[wongarsu]

There's a large body of research into invisible text watermarking, so this would certainly be possible. Maybe the simplest to implement in LLMs would be to bias the token generation slightly, for example by making tokens that include the letter i slightly more likely. In a long enough text you could then see the deviation from normal human text characteristics.

[PeterisP]

All the main scenarios for detecting generating text that I can imagine do have to assume that the LLM isn't "cooperative" but actually is specifically designed (or fine-tuned) to avoid detection.

[lwhi]

Yep, I think it's a good idea.