LLM Basics
The robot doesn’t think. It predicts. Very confidently.
▶ the lesson · ~35s · narrated · tap for sound
the intro
Large language models generate text one piece at a time, predicting what comes next from everything before it. Understanding tokens, the context window, and why temperature changes the output explains almost every weird behavior you will meet.
fun fact ✦
LLMs predict the next token from probabilities — which is why they can be both brilliant and confidently wrong.
the docs
quick hits about LLM Basics
15-second answers · interviews, tips, trivia & hidden gems
🎤 interview
What is a token?
🎤 interview
What does temperature do?
🎤 interview
Is an LLM a search engine?
📚 tutorial
What is a context window?
🧠 trivia
Where did LLMs come from?
💎 deep
Is temperature 0 deterministic?