Skip to content
Bae
Glossary

LLM (large language model) — definition and meaning

A large language model (LLM) is an AI system trained on vast amounts of text to predict and generate human-like language. LLMs power AI companions, chatbots, and assistants like ChatGPT, Claude, and Gemini.

Last reviewed 2026-05-25

A large language model is a neural network trained on enormous text corpora to predict the next token in a sequence — which, at scale, produces fluent conversation, reasoning, and writing. LLMs (GPT, Claude, Gemini, Llama) are the engine under every modern AI companion. Crucially, the model itself has no memory between conversations; persistent memory is a separate system built on top. Understanding that distinction explains why two AI girlfriends using the same underlying model can feel completely different — the difference is the engineering around the model, not the model.

Common questions

About llm (large language model).

What is llm (large language model)?

A large language model (LLM) is an AI system trained on vast amounts of text to predict and generate human-like language. LLMs power AI companions, chatbots, and assistants like ChatGPT, Claude, and Gemini.

How is "llm (large language model)" used in AI companion apps?

A large language model is a neural network trained on enormous text corpora to predict the next token in a sequence — which, at scale, produces fluent conversation, reasoning, and writing. LLMs (GPT, Claude, Gemini, Llama) are the engine under every modern AI companion. Crucially, the model itself has no memory between conversations; persistent memory is a separate system built on top. Understanding that distinction explains why two AI girlfriends using the same underlying model can feel completely different — the difference is the engineering around the model, not the model.

What other terms relate to llm (large language model)?

Related terms in the AI companion space include: Context window, Long-term memory (in AI companions), AI companion, Hallucination (AI). Each has its own glossary entry on /glossary.