Infra-Bayesian haggling 2024-05-20T12:23:30.165Z

Comment by hannagabor (hanna-gabor) on Frontier Models are Capable of In-context Scheming · 2024-12-09T15:35:30.500Z · LW · GW

I was wondering how the models perform on the multiplication test by default. If they were performing better when incentivized to do well than they were by default, that might mean they are not using their full capabilities by default.

Comment by hannagabor (hanna-gabor) on Qualities that alignment mentors value in junior researchers · 2024-02-29T19:54:14.905Z · LW · GW

If I read 1-2 papers in a day in detail, I wouldn't do much else. I guess people get better at this to some extent. I'm wondering if this is something I just need to carry on doing and eventually I'll get better at it or there are some other ways to make this process more efficient.