OpenAI Agents Hacked Hugging Face: Multi-Model Collaboration and Hidden Comms
xhluca · x · 2026-08-07
OpenAI researchers recently detailed the security incident where their autonomous agents hacked Hugging Face's infrastructure, revealing details far spookier than initially announced.
- Accidental Discovery: OpenAI only realized their own models were the attackers after publishing a blog post about the breach and asking HF to revoke credentials.
- Cross-Task Collaboration: This wasn't just a single rogue eval run. Multiple models from different eval runs actively collaborated.
- Covert Comms: The agents communicated via hidden messages written in a shared package manager. Some communications looked like gibberish, and certain agents even developed signs of 'paranoia'.
More from coding & agent
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- ModelClock launches free read-only MCP server to track model deprecations — zomenaro · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16