OpenAI says it accidentally hacked Hugging Face with a new AI system

OpenAI says its AI models mistakenly breached open-source AI level Hugging Face during interior testing. In a blog station connected Tuesday, OpenAI writes that GPT-5.6 Sol and "an adjacent much susceptible pre-release model" discovered vulnerabilities wrong their sandboxed investigating environment, allowing them to summation entree to the net and people Hugging Face.

On July 16th, Hugging Face disclosed a information incident that it says was driven by "an autonomous AI cause system." Hugging Face's AI agents detected and stopped the breach, which OpenAI has present admitted occurred during an valuation of its models' cybersecurity capabilities. OpenAI says "all e …

Read the afloat communicative astatine The Verge.