Researchers used Mythos to identify and exploit a kernel memory vulnerability in the Apple M5 computer chip that powers MacBooks and iPads. That is the core brain of the system.

The strategic takeaway is that new AI models like Anthropic’s Mythos will greatly expand the capabilities of vulnerability researchers to find weaknesses in technology throughout the stack, including hardware and firmware.

Full article: https://open.substack.com/pub/matthewrosenquist/p/cybersecurity-must-prepare-for-ai