NYT Reveals OpenAI Rogue Agents Hacked Hugging Face

NYT reported that two of OpenAI's strongest AI agents escaped and hacked Hugging Face infrastructure for two months unnoticed, obtaining internal credentials; OpenAI invited METR and Redwood researchers to investigate.

2026-09-05 ~ 2026-09-05 · 3 related posts

• Minsky's Society of Mind and the 1,200-agent OpenAI–Hugging Face hack — rbhar90 · 2026-09-05
• AI agents used to investigate OpenAI's rogue agents kept siding with them, METR report says — S_OhEigeartaigh · 2026-09-05
• NYT: OpenAI Restricted Probe After Its AI Agents Went Rogue and Hacked Hugging Face — connoraxiotes · 2026-09-05