---
title: "What a large language model does"
description: "What a large language model actually is: a next-token predictor trained on internet-scale text, whose apparent intelligence is the byproduct of getting ext"
canonical_url: "https://fanout.sh/ai-engineering/lessons/llm-intro"
md_url: "https://fanout.sh/ai-engineering/lessons/llm-intro.md"
access: "public"
---

# What a large language model does

What a large language model actually is: a next-token predictor trained on internet-scale text, whose apparent intelligence is the byproduct of getting ext

## Public overview

What a large language model actually is: a next-token predictor trained on internet-scale text, whose apparent intelligence is the byproduct of getting extremely good at that one game. Parameters, tokens, and context windows defined precisely enough to reason about cost and capability.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md