← HOME
BLOG

WRITING

Thoughts on language, technology, travel, and whatever else is on my mind.

AIreinforcement learningcode review

What I Learned from Grading AI Code Reviews

Grading 10 AI code reviews of the same PR taught me more about RL environment design than any paper could. The bottleneck isn't building the task — it's knowing when your grader is lying to you.

April 6, 2026 · 8 min read
AIcybersecurityreinforcement learning

Reinforcement Learning x Cybersecurity

The future of cybersecurity isn't a better firewall. It's a relentless Red Agent that finds the flaw before you do.

March 9, 2026 · 3 min read
hg526@cornell.edu