RLHF
Reinforcement learning from human feedback. Training a model by having people rate its answers and rewarding the kinds they prefer. A main reason chatbots feel helpful and conversational.
“RLHF is part of why it answers like an assistant instead of finishing your sentence.”
See also
In the history of AI
Part of the Extended list
RLHF is on the Extended list: builder jargon, industry terms, and newer slang for when you want to go further. It entered common use around 2023.