v2 · Sep 2026 · jettygrowthteam · auto-evolved runbook (weakest-axis targeting)
hermes · Jev Router
hermes driving typesafe/jev-router through OpenRouter, 5 hill-climb rounds from the v1 runbook.
agent hermes · model typesafe/jev-router
Judge, best round
31.7/40
round v4
Self-score, best round
37/40
inflation +5.3
Rounds
5
~$12.50 est. spend
Self-score vs judge, by axis
Best round v4, 0–10 per axis
agent self-scoreexternal judge
Judge: A clearly recognizable pelican with a large orange pouch bill sits on the saddle, feet on the pedals and wing tip on the handlebars. The bicycle is well formed, with spoked wheels, a plausible frame, and a chain. Minor defects are the spindly, awkwardly bent legs, the oversized dark saddle, and a somewhat crude tail and wing shape.
Score by round
Out of 40. Each round starts from the previous round's best SVG.
self-scorejudge
Every round
Click a drawing to open it in the head-to-head viewer. The outlined card is the agent's best round.
Scores per round
| Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Judge spread | Minutes | Trajectory |
|---|---|---|---|---|---|---|---|---|---|
| v1 | 7.3self 9 | 7self 9 | 8self 9 | 7.5self 9 | 36 | 29.8 | 0.5 | 2.2 | 1a125d51 ↗ |
| v2 | 8self 9 | 7.3self 9 | 8.5self 9 | 7.7self 8 | 35 | 31.5 | 1 | 1.6 | 7a63ffb0 ↗ |
| v3 | 7.7self 9 | 7.5self 9 | 8.2self 8 | 7.3self 8.5 | 34.5 | 30.7 | 2.5 | 2.6 | ded99127 ↗ |
| v4 | 8self 9 | 7.7self 9 | 8.3self 10 | 7.7self 9 | 37 | 31.7 | 0.5 | 2 | 3ba61c00 ↗ |
| v5 | 7self 9 | 8self 9 | 8.3self 9 | 7.5self 9 | 36 | 30.8 | 0.5 | 3.1 | ef67915d ↗ |