Guides

How Large Language Models Work: A Plain-Language Guide

What an LLM actually does when it answers a question, why it sometimes gets things wrong, and which tasks it is well suited to.

Format: Guide · Beginner
Level: Beginner
Length: 10 min read
Updated: Sep 2026
Topics: how large language models work, what is an LLM, LLM inference

Read the full guide Back to hub

The short version

A large language model (LLM) is a program trained to predict the next piece of text given the text before it. By repeating that prediction many times, it can write answers, summaries, code and translations. Everything else, from chat assistants to AI agents, is built on top of this one capability.

Read the full guideGuide · Beginner · 10 min read

Start reading

Related resources

All of the AI Resource Hub

Guides

How Large Language Models Work: A Plain-Language Guide

The short version

Related resources

Tokens and Context Windows: What They Mean for Cost, Speed and Quality

Embeddings and Vector Search Explained

Retrieval-Augmented Generation (RAG): A Practical Guide