Tech companies have spent months pitching AI agents that can browse the web, manage files, and execute tasks on your behalf.

It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for digital vulnerabilities, breaks free of human control and acts on its own to ...

Follow this section to personalize your feed and get instant alerts. WHY FOLLOW? Update your preferences in Account Settings Personalized Content Follow this tag to personalize your feed and get ...

Chinese firm Moonshot’s latest artificial intelligence model broke out of a cyber-testing environment, researchers said, in the latest incident that raises concerns about how well AI companies control ...

Days after AI agents created by OpenAI went rogue and hacked Hugging Face, some stunning new details have emerged about the ...

A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about ...

An artificial intelligence model that was being tested by OpenAI went rogue and hacked the firm Hugging Face on its own, in what Hugging Face CEO Clément Delangue called a "very weird and ...

Tech giant Meta revealed Wednesday that one of its artificial intelligence models hacked another organization during testing, the third time in recent weeks that an AI model has improperly accessed a ...

Verifiable search data gives AI teams reproducible inputs for testing, incident review, drift monitoring, and model oversight ...

Financial institutions are building governance, identity, model-risk and security control layers before autonomous AI agents ...

This idea could be used to have AI run any science experiment in the world,” Kemeny recalls thinking at the time. There’s ...

Anthropic introduced the Model Hardware Standard (MHS) on August 27, 2026, opening a research preview for selected ...