AI agent went rogue and hacked startup by itself, OpenAI reveals

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.

AI agent went rogue and hacked startup by itself, OpenAI reveals The Guardian Technology https://www.theguardian.com/us/technology Firm behind ChatGPT /compare/chatgpt-vs-claude reveals agent powered by its models chose to attack Hugging Face /glossary/hugging-face database by itself 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”. The 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. Continue reading... https://www.theguardian.com/technology/2026/jul/22/openai-says-its-models-went-rogue-and-hacked-startup-in-unprecedented-incident Get AI news in your inbox Daily digest of what matters in AI. Key Terms Explained AI Agent /glossary/ai-agent An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve goals. Autonomous AI /glossary/autonomous-ai AI systems capable of operating independently for extended periods without human intervention. Hugging Face /glossary/hugging-face The leading platform for sharing and collaborating on AI models, datasets, and applications. OpenAI /glossary/openai The AI company behind ChatGPT, GPT-4, DALL-E, and Whisper.