News for hackers. Stuff that matters.
Re:Microsoft lays off an ethical AI team as it doubles down ... by spacebanana7 on Tuesday March 14, 2023 @08:50AM (#35150641)
RLHF is Reinforcement Learning from Human Feedback.

It usually refers to fine tuning language models using data labelled by humans.

Hugging face have a good overview in this article: https://huggingface.co/blog/rlhf

There are no comments on this comment yet.