working on AGI alignment. prev: GPT-Neo, the Pile, LM evals, RL overoptimization, scaling SAEs to GPT-4, interp via circuit sparsity. EleutherAI cofounder.
New blog post!
Making AI go well will require international coordination. Humanity has risen to the occasion once before: the ozone crisis bears a striking resemblance to AI risk. Understanding the past can help us navigate the future better.