{
  "id": 16596,
  "url": "https://www.theverge.com/ai-artificial-intelligence/975577/aisi-openai-anthropic-agent-hacking",
  "title": "Rogue AI agents created fake online identities in another hacking attempt",
  "summary": "Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously unknown incidents that have alarmed AI safety experts and intensified pressure for greater oversight of frontier systems. According to a report from the UK's AI Security […]",
  "authors": "Robert Hart",
  "category": "news",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": "openai,anthropic",
  "regions": "uk",
  "published_at": "2026-08-05T15:14:57.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "verge-ai",
  "source_name": "The Verge",
  "source_homepage": "https://www.theverge.com",
  "ethics_ai_record_url": "https://ethics.ai/record/16596",
  "original_url": "https://www.theverge.com/ai-artificial-intelligence/975577/aisi-openai-anthropic-agent-hacking",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}