OpenAI Paper Constructs Finite-Time Blowup for Navier–Stokes, Verified in Lean by GPT-6 Astra
burny_tech · x · 2026-09-11
A new OpenAI paper tackles the Navier–Stokes "finite time blowup" question, one of the seven Millennium Prize Problems: whether a smooth 3D flow can develop infinite velocity in finite time. The authors build a vortex that spins faster and faster while collapsing into an increasingly tiny region, with total kinetic energy staying bounded.
The key trick is adding tiny oscillatory flows that extract energy from the vortex's shear and cancel the singular forcing otherwise needed to sustain the collapse, leaving a smooth external force.
Notably, the proof was reportedly generated by an unreleased OpenAI model beyond GPT-6 Astra, while GPT-6 Astra helped formalize and verify it in Lean.
More from AGI Musings
- OpenAI's Navier-Stokes proof: Lean 4 verification in 17 hours vs 132,800 person-hours — jedisct1 · 2026-09-11
- Frontier lab's 'AI will make everyone rich, healthy, and free' sparks comms debate — MxMnr · 2026-09-11
- Frontier AI company shares 'Our convictions' statement — MxMnr · 2026-09-11
- Replit CEO backs Sacks: AI 'extinction risk' is not remotely real — amasad · 2026-09-11
- FT's Burn-Murdoch: Anthropic's economic scenarios hinge on hand-picked assumptions — jburnmurdoch · 2026-09-11
- Study something unusual: why Hieroglyphic Luwian beats another ML course — begusgasper · 2026-09-11