Sure, but I think that human cognition tends to operate at a level of abstract above the configuration of atoms in a 3D environment. Like "that is a chair" is a useful way to reason about an environment. Whilethat "that is a configuration of pixels that corresponds to a chair when projected at a certain angle in certain lighting conditions" must first be converted to "that is a chair" before anything useful can be done. Text just has a lot of useful preprocessing applied already and is far more compressed

Strong +1, that argument didn't make sense to me. Images are a fucking mess - they're a grid of RGB pixels, of a 3D environment (interpreted through the lens of a camera) from a specific angle. Text is so clean and pretty in comparison, and has much richer meaning, and has a much more natural mapping to concepts we understand

Fwiw, this is not at all obvious to me, and I would weakly bet that larger models are harder to interpret (even beyond there just being more capabilities to study)

I would be very surprised if it had changed for early employees. I considered the donation matching part of my compensation package (it 2.5x the amount of equity, since it was a 3:1 match on half my equity), and it would be pretty norm violating to retroactively reduce compensation

I gather that they changed the donation matching program for future employees, but the 3:1 match still holds for prior employees, including all early employees (this change happened after I left, when Anthropic was maybe 50 people?)

I'm sad about the change, but I think that any goodwill due to believing the founders have pledged much of their equity to charity is reasonable and not invalidated by the change

That's technically even more conditional as the intervention (subtract the parallel component) also depends on the residual stream. But yes. I think it's reasonable to lump these together though, orthogonalisation also should be fairly non destructive unless the direction was present, while steering likely always has side effects

Note that this is conditional SAE steering - if the latent doesn't fire it's a no-op. So it's not that surprising that it's less damaging, a prompt is there on every input! It depends a lot on the performance of the encoder as a classifier though

When do you use escape?

It seems unlikely that openai is truly following the test the model plan? They keep eg putting new experimental versions onto lmsys, presumably mostly due to different post training, and it seems pretty expensive to be doing all the DC evals again on each new version (and I think it's pretty reasonable to assume that a bit of further post training hasn't made things much more dangerous)