What Are Large Language Models?
Every modern AI chatbot — from coding assistants to AI girlfriend apps — runs on a large language model. This is a plain-English explanation of what they are and why they changed conversational AI.
The one-sentence version
A large language model (LLM) is a neural network trained on enormous amounts of text to do one thing: predict the next token in a sequence. Everything else — conversation, writing, summarising, reasoning — emerges from doing that prediction extremely well.
Tokens
Models don't read whole words; they read tokens — chunks roughly the size of a word or part of a word. When you send a message, it's split into tokens, the model predicts the next token, then the next, building the reply one piece at a time. Pricing and limits are measured in tokens.
The context window
The context window is how much text the model can consider at once. A bigger window means an AI companion can "remember" more of the current conversation directly. But the window is finite — which is exactly why companion apps add an external memory store to keep continuity beyond a single session.
The system prompt
Before your messages, apps prepend a hidden system prompt that defines behaviour and persona. In an AI companion, this is where the character's personality, tone and boundaries live. Two apps on the same base model feel different mostly because of their system prompts.
Why this matters for companions
An LLM alone is a brilliant improviser with no long-term memory. Turn it into a companion by adding three things: a persona (system prompt), a memory store, and optionally media generation. That's the whole recipe — see our Node.js tutorial for the starting point, and how girlfriend apps work for the full stack.
Frequently asked questions
What is a large language model?
A neural network trained to predict the next token in text — which lets it converse, write and reason.
What is a token?
A chunk of text, roughly a word or part of one. Models read and write one token at a time.
What is a context window?
How much text the model can consider at once — bigger windows mean more direct "memory" of the conversation.
Continue: How AI Girlfriend Apps Work → · Back to the AI Companions Guide