数学家创立MAISI，欲用数学证明AI安全性
原标题：The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable
AI 摘要
加拿大数学家、新晋菲尔兹奖得主 Jacob Tsimerman 宣布成立数学人工智能安全研究所（MAISI），计划于 2027 年 1 月在旧金山湾区启动，由十到三十名数学家研究 AI 安全问题。Tsimerman 同时加入 OpenAI 安全团队，他认为当前安全标准远远不够。MAISI 希望像密码学家证明加密不可破解那样，为 AI 安全性提供数学证明，目标包括验证系统行为负责、多智能体协作不产生意外结果，以及抵御未知漏洞，可能采用零知识证明等工具。
正文节选
The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable Canadian mathematician Jacob Tsimerman, a fresh Fields Medal recipient, has announced the founding of the Mathematical A.I. Safety Institute (MAISI). The independent research institute in the San Francisco Bay Area plans to start work in January 2027 with ten to thirty mathematicians tackling AI safety problems, the New York Times reports. Tsimerman, who is also joining OpenAI's safe