A Day of Intentional Maintenance: Using Claude Code as a Systems Partner
Most AI coding sessions are about building. This one was about knowing what you have, fixing what’s broken, and making the whole thing more defensible.
-
-
AI | AI Watch | Security Watch
Claude Mythos: Anthropic’s AI Can Now Find and Exploit Zero-Day Vulnerabilities
Anthropic’s Claude Mythos Preview can autonomously find and exploit zero-day vulnerabilities in every major OS and browser. Here’s what that means — and what Project Glasswing is doing about it.
-
Interesting Project to Watch: OpenAnt
OpenAnt is an open-source, LLM-based vulnerability discovery project from Knostic. Based on the project description, the workflow is designed to reduce noise by combining a detection stage with an attack/verification stage, so issues that survive both steps are higher-confidence findings. Current language coverage includes Go and Python, with JavaScript/TypeScript, C/C++, PHP, and Ruby marked as…