AI agent benchmarks are broken

(ddkang.substack.com)

181 points neehao | 1 comments | 11 Jul 25 13:06 UTC | HN request time: 0.426s | source

1. let_tim_cook_ ◴[11 Jul 25 14:37 UTC] No.44532633[source]▶

Are any authors here? Have you looked at AppWorld? https://appworld.dev