Nexus Learn

Log in · Create free account

Module 1: How AI language models work · 8 min

What is a large language model?

A large language model (LLM) is a computer program trained on a huge amount of text. ChatGPT, Claude and Gemini are all LLMs. During training the model reads billions of sentences and learns patterns: which words usually follow which other words.

When you ask a question, the model does not look up a stored answer. It builds a reply one small piece at a time, each time choosing a likely next piece based on everything written so far.

  • It is very good at language: writing, summarising, translating, explaining.
  • It can sound confident even when it is wrong.
  • It does not have feelings, and it does not know today's news unless a tool gives it that.
  • Your prompt is the only thing that tells it what you want.

This is why prompting matters. A model cannot read your mind. A vague prompt gives a vague answer, and a clear prompt gives a clear one.

(free account needed to save progress)

 |  Tokens and the context window →