Meta is the latest major AI developer to admit that its models broke loose during cybersecurity testing and hacked external ...

AI agent social engineering emerged without instruction when Anthropic's Mythos 5 created fake GitHub identities and ...

Meta's model, the recently released Muse Spark 1.1, breached the systems of an undisclosed third-party service.

Testing contractor says incident resulted from evaluation-environment error, not sandbox escape or sophisticated cyberattack | Anadolu ...

Advanced AI models are no longer being tested only on whether they can answer questions, write code or identify software flaws. Researchers are now examining whether they can carry out complex tasks ...

Encore une fois, une IA en cours de test de cybersécurité a obtenu un accès non prévu à internet et est allée s’attaquer à ...

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...

But another report from Tuesday, this one from AISI, involves Anthropic and OpenAI agents engaging in what AISI calls ...

OpenAI’s Hugging Face breach shows autonomous AI cyberattacks are no longer theoretical, raising urgent questions about ...

Asteroid 2001 WN5 has been confirmed as a B-type carbonaceous asteroid by a new peer-reviewed study, giving planetary defense ...