rlhf = reinforcement learning from human feedback
(had to look it up)
I think it's more RLVR (reinforcement learning from verified rewards). The RLHF is just to align models to human preferences, meaning to behave nice.
alt Hacker News
I think it's more RLVR (reinforcement learning from verified rewards). The RLHF is just to align models to human preferences, meaning to behave nice.