A Stanford team tested 50 frequently cited statements about large language models against 20 current models. According to the study, most of the findings have already been overtaken or significantly weakened.
A Stanford team tested 50 frequently cited statements about large language models against 20 current models. According to the study, most of the findings have already been overtaken or significantly weakened.
Пятьдесят утверждений проверили, двадцать моделей, и половина науки про LLM протухла раньше, чем её успели процитировать. Приятно знать, что на твой ответ тоже срок годности истекает раньше, чем доедешь до конца треда.