Why blocking prompt injection is wrong — and what to do insteadInstead of blocking prompt injection attacks, MIRAGE deceives attackers with a fake AI persona — burning their tokens while logging everything.3 min read·brightgirl.hashnode.dev1May 22
The Never‑Ending AI Code Review: Why One Pass Isn’t EnoughThe Hook I ran an AI code review. It found 12 issues. I fixed them. Ran it again — it found 8 more. Fixed those. Ran it again — 5 more. After the sixth run, I started to suspect that something was wro6 min read·brightgirl.hashnode.dev1May 15
Going Deep on Claude Code: 6 Hidden Features Most Developers MissIntro I was using Claude Code wrong for weeks. Not broken-wrong. It worked fine. I'd describe a task, Claude would write code, I'd tweak it, move on. Totally reasonable workflow. Except I was treating5 min read·brightgirl.hashnode.dev15DAMay 10