← Back to context Comment by froh 2 days ago rlhf = reinforcement learning from human feedback(had to look it up) 3 comments froh Reply visarga 1 day ago 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. versteegen 18 hours ago More accurate to say RLHF aligns models to human preferences, most significantly to be helpful. redanddead 1 day ago What makes you say that
visarga 1 day ago 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. versteegen 18 hours ago More accurate to say RLHF aligns models to human preferences, most significantly to be helpful. redanddead 1 day ago What makes you say that
versteegen 18 hours ago More accurate to say RLHF aligns models to human preferences, most significantly to be helpful.
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.
More accurate to say RLHF aligns models to human preferences, most significantly to be helpful.
What makes you say that