Nadella 称应假定所有 AI 模型都已被攻破
Satya Nadella says we should assume all AI models are ‘compromised’
精选理由
微软 CEO 自己说别信任何模型，默认它们都被攻破了。做 AI 产品的可以看看他提的防护思路。
微软 CEO Satya Nadella 在 X 发长文谈高级 AI 模型的安全风险。他认为不能再把 AI 当作层层嵌套的黑箱，直接接受其建议和行动。他提出应默认所有模型都可能被攻破，并据此设计防护机制。
原文 · theverge
Satya Nadella says we should assume all AI models are ‘compromised’
In a lengthy post on X, Microsoft's CEO laid out his views on the dangers posed by highly advanced AI models and how to confront those risks. Nadella says we can no longer accept a world where AI is treated as a "set of nested black boxes" whose advice and actions we simply accept or […]
