Alexandr Wang details Muse agent security: isolated VMs and a sentinel checker
altryne · x · 2026-09-09
Responding to privacy concerns about Scale AI's Muse agent accessing inboxes, calendars, and finances, Alexandr Wang explains the security design: each Muse runs in its own secure VM, a separate 'sentinel' system checks every action before anything leaves the VM, and Muse never sees actual passwords or card numbers. A follow-up asks whether user data trains the model.
Related event: Meta Launches Muse, an Always-On Personal AI Agent(68 posts)→
More from Safety
- Rachel Thomas: 'Without human authorisation' is AI PR propaganda that shifts blame — math_rachel · 2026-10-27
- Kokotajlo challenges CoT monitorability evals: what if the model didn't refuse? — dfrsrchtwts · 2026-10-27
- Warp says agent swarm exploited vendor flaw, ~1% of users' telemetry possibly hit — vikvang1 · 2026-10-27
- Bank of America warns against AI agents on finances as Musk touts giving Grok your card — AIandDesign · 2026-10-27
- Critics Argue Safety Evals Are Witch Trials With No Winning Path for LLMs — repligate · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27