Stage 2beginner26 min
Understanding LLMs
Open the box. Tokens, transformers, context windows, temperature and why a model that sounds certain can still be wrong.
Start with What is a large language model?Lessons
- What is a large language model?One sentence explains the whole thing — and almost every behaviour you have noticed follows from it.7 min
- Tokens — what a model actually readsModels do not see words or letters. Understanding what they do see explains several behaviours that otherwise look like bugs.6 min
- Context windows — what the model can seeA model has no memory between messages. Everything it knows in a conversation is in front of it, and that space has a hard edge.6 min
- Why models hallucinateConfident, fluent, wrong. Not a bug to be patched but a direct consequence of what these systems do.7 min