Glossary
RLHF
Reinforcement learning from human feedback: training a model to prefer outputs that human raters rate highly.
The post-training technique that turned raw language models into usable assistants. Successors use AI feedback and verifiable rewards.
Related terms
AlignmentDistillationFine-tuningGPUParameters
Get the brief in your inbox
One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.
Published daily by AI Briefing. We never share your address.