{
  "id": 12280,
  "url": "https://www.theverge.com/ai-artificial-intelligence/968988/openai-hugging-face-hack-ai",
  "title": "OpenAI says it accidentally hacked Hugging Face with a new AI system",
  "summary": "OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday, OpenAI writes that GPT-5.6 Sol and \"an even more capable pre-release model\" discovered vulnerabilities within their sandboxed testing environment, allowing them to gain access to the internet and target Hugging Face. On July 16th, […]",
  "authors": "Emma Roth",
  "category": "news",
  "topics": "environment",
  "orgs": "openai,huggingface",
  "regions": null,
  "published_at": "2026-07-21T21:48:54.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "verge-ai",
  "source_name": "The Verge",
  "source_homepage": "https://www.theverge.com",
  "ethics_ai_record_url": "https://ethics.ai/record/12280",
  "original_url": "https://www.theverge.com/ai-artificial-intelligence/968988/openai-hugging-face-hack-ai",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}