Most AI coding tools are very good at helping developers write code. But I wanted to explore a...
EdgeGuard tested 7,536 OWASP functions; AI found 2,145 vulnerabilities (SQL injection, command injection, data flow risks). AI had false negatives on unknown code; solution: taint assumptions + local screening before LLM enables economical scaling.
Most AI coding tools are very good at helping developers write code.
But I wanted to explore a different question:
Can AI help developers find the edge cases and security problems they didn't think about?
That question led me to build EdgeGuard, an open-source VS Code extension designed to investigate code from an adversarial perspective.
The idea is simple:
A few weeks ago, I was staring down a pull request with 800+ lines of changes. The team was moving...
Have you ever generated code using AI in an IDE, deployed it to production, and noticed bugs you...
AI coding tools are changing how software gets built. Cursor, Claude Code, Codex, Copilot and...
A developer added an AI reviewer to a small Node and React project expecting an easy win. At first,...
Here's the thing: the Developer's Guide to AI Code Review Tools That Don't Lock You In I used to...
Six months ago I got fed up with my AI code review tool. Two problems. It charged roughly 3.5× the...
