All of shash42's Comments + Replies

Great post! Lays out a clear agenda and I agree in most part, including about timeliness of the scientific case due to the second argument. But I'll nitpick on the first argument:

Models finally understand deceptive alignment. Claude and GPT4 give (for the most part) clear explanations of the deceptive alignment, why it’s a risk, why it’s a useful strategy, etc. Previous generations of models mostly did not (e.g., the GPT-3 or 3.5 generation).

Giving clear explanations via simulation (of say, Alignment Forum text in the training data) is likely not the same ... (read more)

3Ethan Perez6mo
Generating clear explanations via simulation is definitely not the same as being able to execute it, I agree. I think it's only a weak indicator / weakly suggestive evidence that now is a good time to start looking for these phenomena. I think being able to generate explanations of deceptive alignment is most likely a pre-requisite to deceptive alignment, since there's emerging evidence that models can transfer from descriptions of behaviors to actually executing on those behaviors (e.g., upcoming work from Owain Evans and collaborators, and this paper on out of context meta learning). In general, we want to start looking for evidence of deceptive alignment before it's actually a problem, and "whether or not the model can explain deceptive alignment" seems like a half-reasonable bright line we could use to estimate when it's time to start looking for it, in lieu of other evidence (though deceptive alignment could also certainly happen before then too).   (Separately, I would be pretty surprised if deceptive alignment descriptions didn't occur in the GPT3.5 training corpus, e.g., since arXiv is often included as a dataset in pretraining papers, and e.g., the original deceptive alignment paper was on arXiv.)

It seems like this argument assumes that the model optimizes on the entire 'training process'. Why can't we test (perform inference) using the model on distributions different from the training distribution where SGD can no longer optimize to check if the model was deceptive aligned on the training environment? 

2Evan Hubinger7mo
Because the model can defect only on distributions that we can't generate from, as the problem of generating from a distribution can be harder than the problem of detecting samples from that distribution (in the same way that verifying the answer to a problem in NP can be easier than generating it). See for example Paul Christiano's RSA-2048 example (explained in more detail here).