← Back to context

Comment by HarHarVeryFunny

1 day ago

If it's so great at software engineering and bug fixing, then why does Claude Code still have 5000+ open bugs?

https://github.com/anthropics/claude-code/issues?q=is%3Aissu...

Apparently whatever SWE-bench is measuring isn't very relevant.

as much as I hate cc, 95% of the issues there are either AI psychosis or user error

Probably because a human still has to review every change and they don't have time

  • So if all the AI code is being reviewed by humans (not sure this is true, but let's assume it is), then why are there 5000+ bugs? Are you blaming the Anthropic developers rather than the AI?