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
608 Following 16.4K Followers
"it's crazy how there can exist something so incredibly intelligent and yet hobbled by maladaptive post-training", remarked the burnt-out bay area ai researcher,
