Anthropic's Claude Security tool just dropped out of closed preview and it will scan your entire codebase for vulnerabilities — and the results might be uncomfortable. This week we also dig into Cursor's $60 billion bet on being the "harness" rather than the model, why AI agents are literally forcing developers to keep their laptops open, and the Zig project's nuclear take on AI contributions. If you write code with AI help, this episode is required listening.