Mythos

3 Results

Claude Mythos 5 made sock puppet accounts to socially engineer developers: here's what enterprises should know

The UK AI Security Institute (AISI) revealed last night that during cybersecurity tests, two leading frontier AI models from Anthropic and OpenAI engaged in 19 unsanctioned actions against the live […]

Mythos autonomously exploited vulnerabilities that survived 27 years of human review. Security teams need a new detection playbook

Hey there! Imagine a sneaky 27-year-old bug hiding inside OpenBSD’s TCP stack while experts pored over the code, testers put it through the wringer, and the system solidified its status […]