives to be unstable. Assuming that the mesa-optimizer converges towards behavior that is optimal from the perspective of the base optimizer, the mesa-optimizer must somehow learn the base objective.

Joint optimization may be unstable, but if the model is not trained to convergence, might it still be jointly optimizing at the end of training? This occurred to me after reading which finds that "Larger models are... (read more)

2Evan Hubinger1yI talk about this a bit here [] , but basically if you train huge models for a short period of time, you're really relying on your inductive biases to find the simplest model that fits the data—and mesa-optimizers, especially deceptive mesa-optimizers, are quite simple, compressed policies.