Glossary / LLM
What is an LLM?
large language model
An LLM (large language model) is an AI model trained on very large amounts of text so it can understand and write language, including code. Claude, GPT and Gemini are LLMs.
An LLM works by predicting what text should come next, given everything it has read so far. Trained on enough writing, that simple idea produces a model that can answer questions, summarise documents, translate and write programs.
On its own an LLM only produces text. Tools built around it give it more abilities: running code, searching the web, reading files, or calling other services. That is how a language model becomes the engine of an assistant or an agent.
LLMs can be confidently wrong, and they only know what they were trained on plus what you give them in the conversation. Giving clear context and checking important answers are part of using them well.
Questions
Is ChatGPT an LLM?
ChatGPT is an app built on top of LLMs made by OpenAI. The model does the language work; the app adds the chat window, memory and tools.
Can I add an LLM to my own app?
Yes. Providers such as Anthropic and OpenAI offer APIs. Your app sends text to the API with a secret key kept on the server, and gets the model's reply back.