LLM finds obscure linear-programming paper that helps solve a K3 quartics problem
burny_tech · x · 2026-07-28
A mathematician recounts how, after getting access to the latest model, they used a carefully designed Codex prompt on a problem about Chern slopes of K3 quartics.
The model unexpectedly surfaced an obscure paper on a variant of linear programming, which helped advance the final part of the proof. The story highlights how LLMs can contribute in niche mathematical research by finding non-obvious connections, not just by doing rote computation.
More from Research
- Retriever: A Framework for Asynchronous, Closed-Loop Robot Agents — ZeYanjie · 2026-08-24
- Converting GMMs ↔ PEFs for fast KLD approximation — FrnkNlsn · 2026-08-24
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- Nature Comment: Provenance, not interpretability, grounds trust in autonomous science — gabepgomes · 2026-08-24
- New Architecture RHEA: Train 1B Model on 8GB VRAM — zemondza · 2026-08-24
- Trained two 16M-param models to do generative CAD with real physics — debreuil · 2026-08-24