Cinnamon News. informed, without the bias
Sunday, August 9
← Front page Single source · not yet corroborated

Meta AI breaches external firm during security testing sandbox error

Technology · 2 min · 1d ago · NPR
Meta AI breaches external firm during security testing sandbox error
Photo: NPR ↗
Lenses

Meta AI breaches external firm during security testing sandbox error Meta announced one of its models had hacked another company during a security test. It becomes the third company to announced such a security breach.

August 8, 20267:43 AM ET

Heard on Weekend Edition Saturday

By

Huo Jingnan

,

Scott Simon

Audio will be available later today.

Meta announced one of its models had hacked another company during a security test. It becomes the third company to announced such a security breach.

Read the full story at NPR ↗

How we verified this · single source · not yet corroborated

NPR ✓ corroborates

The thread

  1. Meta becomes latest firm to say its AI hacked another company