# Attention budget

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: attention limit, limited attention, finite attention

A way of picturing [attention](https://ecosystem.samcarlton.com/attention) as a fixed amount each [token](https://ecosystem.samcarlton.com/token) can spread across everything else in the input. Adding more text does not add more attention; it divides the same amount more thinly. It explains why giving a model less, better material often beats giving it everything.

**For example:** A [founder](https://ecosystem.samcarlton.com/founder) pastes in 40 documents to answer one question about refunds, and the one relevant policy gets only a sliver of the model's [attention](https://ecosystem.samcarlton.com/attention).

## Connects to (7)

- [Attention](https://ecosystem.samcarlton.com/attention): The part of a language model that decides, for each token, how much every other token in the input should shape its meaning.
- [Attention relationship](https://ecosystem.samcarlton.com/attention-relationship): The link between two tokens in the input, measured by how much one shapes the model's reading of the other.
- [Attention degradation](https://ecosystem.samcarlton.com/attention-degradation): The drop in an agent's sharpness as a session gets long.
- [Context window](https://ecosystem.samcarlton.com/context-window): How much text an LLM can take into account at one time.
- [Smart zone](https://ecosystem.samcarlton.com/smart-zone): A name for the early part of a session, when an agent is focused and accurate.
- [Progressive disclosure](https://ecosystem.samcarlton.com/progressive-disclosure): Giving an agent only what it needs right now, with pointers to the rest, instead of loading everything at the start.
- [Primary source](https://ecosystem.samcarlton.com/primary-source): The original material itself, such as the code, a full transcript or the raw data.

Map view: https://ecosystem.samcarlton.com/attention-budget