logoalt Hacker News

thunfischtoast • today at 6:30 AM • 1 reply • view on HN

If you tell a model to find flaws, it will find flaws. What qualifies as critical to you?


Replies

nikolay • today at 9:31 AM

I am talking about functional flaws, not cosmetic ones. For example, in web apps, where a11y is mandated, Claude Code kept violating accessibility (regardless of the installed skills), and even the lackluster GitHub Copilot with some outdated models always finds serious violations. Codex constantly finds race conditions and other timing flaws for distributed services written by Claude Code. But I have to admit that Codex sucks at web design compared to Claude Code!