LLM fundamentals — Understand the thing everything else sits on

If you only ever do one item on this page, do the first one. Almost every confused conversation I have about AI systems traces back to someone never having watched this.

Track 1 of the AI engineering roadmap by K Laxman — about 6 hours across 1 stage.

The whole pipeline, end to end

You can trace a token from raw internet text all the way to a chat reply, naming every stage.

pretraining · tokenisation · transformers · inference · SFT · RLHF · hallucination · tool use · reasoning models

Build this — Re-implement decoding. Take any provider that returns logprobs and implement greedy, temperature and top-p sampling yourself. Write a README explaining, in your own words, when you'd use each. It is thirty lines of code and it makes §0.5 permanent.

You're done when: You can explain, without notes, why a model hallucinates confidently rather than saying 'I don't know'.

Put to work in: Jarvis — six interchangeable providers behind one loop · CAMSCode — enterprise AI coding assistant

Explore more

GitHub · LinkedIn · Email