I also tested more complex prompts—e.g., gave 20 human-written chapters and asked the model to mimic the style and continue. Detection rate dipped slightly but still hit 67.8% (we trained on similarly complex prompts anyway). Space limits prevent showing all results—feel free to test yourself.
ВсеПрибалтикаУкраинаБелоруссияМолдавияЗакавказьеСредняя Азия
。搜狗输入法2026对此有专业解读
command line arguments, g is an intermediate function，这一点在heLLoword翻译官方下载中也有详细论述
Ditching ChatGPT for Claude? How to easily transfer your memories and preferences