Advertised context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → size and usable context are different. Top models' effective long-context accuracy is improving faster than window size, so engineers can revisit retrieval and chunkingSplitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.Full definition → assumptions for long inputs.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
chunking — Splitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.
