{
  "id": 10762,
  "url": "https://thenextweb.com/news/gpt-red-openai-ai-hacker",
  "title": "OpenAI built an AI super-hacker to break its own models, then locked it away",
  "summary": "OpenAI has trained an elite hacker, then locked it in a cage. Its whole job is to break OpenAI’s own AI. The company says it is too dangerous to let anyone else near it. The model is called GPT-Red, and OpenAI detailed it this week. It is an automated red-teamer: software that hunts for ways […] This story continues at The Next Web",
  "authors": "Ana Maria Constantin",
  "category": "news",
  "topics": "safety-alignment,jobs-economy",
  "orgs": "openai",
  "regions": null,
  "published_at": "2026-07-15T21:49:52.000Z",
  "fetched_at": "2026-07-16T05:10:56.605Z",
  "source_slug": "x-the-next-web-ai",
  "source_name": "The Next Web AI",
  "source_homepage": "https://thenextweb.com/topic/artificial-intelligence",
  "ethics_ai_record_url": "https://ethics.ai/record/10762",
  "original_url": "https://thenextweb.com/news/gpt-red-openai-ai-hacker",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}