<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Proof on Tristan Germain</title><link>https://tristangermain.com/tags/proof/</link><description>Recent content in Proof on Tristan Germain</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>© Tristan Germain</copyright><lastBuildDate>Sun, 11 Oct 2026 22:17:31 +0200</lastBuildDate><atom:link href="https://tristangermain.com/tags/proof/index.xml" rel="self" type="application/rss+xml"/><item><title>What OpenAI's math proofs could mean for programming with AI</title><link>https://tristangermain.com/posts/openai-math-breakthrough/</link><pubDate>Sun, 11 Oct 2026 22:17:31 +0200</pubDate><guid>https://tristangermain.com/posts/openai-math-breakthrough/</guid><description>On October 6, 2026 OpenAI published more than 700 math manuscripts on GitHub. They were produced by an unreleased internal model. Many of them come with proofs formalized in Lean. Lean is a proof assistant whose checker validates every logical step mechanically.
What struck me most was not the number. It was the reaction of the people working in those fields. In this interview Hugo Duminil-Copin, Fields medalist in 2022 for his work on probability and statistical physics, explains that OpenAI&amp;rsquo;s model proved the conjectures he was working on.</description></item></channel></rss>