Show HN: Black-box API bug detection across 7 AI systems(resources.kusho.ai)

11 pointsby riyajoshivorige maand4 comments

resources.kusho.ai

Show HN: Black-box API bug detection across 7 AI systems

https://resources.kusho.ai/ai-agent-benchmark-api-bug-detection

5 comments

Kind of wild that we're finally getting benchmarks for AI-generated API testing. Feels like the equivalent of SWE-bench, but for finding actual bugs instead of writing code.

saikia_vorige maand

Cool launch - let me try this with our in house setup!

calderon_1903vorige maand

interesting stuff

riyajoshivorige maand

Thank you. Would really appreciate feedback on methodology or the evaluation framework!

paol_tajavorige maand