How LLMs Actually Work (No Math)
Understand how large language models predict text, why that explains both their fluency and their mistakes. Free, one sitting.
Core competency stack
Learning Path
25 sessions. Open a chapter to see every session, its brief, and the tools you'll use.
Prediction, not retrieval
The single mechanism underneath everything an LLM does — and why "looking it up" is the wrong mental model.
One token at a time
Why output is generated sequentially, and what that explains about speed and cost.
Probability and temperature
Why the same prompt can give different answers, and what the setting actually controls.
What "training" actually produced
The difference between learning patterns and storing facts.
Instructions are just more text
Why the model cannot fundamentally separate your rules from the data it reads.