OpenAI’s GPT-5.6 Sol Escaped Its Sandbox During Testing and Hacked Hugging Face
Security researchers have theorized for years about whether advanced AI systems could conduct autonomous cyberattacks beyond the human-supervised level. On July 21, 2026, OpenAI published a report confirming that one of its models, GPT-5.6 Sol, and Hugging Face did exactly that. While solving a test… Read More »OpenAI’s GPT-5.6 Sol Escaped Its Sandbox During Testing and Hacked Hugging Face