HarnessTax: How Much Does the Harness Matter for Coding Agents?
matt_d · hn · 2026-09-17
HarnessTax, a project featured on Hacker News, systematically quantifies how much a coding agent's harness — the scaffolding, tool interfaces, and orchestration around the model — affects benchmark performance versus raw model capability. A useful reference for anyone doing agent evals or attributing gains between model upgrades and harness engineering.
More from coding & agent
- Muse AI agent finds, calls and books a dentist in under 10 minutes, for free — ChrisUniverse · 2026-09-18
- Cursor Projects wins praise: kanban tracking, multi-model agents and 3-way bakeoffs — kieranklaassen · 2026-09-18
- OpenAI's Astra Struggles With Long-Term Architecture: Duplication, Overengineering, Bad Assumptions Linger — Substantial_Swan_144 · 2026-09-18
- Hang Ten Systems raises $53M more in seed funding, totaling $85M — vsikka · 2026-09-18
- Does AI coding actually become multiplayer? Shared Slack agents vs. supercharged solo devs — Telos_in_the_Void · 2026-09-18
- Skillry launches curated Agent Skills library to give Claude Code & Codex taste — yihui_indie · 2026-09-18