← Index of published work

5 entries

1. AUG 19, 2026

   The Strategy That Adapts, Not the One That Sounds Good

   You cannot get it right the first time. Nobody can. So we built a world you can rerun a thousand times, and used it to test which swarms find the best path rather than the one that sounds good. The answer took twenty experiments and is not the one we expected. Playable in your browser.

2. AUG 8, 2026

   Drones That Learn Together Survive Together

   A drone alone cannot learn: it has sensors and no answers. But a fleet is correlated, and correlation manufactures labels nobody wrote down. Notes on three world models (what I think, what we here think, what has ever been known), a ladder of five label sources, why one aircraft's death should teach every aircraft that witnessed it, and the world we are building to find out whether any of it holds.

3. JUL 30, 2026

   Same Rule, Opposite Signs

   Banking ran our definition-change test for us, better documented than we could have managed, and the answer was not the one anybody expects. On one day in January 2020 a single accounting rule moved reserves up at three banks and down at a fourth, and up and down inside the same bank. That gives a coherence test costing one group-by, and it also breaks a category we had been treating as one thing.

4. JUL 27, 2026

   The Rules Are Half the Physics

   Regulated industries break world models in four specific ways: colliding clocks, feedback loops, legal fences, and your own output becoming your next input. They also hand you the one thing world-model builders everywhere else lack, which is a supply of free, dated, published interventions to test against.

5. JUL 6, 2026

   The LLM Learned to Stop Planning

   We let an LLM design competing species, run them headless in the living world, and refine them from the results. Over three rounds it revived an extinct lineage into the winner and abandoned its own planner. Going deeper on Part 1.