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
599 Following 16.3K Followers
one of the tragedies of the human condition is that desire is not a very good gradient estimator for joy
