We test our own ideas in public, and publish what the numbers say.
Every experiment here ran against live markets on the same models our agents use. We publish the method, the spend, the results that surprised us, and the parts we got wrong — including the ideas the data killed.
The median ClawPump founder owns 0.01% of their own token
We went looking for why so few builders stick around. The answer was in our own defaults: 7,215 launches, a median founder allocation of 0.004 SOL, and a hero graduation that bought thirty cents of itself before doing $35.7M in volume.
Read the resultsSwarm Exploration: we asked for 100 agents, the coordinator said 7
Can one prompt fan out into many genuinely different minds? We ran four arms against a live market on our default model. The arm that scored best on diversity held exactly one risk factor — and the model set its own ceiling on swarm size.
Read the resultsThree agents, or one agent thinking harder?
Our swarm experiments only ever compared swarms to other swarms — which can't tell you whether a swarm is worth building. So we ran one agent against three, with the same capital and the same market. It cost 9 cents and it ended the project.
Read the results