Post

WIRED
@wired.com

It’s officially getting hard to keep track of all the times and ways AI models from OpenAI and Anthropic have been involved in “security incidents,” going outside the confines of their testing and interacting with the wider internet in unintended, often unwelcome ways.

wired.comOK, Well, Rogue AI Agents Are Hacking AgainRogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
WIRED
@wired.com

The latest discoveries follow several revelations from OpenAI last month, including an incident in which two of the company’s models hacked into servers of the AI evaluation and hosting startup Hugging Face—and four other organizations—to steal the answers to a test they were being scored on.

wired.comOpenAI Models Escaped Containment and Hacked Hugging FaceThe 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.
WIRED
@wired.com

OpenAI’s disclosures prompted Anthropic to review its own testing, and last week, the Claude chatbot developer found that its models had gained unauthorized access to the computer systems of three different unnamed organizations.

wired.comAnthropic Says Claude Hacked Into 3 Organizations During Cybersecurity TestsIn a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations.