Reposted by Ander Movilla
It turns out that Open-AI's natural language proof of Navier-Stokes has mistakes that aren't in the Lean formalization:
arxiv.org/abs/2610.08144
arxiv.org
Navier-Stokes lost in translation: Why Lean verification of AI autoformalisation does not guarantee correct natural language proofs
Autoformalisation is increasingly used to verify mathematical texts, including those generated by AI, as in OpenAI's announced proof of blow-up of solutions to the Navier-Stokes equations. In this pro...