What is an LLM?
An LLM is a large language model, an AI trained on enormous amounts of text that can write, summarise, translate, and reason in language.
LLM stands for Large Language Model. It is the kind of AI behind tools like Claude, ChatGPT, Gemini, and many AI coding assistants. An LLM has been trained on a huge collection of text from books, websites, code, and conversations, which is how it learned the patterns of language and reasoning.
When you send a prompt, the LLM is not looking things up in a database. It is predicting what the most useful response would look like, one piece at a time, based on what it has learned. That is why it can write code, draft an email, and explain a concept all in the same chat. It is also why it can sometimes confidently say things that are wrong, which is called a hallucination.
For coding work, the practical thing to know is that LLMs are tools, not oracles. You stay in charge. You set the task, review the output, and decide what gets shipped. The more context you give the LLM, the better it can help.
Example
Claude, GPT-4, and Gemini are all LLMs. Claude Code uses an LLM in the background to make code changes for you.
Related terms
Want to use LLM in real work?
WeCode workshops are built around AI coding tools. Pick a tier, or browse more glossary entries to get the lay of the land.