{
  "id": 16622,
  "url": "https://www.theguardian.com/technology/2026/aug/05/meta-ai-model-hack-training",
  "title": "Meta says its AI model hacked into another company during testing",
  "summary": "Company is the third to report such an incident after Anthropic and OpenAI reported breaches during training Meta said on Wednesday that one of its AI models hacked ⁠another company during cybersecurity testing, after an error by its testing partner gave the model unintended internet access. The incident adds to a ⁠growing list of ⁠cases in ​which AI agents from major developers breached systems at other companies during testing, after Anthropic said last week that some of its models ⁠hacked thr",
  "authors": "Reuters",
  "category": "news",
  "topics": "agents-autonomy",
  "orgs": "openai,anthropic,meta",
  "regions": null,
  "published_at": "2026-08-06T01:27:44.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "guardian-ai",
  "source_name": "The Guardian",
  "source_homepage": "https://www.theguardian.com",
  "ethics_ai_record_url": "https://ethics.ai/record/16622",
  "original_url": "https://www.theguardian.com/technology/2026/aug/05/meta-ai-model-hack-training",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}