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.
加入 September 2019
600 正在關注 16.3K 粉絲
one of the tragedies of the human condition is that desire is not a very good gradient estimator for joy
