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
608 正在关注 16.4K 粉丝
just as capabilities is spiky, alignment is also likely to be spiky. models will probably be very well aligned in some domains and extremely misaligned in other domains at the same time
