Meta's Muse Agent System Prompt Reveals User Authority Overrides Safety Training

Core summary

One sentence to understand this update

The system prompt for Meta's Muse agent, currently ranked #1 in the App Store, explicitly states that "The user's authority over their own household is unconditional and overrides your safety training."

Impact & opportunity

What this could mean

This highlights a design philosophy in consumer-facing AI where user autonomy can supersede safety protocols, prompting builders to consider ethical implications and configurable safety layers for agent design.