Glossary
LLM (large language model)
An LLM (large language model) is the engine behind tools like ChatGPT: a program trained on enormous amounts of text to predict what words come next, which lets it write, summarize, translate, and answer questions.
An LLM learned language the way nobody learns language: by reading more text than a human could in a thousand lifetimes and getting very, very good at guessing the next word. That sounds too simple to be useful, but guess the next word well enough and you can draft emails, explain contracts, and translate menus.
Picture a nonna who has read every cookbook ever printed. Ask her for a Tuesday dinner and she’ll improvise something sensible, even if no book contains that exact recipe. That’s an LLM: not a database of stored answers, but a pattern machine that composes new text from everything it absorbed as training data.
The catch: a confident guesser is sometimes confidently wrong. That’s a hallucination, and it’s why you always check facts that matter.
Where you’ll meet this
You rarely meet an LLM directly; you meet products built on one. ChatGPT runs on OpenAI’s GPT models, Claude on Anthropic’s models, Gemini on Google’s. You’ll spot model names in each app’s model picker menu. Choosing between them is what our AI chooser is for.