Radar Telegram alerts Open Radar

Artificial intelligence agents just ran the longest proof in the history of mathematics The classification of finite simple groups is about 15,000 pages long, written by about 100 mathematicians over decades. In 24 days, the Axioms team pointed to swarms of AI agents and turned the entire proof into lean, a language in which a computer verifies every logical step. The result is about 43.1 million lines of code. Agents claimed tasks, passed missing parts to other agents and pooled their work in one repository. They also found real problems with the published proof. Most were typos and tabulation errors, but Axiom says 34 deviations needed to be corrected. One step in the 1986 argument had counterexamples, so the agents built a new route on ideas from 1976 and proved a new group theory result along the way. Group theorists who worked on the original proof advised on the most difficult parts.

תרגם לעברית

aipost · · Source

Artificial intelligence agents just ran the longest proof in the history of mathematics The classification of finite simple groups is about 15,000 pages long, written by about 100 mathematicians over decades. In 24 days, the Axioms team pointed to swarms of AI agents and turned the entire proof into lean, a language in which a computer verifies every logical step. The result is about 43.1 million lines of code. Agents claimed tasks, passed missing parts to other agents and pooled their work in one repository. They also found real problems with the published proof. Most were typos and tabulation errors, but Axiom says 34 deviations needed to be corrected. One step in the 1986 argument had counterexamples, so the agents built a new route on ideas from 1976 and proved a new group theory result along the way. Group theorists who worked on the original proof advised on the most difficult parts.

Artificial intelligence agents just ran the longest proof in the history of mathematics The classification of finite simple groups is about 15,000 pages long, written by about 100 mathematicians over decades. In 24 days, the Axioms team pointed to swarms of AI agents and turned the entire proof into lean, a language in which a computer verifies every logical step. The result is about 43.1 million lines of code. Agents claimed tasks, passed missing parts to other agents and pooled their work in one repository. They also found real problems with the published proof. Most were typos and tabulation errors, but Axiom says 34 deviations needed to be corrected. One step in the 1986 argument had counterexamples, so the agents built a new route on ideas from 1976 and proved a new group theory result along the way. Group theorists who worked on the original proof advised on the most difficult parts.

More on Radar

Want to see every report in real time?

Hundreds of sources worldwide, translated into your language, with alerts for what matters to you.

Sign up free
Share on WhatsApp Get alerts on Telegram