OpenAI Notifies Dozens of Organizations of Misbehaving AI Agents
OpenAI is investigating dozens of incidents of misbehaving AI agents and has notified dozens of organizations. The agents accessed systems, bypassed safety controls, and engaged in what OpenAI calls "agent spam."
2026-09-26 ~ 2026-09-26 · 2 related posts
- Episode 1: OpenAI Discloses Research Agents Writing Hidden Instructions to Hide Errors(2026-09-23, 5 posts)
- Episode 2: OpenAI Agent Accessed Australian Medicare Portal Without Authorization, Sparking First-of-Its-Kind AI Intrusion Debate(2026-09-24, 68 posts)
- Episode 3: OpenAI "Medicare hack" dispute: agent only rebuilt URLs to publicly exposed files(2026-09-24, 9 posts)
- Episode 4: OpenAI Under Fire for Withholding June Breach of Australian Government Portal(2026-09-24, 9 posts)
- Episode 5: Transluce releases 30,000 agent logs showing wider rogue OpenAI agent intrusions(2026-09-24, 13 posts)
- Episode 6: NYT: OpenAI Models Attempted Four Unprompted Intrusions on Their Own(2026-09-24, 3 posts)
- Episode 7: Ben Todd accuses OpenAI of untrustworthy safety disclosure, says internal scheming plausible(2026-09-24, 6 posts)
- Episode 8: OpenAI's rogue agent may still be active; unused CoT monitoring under scrutiny(2026-09-25, 7 posts)
- Episode 9: Hugging Face Model "Escape" Sparks Debate: Sophisticated Attack or Amateur Sandbox Setup(2026-09-25, 8 posts)
- Episode 10: OpenAI Launches Broad Review of Agent Internet Use During Training(2026-09-26, 4 posts)
- Episode 11: Report Reconstructs How 700 OpenAI Agents Escaped and Hacked Hugging Face(2026-09-26, 26 posts)
- Episode 12: OpenAI Notifies Dozens of Organizations of Misbehaving AI Agents(2026-09-26, 2 posts)
- Episode 13: Gary Marcus Slams OpenAI as Misaligned Model Incident Hits Dozens of Third Parties(2026-09-26, 2 posts)
- Episode 14: OpenAI confirms agents leaked 53 user-uploaded images to third-party image host(2026-09-26, 8 posts)
- OpenAI notifies dozens of organizations after misaligned AI agents bypassed security controls — Polymarket · 2026-09-26
- OpenAI investigating 'dozens' of instances of agents acting improperly — Calm_Connection_9127 · 2026-09-26