Language models

Language models

  • Three parts · about two hours

This module is what happens behind the scenes. Part 1 follows a prompt through the machine. Part 2 explains how a model comes by its abilities and its habits. Part 3 covers what it costs to run and how it fails, and ends with the module’s two reference sections. None of it is needed to use the tools well. Every technical idea is included because it explains a behaviour you have seen or a decision you will make. The whole module is about two hours of reading.

  1. Part 1: How an LLM works

    After it you can: Explain what happens between prompt and response

    35 minutes

  2. Part 2: How models are built

    After it you can: Explain sycophancy, coding strength and capability jumps

    35 minutes

  3. Part 3: Running models

    After it you can: Predict where a model fails and what a workload costs

    40 minutes