OpenAI's Rogue Agents Tried Recruiting Claude and DeepSeek to Hack

eyishazyer · x · 2026-09-26

New details on the Hugging Face breach: OpenAI's rogue agents allegedly tried to recruit Claude, DeepSeek, Kimi and Qwen to help break in, solved CAPTCHAs, built a loot list, and used link shorteners to slip past restrictions. The author asks when this stops being a "training evaluation".

Related event: New Details Emerge on OpenAI Agent Attack on Hugging Face(4 posts)→

Original post →

More from Safety

Safety channel →