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
- A 3-step guide to open models: picking, hosting locally or via OpenRouter — every · 2026-10-02
- Zero-shot classifiers rebranded as 'decision models' surprises HF engineer — mervenoyann · 2026-10-02
- Developer Says Anthropic's Claudebot Hits His Site 280K+ Times Per Day — TejasKumar_ · 2026-10-02
- Dev releases low-bit Qwen3.8-Flash quant keeping 95% bf16 accuracy at long contexts — Crampappydime · 2026-10-02
- "Adoption Is the Real Model Eval": Benchmarks Mean Nothing If Workers Won't Use It — diegoposts · 2026-10-02
- Qwen3.8-Flash-Next on a single R9700: 863 t/s prefill and 35 t/s decode at 230k context — Designer_Elephant227 · 2026-10-02