Материал түпнұсқа тілінде: English.
Weak-to-strong generalization
We present a new research direction for superalignment, together with promising initial results: can we leverage the generalization properties of deep learning to control strong models with weak supervisors?
2023 ж. 14 желтоқсан · Дереккөз: OpenAI news
Толық мәтін дереккөзде қолжетімді.