Glossary

Fine-tuning

Also: fine-tuning · файнтюнинг

Further training of an existing model on your own examples so it handles a narrow task or format better. Unlike RAG, it changes the model itself rather than its context.

Example

Fresh facts from a knowledge base usually go in via RAG; fine-tuning is for a stable style or output format.

Where it shows up

What you need to have an AI agent of your own — Post 6 of 8

Related terms

RAGretrieval-augmented generation LLMlarge language model Prompt engineering LoRALow-Rank Adaptation RLHFreinforcement learning from human feedback

Source

Claude Docs — Glossary