1. Data
Where training data comes from.
LLMs Explained
The life cycle of a large language model, from raw text data to advanced coding agents.
The journey
Section titled “The journey”2. Tokenization
How text is converted to numbers.
3. Training
Chunking and next-token prediction.
4. Inference and the API
Requests and responses.
5. Tools and Harnesses
How a model is made to act reliably.
6. Agents
Coding agents and applications.