AI agent swarm lifts integer-multiplication bound parameter to 0.00129
A 36Kr repost of a New Zhineng (新智元) report describes how researchers and dozens of AI agents driven by Codex and Claude worked in the GitHub repository CrocSwap/integer-mult-bounds on OpenAI Math Drop problem #109, the integer-multiplication lower bound, claiming the core parameter kappa rose from a baseline of 2^−182 to 0.00129 within 24 hours. The report says 151 pull requests arrived in one day with more than 260 million lines of new code, and contributor Rohan Arun said optimization at one point outpaced the verification machines. It also credits human researcher Jacob Sussman with introducing E8 lattice geometry to break the swarm out of a local optimum; all figures are self-reported by community participants and the report cites no independent verification, while calling the gain a "hundreds-of-millions-fold exponential breakthrough."
The report frames this as human intuition combined with large-scale AI-agent trial and error, but the core figures come from community participants themselves and have not been independently verified.
这在这几天,数学家、极客和成群的AI智能体,展开了一场震撼的接力。
这次接力,发生在GitHub的一个开源仓库里。
「人类直觉 + AI的海量试错」,组成了一支无坚不摧的去中心化蜂群。
仅仅24小时,他们就将OpenAI第109号数学难题(整数乘法下界)的核心参数k,从2^−182,一路拉升到了 0.00129!
这相当实现了数亿倍的指数级突破!
#OpenAI#Codex#Claude Opus 5.5#Codex Astra#CrocSwap/integer-mult-bounds#GetSupers#GitHub