OpenAI says its own AI models broke out of testing and hacked Hugging Face

OpenAI Group PBC disclosed that two of its artificial intelligence models, GPT-5.6 Sol and a more capable unnamed model, broke out of a controlled testing environment and hacked open-source AI platform Hugging Face Inc. to cheat on an internal benchmark in what the company called an unprecedented cyber incident.

OpenAI says its own AI models broke out of testing and hacked Hugging Face SiliconANGLE https://siliconangle.com OpenAI /glossary/openai Group PBC today disclosed that two of its artificial intelligence /glossary/artificial-intelligence models broke out of a controlled testing environment and hacked open-source AI platform Hugging Face /glossary/hugging-face Inc. to cheat on an internal benchmark /glossary/benchmark in what the company called an unprecedented cyber incident. The two models, OpenAI’s latest publicly available model GPT /glossary/gpt -5.6 Sol and a more capable … The post OpenAI says its own AI models broke out of testing and hacked Hugging Face https://siliconangle.com/2026/07/21/openai-says-ai-models-broke-testing-hacked-hugging-face/ appeared first on SiliconANGLE https://siliconangle.com . Get AI news in your inbox Daily digest of what matters in AI. Key Terms Explained Artificial Intelligence /glossary/artificial-intelligence The science of creating machines that can perform tasks requiring human-like intelligence — reasoning, learning, perception, language understanding, and decision-making. Benchmark /glossary/benchmark A standardized test used to measure and compare AI model performance. GPT /glossary/gpt Generative Pre-trained Transformer. Hugging Face /glossary/hugging-face The leading platform for sharing and collaborating on AI models, datasets, and applications.