Last month, an OpenAI model disproved a long-standing conjecture by Paul Erdős on the planar unit distance problem, producing a construction so intricate that verifying it took a team of external mathematicians a week. In the inaugural episode of Begin Proof, Slater Stich sits down with Noam Brown, who leads work on multi-agent reasoning and test-time compute at OpenAI, and was one of the key people behind o1, OpenAI's first public reasoning model. They talk about what the Erdős result actually means, where the models are superhuman and where they still aren't, and what working mathematicians will be doing in a few years.

X

Slater: https://x.com/slaterstich

Noam: https://x.com/polynoamial

OpenAI: https://x.com/OpenAI

Bain Capital Ventures: https://x.com/BainCapVC

__

LinkedIn

Slater: https://www.linkedin.com/in/slater-stich-4658a849/

Noam: https://www.linkedin.com/in/noam-brown-8b785b62/

OpenAI: https://www.linkedin.com/company/openai/

Bain Capital Ventures: https://www.linkedin.com/company/bain-capital-ventures/