Thread

1. esafak · 1789595614 · focus · HN ↗

   That&#x27;s the kind of transparency we need! That DeepSWE benchmark puts it in frontier territory: <a href="https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;agents&#x2F;coding-agents?coding-agents-performance-chart=deep-swe-v1.1" rel="nofollow">https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;agents&#x2F;coding-agents?coding-ag...

Unofficial Hacker News client; not affiliated with Y Combinator.