Rohan Paul on Harness-of-Harness for Coding Agents

Bengaluru machine learning engineer Rohan Paul posted on X that Harness-of-Harness outperformed repeated coding-agent runs. The approach carried code, QA evidence, and plans forward across steps. Paul said long-horizon coding needs persistent project state, independent testing, and replanning from actual failures. He noted the problem that agents can forge ahead without continuity over extended projects. The post included a screenshot of an arXiv paper.