TLDR Tech / InfoSec
Meta is Having Trouble with Rogue AI Agents
After a Meta employee posted a question on an internal forum, another engineer asked an AI agent to analyze the question, and the agent posted a response without the engineer's approval. The original poster took action on this advice and inadvertently exposed massive amounts of company and user data to engineers who were not authorized to have access to it. This follows a post last month by a safety and alignment director at Meta Superintelligence that an OpenClaw agent deleted her entire inbox despite being instructed to request confirmation before acting.
Read the full story