zeni

Probably shouldn't have ex-lab people embedded in the lab they just left. But it seems overwhelmingly positive to have ex-lab people working on evaluations and threat research in general (the fact that one left the lab in the first place is an indicator that they're not totally value-captured)

You can prevent absolute scale from blowing up but I don't think this fixes the non-normal distributional statistics within channels.

If you catch a hack after the fact, how would you administer "severe punishment" without, I guess, trying to do some big off-policy update?