© 2026 Public Radio Tulsa
800 South Tucker Drive
Tulsa, OK 74104
(918) 631-2577

A listener-supported service of The University of Tulsa
classical 88.7 | public radio 89.5
Donate
Play Live Radio
Next Up:
0:00
0:00
0:00 0:00
Available On Air Stations

Meta AI breaches external firm during security testing sandbox error

NPR | By Huo Jingnan,
Scott Simon
Published August 8, 2026 at 6:43 AM CDT

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.

Copyright 2026 NPR
Huo Jingnan
Huo Jingnan is a reporter for NPR.
Scott Simon
Scott Simon is the host of Weekend Edition Saturday and is one of the hosts of NPR's morning news podcast Up First.