Posts

AISafety.world is a map of the AIS ecosystem 2023-04-06T18:37:15.360Z

Comments

Comment by Hamish Doodles (hamish-doodles) on Against Almost Every Theory of Impact of Interpretability · 2023-08-23T15:35:59.547Z · LW · GW

The proportion of junior researchers doing interp rather than other technical work is too high

 

I think that's because it's almost the only thing that junior researchers can productively work on.

Even if mech interp isn't in itself useful I'd guess it's pretty useful as a souce of endless puzzles to help people skill up in doing technical ML work.