Writing

Essays land when the numbers do.

Nothing published yet. The first essay ships with the first real measurement. The schedule below is the commitment, kept honestly.

Scheduled

titles will change · dates won't slip quietly

I added evals to my AI writer. Here's what was actually broken.

A production writer, scored for the first time. What the baseline says, and what vibes never caught.

Q3 2026

Context-stuffing vs. real RAG: four approaches, measured on my own data.

Stuffing, keyword, semantic, hybrid+rerank. Same queries, same content, real numbers. One winner ships.

Q4 2026

I cut my AI cost with zero quality loss. Here's the trace.

Where waste hides in a production LLM funnel, and the proof the savings cost nothing.

Q1 2027

I red-teamed my own AI products.

Attack success before and after guardrails, benign-refusal rate alongside. Refusing everything isn't safety.

Q2 2027