How well do agents use test and verification techniques?

·Dan Luu··

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 effective agents are when guided by someone with no expertise in testing who's may...

Read full article →

Related Articles

Should I run plain Docker Compose in production in 2026?
pmig · Hacker News · 4mo ago
Computer Use is 45x more expensive than structured APIs
palashawas · Hacker News · 4mo ago
Bun is being ported from Zig to Rust
SergeAx · Hacker News · 4mo ago
Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem
ozkatz · Hacker News · 4mo ago
RaTeX: KaTeX-compatible LaTeX rendering engine in pure Rust
atilimcetin · Hacker News · 4mo ago