AI glossary / How it works

RLHF

How it works

Reinforcement learning from human feedback. People rate the AI's answers and it learns to give the kind people prefer.

More words in How it works

• Self-supervised learningLearning from raw data without human labels, for example by hiding a word in a sentence and trying to guess it. This is how language models learn.
• SubagentA helper agent that a main agent hands part of a job to. It works on its piece and reports back.
• Supervised learningTraining with examples that come with the right answers attached, such as photos already labelled cat or dog.
• Synthetic dataArtificially generated data used for training when real data is scarce, expensive or private.
• Test-time computeLetting a model think for longer on a hard question to get a better answer, at the cost of speed and money.