How well do agents use test/verification techniques?
What happened
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 of test to see how…
Summary assembled by rule from the sources below
Why it's spreading
Timeline
- First appeared on LobstersLobsters
- Discussion started on Hacker NewsHacker News