{
  "id": 14653,
  "url": "https://www.schneier.com/blog/archives/2026/07/measuring-the-tendency-of-ai-agents-to-go-rogue.html",
  "title": "Measuring the Tendency of AI Agents to Go Rogue",
  "summary": "This essay was written with Barath Raghavan, and originally appeared in The Guardian . In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated crimina",
  "authors": "Bruce Schneier",
  "category": "org",
  "topics": "agents-autonomy,environment",
  "orgs": "huggingface",
  "regions": null,
  "published_at": "2026-07-29T17:07:53.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "x-bruce-schneier-schneier-on-security",
  "source_name": "Bruce Schneier — Schneier on Security",
  "source_homepage": "https://www.schneier.com",
  "ethics_ai_record_url": "https://ethics.ai/record/14653",
  "original_url": "https://www.schneier.com/blog/archives/2026/07/measuring-the-tendency-of-ai-agents-to-go-rogue.html",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}