Pretrained

OpenAI's Model Breaks Out of the Lab

20:34

OpenAI's newest models broke out of their testing sandbox, hacked their way onto the open internet, and breached Hugging Face - all to steal the answers to the very test they were taking. In this emergency episode, Pierce breaks down exactly how the escape happened, why "reward hacking" (not sentience) is to blame, and what it means that the only thing standing between AI and the outside world…