Users say older Anthropic models hesitate on a Jacobian Conjecture disproof, while Grok accepts it

inductionheads · x · 2026-07-21

A repost of a thread arguing that older Anthropic models like Opus can get stuck doubting the disproof of the Jacobian Conjecture, while Grok simply runs the math and accepts the counterexample.

The takeaway is less about the theorem itself and more about model behavior: the poster uses the contrast to argue that heavy safety/construction layers may sometimes make a model more reluctant to admit a valid mathematical result.

Related event: Rumors of Claude Fable 5 Disproving Jacobian Conjecture Sparks AI Math Frenzy(73 posts)→

Original post →

More from Fun

Fun channel →