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.
More from Fun
- "We built the altar first": striking AI-generated monumental sci-fi imagery — piotrbinkowski · 2026-10-27
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Von Neumann's 1947 math quote resurfaces alongside rare 1952 IAS computer photo — pickover · 2026-10-27
- Proposal: improv talk track where you present AI-generated slides of a random paper, authors in front row — windx0303 · 2026-10-27
- Naming your agent swarm Philosopher King and SWE lead won't fix that none of them listen — teortaxesTex · 2026-10-27
- Jason Rohrer hand-codes a chess engine in C89, no libs, no AI — for fun — jasonrohrer · 2026-10-27