Do you have any arguments for why this would be more important rather than working on evals of deceptive AI or evals of cybersecurity capabilities? Asking in general, I’m trying to figure out how one should think about prioritizing things like that.
Do you have any arguments for why this would be more important rather than working on evals of deceptive AI or evals of cybersecurity capabilities? Asking in general, I’m trying to figure out how one should think about prioritizing things like that.