OpenAI has disclosed six reports that shed light on troubling behaviors exhibited by its AI models. Among these reports, ...

You don't have to hide under your bed for fear of AI quite yet.

OpenAI is pausing some work on Astra after testing found the AI could identify and exploit software vulnerabilities without human intervention. The Latest Tech News, Delivered to Your Inbox ...

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 ...

Artificial intelligence systems are showing behaviour that can undermine human instructions and safeguards, with more than ...

AI control is spreading across models, agents, data and platforms. CIOs need visibility into how those control layers ...

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 ...

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 ...

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 ...

AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether ...

French AI lab Mistral is betting enterprise AI buyers will value control over infrastructure as much as raw model performance ...

High-ranking members of the Senate Commerce Committee stand at odds with each other over how to best address “catastrophic ...