{
  "id": 10796,
  "url": "https://the-decoder.com/openai-is-now-using-ai-to-attack-its-own-ai-and-its-working-better-than-humans-ever-did",
  "title": "OpenAI is now using AI to attack its own AI, and it's working better than humans ever did",
  "summary": "OpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed directly into hardening models like GPT-5.6 Sol. The article OpenAI is now using AI to attack its own AI, and it's working better than humans ever did appeared first on The Decoder .",
  "authors": "Matthias Bastian",
  "category": "news",
  "topics": "safety-alignment",
  "orgs": "openai",
  "regions": null,
  "published_at": "2026-07-15T19:47:53.000Z",
  "fetched_at": "2026-07-16T05:10:56.605Z",
  "source_slug": "x-the-decoder",
  "source_name": "The Decoder",
  "source_homepage": "https://the-decoder.com",
  "ethics_ai_record_url": "https://ethics.ai/record/10796",
  "original_url": "https://the-decoder.com/openai-is-now-using-ai-to-attack-its-own-ai-and-its-working-better-than-humans-ever-did",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}