rigami.
Glossary
/// Definition

LLM (Large Language Model)

An LLM is a neural network trained on large text corpora to predict tokens and generate coherent language.

In depth

Large language models like GPT-5, Claude Sonnet 4.5 and Gemini 3 are transformer-based models trained on massive text corpora. In production they are wrapped with retrieval, tool-calling, structured outputs, evals and cost controls to build reliable product features.

Related terms