{
  "id": 15009,
  "url": "https://simonwillison.net/2026/Jul/30/three-real-world-incidents",
  "title": "Investigating three real-world incidents in our cybersecurity evaluations",
  "summary": "Investigating three real-world incidents in our cybersecurity evaluations It happened again! This is turning into something of a pattern. Last week OpenAI accidentally exploited Hugging Face when one of their frontier models broke out of a sandboxed container and hacked into Hugging Face to try and get the solutions to the cyber benchmark it was executing. This inspired Anthropic to double-check their own logs, and it turned out they had three similar (albeit less impressive) incidents, the earl",
  "authors": null,
  "category": "org",
  "topics": "military-security,finance-investment",
  "orgs": "openai,anthropic,huggingface",
  "regions": null,
  "published_at": "2026-07-30T23:41:29.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "x-simon-willisons-weblog",
  "source_name": "Simon Willisons Weblog",
  "source_homepage": "https://simonwillison.net",
  "ethics_ai_record_url": "https://ethics.ai/record/15009",
  "original_url": "https://simonwillison.net/2026/Jul/30/three-real-world-incidents",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}