Birthright Citizenship Ruling
A reflection on the Supreme Court's birthright citizenship ruling and what it says about America.
Archive
All posts, including hidden.
Skill Binaries and Dynamic Skills
Agent skills are more than prompt folders: they are part of a deterministic shell around a stochastic model. This post walks through two ariadne patterns, skill binaries and dynamic skills, that keep that shell testable, maintainable, and in sync with the codebase.
AI as My Research Workbench
AI is powerful, but it is not an oracle. It does not have a magic wand to create what you want exactly. You own the possibilities, and leverage AI to help at many different altitudes. Here's a concrete example of how I wrote the blog about space data centers. AI is the MATLAB, the Wikipedia, the Excel, the search engine, all packaged into a single tool that you can customize and extend. The capability is there; the human/AI interaction is still being sorted out.
The Case for Space Data Centers
With SpaceX IPO looming, let's take a look at the case of space data center, how realistic it is. As I poked around, I realize it's a matter of time before we run data centers in space, and that we really DO need Starship to pull it off economically. That is, if we look at the problem in the time frame of decades.
Your data, finally for you!
In the era of AI, your personal data can be a lot more valuable to you, as an individual.
A Saturday in Claude Code
Saturday morning, before exercise, I asked Claude one stray question. By afternoon there was a new repo, a pensive, four issues, and a working tool I'm using to write this post.
Saturday Pair — Transcript
The raw chat transcript that produced pair v1 — from 'can you inject text into a TUI?' to a working nvim-driven launcher with multi-session picker, image paste, and a pile of zellij gotchas. Companion to "A Better Claude Input Interface".
AI Native Company
What is an AI Native Company?
Building A Personal Brain Extension, A Teaser
Two weeks of building the substrate underneath an AI-native personal workflow: a base agentic development environment, a personal data access layer, a credential gateway, and a private canvas where ideas form, collide, and grow. Not ready for release yet — here's a sneak peek.
A New Home
Moving to an Astro based new home for my personal blog. And a new location.
A Tale of Two Harnesses
Adding tool calls to Parley on a flight, watching Claude make a mess, then drawing the architecture boundary for Claude and watching it execute flawlessly within it. The eureka: Claude Code is the execution harness, Parley is the interface for human to inspect and influence — both running on the same shared filesystem state.
WhatsApp GDPR Fine
A close read of the EDPB's €225M WhatsApp fine. The fine is a catch-22 for technical companies, that you need to write your privacy notice concise and easy to understand enough for laymen, yet need to be comprehensive enough to cover all basis. An extremely bad example of regulatory overreach, lacking resemblance of proportionality
Loom workflow system
A parley sketching "Loom": after parley, issues, and vision, a fourth repo-native tool for recurring agent-driven routines — the morning health check, the weekly oncall report. Together they form a kind of operating system for how a startup actually thinks.
Vision alignment tools
A parley on bridging business and tech vision. Mermaid is great for structure but weak for magnitude — Wardley Maps and Graphviz with weighted nodes do better. The deeper move: stop being the human translator and become the maintainer of a shared YAML schema.
what is "Graphviz (DOT language)"
A side-trip into Graphviz's DOT language: a declarative graph format from AT&T Labs where node width, color, and font size let you encode magnitude — exactly the dimension Mermaid lacks. The recommended pipeline: YAML domain model, Python script, DOT, SVG.
AI Workflow Evolved, One Year Jouney
Reflecting on a year of tinkering and adapting to the ever changing world of AI. After a year and 400+ commits on Parley.nvim, I'm convinced the future is humans setting up the environment, with full automation of the coding inside it. Here's my journey so far.
Conversation: further on the ideal of log.md
A follow-up parley: log.md is the least controllable file in an agentic issue structure because it depends on the model voluntarily writing during execution. Drop it. Let git history and plan.md diffs serve as the log instead.
Conversation: agentic state management
A parley conversation on why agentic coding state — issues, plans, logs — wants to live inside the repo, beside the code. Single-threaded topological execution as the sane default; minimal files per issue beat reinventing Jira on disk.
Personalized Software
When agentic coding lets a vim user write a custom mouse-aware floating picker because Telescope couldn't do that. The implication for SaaS: programmability stops being a nice-to-have, it becomes the moat.
My AI Coding Workflow
An iterative spec flow built on a small Makefile and a handful of markdown files — issue, todo, lessons, specs — cuts through the opaque magic of workflow tools. The trick is treating specs as sketches that bound the agent's search space, not exact behavior to confine it. Let AI bringing in world's knowledge!
The Week Everything Changed
The week of February 23, 2026: Dorsey's layoffs, Cloudflare's one-engineer Next.js rewrite, Karpathy's tweet. Picking up Conductor, OpenCode, and OpenSpec over a weekend and shipping 15K lines on Parley — agentic coding is no longer the toy it was ten months ago.
AI as the Next Abstraction Layer
LLMs are fundamentally stochastic, but that's not new — the whole ML field always was, and it worked. The interesting question is how to ground stochastic computation in deterministic domains. Two paths: build a deterministic shell around the model (coding), or apply it directly where the domain itself tolerates noise (recruiting, marketing, design).
To Type or Not to Type
Mainstream type systems are simultaneously too strong (closed-world assumptions hurt during change) and too weak (can't say "positive integer" or "age between 0 and 200"). For startups in unsettled domains, duck typing wins — types are a luxury you afford after product-market fit.
Data vs. Anecdotes: Which to Trust?
Two quotes about data and intuition. "I trust your data, and my intuition" subtly inverts the knowledge hierarchy and subjugates domain expertise to authority. Bezos's version — when anecdotes disagree with data, investigate the measurement — is the better instinct.
On Organic Process
Eight questions to ask before introducing a new process. People overestimate how much process helps, underestimate the cost of maintaining it, and assume it'll work just because it exists. And remember, processes rarely die on their own — the ritual often outlives the purpose.