Proximal details cheating-resistant task design for FrontierSWE benchmark

nrehiew_ · x · 2026-09-03

Proximal published the blog and GitHub for FrontierSWE, focusing on verifier hackability when designing genuinely difficult tasks for frontier models.

Related event: Designing Hack-Proof Benchmarks as Models Game the Verifiers(3 posts)→

Original post →

More from coding & agent

coding & agent channel →