There is already some intentional randomness in token selection, because it actually improves the quality of responses if you intentionally don't always pick the most likely next token.
You can hide data in that randomness without impacting the quality of the response by using a sufficiently "random looking" pseudorandom bit stream instead of real random numbers.
You can hide data in that randomness without impacting the quality of the response by using a sufficiently "random looking" pseudorandom bit stream instead of real random numbers.
I previously worked on a project to do that here: https://github.com/shawnz/textcoder