Leo Gao
@nabla_theta
working on AGI alignment. prev: GPT-Neo, the Pile, LM evals, RL overoptimization, scaling SAEs to GPT-4, interp via circuit sparsity. EleutherAI cofounder.
Joined September 2019
600 Following 16.3K Followers
“we must go faster to beat china [we invent novel algorithmic improvements and immediately accidentally leak them to china via poor opsec, its not clear what kind of move we were trying to do]“
