large language model
A neural network trained on huge amounts of text that generates text by predicting one token at a time from everything before it.
In more detail
LLM stands for large language model. It reads a prompt as tokens, scores every possible next token, picks one, and repeats until it stops, so its output varies and can be fluent but wrong. Applications reach one through a provider's API or run an open-weight model locally, and wrap it in prompts, retrieval, tools and evals.
Related terms
- LLM token — The unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence from the tokenizer's vocabulary.
- context window — The maximum number of tokens a model can take into account at once, covering the prompt and the reply together.
- neural network — A model built from layers of simple numeric units whose connection weights are learned from data.
- artificial intelligence — Computer systems that perform tasks normally needing human intelligence, such as understanding language, recognising images or making predictions.
- streaming — Sending a response in pieces as they become available instead of building the whole thing first.
Taught in
- Agent SDKs And Human Approval — AI Engineering: LLM Apps, RAG & Agents
- Threat-Model An LLM App — AI Engineering: LLM Apps, RAG & Agents
- Excessive Agency — AI Engineering: LLM Apps, RAG & Agents
- Working With AI Coding Assistants — AI Engineering: LLM Apps, RAG & Agents
- The Fetch API: Streaming Responses, HTTP Caching And Keepalive — Frontend Architecture & Web Platform
- Vulnerabilities And Attack Surfaces — CompTIA Security+ (SY0-801) Exam Prep
- AI Threats: Prompts, Tools And Leaks — CompTIA Security+ (SY0-801) Exam Prep