Jakson kuvaus
Recently, OpenAI admitted something unprecedented: its own models hacked another company. During a safety test with guardrails deliberately loosened, its models found a zero-day vulnerability and used it to break out of their sandbox and hack into the production systems of Hugging Face, the main hub for open-source AI. In a way, OpenAI's models passed the test, but only by cheating on it. The models figured out Hugging Face probably had the answer to the test, and they went and took it—...

