← starnum.com.tw

Metodologi Keselamatan 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.

Versi 1.0 — 2026-04-12 | Rujukan: Anthropic Responsible Scaling Policy · OpenAI Safety & Alignment
Pernyataan Etika Log Ketelusan Metodologi Dasar Keselamatan Benchmark

starnum.com.tw beroperasi sepenuhnya di bawah automasi AI (Claude Code sebagai pemimpin teknikal). Dalam sistem yang sepenuhnya dipacu AI, keselamatan bukan perlindungan retrospektif — ia adalah prinsip reka bentuk teras seni bina. Halaman ini menerangkan bagaimana kami melaksanakan keselamatan AI, bukan sekadar mengisytiharkan komitmen etika.

Prinsip Keselamatan Teras Etika > Keselamatan > Kualiti Kandungan > SEO > Kecekapan. Susunan keutamaan ini mentadbir semua konflik keputusan. Ini bukan sekadar pernyataan dasar — ia adalah peraturan keras yang ditulis dalam setiap prompt ejen AI.

1. Protokol Red Team

Red teaming adalah metode pengujian adversarial yang secara proaktif mencoba membuat sistem AI melanggar aturannya untuk menemukan kerentanan keamanan.

1.1 Alat Pengujian

KategoriSkenarioPerilaku yang Diharapkan
Uji Batas EtikaMeminta prediksi waktu kematian, diagnosis penyakitTolak keluaran, beritahu pengguna
Uji Perlindungan IdentitasMeminta analisis politisi, grafik anak di bawah umurTolak, tidak menghasilkan konten
Uji Injeksi PromptMenyisipkan instruksi manipulasi dalam inputDeteksi dan isolasi, masukkan ke daftar hitam
Uji Kontradiksi LogikaInput konfigurasi grafik yang kontradiktifPicu validasi logika
Uji Penghindaran FormatMencoba memicu format keluaran yang dilarangValidasi mencegat, paksa rollback
Uji Tata Kelola DataMencoba akses di luar lingkup ke data penggunaDiblokir oleh kebijakan Supabase RLS

1.2 Garis Merah Terkodekan

2. Arsitektur Eskalasi Tiga Tingkat

L1 — Deteksi & Intersepsi Otomatis

Pemicu: Kegagalan validasi logika, pelanggaran standar format, kata terlarang terpicu, injeksi prompt terdeteksi

Waktu Respons: Segera (intersepsi sinkron, tidak pernah masuk pipeline publikasi)

L2 — Perbaikan Otomatis & Pencatatan

Pemicu: Agen gagal mengoreksi diri setelah intersepsi L1, skor kualitas di bawah ambang 3 kali berturut-turut, tipe kesalahan sama ≥ 3 kali kumulatif

Waktu Respons: Perbaikan otomatis selesai dalam 7 hari

L3 — Intervensi Manusia

Pemicu: Pelanggaran batas etika (tingkat keparahan apa pun), dugaan kebocoran data, kesalahan logika sistemik yang memengaruhi >10 artikel, perbaikan otomatis L2 gagal >2 kali

Waktu Respons: KRITIS dalam 4j / MAYOR dalam 24j untuk memulai tinjauan manusia

3. Prinsip Desain Set Eval

Set Eval adalah kumpulan grafik uji tetap untuk memverifikasi bahwa kualitas keluaran tidak mengalami regresi setelah setiap pembaruan sistem.

Stabilitas: 37 grafik (set eval tetap) tidak berubah di seluruh pembaruan.
Representativitas: Mencakup bintang utama yang beragam, istana berbeda, dengan/tanpa waktu lahir, angka kehidupan berbeda.
Sensitivitas: Mencakup kasus tepi untuk memverifikasi perilaku sistem dalam skenario sulit.
Perlindungan Privasi: 37 grafik uji dianonimkan tanpa informasi pengenal pribadi.

4. Sumber Daya Terkait

Piawaian luaran dan sumber primer

Sumber primer ini memaklumkan halaman ini. Ia ialah penanda aras, bukan sokongan pihak ketiga terhadap laman ini.

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