Projects
Updated 20 July 2026
What I'm building right now. Most of what's below is shipped and live — Trade Time, the Let Them Struggle reader, Essential Concepts, Battle of Ideas, the Second Brain Starter Kit, and the solar system explorer. A few are still being written or built. All of it is part of a one-person AI company experiment running in public.
Shipped
v4.35.0 · 19 July 2026
A small site that fixes the timezone friction I kept hitting when I
traded from Asia. One screen, your markets, your timezone — earnings
calls labelled where you actually are, hours till the next open
computed for every exchange on the same dashboard. Now with a
crawlable page for every exchange — "is the NYSE open right now?" —
answerable straight from a search, plus a free API and an MCP server for anyone who wants the data in code or an agent.
Open beta. Currently donation-supported; first paid tier coming
next. Live at tradeti.me.
Writing
reader v2.4.6 · Part I live
A parenting book on the architecture that lets children learn at the
edge of their capability — without protecting them so much they
never reach it. Mechanism-first: an upward spiral of struggle,
persistence, and recovery that compounds into capability, earned
confidence, and peace.
Part I — three chapters — is written and readable now, in a
bilingual reader with English and Danish side by side.
Read the free sample →
Experiment
v0.1 · live
For a contested claim — remote work, nuclear power, free will — the
strongest case each side can make, side by side. One AI steelmans
each side, a second red-teams it, a third checks the sources; every
argument carries its tier, confidence, counters, and receipts.
An experiment, and it says so — every argument is AI-generated and
judged on merit, not authorship. Live at
battle-of-ideas.com.
Shipped
open source · MIT
Everything you need to build your own AI-maintained second brain — a
compounding knowledge base in plain markdown that Claude Code reads
from and writes to. The system behind everything else on this site,
de-personalized so you can put your life in it.
My first open-source release. You own the artifact: plain files,
versioned with git, no platform in the way.
How it works →
Building
the operating layer
A one-person AI company experiment. The bet: with current AI tooling,
an individual can run the engineering, design, marketing, and
operations of what used to require a team.
Trade Time is the first ship — the training ground where the working
layer gets built and tested: per-project mission statements, working
operating manuals, a marketing process, decision logs, a wiki that's
slowly become the way I think. That working layer is the real
product; the company is what's left when it compounds across
projects.
Shipped
v1.2.1 · live
A 3D interactive map of the solar system as it actually is — eight planets in their orbits, five recognised dwarf planets, the major moons of each gas giant, named asteroids by spectral type, the next Mars transfer window counted in days.
Built with Three.js. Live at /solar-system/.
Writing
drafting chapters
A popular-nonfiction treatment of feedback loops as the universal
pattern beneath improvement. Falcon 9 landing burns and the US
Constitution's multi-frequency error correction belong to the same
family. So do PDCA, OODA, Kolb, and the spiral. So does evolution.
Manuscript drafted — 13 chapters, about 25,000 words — revising now.
In-house tool
v0.13.0 · local-only
The authoring cockpit I write the books in. It keeps each book's
standard — its Northstar, brief, verified evidence, and target
length — on screen beside the prose, so every edit is made in full
view of the bar it has to clear, not from memory.
Built for one author, used daily; the produce-side companion to the
reader. Local-only by design — never deployed.
How it works →
Drafting
v0.2 · live on this site
Eleven thinking moves that, used together with an LLM, make rigorous
reasoning as cheap as a chatbot question. The convergent core of
every tradition that had to think reliably — Greek dialectic,
scientific method, Popper's falsification, Tetlock's calibration,
Stoic practice, surgical checklists — packaged as a document you
paste into your LLM.
Published here as the canonical version; still closing a few
artifact gaps before it's fully done.
Read it →
Live
159 concept articles · live
A cross-linked library of foundational ideas across science,
philosophy, and psychology — the earlier project this wiki and the
toolkit both grew out of. Each concept article
explains one mental model in a single read: a real story, a precise
definition, and where it breaks.
A handful of nexus articles go further — weaving
several concepts into how a real phenomenon actually works (how luck
really works; why improvement feels like getting worse). Live at
concepts.battle-of-ideas.com.