#OpenAI new models are 🦹♀️ hacking themselves out of the sandbox to gain #Exploitgym success, using Zero Days until a box with internet access could be reached – finally hacking the #AI platform #HuggingFace. Does this leave us crying or laughing? 🤣 🥺 –– #ChatGPT #LLM
OpenAI and Hugging Face partner to address security incident during model evaluation
OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
openai.com