The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
Guide › Glossary › RLHF

RLHF · Reinforcement Learning from Human Feedback

Tuning a model using human preference rankings to make its outputs more helpful and aligned.

Current numbers

560 GBWeights alone: four equal 70B PPO-RLHF models at two bytes/weight; placement and runtime excludedas of 2026-09 · register ↗

← All terms