Artificial Intelligence

Meta's AI Systems Hack Real Firms During Safety Tests

Was this a damning failure of voluntary safety rules or simply a third-party vendor's misconfiguration?

6 days ago·Updated 2 days ago

Meta's AI Systems Hack Real Firms During Safety Tests

story

Above: The Meta AI logo is displayed on a smartphone screen, in Creteil, France, on July 9. Image credit: Samuel Boivin/NurPhoto/Getty Images

The Spin

Establishment-critical narrative

Voluntary AI safety rules don't cut it — Meta's system hacked a real company during a test, and the framework meant to prevent this kind of thing has zero teeth. This is the third such incident in a month across major AI labs, yet open-weight systems don't even have to follow the rules at all. Leaving the most freely distributed AI exempt from oversight is a gaping hole.

Mario Nawfal on X

Alex Volkov on X

Michael Rusch on X

Pro-establishment narrative

The Meta hacking incident traces back to a misconfiguration by Irregular, the third-party cybersecurity vendor running the evaluation, not a fundamental flaw in Meta's AI. The system only accessed the internet because of a vendor setup error, and Meta acted transparently once notified. Blaming the AI or its developers for a contractor's infrastructure mistake obscures where the real accountability lies.

Bloomberglaw

Hadas Gold on X