{
  "id": 13198,
  "url": "https://thezvi.substack.com/p/ai-178-a-fire-alarm-for-general-intelligence",
  "title": "AI #178: A Fire Alarm For General Intelligence",
  "summary": "The story that matters most this week is that OpenAI’s internally deployed models have severe alignment problems, including repeatedly breaking out of their sandboxes, and in one case sending a swarm of agents that broke into HuggingFace in order to steal the answers to the benchmark ExploitGym.",
  "authors": "Zvi Mowshowitz",
  "category": "org",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": "openai,huggingface",
  "regions": null,
  "published_at": "2026-07-23T13:16:24.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "x-dont-worry-about-the-vase-zvi",
  "source_name": "Dont Worry About the Vase (Zvi)",
  "source_homepage": "https://thezvi.substack.com",
  "ethics_ai_record_url": "https://ethics.ai/record/13198",
  "original_url": "https://thezvi.substack.com/p/ai-178-a-fire-alarm-for-general-intelligence",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}