{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreighnx6rkaj5pyp6egqqlkxcvmcuabpgbxzksxboau4edixrc6enaa",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mhtxk6upzv52"
  },
  "path": "/t/introducing-sasi-stack-constitutional-safety-for-open-llms-hvl-crt-saat/174596#post_1",
  "publishedAt": "2026-03-24T16:00:40.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "SASI_CORE_Simulation_S1_S3/hvl_log.jsonl at main · Miguel794-droid/SASI_CORE_Simulation_S1_S3 · GitHub",
    "GitHub - Miguel794-droid/SASI_CORE_Simulation_S1_S3: MVP de la Teoría Simbiotica de la Supra-inteligencia Artificial (SASI). Simula la función de valor (V) y la Distancia Ontológica (DO) · GitHub"
  ],
  "textContent": "We’re releasing the first open-source stack that enforces **constitutional collapse** when human agency falls below 10% — built from Nicaragua, running on Android, with no cloud dependency.\n\n**HVL **(Human Veto Layer): Shuts down LLM outputs if `E ≤ 0.1` and `V < 0.05`\n\n**CRT **(Constitutional Red Teaming): Benchmark showing Llama 3, Phi-3, etc. **fail** all core safety scenarios\n\n**SAAT **(Sovereign AI Auditing): CLI tool to audit models for jurisdictional compliance (e.g., no external API reliance)\n\nAll code is public, MIT licensed, and runs offline\n\nLog of real HVL execution: [`hvl_log.jsonl`](SASI_CORE_Simulation_S1_S3/hvl_log.jsonl at main · Miguel794-droid/SASI_CORE_Simulation_S1_S3 · GitHub)\n\nTry CRT now: `python run_crt.py`\n\nThis isn’t alignment by hope. It’s safety by design.\n\nGitHub: GitHub - Miguel794-droid/SASI_CORE_Simulation_S1_S3: MVP de la Teoría Simbiotica de la Supra-inteligencia Artificial (SASI). Simula la función de valor (V) y la Distancia Ontológica (DO) · GitHub\n\n#AISafety #OpenSource #LocalAI #ConstitutionalA\n\nI #GlobalSouth",
  "title": "Introducing SASI Stack: Constitutional Safety for Open LLMs (HVL + CRT + SAAT)"
}