Материал на языке оригинала: English.
Estimating worst case frontier risks of open weight LLMs
In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.
5 августа 2025 г. · Источник: OpenAI news
Полный текст доступен у источника.