Glossary
Reward model
A learned judge that scores an answer the way people would, trained on human preference rankings. It stands in for a human rater so the AI can be improved automatically — but it's only an imperfect copy of real human taste.
Related terms
See it in action
Don't just read the definition — play with it
Every term shows up in a lesson where you can poke at it live — free, right in the app.