aifollow.news
Search
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
A new Google DeepMind and Cambridge paper says a Gemini-based agent found exact rules for 11 Busy Beaver Turing machines with no prior documented analysis and verified them in Lean. The described process tests edge cases in a simulator, drafts proofs and checks them in Lean; the results concern a specific math problem and do not establish that the agent can solve math problems in general.
谷歌 DeepMind 与剑桥大学的一篇新论文表明，AI 智能体能够自行发现新的数学成果，为 11 台尚未解决的图灵机证明精确规则。
一个基于 Gemini 的智能体为 11 台此前没有公开分析记录的忙碌海狸图灵机找到了新规则，并用 Lean 验证了这些规则。这表明，AI 能够从回答人类提出的数学问题走向开放式发现。
它在模拟器中测试边界情况，起草非形式化证明，然后在 Lean 证明检查器中证明这些规则。
