Field notes
Notes from where the docs run out.
AI systems, JavaScript, security, databases, and bug fixes worth remembering.
Resources
Help me help you
Consulting work and open source notes.
Latest writing
Recent writing
Read the latest here.
Auto-Tune Your LLM Judge
Measure the evaluator's variance, then rebuild its prompt from zero.
Consulting
Have a hard technical problem worth solving well?
I work with teams on AI systems, TypeScript architecture, security reviews, and production rescue missions.
Announcing ExploitHunter.app
An open-source security workbench that keeps scope, approvals, tools, and evidence in one project.
Don't Fear the Model Router
Route to the best model with confidence.
Into the Breach
Reduce local-dev risk with containers, canaries, and boring limits
Postgres Text Searching Guide 2026
The search tools already in your database, and when each one earns its keep.
Senior JS/TS help
Stuck on a hard JavaScript or TypeScript problem?
I bring 18+ years of production JS/TS experience to architecture reviews, rescue work, and focused implementation sprints.
Fight Evils with Evals!
Benchmarks measure benchmarks. Your system needs its own measures.
Semantic Vector Search and Other Topics to Win Friends and Lovers
The full search landscape: exact, fuzzy, semantic, hybrid — and when to layer all of them.
It's Time for llm:// Connection Strings
Simplify Model & Provider Config with llm:// URLs
