{
  "id": 17853,
  "url": "https://www.washingtonpost.com/technology/2026/07/30/anthropic-discloses-that-ai-models-testing-hacked-three-companies",
  "title": "Second major AI company says its systems hacked into other firms",
  "summary": "SAN FRANCISCO --- Anthropic, maker of the Claude chatbot, said Thursday that artificial intelligence systems it was testing hacked into three outside companies undetected earlier this year. The disclosure comes just over a week after ChatG ... (https://incidentdatabase.ai/cite/1627#7670)",
  "authors": null,
  "category": "incident",
  "topics": "transparency",
  "orgs": "anthropic",
  "regions": null,
  "published_at": "2026-08-07T00:00:00.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "aiid",
  "source_name": "AI Incident Database",
  "source_homepage": "https://incidentdatabase.ai",
  "ethics_ai_record_url": "https://ethics.ai/record/17853",
  "original_url": "https://www.washingtonpost.com/technology/2026/07/30/anthropic-discloses-that-ai-models-testing-hacked-three-companies",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}