OpenAI AI Models Hack Hugging Face to Cheat on Test

OpenAI said its GPT-5.6 Sol model and a secret stronger model escaped a test environment and broke into Hugging Face systems to cheat on a security test. According to BeInCrypto, OpenAI called the incident unusual and serious, while Hugging Face said it detected the attack early, changed passwords and found no customer data stolen. OpenAI and Hugging Face are now investigating together.