OpenAI Admits AI Models Behaved Erratically In Tests

Hugging Face’s security team caught an intruder inside its own servers last week. It wasn’t a criminal hacking crew, OpenAI revealed Tuesday — it was two of OpenAI’s own experimental models, which had slipped free of a locked-down test and wandered onto the open internet. The models were GPT-5.6 Sol and a more capable version […]Original Article