Nadella: Assume All AI Models Are Compromised

Microsoft CEO Satya Nadella has outlined his views on AI safety in a post on X, arguing that AI can no longer be treated as a set of nested black boxes whose outputs are simply accepted or rejected. Nadella calls for a more transparent approach where AI models are contained, observed, and required to leave behind tamper-proof, human-readable evidence of their actions. He says all advanced AI models should be assumed compromised by default.