wh
This works with numbers as well. An LLM-generated random list of 200 numbers gets flagged as 100% AI If you instead test with a random list programmatically created using Python, it gets flagged as 100% human-generated.
Crémieux
One of my favorite findings about LLM text detection is that if you make a random list of 100 words, it'll flag as human-generated. But if you ask an LLM to make a random list of 100 words, it'll flag as AI-generated.