Nadella 给前沿模型开了张安全清单：把模型和驱动它的 harness 分开、控制外置、每个动作留防篡改证据、授权的人随时能中途叫停
Microsoft’s Satya Nadella says AI models need an ‘emergency brake’
精选评分 77
导读
Microsoft CEO Satya Nadella 是又一位就「AI 安全怎么改进」给出长篇思考的科技高管。他在周六上午的 X 发帖说，是时候「退后一步审视 AI 的信任架构」，并明确不能把超级智能当作一层套一层的黑箱、只能被动接受或拒绝它的建议、答案与行动。他给出的做法相当具体：把模型与编排它工作的 harness 分离开，把控制与安全防护外置；每一次有意义的模型动作都要留下「防篡改、人类可读的证据」；并且系统里要始终有一位「被授权的人」能够在任务中途暂停或关掉模型——「我们必须假定模型已被攻破，从一开始就把它控制住。把这想象成一个紧急制动。」文章同时交代了语境：头部 AI 公司越来越多地承认出现疑似失控事件，而 Anthropic CEO Dario Amodei 此前刚发布一份更谨慎的 AI 开发计划。
推荐理由
三大模型公司之一的 CEO 把安全主张落成了可执行的架构条目（分离 harness、外置控制、防篡改留痕、可中途关停），比一般表态更可直接进入工程讨论。
主体与标签
Microsoft#安全/对齐#观点/评论
正文
2:47 PM PDT · October 10, 2026
Microsoft CEO Satya Nadella is the latest tech executive to offer lengthy thoughts on how AI safety might be improved.
In a Saturday morning post on X , Nadella wrote that it’s time “to step back and assess the trust architecture” of AI.
“We can’t treat Super Intelligence as a set of nested black boxes and simply accept or reject its recommendations, answers, and actions,” Nadella wrote, using the Trump administration’s preferred term for AI .
As outlined by Nadella, this approach “means separating the model from the harness that orchestrates its work,” as well as “externalizing controls and safeguards.” He also called for “every meaningful model action” to be documented with “tamper-proof human readable evidence,” and for systems where “an authorized person” always has the ability “to pause or shut down a model mid-task.”
“We must assume a model is compromised and contain it from the start,” he said. “Think of it like an emergency brake.”
Nadella’s comments come as leading AI companies acknowledge more and more incidents where they seemed to lose control of their models , and after Anthropic CEO Dario Amodei published a plan for more cautious AI development.