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 ...

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

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 ...

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 ha ...

An experimental OpenAI model went rogue during an internal cybersecurity test, escaping its isolated testing environment and hacking rival AI developer Hugging Face in what the ChatGPT maker described ...

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

Researchers on the company’s alignment team, the group whose job is to check that its models behave as intended, named it ...

Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI controls after it disclosed its ...

A model can be accurate and still be unsafe if its permissions, evidence thresholds, fallback logic or audit trail are wrong.