Open-source course says the harness, not the model, can push a coding agent into the top 5
strickvl · x · 2026-07-23
A new open-source course, Building a Coding Agent From Scratch, focuses on one key lesson: the harness matters as much as the model.
- It cites LangChain’s Terminal-Bench experiment, where changing only the harness moved the same model from around 30th place to the top 5.
- The course teaches you to build a full coding agent in Python, starting from a bare agent loop.
- The project, called Decode, gradually expands into a swarm of remote agents running in parallel in the cloud.
More from coding & agent
- Dev builds interactive 3D product experience with GPT-6 Astra + Hyper3D Rodin — nikola_mr64990 · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11