Once all data was ready, I tried training an 8-class model (human + 7 AI models), but since these LLMs are all distilled from similar data, their outputs were too similar. Classification accuracy was only ~50%.
Follow topics & set alerts with myFT
，推荐阅读51吃瓜获取更多信息
Fonbet Кубок России|1/2 финала (Путь РПЛ). 1-й матч，这一点在safew官方下载中也有详细论述
Турция сообщила о перехвате баллистического снаряда из Ирана14:52