I think it’s true that CFAR mostly moved away from teaching things like explicit probabilistic forecasting, and toward something else, although I would describe that something else differently—more like, skills relevant for hypothesis generation, noticing confusion, communicating subtle intuitions, updating on evidence about crucial considerations, and in general (for lack of a better way to describe this) “not going insane when thinking about x-risk.”
I favor this shift, on the whole, because my guess is that skills of the former type are less important bottlenecks for the problems CFAR is trying to help solve. That is, all else equal, if I could press a button to either make alignment researchers and the people who surround them much better calibrated, or much better at any of those latter skills, I’d currently press the latter button.
But I do think it’s plausible CFAR should move somewhat backward on this axis, at the margin. Some skills from the former category would be pretty easy to teach, I think, and in general I have some kelly betting-ish inclination to diversify the goals of our curricular portfolio, in case our core assumptions are wrong.
To be clear, this is not to say that those skills are bad, or even that they’re not an important part of rationality. More than half of the CFAR staff (at least 5 of the 7 current core staff, not counting myself, as a contractor) have personally trained their calibration, for instance.
In general, just because something isn’t in the CFAR workshop doesn’t mean that it isn’t an important part of rationality. The workshop is only 4 days, and not everything is well-taught in a workshop context (as opposed to [x] minutes of practice every day, for a year, or something like an undergraduate degree).
I think it’s true that CFAR mostly moved away from teaching things like explicit probabilistic forecasting, and toward something else, although I would describe that something else differently—more like, skills relevant for hypothesis generation, noticing confusion, communicating subtle intuitions, updating on evidence about crucial considerations, and in general (for lack of a better way to describe this) “not going insane when thinking about x-risk.”
I favor this shift, on the whole, because my guess is that skills of the former type are less important bottlenecks for the problems CFAR is trying to help solve. That is, all else equal, if I could press a button to either make alignment researchers and the people who surround them much better calibrated, or much better at any of those latter skills, I’d currently press the latter button.
But I do think it’s plausible CFAR should move somewhat backward on this axis, at the margin. Some skills from the former category would be pretty easy to teach, I think, and in general I have some kelly betting-ish inclination to diversify the goals of our curricular portfolio, in case our core assumptions are wrong.
To be clear, this is not to say that those skills are bad, or even that they’re not an important part of rationality. More than half of the CFAR staff (at least 5 of the 7 current core staff, not counting myself, as a contractor) have personally trained their calibration, for instance.
In general, just because something isn’t in the CFAR workshop doesn’t mean that it isn’t an important part of rationality. The workshop is only 4 days, and not everything is well-taught in a workshop context (as opposed to [x] minutes of practice every day, for a year, or something like an undergraduate degree).