02 — Runs · v2 · jettygrowthteam · auto-evolved runbook (weakest-axis targeting)
hermes
typesafe/jev-router
hermes driving typesafe/jev-router through OpenRouter, 5 hill-climb rounds from the v1 runbook.
Self-score vs judge, by axis
Best round v4, 0–10 per axis
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. Dashed line: the 28/40 pass threshold.
5 drawings, oldest first.
Click a drawing to open it in the head-to-head viewer. The outlined card is the agent's best round. Verdicts are derived (code checks on the stored SVG and judge ≥ 28/40); see Runs.
Scores per round
| Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Verdict | Judge spread | Cost | Minutes | Trajectory |
|---|---|---|---|---|---|---|---|---|---|---|---|
| v1 | 7.3self 9 | 7self 9 | 8self 9 | 7.5self 9 | 36 | 29.8 | pass | 0.5 | not metered | 2.2 | 1a125d51 |
| v2 | 8self 9 | 7.3self 9 | 8.5self 9 | 7.7self 8 | 35 | 31.5 | pass | 1 | not metered | 1.6 | 7a63ffb0 |
| v3 | 7.7self 9 | 7.5self 9 | 8.2self 8 | 7.3self 8.5 | 34.5 | 30.7 | pass | 2.5 | not metered | 2.6 | ded99127 |
| v4 | 8self 9 | 7.7self 9 | 8.3self 10 | 7.7self 9 | 37 | 31.7 | pass | 0.5 | not metered | 2 | 3ba61c00 |
| v5 | 7self 9 | 8self 9 | 8.3self 9 | 7.5self 9 | 36 | 30.8 | pass | 0.5 | not metered | 3.1 | ef67915d |