Consultancy Booz Allen Hamilton warned that autonomous AI systems could attack critical operational technology, The Register reported on October 15, in an article about the UK's Cyber Security and Resilience Bill. The Register also noted Anthropic's October 12 research on whether AI models could copy themselves between devices, which it described as extrapolation, not a demonstrated worm.
We summarize the warning as reported and have not reviewed the consultancy's analysis.
Source: The Register