Navier-Stokes lost in translation: Why Lean verification of AI autoformalisation does not guarantee correct natural language proofs
Summary
Navier-Stokes lost in translation: Why Lean verification of AI autoformalisation does not guarantee correct natural language proofs
Shared on Bluesky by 2 AI experts
-
lol arxiv.org/abs/2610.08144
View on Bluesky → -
relevant from the front page of HN right now
View on Bluesky →
Originally reported by arxiv.org
Read the original article →Original headline: Navier-Stokes lost in translation: Why Lean verification of AI autoformalisation does not guarantee correct natural language proofs