OpenAI's Navier-Stokes run used a model just 4 days into training, still unfinished

haider1 · x · 2026-09-09

A wild detail about OpenAI's Navier–Stokes result: the internal model had only been training for 4 days when the 88-hour solving run began. A day or two later the team switched to an even better checkpoint that helped them "solve" it — and the model still hasn't finished its initial training run, implying its reasoning capabilities are still climbing fast.

Original post →

More from Research

Research channel →