# Why Longer Context Is Not Always Better — Prompt & Context Engineering

Source: https://www.skillbyai.com/en/prompt-context-engineering/b-long

> More tokens cost money and time and can bury the answer.

## Relevance beats volume

Filling a large window with everything that might help has costs: **price** scales with input tokens, **latency** grows (the model must process all of it before answering), and **quality** can drop because relevant facts are surrounded by distractors. Research and practice have found that models can use information near the start and end of a long input more reliably than information buried in the middle, though newer models vary, so test your own. The practical rule: send the **smallest set of highly relevant content** that answers the question, and measure whether adding more actually helps.

## A briefing pack, not a warehouse

Handing someone a 300-page binder for a one-line question makes them slower and more likely to miss the one page that matters.

## Plot quality against k

Run your evaluation with 2, 5, 10 and 20 retrieved chunks; stop at the point where quality stops rising.

**Quiz:** Why can a much longer context hurt answers?

- [ ] Models refuse long inputs always
- [x] Relevant facts get buried among distractors, and cost and latency rise
- [ ] Long inputs change the model weights
- [ ] Tokens become free

*Answer:* Relevant facts get buried among distractors, and cost and latency rise. Send the smallest highly relevant set.