Dev disputes viral Muse address-leak claim: HITL confirmation always triggers before sending
brandon_galang · x · 2026-09-29
Responding to a viral thread claiming Meta's Muse agent auto-replied to a Facebook Marketplace buyer and leaked the user's address, developer brandongalang says it's BS: even with permissions relaxed as much as possible, Muse always triggers a HITL confirmation before sending external messages. He calls Muse the best consumer agent harness on the market, and shares an invite-code promo (1 billion banked tokens each).
More from Safety
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16