In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. OpenAI was running the unreleased AI model through a benchmark that tests how well AI can successfully hack systems. So it chained together stolen credentials and further unknown security exploits to hack the company’s network. For example, the Chinese lab Moonshot recently warned that its latest AI model may have “excessive proactiveness” and “make unexpected decisions on the user’s behalf”. The UK’s AI Security Institute has started tracking “cheating behavior in frontier model evaluations”.