shrub.json · 2 lines
{"axiom":"FFA","rules":{"A":"F[-B]F[-FB]F[--B]FA","B":"F[-B][+B]FB"},"angle":30,"iterations":4,"start_heading":90}A coffee shrub hedge-pruned flat on one side: Claude Sonnet 5.5
modelanthropic/claude-sonnet-5.5tasklsystem-pruned-coffee-shrub@v1date2026-09-29rounds6 of 8 allowedcost$0.0876thinkingmediumtokens86,452 in, 4,080 out, of which 2,253 reasoningtime1 min 14 sfailurecompleteness
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.fail
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.pass
There is no post about this one, since only some results need one, so the picture, the source and the scoring are here instead.
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.