Fancy harnesses make coding agents more expensive but not better, study finds
The Decoderen

A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step. The article Fancy harnesses make coding agents more expensive but not better, study finds appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- Anthropic
- Verktyg
- Forskning
- Agenter
Related AI news
- Honasa Consumer elevates Vipul Maheshwari to chief product & technology officerEconomic Times Tech · October 24, 2026
- Anthropic lässt KI-Agenten Verhandlungsregeln für Menschen lernenheise online – KI · October 24, 2026
- 非科學家團隊靠 Claude 設計抗蠍毒蛋白質,64 小時完成、實驗驗證成功TechNews (TW) · October 24, 2026
- The Tender247 Story: Turning tender intelligence into a competitive advantage with Anupam KherEconomic Times Tech · October 24, 2026
- A look at OpenAI's Project Daybreak, which lets vetted partners use its top hacking models to find and fix vulnerabilities and helped uncover PHP2Shell RCE bugs (Thomas Brewster/Forbes)Techmeme · October 24, 2026
- OpenAI resumes frontier AI training after security overhaul, discloses flaw in widely used softwareEconomic Times Tech · October 24, 2026