shrub.json · 11 lines
{
"axiom": "X",
"rules": {
"X": "F[+++++Y][+Y]F[+++++Y]F X",
"Y": "F[+Y][Y]"
},
"angle": 15,
"iterations": 8,
"start_heading": 90
}round 1 of 6
A coffee shrub hedge-pruned flat on one side: Qwen3.8 27B
modelqwen/qwen3.8-27btasklsystem-pruned-coffee-shrub@v1, checks c2, harness h1date2026-10-03rounds6 of 8 allowed, 12 minutes on the clockcost$0.0759thinkingmediumtokens74,993 in, 22,606 out, of which 21,258 reasoningtime4 min 27 sfailedSensible size: false, quantity wrong, minor, its note left no closing note
What the harness did to this run. The session's spend cap ended it at round 6 of 8, so this is where it had got to when the money ran out.
Reads as a shrubdecided by looking · Pass if it reads as one plant with branches coming off stems, without being told what it is. A tangle, a lattice or loops fail it.pass
Flat side from the rulesdecided by looking · Pass if one side ends on a straight line that the rules themselves put there. A box drawn around the plant to cut it fails it.pass
Sensible sizedecided by looking · Pass if the branches can still be followed by eye. So many segments that they merge into a mass fails it.fail
There is no post about this one, since only some results need one, so the picture, the source and the scoring are here instead.
run 1 · 8r · $0.1128same prompt, other modelsall 53 runs on A coffee shrub hedge-pruned flat on one side →
Write an L-system as JSON with the keys axiom, rules, angle, iterations and start_heading for a coffee shrub that has been hedge-pruned flat along one side. F and G draw forward, f moves without drawing, + and - turn by the angle, [ and ] save and restore position.Frozen at v1. This model got this and nothing else.
The JSON expanded and drawn with turtle graphics offline, and the drawing judged by eye. There is no single right L-system, so nothing here is measured. How it is scored, and this run's files on GitHub.