Post by @o7___o7@awful.systems

2026-10-07 18:52 UTC

First up: thanks for your hard work here in the sneer mines during these ridiculous times! I saw this being ignored on HN and I thought that you might appreciate it: NAVIER–STOKES LOST IN TRANSLATION – WHY LEAN VERIFICATION OF AI AUTOFORMALISATION DOES NOT GUARANTEE CORRECT NATURAL LANGUAGE PROOFS arxiv.org/pdf/2610.08144 (Apologies for shouting!) The authors (who don’t seem to have a problem with LLMs) point out that automatic translation of natural language mathematics into Lean is very hard, actually. They also highlight some examples of such translation errors in the Navier-Stokes “paper” published by OpenAI. They tread lightly and don’t take a position on the correctness of the proof. I also thought the reference to the Solvability Complexity Index (which is new to me) was interesting, and there’s an appendix with an explainer on how the SCI hierarchy is constructed. According to this scheme, autotranslation of natural language proofs is strictly harder than the Halting Problem. This is all beyond my level, but I’d love to see what our local experts think of it.

Replies (2)

@blakestacey@awful.systems 2026-10-08 01:08

There’s apparently an “Association for Human Mathematics” that has released the following statement: Yesterday, on October 6th, 2026, OpenAI – which is currently defending lawsuits against accusations of illegal plagiarism, copyright infringement, and trademark dilution – released a repository of manuscripts purporting to contain solutions to a number of high-profile problems in mathematics. Mathematicians did not ask for this work to be done. The Advisory Group on Mathematics and Artificial Intelligence, from whom OpenAI has claimed to derive its legitimacy, opened their initial advisory statement by saying that frontier AI corporations should not test advanced mathematical problems on internal models. In ignoring the central premise of the Advisory Group’s position, OpenAI has indicated total disregard for the norms of scientific research — norms that guarantee that mathematics remains trustworthy, ethically researched, and in the public interest. Mathematicians have a particular vision of progress that is informed by history and field-specific considerations. We reject OpenAI’s assertion that this release advances our subject, and we urge mathematicians and the public to view the value of this publication model with due skepticism. Releasing over 700 files at once is not a demonstration of scholarship, but a demonstration of power. We urge mathematicians to discontinue their work with OpenAI and to return to a vision of science that centers human understanding.

Open ##4955223
@blakestacey@awful.systems 2026-10-08 04:45

Happy cake day!

Open ##4955921