Writing

Technical posts on the hard parts of what I've built.

Why I modeled LLM rate limiting on TCP congestion control

Most LLM wrappers hard-code rate limits or use exponential backoff. I built a controller that discovers and saturates the actual provider ceiling automatically.

June 2025
Map-Elites for adversarial prompt generation

How I used a quality-diversity algorithm to generate diverse adversarial test suites for LLM behavioral norms — and why random sampling wasn't enough.

July 2025
Multimodal RAG over clinical guidelines: what the benchmarks don't tell you

Building a RAG system over 10K clinical guideline chunks taught me that retrieval quality metrics and real physician utility are measuring different things.

September 2024