ar0cket1
@ar0cket1
not enough information | RL science
가입 May 2025
244 팔로잉 중 1.6K 팬
dont create architectures that become harder to RL (cough cough continuous models that use previous latent states as the first state of the next generated token), create archiectures that are built to be RLed.
더 보기
