📚 What is an LLM?

LLM stands for 'Large Language Model'. It's the specific kind of AI behind ChatGPT, Claude, Gemini and the rest. 'Language' because it works on text. 'Model' because it's a neural network that learned patterns. 'Large' because it has billions of parameters — the dials it tunes during training.

The 'large' part matters more than it sounds. When a model gets big enough, and is trained on enough text, it starts to do things nobody explicitly taught it: follow instructions, reason through a problem, write code, translate. These 'emergent' abilities are why a big language model feels different from a small one.

At its core, an LLM is still the next-word predictor. Give it text and it predicts what comes next — but at 'large' scale, that simple trick compounds into something that can hold a conversation, summarise a document, or help you brainstorm.

So when someone says 'LLM', they mean: a big text-prediction model that's been trained on a huge amount of language and is therefore good at producing useful text. The product you chat with — ChatGPT — is an LLM plus a lot of product wrapping around it.