How well do agents use test/verification techniques?

danluu.com
September 8, 2026
64 min read
57/100
Summary
We previously noted that, while it's easier than ever to hit a particular quality bar by having coding agents use effective test techniques, software quality seems to be getting worse, indicating that whatever defaults developers are using may not work very well. Here, we test if simple instructions to agents to use particular techniques or libraries improve implementation correctness, as a kind o...
Coverage & discussions
Hacker News · danluu.com
Community discussions
Historical count: 14 · 14 saved in sample · Historical sample
Awaiting analysis