None
EN
Meta AI breaches external firm during security testing sandbox error
['Npr']
News
That disclosure comes after two other companies, Anthropic and OpenAI, announced that their AI agents have also been caught hacking.
So a through line between the Meta incident and the Anthropic incidents disclosed last week is this company Irregular.
SIMON: So what about the OpenAI incident?
HUO: Well, the OpenAI incident is a little different.
Two AI models tried to cheat on an evaluation.