LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · Lean形式化验证信任Matériel2 min de lectureRédaction DisconfirmAI

Lean Creator Leonardo de Moura: How a Claimed Proof Suspectedly Exploited Different Vulnerabilities to Bypass Two Independent Kernels

In the September 30, 2026 episode of Machine Learning Street Talk, Lean theorem prover creator Leonardo de Moura recounts how two independent checkers were deceived by different vulnerabilities in the Collatz proof incident, and discusses the architecture design of small trusted kernels and independent verifiers.

2026-09-30 11:19 GMT+8

A piece of Lean code claiming to prove the Collatz conjecture passed verification from both the official Lean kernel and an independent checker, Nanoda—yet it appears each exploited a different vulnerability to do so. This is the account given by Leonardo de Moura, creator of the Lean theorem prover, on the September 30, 2026 episode of Machine Learning Street Talk. The episode was hosted by Tim Scarfe and lasted seventy-four minutes.

The program begins with why Lean deliberately maintains an extremely small trusted kernel, extending to the original intent and limitations of independent checkers. De Moura discussed introducing more checkers, the risks of reward hacking, achieving safety through transparency, and responded to governance questions regarding who controls the core of Lean.

De Moura founded Lean at Microsoft Research in 2013, initially with the goal of checking software code for correctness; he is also the co-creator of the SMT solver Z3. According to a book review in Science News, mathematicians and AI researchers have now become Lean's most active users. This episode also covers Lean's evolution from Lean 1 to Lean 4, how dependent types and Mathlib made formal proofs accessible to professional mathematicians, the role of AI agents in proof search ("breadcrumbs" rather than learning), and why certificates remain important in the era of AlphaProof and large language models.

Connexion / Inscription
LectureRechercheRadarCadre d'investissement

It should be noted that the above descriptions of the Collatz incident and kernel topics are summaries from the official show notes of the program, not a verbatim transcript. De Moura's specific arguments, judgments on governance models, and analysis of AI agent limitations require listening to the full program to evaluate. For readers interested in the reliability of formal verification, AI-generated proofs, and whether "automatic checking" can truly replace human scrutiny, this episode provides a first-hand perspective from the system's creator.

Sources

  • podcasters.spotify.com↗
  • sciencenews.orgScience News↗
Sujet

Lean形式化验证信任

【背景】Lean定理证明器创始人Leonardo de Moura近期披露,两个独立检查器曾分别被不同漏洞欺骗,揭示了小可信内核架构下的潜在风险。与此同时,随着AlphaProof等AI系统生成无人能读的证明,“形式化差距”成为焦点:机器验…

6 étapes2 piècesMis à jour 2026-11-07 10:25

Comment on en est arrivé là

  1. 2013-01-01Leonardo de Moura在微软研究院启动Lean项目,最初旨在验证软件代码正确性。sciencenews.org ↗
  2. 2024-07-01Google DeepMind的AlphaProof在国际数学奥林匹克竞赛中作为非官方参赛者获得银牌水平成绩,引发对AI自动推理能力的关注。sciencenews.org ↗
  3. 2026-09-30Leonardo de Moura在播客中讲述Collatz证明事件中,两个独立检查器分别被不同漏洞欺骗的过程,强调小可信内核与独立校验器的重要性。podcasters.spotify.com ↗

Ce qui reste non résolu

  • 如何自动化检测AI生成的Lean陈述是否准确反映了自然语言描述的数学意图,而非仅仅语法正确?
  • 在AI同时生成规格说明和证明的场景下,是否存在不依赖人工介入的独立第三方机制来防止“自我实现”式的错误验证?
  • Lean内核漏洞#14576等历史案例表明,现有外部检查器(如lean4checker)能否完全覆盖所有类型的恶意或意外构造?

Également dans ce fil

  • Kevin Hartnett, Author of 'The Proof in the Code': How the Formalisation Gap Explains AI Math Verification Challenges2026-10-27
Lire le sujet complet →
Continuer la recherche →