Those would indeed be good. In the 2y since I made that comment I’ve worked on and made progress on one ambitious interp direction, self-supervised internal steering. The idea is to “amplify” honesty or corrigibility without labels or relying on outputs. It might even target deeper concepts, though so far it appears to intervene more at the behaviour level.
My feeling is that interp is held back because researchers aren’t insisting on hard and meaningful metrics and evals, for example doing the things you described, and also out of distribution, without labels. This is very hard, but so is the actual alignment challenge.
Those would indeed be good. In the 2y since I made that comment I’ve worked on and made progress on one ambitious interp direction, self-supervised internal steering. The idea is to “amplify” honesty or corrigibility without labels or relying on outputs. It might even target deeper concepts, though so far it appears to intervene more at the behaviour level.
My feeling is that interp is held back because researchers aren’t insisting on hard and meaningful metrics and evals, for example doing the things you described, and also out of distribution, without labels. This is very hard, but so is the actual alignment challenge.