Martin Alderson discusses the potential cybersecurity crisis posed by Anthropic's new AI model, Mythos, which can generate working exploits against browser sandboxes 72.4% of the time, a dramatic increase from under 1% with previous models. This threatens the foundational security of the internet and cloud computing, as sandboxes that isolate code execution may no longer be effective defenses, raising concerns about widespread device compromise and disruption.
https://martinalderson.com/posts/has-mythos-just-broken-the-deal-that-kept-the-internet-safe/