AI glossary / How it works
Post-training
Everything done to a model after its main training to make it helpful and safe, including instruction tuning and RLHF.
More words in How it works
- Pre-trainingThe first and most expensive stage of building a model, where it reads enormous amounts of text to learn how language and the world work.
- QuantizationShrinking a model by storing its numbers less precisely, so it runs on smaller devices with a small loss in quality.
- Reasoning modelA model built to think through a problem step by step before it answers. Slower, but stronger on maths, logic and planning.
- Reinforcement learningTraining by trial and error, where the AI is rewarded for good results.
- RLHFReinforcement learning from human feedback. People rate the AI's answers and it learns to give the kind people prefer.