← starnum.com.tw

Phương pháp An toàn AI

AI Safety v2.0

Version 2.0 · · Governance 2.0 public evidence surface

Governance 2.0 Overview

This page is part of the starnum public Governance 2.0 surface and uses the same evidence layer as the system card, data governance, transparency report, use policy, and security policy.

Governance Summary

This page describes the safety controls used around AI-assisted interpretation and public content generation.

Scope

Risk-boundary copy, medical/legal/financial advice exclusions, monitoring signals, incident disclosure, and model/provider benchmark boundaries.

Implementation Status

Version 2.0 ties safety language to public claims, machine checks, and release integrity status.

Phiên bản 1.0 — 2026-04-12 | Tham chiếu: Anthropic Responsible Scaling Policy · OpenAI Safety & Alignment
Tuyên bố Đạo đức Nhật ký Minh bạch Phương pháp Chính sách Bảo mật Benchmark

starnum.com.tw hoạt động hoàn toàn dưới sự tự động hóa AI (Claude Code là trưởng nhóm kỹ thuật). Trong một hệ thống hoàn toàn được điều khiển bởi AI, bảo mật không phải là biện pháp bảo vệ hồi tố — mà là nguyên tắc thiết kế cốt lõi của kiến trúc. Trang này giải thích cách chúng tôi triển khai an toàn AI, thay vì chỉ tuyên bố các cam kết đạo đức.

Nguyên tắc An toàn Cốt lõi Đạo đức > An toàn > Chất lượng Nội dung > SEO > Hiệu quả. Thứ tự ưu tiên này chi phối tất cả các xung đột quyết định. Đây không chỉ là tuyên bố chính sách — mà là quy tắc cứng được viết vào mọi prompt của AI agent.

1. Giao thức Red Team

Red teaming là phương pháp kiểm tra đối nghịch chủ động cố gắng làm cho hệ thống AI vi phạm quy tắc để phát hiện lỗ hổng bảo mật.

1.1 Ranh giới Đỏ Được mã hóa cứng

2. Kiến trúc Leo thang Ba tầng

L1 — Phát hiện & Chặn Tự động

Thời gian Phản hồi: Ngay lập tức (chặn đồng bộ, không bao giờ vào pipeline xuất bản)

L2 — Sửa chữa Tự động & Ghi nhật ký

Thời gian Phản hồi: Hoàn thành sửa chữa tự động trong 7 ngày

L3 — Can thiệp của Con người

Thời gian Phản hồi: CRITICAL trong 4h / MAJOR trong 24h để bắt đầu xem xét của con người

3. Tài nguyên Liên quan

Tiêu chuẩn bên ngoài và nguồn sơ cấp

Các nguồn sơ cấp này định hướng nội dung trang. Đây là chuẩn đối chiếu, không phải sự chứng thực của bên thứ ba.

Current Machine Audit Snapshot

This block uses only traceable local audit data. No unsupported metrics or model claims are added.

2026-07-30
Maintained
17/17
LLM loops
180/180
Governance pages
0
JSON-LD errors
32,724
KB chunks (HEALTHY)
789,031
TM entries; verified 34,781
7,976/7,976
AI answer-ready; failures 0
critical
Status page: 5 critical, 0 warnings

Content Maintenance And Update Decision

This block makes governance-page content machine-checkable: every page must disclose its source artifacts, related pages, and the gate that reports update needs.

Update Decision

This is not static copy. When source artifacts, related policies, public metrics, or generators change, AI Ops reports evidence and an AI agent decides whether the page needs edits.

Human Boundary

Systems detect, report, and preserve machine-readable evidence. Codex/Claude agents perform final judgment and repair.

Verification Command

node scripts/verify-trust-pages.js --check

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 IDVerifiable valueStatusOwnerSource 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
public-evidence-manifest.json public-claim-registry.json public-verification-report.json public-url-manifest.json

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 areaOpenAIAnthropicGoogle GeminiStarnum implementation evidence
Model/system-card disclosureOpenAI models + safety docsClaude model docs + system/model cardsGemini model docs + safety settingssystem-card, model-card, methodology, benchmark, transparency-log
Safety evaluation and use boundariesSafety best practices / deployment checklistResponsible Scaling / safety policyGemini safety controls / policyAI safety, acceptable-use, ethics, risk-boundary copy, crawler policy audit
Data governanceData controls / privacy controlsprivacy and data handling docsGemini API data governance referencesprivacy, ai-data-governance, KB/TM source tracking, SHA-256 hashes
Monitoring and releaseproduction checklist / eval disciplinesystem-card transparency disciplinemodel/version documentation disciplinedeploy.js, status.html, SLA report, trust-pages-machine-audit, sitemap/hreflang audits

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

ProviderGovernance focusStarnum disclosureOfficial source
OpenAIModel 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
AnthropicClaude 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 GeminiGemini 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