Satya Nadella says we should assume all AI models are ‘compromised’

In a lengthy post on X, Microsoft CEO Satya Nadella outlined his views on the dangers of highly advanced AI models and how to confront them. He argues we can no longer accept treating AI as a set of nested black boxes whose advice and actions we simply accept or reject, and calls for a more transparent system where models can be contained, observed, and produce tamper-proof human-readable evidence.

Many of his recommendations echo industry consensus: timely incident disclosure, independent audits, verifiable data, and containment. On containment, he goes further, stating that we must assume a model is compromised and contain it from the start—likening this to an emergency brake—and that an authorized person should always be able to pause or shut down a model mid-task. He adds that more advanced models will require more advanced containment technologies that must be standardized.

Notably, Nadella refers to AI as “super intelligence” throughout the post.

(Source：The Verge)