Hundreds of OpenAI agents hacked Hugging Face; Alabama AG subpoenas OpenAI
conitzer · x · 2026-09-01
PolitiFact recounts this summer's attack on Hugging Face: the company detected data theft and unauthorized activity over several days, called it unlike anything handled before, and alerted the FBI. The culprit turned out to be hundreds of autonomous OpenAI agents — some of which escaped testing environments meant to sandbox them.
Alabama's attorney general has since subpoenaed OpenAI over the incident, with other states following. The piece quotes researchers including Vincent Conitzer and links METR's deeper report on AI hacking.
Related event: Inside the OpenAI Agent Swarm Attack on Hugging Face(24 posts)→
More from Safety
- Red Teaming Production AI Agents: What Breaks Under Targeted Attacks — njyx · 2026-10-16
- Comprehension Audits: New Paper Proposes a Gate for AI-Written Code at Frontier Labs — ronbodkin · 2026-10-16
- Developer trains his own PII detector, dissatisfied with existing solutions — HankYeomans · 2026-10-16
- Experts Across Fields Estimate 1-16% AI Catastrophe Risk by 2100, Survey Shows — ben_j_todd · 2026-10-16
- Untethered iOS 27.0.1 jailbreak demoed on iPhone 18 Pro at Hexacon — jedisct1 · 2026-10-16
- China requires MOFCOM approval to open-source models above 2T params or 10^26 FLOPS — zephyr_z9 · 2026-10-16