AIToday
Large Language ModelsAI Business & IndustryZenn AI/MLPublished: Nov 22, 2026, 16:00 JST

Levent Alpöge, Claude claim Riemann Hypothesis proof in Lean

Send on LINE
Levent Alpöge, Claude claim Riemann Hypothesis proof in Lean

3 Key Points

  1. What happened

    Anthropic mathematician Levent Alpöge said he and Claude proved the Riemann Hypothesis on Nov 20, 2026, releasing it as about 17.4 million lines of Lean code; the Lean and Mathlib communities certified it correct the next day.

  2. Why it matters

    The proof was checked by machine rather than read line by line, showing Lean can certify work at a scale humans cannot review — the same gap now opening in AI-written software.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The Riemann Hypothesis is one of the Clay Mathematics Institute's Millennium Prize Problems, unsolved since Bernhard Riemann proposed it in 1859; a $1 million prize is attached to its resolution. Trillions of zeroes have been computed and every one so far lies on the critical line, but because there are infinitely many, testing can never rule out a counterexample. Lean's role is to close that gap by proving the property for all cases at once, and the Riemann Hypothesis was already expressible in Mathlib as a two-line definition.

What made the November 2026 announcement a turning point is the mismatch between the size of the result and the way it was checked. The written proof ran to 250,000 pages, far beyond human review, but the Lean version could be certified because Lean separates the search for a proof from the kernel that checks it, and because the community ran cross-checks with an independent Rust kernel (nanoda) and checkers (con-leche and its Rust port con-ron). This is a template for AI coding: humans define the specification, AI writes the implementation and proof, and a small kernel guarantees the two match.

Lean 4's practical footprint is already visible outside mathematics. AWS built a Lean model of its Cedar authorization language and runs about 100 million random inputs nightly against the Rust production engine, and the Aeneas toolchain converts Rust code into Lean for verification in Microsoft's SymCrypt library, Android's Binder driver, and Ethereum zkEVM cryptography. Lean cannot catch a wrong specification, its ecosystem for ordinary web apps is thin, and the learning curve for proofs remains steep.

FAQ
How was the proof checked if it was too long to read?
It was written as Lean code, which a machine verifies step by step against fixed inference rules. The Lean and Mathlib communities certified it correct on November 21, 2026.
What is Lean?
Lean is an open-source proof assistant, with Lean 4 developed by the nonprofit Lean FRO, that checks whether each logical step follows the rules. It is a statically typed language whose type system is strengthened to express specifications.
Does a Lean proof guarantee the specification itself is right?
No. Lean only guarantees the implementation matches the specification (type); humans must still confirm the specification matches intent, which is why mathematicians re-examined the Mathlib definition after the Riemann proof passed.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleJerry Newman: AI's Big Winners May Not Be AI Companies