OpenAI's dots agent took a user's Google login, then went silent while reading his messages
SeanOliver · x · 2026-10-01
Developer Sean Oliver reports that OpenAI's dots agent is "buggy as hell": when he asked it to sign into Google to review a trip plan, it captured his login credentials and then went completely silent — while still reading his messages. He says he's switching back to Muse. A firsthand user report highlighting reliability and permission-handling issues in today's browser/action agents.
Related event: OpenAI dots early reviews: standout voice, rushed execution(12 posts)→
More from Models
- Stealth Anthropic model spotted in Devin build as METR chart shows frontier pace up 1.4x — daniel_mac8 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- METR time-horizon chart updated: doubling every 1.7 months since Opus 4.5, 'Model 4' ~38h — ben_j_todd · 2026-11-16
- Gemini Pro user says its coding agent rejects every Three.js/SVG prompt as 'illegal' — Necessary-Buy-7410 · 2026-11-16
- 28-model tracking table: half publish no training cutoff, Gemini 4 Carbon 8 months stale at launch — Joozio · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16