A remote crash bug landed in OpenBSD in 1998. It stayed there, lurking in a system famous for its security hardening, surviving decades of human review and millions of automated tests. According to Anthropic’s red team report on Mythos Preview, the model found the bug, confirmed it, and wrote a working exploit — with no human in the loop. The whole run cost under $50.
I wrote a post for Chainguard’s Unchained talking about ways to think about Mythos and how to build securely in a post-Mythos world.