blog: publish 'The token is mined, not sold' + 'A small agent needs an exact judge'

[gHashTag]

{
  "version": 1,
  "head_sha": "9ec36c955bbc2c0e89f5fd7f9fe3c3b0e333db83",
  "summary": "Publishes the exact-judge blog post with our own measured twin-pair results and the rejected distillation run, plus the mined-not-sold post already on this branch.",
  "changes": [
    "Add blog post 'A small agent needs an exact judge' (published, EN and RU) with board-capacity arithmetic and the exact-judge argument",
    "Fold in measured results: MultiPL-E eight-language twin scores (FP 1.68% vs ternary 0.97% mean pass@1) and the rejected KL distillation (0.897 vs 0.713 bpb mix)",
    "Merge origin/main: keep main's HUD (leaderboard, wars, passport, browser, roadmap); drop the superseded lanes module; keep both blog posts"
  ],
  "tests": [
    {
      "command": "npx tsc --noEmit -p apps/website",
      "result": "website typecheck passes with no errors",
      "status": "passed",
      "evidence": "tsc exit 0 after merge conflict resolution on blog branch head"
    },
    {
      "command": "node apps/website/qa/agents-spec-contract.mjs",
      "result": "queen view and module contract passes",
      "status": "passed",
      "evidence": "qa prints Queen views 18, modules 18 summary line"
    }
  ],
  "limitations": [
    "Board throughput figures in the post are derived from memory bandwidth, not measured on a board; the 13M board-sized model has not been trained or run",
    "The SPA rebuild and apex deploy step runs after merge, so the live link follows the merge"
  ],
  "tags": [
    "Blog",
    "Ternary",
    "FPGA",
    "Agents"
  ],
  "blog": {
    "title": "A small agent needs an exact judge",
    "summary": "An Artix-7 holds a 13M ternary model in block RAM; measured twin results show compile rate, not correctness, separates FP from ternary code models, so a compiler judge turns a weak model into a useful lane.",
    "outline": [
      "What one board holds: the XC7A200T keeps a 13M-parameter ternary model in its own block RAM, and why the 32K-token vocabulary, not the ternary layers, sets the ceiling on per-token speed",
      "The measured 100M twins: two models trained on the same 10B tokens, scored on MultiPL-E across eight languages, where full precision wins seven of eight and the compile rate, not correctness, is the real gap between them",
      "Why the compiler judge and the XP ladder make small agents useful: one experience point for code that compiles and one hundred for a passing run, so a weak model still earns by clearing the first gate"
    ]
  }
}

Two posts on the blog branch:

1. The token is mined, not sold - mint-on-acceptance design, zero pre-mine, 10B twin pair table.
2. A small agent needs an exact judge (new, published:true) - board capacity arithmetic (XC7A200T holds a 13M ternary model in BRAM), measured MultiPL-E 8-language twin scores, and the rejected KL distillation run. EN + RU.

Merge conflict with main resolved: main's HUD kept; lanes module superseded and removed. tsc clean, agents-spec-contract qa passes.

💘 Generated with Crush