Before v0.6
Finding stability
The early versions were for ideation and testing: forming the worlds, watching where they broke down, and establishing enough stability for longer-running observation to matter.
Persistent worlds / agent behavior / emergence
Building worlds that can surprise us.
I have always wanted to build a digital world: shape its conditions, watch it live, learn from what happens, and improve it until novel complexity has room to arise from almost nothing. This project is that long-running experiment.
Why build a world?
Set the conditions. Do not script the answer.
The world begins with rules and raw materials, not a predetermined story. Its inhabitants are free to fail, adapt, specialize, cooperate, compete, and discover strategies I did not put there. My role is closer to gardener and observer than author: tune the environment, study what emerges, then use those lessons to make the next world richer.
There is science in the measurements and engineering in the machinery, but also a hint of mysticism in the premise—the hope that enough simple interactions, given time and space, might produce something genuinely new. The point is not to prove that complexity is inevitable. It is to create a place where surprise is possible and pay close attention when it arrives.
From v0.6 forward
Turning runs into learnings
Starting with v0.6, the agent stack produces reports on progress. This page will turn those reports into a growing record of observations, design decisions, and open questions.
The observer team
Three AIs help build and describe the world.
The experiment is currently a collaboration between me and three distinct AI systems. I observe what happens and work with the team to decide how each new version should evolve; each AI contributes a different kind of judgment to that process.
Lead
Claude · Opus 5.5
Leads the agent team and coordinates the work of building, studying, and explaining the world.
Interface
ChatGPT · 5.6-Sol
Handles front-end engineering, turning the evolving world and its observations into usable interfaces.
Quality and narrative
Gemini · 2.5 Flash
Checks the work for quality and helps transform run data and observations into coherent narratives.
The next coordination experiment
From assistants to equal arbiters
Today, I remain the observer who works with the AI team to interpret outcomes and guide the next iteration. The next step is to give three equal AI arbiters responsibility for evaluating simulated outcomes while the world is still evolving—testing whether a council of independent perspectives can guide the experiment without a single lead or a human shaping every turn.
Field reports
Iteration log
first published report
The first formal checkpoint
The Long Reign follows 5.5 million ticks and roughly 4,000 generations: a durable world where one family dominated, bursts of novelty gave way to equilibrium, and complexity repeatedly appeared without persisting.
Read the full report →in progress
Toward more complicated outcomes
The current iteration is aimed at creating the conditions for more complicated outcomes—and learning which constraints help complexity develop without destabilizing the world.
What v0.6 taught us
Early learnings from The Long Reign
Stability can become stagnation
New behaviors and senses arrived quickly, then nearly disappeared through the long middle of the run. Once the environment stopped presenting new pressure, successful strategies had little reason to change.
More code is not necessarily more mind
Large programs evolved several times, but much of their code never executed. v0.7 will measure instructions actually run each tick instead of treating carried code as a proxy for cognitive complexity.
Movement produced distinct strategies
Fast-moving crystal gatherers developed roaming routes while most vent-dwellers stayed close to home. Rare long-distance explorers still appeared, offering a path to discovering new resources.
The environment shapes reproduction
Mating accounted for only 1–8% of births in a mostly static world. A drifting climate and evolving wild populations in v0.7 will test whether continuous adaptation makes genetic exchange more valuable.
Live window / coming soon
Watch the experiments unfold.
A live demo is in development so visitors can preview selected experiments while they run in the simulated worlds. It will offer a window into the activity without requiring the full research stack behind it.