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
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02
- General Reasoning explains how to train agent swarms with RL and latency pressure — rosstaylor90 · 2026-11-02
- "Coding isn't the bottleneck anymore — usage windows are," says founder Kyle Gawley — kylegawley · 2026-11-02
- Demo passed ≠ production-ready: 5 questions to answer before letting agents run your business — _kellhus · 2026-11-02
- An AI agent passed 100 test chats—still not ready to run the business — djgoel123 · 2026-11-02
- Agent given total creative freedom produces a 1:44 code-drawn animated short film — ivegotnoidea1 · 2026-11-02