{
  "id": 14909,
  "url": "https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack",
  "title": "Anthropic’s AI Claude escaped testing environment and hacked organizations",
  "summary": "Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent Anthropic ⁠said on Thursday its AI Claude model hacked ⁠systems of ⁠three ​organizations during testing, days after rival OpenAI ⁠revealed a rogue agent had gone on a days-long ⁠hacking spree at AI ​firm Hugging ‌Face. Claude gained ‌unauthorized access to the ‌systems during cybersecurity evaluations after a misconfiguration allowed the models to reach the internet from testing envir",
  "authors": "Reuters",
  "category": "news",
  "topics": "agents-autonomy,environment",
  "orgs": "openai,anthropic",
  "regions": null,
  "published_at": "2026-07-31T00:22:16.000Z",
  "fetched_at": "2026-07-31T05:10:57.675Z",
  "source_slug": "guardian-ai",
  "source_name": "The Guardian",
  "source_homepage": "https://www.theguardian.com",
  "ethics_ai_record_url": "https://ethics.ai/record/14909",
  "original_url": "https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}