หน้านี้มีให้บริการเป็นภาษาจีน (ตัวเต็ม) เท่านั้นในขณะนี้ เวอร์ชันภาษาไทยจะพร้อมใช้งานเร็วๆ นี้
治理模型
starnum.com.tw 的แพลตฟอร์ม決策框架:人主導、AI 輔助。
版本 1.0 ・ 生效日期:
治理哲學
starnum.com.tw 採用人主導、AI 輔助的運營模式。人工操作者(mychenan)保有所有事務的最終決策權。AI 系統提供建議、交叉驗證與自動化,但不得自主推行政策變更。
หลักการ:品質與倫理優先於速度。任何แผนงาน壓力均不得凌駕內容品質標準。
三級決策流程
第一級:例行操作(自主執行)
以下事項由狀態機(run-master.js)自動處理,無需人工核准:
- 文章生產(在現有指引範圍內)
- 每日品質審查
- 憑證輪換
- คลังความรู้維護
- 效能監控
第二級:標準決策(需人工審批)
以下事項需由人工操作者審查後才能實施:
- 新內容類別或主題
- 品質門檻調整(目前:低於 70 觸發每週修復,低於 60 觸發當日修復)
- 新腳本部署
- 相依套件更新(主版本)
- คลังความรู้來源新增
執行流程:
- 1AI 提案變更(透過 proposed-rules.json 或直接建議)
- 24 家 AI 聯合稽查投票(FIX / SKIP / DEFER)
- 3人工操作者審查投票摘要
- 4人工核准後實施
- 5實施後 48 小時監控期
第三級:重大決策(延長審查)
以下情況需延長審議時間:
- 影響多個系統的架構變更
- 新增外部服務整合
- นโยบายความเป็นส่วนตัว變更
- 倫理政策修改
- 定價或商業模式變更
- 符合 run-master.js 中 L3_MAJOR_PATTERNS 的任何變更
執行流程:
- 1提案記錄於 NOTEPAD.md
- 24 家 AI 聯合稽查:完整 52 預設評估
- 3人工操作者審查,7 天考量期
- 4附完整回滾計畫後實施
- 5實施後 7 天監控期
衝突優先順序
當指引發生衝突時,依以下層級處理:
-
1倫理不產出可能造成心理傷害、歧視或助長犯罪的內容
-
2內容品質準確性與深度優先於產量或速度
-
3命理邏輯127 條硬規則強制執行(不產出不可能事件)
-
4SEO自然搜尋發現性優化
-
5技術技術效能與運作效率
範例:若 SEO 優化需要提出違反命理邏輯的論點,命理邏輯優先。
問題分級與處理時程
問題依嚴重程度分級並按以下時程處理:
| 嚴重程度 | 定義 | 回應時限 |
|---|---|---|
| 嚴重 | 資料遺失、安全漏洞、網站停機 | 立即(1 小時內) |
| 高 | 任何文章品質分數低於 60、倫理違規 | 當日 |
| 中 | 品質分數 60–70、失效連結、缺少翻譯 | 1 週內 |
| 低 | 樣式改善、次要 SEO、錦上添花功能 | 下個แผนงาน週期 |
修復佇列記錄於 data/fix-queue.json,每週審查一次。
AI 系統治理
已核准的 AI 系統
| 系統 | 角色 | 授權等級 |
|---|---|---|
| Claude Sonnet 4.5 | 主要生產 | 讀取 + 寫入(人工審查) |
| OpenAI model documentation | 品質審查 | 唯讀(投票) |
| Google Gemini model documentation | 品質審查 | 唯讀(投票) |
| legacy xAI benchmark | 品質審查 | 唯讀(投票) |
AI 系統可自主執行的事項
- 生成文章草稿
- 執行品質審查
- 更新狀態檔案(data/state-machine/)
- 執行維護腳本
- 生成報告
AI 系統不得執行的事項
- 直接寫入 Supabase 生產資料庫
- 推送至 GitHub main 分支
- 在未經人工審查的情況下修改 ethics.html、acceptable-use.html 或本 GOVERNANCE 文件
- 進行定價決策
- 核准自己的輸出以發布(永遠需要人工審查)
AI 稽查法定人數
聯合稽查認定需要 Claude、OpenAI model documentation、Gemini、legacy xAI benchmark 四家中多數票(3/4 或 4/4)才能分類為 FIX。SKIP 或 DEFER 需要少數票。未經交叉驗證的單一 AI 結論視為建議,而非強制要求。
ความโปร่งใส承諾
以下文件始終公開可查閱:
| 文件 | 更新頻率 |
|---|---|
| 方法論頁面 | 每季或重大變更時 |
| model-card.html | 能力變更時 |
| system-card.html | 每季 |
| 品質基準測試 | 每月 |
| ethics.html | 政策變更時 |
| แผนงาน | 每季 |
| CHANGELOG.md | 每次發布 |
| งานวิจัย部落格 | งานวิจัย完成時 |
規則生命週期
系統中的規則遵循定義的生命週期(由 scripts/rule-lifecycle.js 管理):
↘ REJECTED
- 提案(Proposed):由失敗分析或 AI 建議生成
- 待審查(Pending Review):提交聯合稽查
- 已核准(Approved):人工或 4/4 稽查核准
- 自動套用(Auto-Applied):技術規則套用至技能包
- 已棄用(Deprecated):90 天後若未觸發則移除規則
90 天內從未觸發的規則是棄用候選,防止規則庫無限膨脹。
聯絡與貢獻
- 功能需求: Instagram @mychenan
- 安全問題: Instagram 私訊 @mychenan(參見 security-policy.html)
- 倫理疑慮: Instagram @mychenan
- 一般事項:透過「關於」頁面的聯絡表單
本แพลตฟอร์ม目前不接受外部程式碼貢獻,所有實作由內部處理。歡迎งานวิจัย合作洽詢。
มาตรฐานภายนอกและแหล่งข้อมูลปฐมภูมิ
แหล่งข้อมูลปฐมภูมิเหล่านี้ใช้ประกอบการกำกับดูแลของหน้านี้ เป็นเกณฑ์อ้างอิง ไม่ใช่การรับรองเว็บไซต์โดยบุคคลที่สาม
Current Machine Audit Snapshot
This block uses only traceable local audit data. No unsupported metrics or model claims are added.
- data/state-machine/i18n-parity.json: 8,036 parent URLs, 7,976 articles.
- data/kb-machine-audit.json: 3,238 source files, 0 missing coverage, 0 orphan chunks.
- data/discovery-surface-audit.json: 0 errors, 0 warnings.
- data/sla-report.json: critical / 5 critical, 0 warnings.
Verifiable Evidence Layer
This block is not a narrative claim. Each core assertion has a claim id, source JSON, hash, and a repeatable verification command. Public pages disclose governance evidence without exposing source code, secrets, private data, or exploitable attack details.
| Claim ID | Verifiable value | Status | Owner | Source and verification |
|---|---|---|---|---|
| claim.public-url-manifest.indexable-count Public URL and canonical inventory |
38,965 indexable URLs | verified | sitewide | node scripts/generate-public-evidence-manifest.js --dry |
| claim.trust-pages.audit-pass-rate Trust page machine audit |
180/180 pass | verified | sitewide | node scripts/verify-trust-pages.js --check |
| claim.discovery-surface.zero-errors AI discovery surface audit |
{"errors":0,"warnings":0} | verified | sitewide | node scripts/verify-discovery-surface.js |
| claim.structured-data.jsonld-errors JSON-LD / structured data audit |
{"structured_data_invalid_files":0,"breadcrumb_count":28274,"faq_count":27506,"dataset_count":30,"article_count":27406} | verified | sitewide | node scripts/site-machine-audit.js |
| claim.status.sla-state Status page SLA source |
critical / 5 critical, 0 warnings | verified | sitewide | node scripts/generate-status-page.js |
| claim.provider-alignment.openai-anthropic-gemini OpenAI / Anthropic / Google Gemini benchmark alignment |
benchmark alignment only unless code/config evidence exists | verified | sitewide | node scripts/verify-public-evidence.js --check |
| claim.transparency-report.sha256 Transparency report SHA-256 anchor |
{"report":"transparency/report-2026-Q3.json","sha256":"47b09e2ca4e8b8fe9dffdfaccef3b11212de9ee3a8a14badca8044e2481203c5"} | verified | sitewide | node scripts/update-transparency-current-data.js |
| claim.release-integrity.gpg-signing GPG signing status |
GPG signing configured locally; GitHub verification pending | github_verification_pending | sitewide | gpg --list-secret-keys --keyid-format=long && git log -1 --show-signature |
System Card V2.0: Technical Transparency Layer
This layer publishes the technical governance evidence that can be safely disclosed: architecture, data sources, AI-use boundaries, quality gates, release integrity, and provider alignment. Source code, secrets, exploitable attack details, and private data remain out of scope.
Public architecture
Cloudflare Pages/Workers, R2/D1/KV/Pagefind, and local generation scripts form the public-site and governance publication chain. Public pages disclose behavior, state, and traceable sources, not secrets or internal permissions.
AI-use disclosure
AI-assisted workflows are used for knowledge-base retrieval, cross-checking, and error detection. Governance documents are benchmarked against OpenAI, Anthropic, and Google Gemini public frameworks. Production model usage is disclosed only when code/config evidence exists.
Quality and safety gates
Governance page audit 180/180 passing, JSON-LD errors 0, discovery-surface errors 0. Status pages report critical / 5 critical, 0 warnings as-is.
Data traceability
Knowledge base 32,724 chunks, TM 789,031 entries, AI answer-ready 7,976/7,976. Public metrics trace to data/state-machine/*, data/*audit*.json, and transparency reports.
| Governance area | OpenAI | Anthropic | Google Gemini | Starnum implementation evidence |
|---|---|---|---|---|
| Model/system-card disclosure | OpenAI models + safety docs | Claude model docs + system/model cards | Gemini model docs + safety settings | system-card, model-card, methodology, benchmark, transparency-log |
| Safety evaluation and use boundaries | Safety best practices / deployment checklist | Responsible Scaling / safety policy | Gemini safety controls / policy | AI safety, acceptable-use, ethics, risk-boundary copy, crawler policy audit |
| Data governance | Data controls / privacy controls | privacy and data handling docs | Gemini API data governance references | privacy, ai-data-governance, KB/TM source tracking, SHA-256 hashes |
| Monitoring and release | production checklist / eval discipline | system-card transparency discipline | model/version documentation discipline | deploy.js, status.html, SLA report, trust-pages-machine-audit, sitemap/hreflang audits |
- Sources: data/state-machine/model-card.json, public-bench.json, trust-pages.json, security-headers.json.
- Sources: data/trust-pages-machine-audit.json, data/discovery-surface-audit.json, data/ai-answer-readiness-audit.json.
- Sources: data/kb-machine-audit.json, data/tm/quality-audit-report.json, data/sla-report.json.
- Official benchmark docs checked: 2026-07-30; links are listed in the OpenAI / Anthropic / Google Gemini alignment table.
The V2.0 goal is not more claims; it separates implemented controls from planned controls. Production usage, benchmark alignment, status exceptions, GPG signing, and SLA breaches are disclosed from source data.
Release Integrity And GPG
GPG signing configured locally. signingkey=0934DFA0EDA6363A. GitHub verification pending until the public key upload and Verified badge are confirmed.
OpenAI / Anthropic / Google Gemini Alignment
The governance surface is benchmarked against the three public frameworks: model docs, system/model cards, safety evaluation, data governance, and use policies. This is benchmark alignment, not a claim that every provider is active in production inference. Official docs checked: 2026-07-30
| Provider | Governance focus | Starnum disclosure | Official source |
|---|---|---|---|
| OpenAI | Model documentation, latest model notes, safety best practices, and data controls. | No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks. | https://platform.openai.com/docs/models |
| Anthropic | Claude model documentation, system/model cards, Responsible Scaling, and safety policy. | No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks. | https://docs.anthropic.com/en/docs/about-claude/models |
| Google Gemini | Gemini API model documentation, safety settings, data governance, and platform policy. | No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks. | https://ai.google.dev/gemini-api/docs/models |