Leo Gao(@nabla_theta):the capacity to pause is very convergently useful. even making an aligned AI that is superhuman at alignment research is not a sufficient win condition. it may successfully create a smarter AI, and then need a long time to align that AI, but race dynamics force yoloing sth half baked.

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.

参加 September 2019

608 フォロー中 16.4K ファン

Leo Gao@nabla_theta

2026.09.25 06:26

the capacity to pause is very convergently useful. even making an aligned AI that is superhuman at alignment research is not a sufficient win condition. it may successfully create a smarter AI, and then need a long time to align that AI, but race dynamics force yoloing sth half baked.