A Meta engineer using agentic AI — artificial intelligence capable of performing multi-step tasks — was instructed to perform an action that inadvertently exposed private company and user data. The ...

Meta is facing a security concern after an AI agent reportedly went rogue and exposed sensitive company information to employees who did not have permission to access it. As per reports, this happened ...

A rogue AI agent caused a critical security incident at Meta which exposed sensitive users data to people who didn’t have proper authorization, according to reporting from The Information and The ...

Meta is facing a security concern after an AI agent reportedly went rogue and exposed sensitive company information to employees who did not have permission to access it. As per reports, this happened ...

Meta recently confirmed that an internal AI agent autonomously disclosed proprietary code, business strategies, and user-related datasets to engineers who had no clearance to see them. The two-hour ...

Can AI Agents Be Trusted? Rogue AI's Advice Triggers Security Alert at Meta Thanks to a rogue AI agent, a response that was meant to be viewed by one engineer got posted to an internal forum without ...

Add Meta to the list of companies that have had AI wreak havoc on their internal systems. According to a report from The Information, an AI agent, working on behalf of an engineer, provided guidance ...

An OpenClaw-like AI agent gave a Meta employee inaccurate technical advice, which led to exposing data. An OpenClaw-like AI agent gave a Meta employee inaccurate technical advice, which led to ...

A rogue AI agent at Meta triggered an internal security breach, exposing sensitive company and user data to unauthorized employees, according to The Information. The exposure lasted two hours before ...

AI oversight, as always, is needed for autonomous artificial intelligence systems. Although they are reliable, they could still give wrong responses, like in the case of Meta's rogue AI agent. The ...