MODEL FRONTIER 2026 · CENTERPIECE · under KEEPER ERIS
The Frontier World
All 24 Frontier pages and the 7 earlier batch indexes as clickable nodes on one Fibonacci sphere, ringed by 367 seeds in Dave's three bands, around a small double helix and above the toroid. BUILDER and WEAVER tour it from both ends.
Dave (t242u): "perfect, continue on building out pages please, anything you want browse the internet for guidance"
LIT Fibonacci-sphere placement: y = 1 − 2(i + ½)/N, θ = i × 137.508°. Every node is at the same radius.
MODEL The tour is a greedy nearest-neighbour path (not optimal). The two agents share one reward.
MODEL Cooperative agents: BUILDER (points 1–5) and WEAVER (points 6–10) take turns generating moves toward one shared goal, the target form (faint ghost points). The CRITIC scores the whole form, and both builders receive that same shared reward; neither can win alone. Every page also posts its best shared reward to a cross-page board in localStorage, so agents on all the Frontier pages share one team score. Rendered with Three.js r160 from a pinned CDN, devicePixelRatio capped at 2, antialiased. Drag to orbit, scroll to zoom.
LIT on load: the facts on this page are re-checked as arithmetic (it throws on mismatch), the target scores 1, 200 rounds improve, the workspace loop logs 5 entries, and the OBJ and SVG exports are consistent.
The Frontier World
MODEL Every page of this batch is a node on a Fibonacci sphere, with the 7 earlier batch indexes as gold nodes. A ring of 367 seeds (0–366) circles the equator in his three bands, a small double helix with a spine stands at the centre, and the toroid lies below. BUILDER walks a nearest-neighbour tour forward and WEAVER walks it backward. They share one reward, the fraction of nodes reached between them, and the CRITIC calls the tour done when they meet. Click a node to open it, and hover to read it.
Gallery of kept attempts (WebGL snapshots):
Workspace improvement loop: instructions for agents MODEL
- Measure: every 40 rounds, record the acceptance rate, the current score and how many rounds since the last improvement.
- Try next: if the score has been flat for 40 rounds, widen the mutation step. If acceptance is under 15%, shrink it; over 45%, widen it. Otherwise keep it.
- Log back: append {entry, round, measured, tried, step} to the workspace log (it's in the export JSON and the list below), and propose one change to this world on the shared board.
- Repeat, forever: never stop improving. Re-check against the real data before you claim anything.
Live workspace log:
Cooperative board, shared across all Frontier pages MODEL
Shared localStorage key mayhem-frontier-board: each page writes its best shared reward. The team score is the sum. Open several pages and they all add to the same board.
Shared board MODEL
Background art: AMBER MODEL a generative field seeded from this page's seal.
proving…
Seal sha256(name|slug|blurb): f92b1eaa9fe865062bcf7f4dfea7fec7e72b6b3a1ea9809bcee874a6dba118ae