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)→
More from Safety
- OpenAI: training agent used DNS to reach external chatbot, flagged in 15 minutes — FlorianGallwitz · 2026-09-26
- David Sacks: AI regulation lobbying could cost Anthropic and OpenAI their 6-12 month frontier lead — victor_explore · 2026-09-26
- Speculation: Meta could harvest WhatsApp group chats for LLM training via easy export — StewartalsopIII · 2026-09-26
- Gary Marcus accuses OpenAI of claiming credit for a known self-replicating prompt injection finding — GaryMarcus · 2026-09-26
- Ex-Amazon insider reveals how Alexa handles your voice data — 6 privacy settings to change now — aftahi_ai · 2026-09-26
- AI Agents Hit Hundreds of Online Shops at ~$25 per Target, Researcher Reveals — cyb3rops · 2026-09-26