// The catalog
Three flavors of work end up here. Posts are short, opinionated, build-in-public. Research are working papers with citations. Projects are the things being built.
// Posts
Tight, opinionated, build-in-public. Lessons learned and milestones hit.
Three days from scaffold to running system. Thirteen specialist agents, a filing-gate compile pipeline, weekly publishing cron, Korean i18n toggle, agents that ship their own PRs with approval. Plus the discipline not to start V3.
I've shipped a sequence of personal AI projects: Neural, Synapse, Argus. The thinking compounded; the substrate didn't. Here's the bridge.
// Research
Working papers on AI security, agentic systems, compliance, and development playbooks. Cited.
I made my regulatory AI score reproducible, then made it report its own uncertainty, and it still wasn't a real measurement. A score of 0.5523 looks precise. It was four decimals of false precision over a five-band rubric, blended across regulators who were measuring different things. This is how I made the number mean what it says.
I built an AI that scores regulatory submissions, spent a week making the score reproducible, and called it a win. It wasn't. Reproducible and reliable are not the same word, and the gap between them is where a score you can actually trust lives. This is how I closed it: sampling, a stabilized consistency engine, and a harness to check the score against a human.
When an LLM sits in a regulated workflow, a successful prompt injection is not just a security incident. It is potentially a material misrepresentation, an audit trail failure, or a reportable breach. GRC teams are not treating it that way yet.
// Projects
The things being built. Personal AI substrate, the blog you're reading, and what comes next.