When the agent writes the patch, who audits the tests?
In the METR randomized trial published in July 2025, sixteen experienced open-source developers worked on 246 real issues in their own repositories. Half the tasks allowed AI tools, half did not. The AI-allowed tasks took 19% longer. Before the study the same developers expected a 24% speedup, and…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-16 05:24 · DEV Community — AI
When the agent writes the patch, who audits the tests?