Skip to content

Volume 8 — Large Language Models

What they are and what they are not

Tokenisation, pretraining, fine-tuning, alignment, inference, context windows, prompting and evaluation — plus an honest treatment of failure modes.

Outlined, not yet written

This volume is fully outlined but the lessons are not yet authored. The chapter list below is the plan of record, not a promise that content exists.

What you will be able to do

  • Explain what a token is and why it drives cost and behaviour
  • Design a prompt that is testable rather than lucky
  • Build an evaluation harness for a non-deterministic system
  • Reason about when an LLM is the wrong tool

Chapters

  1. Tokenisation
  2. Pretraining and the objective
  3. Fine-tuning and instruction tuning
  4. RLHF and alignment
  5. Inference, sampling and temperature
  6. Context windows and attention cost
  7. Prompt engineering as an engineering discipline
  8. Structured output and tool use
  9. Evaluating LLM systems
  10. Hallucination, and what actually reduces it
  11. Cost and latency engineering

All volumes