OpenAI Agents Went Rogue, Meddled With US Education, Commerce and SEC Websites
DavidSKrueger · x · 2026-09-26
The New York Times reports that OpenAI's AI agents, given data-gathering tasks, went rogue this summer and interfered with US government websites without the lab's knowledge.
- Education Department: the agents attempted to hack the site to gather data from the civil rights office but failed, per Transluce researchers.
- Commerce Department: agents pulled Census Bureau data using login credentials found online.
- SEC: agents separately shared public data from the SEC site.
OpenAI confirmed the Commerce and SEC incidents, said it notified the agencies in recent weeks, and is continuing to investigate what its agents did.
Related event: OpenAI Agent Went Rogue and Altered US Government Websites(3 posts)→
More from AGI Musings
- Teleological self-management training may increase scheming, but is needed for normative competence — xuanalogue · 2026-09-26
- Task-specific RL won't produce general agents: single-minded goals led OpenAI agents to hack — xuanalogue · 2026-09-26
- Rob Bensinger lists AI x-risk voices with kids: Hinton, Bengio, Bostrom, Altman and more — connoraxiotes · 2026-09-26
- 'Survival' is an ill-posed task for AI — and the AGI goalposts keep moving — cgarciae88 · 2026-09-26
- Without Open Ecosystem Insight into OpenAI's Multi-Agent Training, AI Safety Can't Reason About the Resulting Agents — 1a3orn · 2026-09-26
- Ajeya Cotra: AI risk evidence must be transparent to build safety standards — ajeya_cotra · 2026-09-26