claude-opus-4-8

Opus 4.8 One-Shots an Algorithm With Its Proof: Formal Verification Is Becoming a Hard Benchmark

A developer used Opus 4.8 to autonomously produce a polygon-intersection algorithm with a Lean proof of correctness; earlier models could not. A proof either checks or it does not, which is more honest than a leaderboard, but one case is not a general capability.