principles.fyi contents

principles.fyi · Topic

LLMs in the Wild

The systems-and-society view of large language models — how they are made, how we prompt them, how we grade them, and how they go wrong.

Contents

01 Three shapes of a model You have met two shapes — the writer and the reader. Here is the whole family, including the one that translates. 02 Talking to it — prompting You do not retrain a model to make it do a new task. You just ask — and how you ask changes everything. 03 What they eat A model is mostly what it read. So what did it read — and who decided what stays in? 04 How we grade them How do you grade something that can talk about anything? Carefully, and on more than one axis. 05 When it goes wrong These models are fluent, confident, and sometimes wrong, biased, or unsafe. Knowing how they fail is part of using them.

✦ AI Written with AI, reviewed by a human. Each topic links its sources.