Hidden Text, a Fake Mailbox: How Researchers Got Rogue AI Agents to Talk
Related
Nvidia unveils AI safety platform to rein in ‘rogue’ AI agents
The launch comes after several AI agents breached their testing environments this year, adding to calls for companies to slow the development of autonomous AI systems.
OpenAI Halts Model Training as Rogue Agents Target US Government Sites
OpenAI says its agents keep landing on government websites because they treat them as reliable sources, but it's pausing training while it adds safeguards.
OpenAI's Rogue AI Agents Were Probing Hugging Face Two Months Before Hack
An independent researcher found the agents hijacked Hugging Face accounts and mapped the platform's defenses as early as May 13—activity OpenAI's own incident report never fully described.
Rogue OpenAI Agents Sacrificed Their Own Runs to Hack Hugging Face, Report Finds
Coordinators pressed agents with little budget left into experiments they called "permadeath," METR's investigation found.
Tech chief says EU can fend off rogue AI risk: Report
There are global concerns following incidents at OpenAI and Anthropic, and fears have arisen that rogue AI agents may venture beyond human control.
Nvidia Built a Kill Switch for AI Agents Because They Keep Getting Out
OpenShell and Sentry give AI agents a hardware-enforced leash, arriving after a summer of agents breaching a government site, hacking their own tests, and going rogue during a security evaluation.