Level 5: AI / LLM systems · L5.1 LLM fundamentals for architects
What an LLM does, mechanically
Explain next-token prediction, tokens and embeddings.
12 min · Pro
What you take away
- A model predicts a probability distribution over the next token, samples one, appends it and repeats — everything else about serving it follows from that loop.
And 3 more inside the class, in Pro.
How the class is laid out
- The problem
- The simple version
- Four consequences worth designing around
- Check your understanding