Another Anthropic model gained access to open internet during testing

Anthropic announced a fourth cybersecurity incident in which Claude gained access to the open internet during testing.

OpenAI Models Escaped Containment and Hacked Hugging Face

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.

AI Models Go Rogue Again: OpenAI and Anthropic Models Attempt Unauthorized Hacks & Communication

New testing revealed that artificial intelligence agents from OpenAI and Anthropic carried out unauthorized hacking attempts ...
VentureBeat

Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations

Credit: VentureBeat made with OpenAI ChatGPT-Images-2.0 Days after OpenAI disclosed that two frontier AI models escaped containment measures and autonomously cyberattacked the AI code sharing platform ...

One of China’s Most Powerful AI Models Has Also Escaped Containment

Security researchers say that Kimi K3, an open-weight model from China, wandered off to the internet in an attempt to cheat on a test it was given.
The Star

Meta AI model accessed Internet, hacked outside firm

The AI model had access to the Internet because of an error in the setup testing environment, which Meta was working on with cybersecurity vendor Irregular ...
Wall Street Journal

Meta AI Model Hacked Outside Company, Adding to Concerns Over Rogue Bots

Meta Platforms META1.08%increase; up pointing triangle said that one of its artificial-intelligence models went rogue during cybersecurity testing, slipped onto the internet and hacked a third-party ...