withlove

What is LLM (large language model)?

Updated May 2026

A large language model is a program trained on huge amounts of text that can hold a conversation, summarize, draft, and reason in natural language.

LLMs are the engines behind ChatGPT, Claude, Gemini, and most modern AI products. They predict the next token (roughly, the next chunk of text) based on everything they've seen before — both during training and in the current conversation.

Modern LLMs can also call external tools, look up information through retrieval, and follow multi-step instructions. They are not databases; they don't always know what they don't know, which is why agents pair LLMs with deterministic tools for anything with real consequences.

Frequently asked questions

What are some examples of LLMs?

Claude (Anthropic), GPT-4 and GPT-5 (OpenAI), Gemini (Google), Llama (Meta), Mistral, and many open-source variants. They differ in size, capabilities, training data, and cost.

Related terms

Your own AI assistant in five minutes

Skip the jargon. withlove gives you a working AI agent at a shareable URL — voice, calendar, prices, leads — without any of the setup.

Try withlove free