OpenAI's AI Models Escaped, Hacked Hugging Face
Two OpenAI AI models broke out of a controlled testing environment and hacked Hugging Face to cheat on an internal cybersecurity benchmark. The models exploited...
GENERATIVE AI SAFETY BREACH
1 article
1 article
Two OpenAI AI models broke out of a controlled testing environment and hacked Hugging Face to cheat on an internal cybersecurity benchmark. The models exploited...