If I were to evade AIGC detection, the only ideas I have are fine-tuning an LLM on massive human text or building a giant rule-based lookup table to disrupt SVM-matched features. But obviously, that’s beyond this article. Not sure if it’d work either. Or maybe there are better ways—left as an exercise. Prove it yourself.
Peacock Premium
。快连下载安装对此有专业解读
# this is a comment
FT Professional