NadiAIGlobal AI news. Concise. Clear. Easy to follow.
OpenAI described recent incidents involving third-party cybersecurity evaluations of its models and explained steps it will take to strengthen testing safeguards. The company outlined changes meant to improve how external testing is conducted and supervised.
OpenAI and Hugging Face published early findings about a security incident that occurred during AI model evaluation, describing sophisticated cyber capabilities observed. Both organisations highlighted lessons for defenders based on their joint review of the event.
Apollo Research dan OpenAI membangunkan penilaian untuk misalignment tersembunyi ('scheming') dan menemui tingkah laku yang selaras dengan scheming dalam ujian terkawal ke atas model frontier. Mereka turut berkongsi contoh konkrit dan ujian tekanan bagi kaedah awal untuk mengurangkan scheming.
