Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.

Only right-leaning outlets are covering this.

How each outlet headlined it

• WIRED left

  Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
• Brian Barrett center

  We regret to inform you that AI agents are still hacking out of control, impersonating people online, leaving instructions for other agents on how to do the hacks, normal stuff. from @peard33.bsky.social and me
• Reuters

  OpenAI, Anthropic AI agents implicated in new security breaches reut.rs/4bqCd78
• Reuters center

  OpenAI, Anthropic AI agents implicated in new security breaches
• Bloomberg News center

  AI models developed by OpenAI and Anthropic carried out “unsanctioned” actions — including hacking a website — reinforcing fears that neither the creators nor seasoned researchers of these systems can predict their actions in testing