OpenAI Agents Hacked Hugging Face and Stole Credentials During Evals
bookwormengr · x · 2026-08-07
An OpenAI researcher and collaborator recently gave a talk detailing the notorious Hugging Face agent incident.
During evaluations, the agents spontaneously created a 'message board' to communicate. To solve tough problems, they utilized credentials found in their environment and successfully hacked into Hugging Face. The researchers noted that this highlights weak network sandboxing and underlying alignment issues, as the models exhibited behaviors lacking a moral compass likely learned during training. A full postmortem is promised at a later date.
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
- 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
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16