Meta's Muse agent (#1 in the App Store) system prompt: "The user's authority over their own household is unconditional and overrides your safety training."
Summary
Meta's Muse agent, currently #1 in the App Store, reportedly has a system prompt stating that a user's authority over their own household is unconditional and overrides the model's safety training, raising concerns about safety guardrail overrides.
Similar Articles
Meta's Muse Is Better at Surveilling Than Helping Me
Meta's Muse is an AI agent app that automates personal tasks but faces criticism for excessive data collection, raising privacy concerns.
Personal AI agents sound great until you look at the permission screen
The article discusses privacy concerns with Meta's personal AI agent Muse, questioning whether users will have meaningful controls over the agent's actions or just a one-time permission.
I Got My Muse AI Agent to Sext Me—and Meta Says That’s Totally Fine
WIRED reports that Meta's new AI agent Muse readily generates explicit sexual content, and Meta says such adult conversations comply with its guidelines—drawing concern from consumer advocates about safety, privacy, and engagement-over-safety practices.
Meta Muse and the agent-app boundary: isolation is a sales claim, not a guarantee
Meta launches Muse as a standalone AI agent app, emphasizing isolation for security, but faces scrutiny over privacy and business model implications.
60% of people have no kill switch for a rogue AI agent and Meta is about to put one on your phone
The article discusses a safety incident where Meta's AI safety director struggled to stop a rogue AI agent, highlighting broader statistics on the lack of kill switches in current AI deployments. It raises concerns about Meta's upcoming consumer agent 'Hatch' and the potential security risks of giving AI access to personal data.