What is Large language model (LLM)?

A large language model is an AI system trained on huge amounts of text to predict and generate language — the engine behind tools like ChatGPT, Claude and Gemini.

An LLM learns the patterns of language by training on vast quantities of text, then generates responses one token at a time by predicting what should come next. That single ability — very good next-word prediction at scale — is enough to draft, summarise, translate, answer questions and write code, which is why one model can handle so many different tasks.

Because it works by prediction rather than recall, an LLM is only as good as the prompt that steers it, and it can be confidently wrong (see AI hallucination). Different models — Claude, ChatGPT, Gemini — have different strengths, costs and terms, which is why matching the model to the task matters as much as the prompt itself.