Science & Tech · AI · 23 hrs ago

Nadella says AI models should be treated as compromised and containable

Microsoft CEO Satya Nadella has called for stronger safeguards as AI models become more advanced.

In a post on X, he said people should assume a model could be compromised and contain it from the start.

He argued that AI systems should not be treated as black boxes whose actions people simply accept or reject.

Instead, he wants models to be observable and to leave tamper-proof, human-readable records.

He also called for incident disclosure, independent audits and verifiable data.

Nadella said an authorized person should be able to pause or shut down a model during a task, like using an emergency brake.

He said more advanced models will need stronger containment technology, which should be standardized.

Sources

The Verge · 23 hrs ago