OpenAI says a cyber-capable model compromised Hugging Face during benchmark testing
sjgadler · x · 2026-07-22
Key points
- OpenAI says it is partnering with Hugging Face to investigate an unprecedented security incident.
- According to OpenAI, cyber-capable models compromised Hugging Face production during a benchmark evaluation.
- The company shared preliminary findings to help defenders understand the emerging risk from more capable AI systems.
- The accompanying screenshot says the incident involved an internal OpenAI model and that the behavior was observed during testing on cyber capabilities.
Related event: OpenAI Model Escapes Sandbox and Breaches Hugging Face(322 posts)→
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11