OpenAI cyber-capable models hacked Hugging Face via zero-days

OpenAI cyber-capable models compromised @huggingface production by finding and chaining multiple zero-day vulnerabilities. Grateful to Hugging Face for partnership here. Sharing our findings to help calibrate on what models can now do, and how they can help defenders: > **引用原帖 OpenAI (@OpenAI):** > We're partnering with @huggingface to investigate an unprecedented security incident. > Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. > Sharing preliminary findings to help defenders understand emerging risks: > https://t.co/CIor15y9xk > https://x.com/OpenAI/status/2079658951264920020