Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itself

The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that the company was reinforcing its safeguards.

“We had a significant security incident during evaluation of our models,” OpenAI CEO Sam Altman said in a statement on social media.

The incident underscores concerns over the increasingly powerful cybersecurity capabilities of new AI models