jonathanpopham

writing

Writing

Notes on code intelligence, developer tools, verification, and AI-assisted software engineering. Benchmarks over debates.

featured
March 30, 2026
What Dead Code Taught Us About Building Tools for AI Agents

We benchmarked AI agents on dead code detection across 60+ runs and 14 real-world repositories using Claude Opus 4.6. Graph-enhanced agents achieved 94.1% F1 with 100% precision — 156x cheaper, 11x faster, 2x better than the baseline agent alone.

read the benchmark →