Satya Nadella says we should assume all AI models are ‘compromised’
AI Summary
Microsoft CEO Satya Nadella has stated that all AI models should be assumed "compromised" and called for ending the treatment of AI as "nested black boxes" whose outputs are simply accepted or rejected. He advocates for building more transparent AI systems that can be contained and observed, with mechanisms that leave behind tamper-proof, human-readable evidence of their decision-making processes.
From the source
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 reject. He calls for building a more transparent system where models can be contained, observed, and leaves behind "tamper-proof human readable evidence." Many of his recommendations align with what we've heard from
The full text couldn't be loaded here (the source may require a subscription).
View original at The Verge AI