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.
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.
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.
What is an AI Native Company?
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.
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.
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.
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.
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 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.
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).
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.
Andrew Grove treats management as a production system, but the deeper claim is that information workers are managers — their raw material is information, their output is influence. In modern Big Tech, being "a manager" isn't a promotion. It's just different work.
Healthcare's fragmentation isn't an accident — it's federalism plus misaligned incentives, where EHR vendors profit by locking customers in. NexHealth's Synchronizer attacks the problem at the technical layer, with the law (and a recent 4th Circuit ruling) on its side, eventually.
How WhatsApp actually worked: Erlang/BEAM/OTP all the way down, the biggest machines money could buy, location-transparent actors, and code hotloading as deployment. They bucked every Cloud Computing canon and ran the world's largest messaging system with a tiny team.
Joining NexHealth as Director of Engineering. Software and AI are eating the world — it's time they ate healthcare too. The mission: build the infrastructure layer that lets EHRs, doctors, developers, and patients actually exchange data.
After more time pair-coding with Claude Code, the awe wears off. It's an overly eager junior with raw smarts and no taste — fast, useful for onboarding, but prone to ridiculous code that you'd reject from a new grad.
Leaving Meta after a decade. The Facebook of the Red Culture Book — "What would you do if you were not afraid?" — is not the Meta of muscular energy and top-down NFT, Messaging Interop, and Metaverse. A goodbye, and a question worth carrying into the next chapter.
Five days, ten thousand lines of Lua, no prior experience with the language. Claude Code is not auto-complete — it's a giant pattern-matching machine that needs grounding through tests and architecture. The 25x figure is cheeky, but the shift is real.
First real run with Claude Code: 500 lines of Lua changes from someone who hadn't written a line of it before. Not AGI, not a junior engineer replacement — a powerful, imprecise statistical machine that makes knowledge workers dramatically more effective.
Introducing Parley.nvim: a Neovim plugin that turns chatting with an LLM into a living, editable transcript. Trees of follow-up questions, annotations, and context compaction via assistant-summarized lines — built collaboratively with Claude Code.
Six years inside WhatsApp's improbably quiet Menlo Park building, where the motto was Keep It Simple and the F word was Focus; and where you hot-loaded code straight into production, no code review. It worked.
The stock ChatGPT app is awful for organizing long research threads. Running gp.nvim in Neovim instead — full transcript, freely editable, customizable syntax highlighting — turns a chat into the building blocks of a real research report.
How to run a GitHub Pages blog from a private staging repo with a publish.sh script — drafts in private, posts in public, and an identity that's not trivially traceable back to you. A practical walk-through, not a manifesto.
A new-Mac setup checklist for the terminal-and-Neovim crowd: Ghostty, zsh, Oh My Zsh, yadm for dotfiles, Homebrew bundles, and the AI tools (Claude Code, Codex, Gemini CLI) now sitting alongside the classics.
