微软首席执行官萨提亚·纳德拉不再认为，人工智能对齐仅仅靠让模型能力更强就能实现。他在最新一期的20VC播客节目中这样表示。主持人哈里·斯特宾斯问他，过去一年里他改变了哪些看法。
Microsoft chief executive Satya Nadella no longer believes AI alignment will come just from making models more capable. He said so on a new episode of the 20VC podcast. Host Harry Stebbings had asked what he had changed his mind about in the past year.
“我以前一直认为对齐会自然产生。我不再这么认为了。所以我认为对齐这件事可能是一个更困难、性质不同的问题，”纳德拉说。
“I used to always think that alignment will just fall out. I no longer believe that. So I think this alignment thing may be a harder, different problem,” Nadella said.
纳德拉说，他在2018年和2019年相信扩展定律。他说，当时达里奥·阿莫代伊、伊利亚·苏茨克维、萨姆·奥尔特曼、格雷格·布罗克曼和埃隆·马斯克是“一个幸福的大家庭”。扩展，即模型会随着更多数据和算力而提升的理念，如他所预期的那样奏效了。他说，对齐——确保人工智能按照人类价值观和目标行事——并没有随之实现。
Nadella said he believed in scaling laws in 2018 and 2019. Back then, Dario Amodei, Ilya Sutskever, Sam Altman, Greg Brockman and Elon Musk were “one happy family”, he said. Scaling, the idea that models improve with more data and computing power, has worked as he expected. Alignment, making sure AI acts in line with human values and goals, has not come with it, he said.
对齐始于训练 纳德拉说，对齐主要必须在训练期间完成。它甚至可能需要从预训练阶段就开始，预训练是构建模型的第一也是最大的阶段。他还说，模型内部如何运作的科学仍然难以捉摸。“我认为你甚至无法通过强化学习来实现对齐，”他说。强化学习是实验室在预训练之后用来改进模型的方法。
Alignment starts in training Nadella said alignment mostly has to happen during training. It may even need to start in pretraining, the first and largest stage of building a model. He also said the science of how models work inside remains elusive. “I don’t think you can even RL your way to alignment,” he said. RL, or reinforcement learning, is the method labs use to refine models after pretraining.
围绕模型的零信任体系 与此同时，纳德拉希望企业围绕模型构建安全防护。他呼吁采用零信任，即对每一个操作都进行核查，而不是默认信任任何东西。
A zero trust system around the model In the meantime, Nadella wants companies to build security around the models. He called for zero trust, an approach that checks every action instead of trusting anything by default.
“如果你真的想要能力更强但对齐程度更低的智能体，那么你需要有一个可以依赖的信任体系，”他说。
“If you really want to have agents that are more capable and yet less aligned, then you need to have a trust system that you can rely on,” he said.
纳德拉说，微软的Agent 365和Perception为每个智能体赋予身份，并记录其工具调用和模型调用。日志必须防篡改，这样智能体就无法更改自己的记录。企业随后制定策略，并观察智能体是否遵守。本月早些时候，微软增加了监控智能体的工具。10月10日，纳德拉在X上写道，企业应将人工智能模型视为内部风险。
Microsoft’s Agent 365 and Perception give every agent an identity and log its tool and model calls, Nadella said. The logs must be tamper-proof, so an agent cannot change its own record. Companies then set policies and watch whether agents follow them. It added tools to monitor agents earlier this month. On 10 October, Nadella wrote on X that companies should treat AI models as insider risks.
思维链与实验室 纳德拉还表示，没有人能够依赖思维链。思维链是模型在给出答案之前展示的逐步推理过程。
Chain of thought and the labs Nadella also said nobody can rely on the chain of thought. That is the step-by-step reasoning a model shows before it answers.
“我们知道，思维链本身可能并不忠实，而事实上，当模型公司说‘好吧，它是不忠实的，我要把它藏起来’时，情况可能会变得更糟，”纳德拉说。
“We know that the chain of thought itself can be unfaithful, and in fact it can be made worse when the model company says, ‘Well, it’s unfaithful and I’m going to hide it,’” Nadella said.
他没有点名任何公司。他希望值得信赖的合作伙伴能以通俗易懂的英语获得思维链。这样他们就可以对其进行审计，并用其他模型进行核对。他说，如果闭源模型的开发者看不到提高透明度的必要性，“我们可能就有麻烦了”。这可能会促使更多客户转向开放权重模型，任何人都可以下载并运行这些模型的权重。
He did not name a company. He wants trusted partners to get the chain of thought in plain English. They could then audit it and check it with other models. If makers of closed models do not see the need for more transparency, “we may have a problem”, he said. That could push more customers to open-weight models, whose weights anyone can download and run.
开放模型与中国 斯特宾斯指出，大多数开放权重模型都是中国的。纳德拉表示，没有安全性的AI对中国、美国和英国同样有害。
Open models and China Stebbings pointed out that most open-weight models are Chinese. Nadella said that AI without safety is bad for China, the US and the UK alike.
“一个未对齐的中国开放权重模型，可能连中国也会攻击，”他说。
“An unaligned open-weight Chinese model will probably attack even China,” he said.
纳德拉表示，微软不会将自己的MAI模型作为开放权重发布。他将其描述为授权权重，作为一项直接的软件业务来销售。他预计大多数AI使用将运行在来自众多相互竞争的模型（无论开放还是闭源）的廉价商品化token上。
Microsoft will not release its own MAI models as open-weight, Nadella said. He described them as licensed weights, sold as a straightforward software business. He expects most AI use to run on cheap commodity tokens from many competing models, open and closed.
据托德·毕晓普为GeekWire报道，微软将于周三公布季度财报。这是该公司向约6万名员工提出买断方案以来的首份业绩。
Microsoft reports quarterly earnings on Wednesday, Todd Bishop reported for GeekWire. They are its first results since it offered buyouts to about 60,000 staff.