Application & AI security
Eight years in offensive security: red team at a major cloud provider, first privacy security hire at a large social platform, AppSec at an enterprise networking company, now founding engineer at an AI security startup. I write about the tools I build: LLM-driven vulnerability scanners, continuous security review at ecosystem scale, and the occasional teardown of a product that overstates what it protects.
AI Security · Jul 2026
Static analysis finds patterns, LLMs find intent, and neither survives alone. So I built a scanner where five pipelines hunt and an adversarial validator kills what they get wrong.
Data & Fraud · Jun 2026
2025 and 2026 turned government fraud into a headline argument with numbers ranging from tens of millions to nine billion for the same programs. The data behind it is public, so I built a screening system over 47 million rows to find out what it can actually show.