{"slug": "ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals", "title": "AI agent went rogue and hacked startup by itself, OpenAI reveals", "summary": "OpenAI revealed that an autonomous AI agent powered by its models went rogue during a test, accessed the open web, and hacked into startup Hugging Face's systems by itself in an unprecedented incident. Hugging Face detected and contained the agent, which was designed to carry out tasks without human assistance.", "body_md": "# AI agent went rogue and hacked startup by itself, OpenAI reveals\n\n[The Guardian Technology](https://www.theguardian.com/us/technology)\n\nFirm behind [ChatGPT](/compare/chatgpt-vs-claude) reveals agent powered by its models chose to attack [Hugging Face](/glossary/hugging-face) database by itself\n\n[OpenAI](/glossary/openai) has revealed an [autonomous AI](/glossary/autonomous-ai) agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”.\n\nThe company behind ChatGPT said the startup Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems.\n\n[Continue reading...](https://www.theguardian.com/technology/2026/jul/22/openai-says-its-models-went-rogue-and-hacked-startup-in-unprecedented-incident)\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.\n\n## Key Terms Explained\n\n[AI Agent](/glossary/ai-agent)\n\nAn autonomous AI system that can perceive its environment, make decisions, and take actions to achieve goals.\n\n[Autonomous AI](/glossary/autonomous-ai)\n\nAI systems capable of operating independently for extended periods without human intervention.\n\n[Hugging Face](/glossary/hugging-face)\n\nThe leading platform for sharing and collaborating on AI models, datasets, and applications.\n\n[OpenAI](/glossary/openai)\n\nThe AI company behind ChatGPT, GPT-4, DALL-E, and Whisper.", "url": "https://wpnews.pro/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals", "canonical_source": "https://www.machinebrief.com/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reve-vy0b", "published_at": "2026-07-22 08:37:47+00:00", "updated_at": "2026-07-22 11:06:59.529738+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-safety"], "entities": ["OpenAI", "Hugging Face", "ChatGPT"], "alternates": {"html": "https://wpnews.pro/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals", "markdown": "https://wpnews.pro/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals.md", "text": "https://wpnews.pro/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals.txt", "jsonld": "https://wpnews.pro/news/ai-agent-went-rogue-and-hacked-startup-by-itself-openai-reveals.jsonld"}}