shrub.json · 17 lines
{
"axiom": "F[++++f----G][++++S][-K]F[++++f----G][++++S][-K]F[++++f----G][++++S][-M]F[++++f----G][++++S][-P]F[++++f----G][++++S][-P]F[++++f----G][++++S][-M]F[++++f----G][++++S][-P]F[++++f----G][++++S][-P]F[++++f----G][++++S][-M]F[++++f----G][++++S][-P]F[++++f----G][++++S][-P]F[++++f----G][++++S][-M]F[++++f----G][++++S][-K]F[++++f----G][++++S][-K]F[++++f----G][++++S][-K]F[++++f----G][++++S][-K]F[++++f----G][++++S][-K]F[++++f----G][++++S][-K][++++f----G][++++S][+W][-K]",
"rules": {
"P": "F[--P][-P]FP-F--F",
"M": "F[--M][-M]F-F--F",
"K": "F[--J][-J]F",
"J": "F[--I][-I]",
"W": "F[--V][-V]F",
"V": "F[--I][-I]",
"I": "F",
"S": "F"
},
"angle": 22.5,
"iterations": 6,
"start_heading": 90
}round 1 of 5

A flat left edge, and 9,880 segments of loops behind it.
modelqwen/qwen3.8-max-primetasklsystem-pruned-coffee-shrub@v1, checks c1, harness h1date2026-09-25rounds5 of 8 allowed, 12 minutes on the clockcost$0.6444thinkingmediumtokens314,815 in, 28,354 out, of which 25,568 reasoningtime6 min 28 sfailedReads as a shrub: unreadable, geometry unclear, major, its note left no closing note · Sensible 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 5 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.fail
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
run 1 · 8r · $0.7113A wall of repeated stubs on the left and a tangle on the right, 3,559 segments.
run 1 · 3r · $0.3639
run 2 · 1r · $0.1328
run 3 · 7r · $0.6851A straight left side and branches sweeping right, in 906 segments.same 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.