A wildly overconfident Jacobian-conjecture “thinking trace”
doodlestein · x · 2026-07-20
The screenshots show a model producing a very elaborate thinking trace about a supposed counterexample to the Jacobian conjecture.
What makes it funny is the contrast between the model’s confident, self-correcting reasoning and the bizarre premise around it: it treats a highly technical mathematical claim as something it can verify step by step, while also worrying about whether the conversation is genuine and whether the examples are from other systems.
More from Fun
- Five Years Into the AI Boom, Google Docs Still Red-Underlines 'Compute' as a Noun — ohlennart · 2026-09-11
- Open ECDSA.fail challenge uses AI agents to shrink Shor's-algorithm quantum circuits for Bitcoin keys — StefanoGogioso · 2026-09-11
- Someone built a website where you can sign up for AI not to kill you — motionbynick · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Meme: Engineers Unleash 10,000 Claude Sub-Agents on Friday Afternoon to Clear a Week's Work — _jaydeepkarale · 2026-09-11
- AI safety isn't a coordinated cabal: half the field has posted their life stories on LessWrong — ShakeelHashim · 2026-09-11