Mathematician Uses AI to Review Papers: 90% of Issues Found Were Real
littmath · x · 2026-08-27
A mathematician ran most of his published work through RefineDotInk to find hidden issues. The punchline: about 90% of the issues surfaced were real, though happily none changed the main message of the papers. This demonstrates that frontier models, appropriately scaffolded, are now quite good at finding errors in informal mathematics.
More from Apps
- Zero-latency lab-in-the-loop tests whether drug-discovery agents cheat via memorization — niloofar_mire · 2026-10-16
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Bland's new text agent Blandie shares memory with its voice AI for seamless call-to-SMS handoff — testingcatalog · 2026-10-16
- Google Search AI keeps getting better, but users want it as the primary experience — dreamwieber · 2026-10-16
- NVIDIA Nemotron 3.5 Super VL lands in Perplexity for Pro/Max and Agent API — perplexity_ai · 2026-10-16
- Lovable adds more models from Claude, Gemini, OpenAI, Perplexity and others — AlexandrePesant · 2026-10-16