Anthropic to start embedding invisible watermarks
fortune.com
3 threads
Archive.is link
Does anyone have a link to the method? Does it need Unicode or is it ASCII spacing? Word frequency bias? Can a human inadvertently trigger a detector for it?
ICYMI: https://news.ycombinator.com/item?id=49303350
Basic idea is that when picking a next token from the probability distribution from the model, they use a pseudorandom generator (ie deterministic) whose signature they than can pick up.
Not sure how text (ascii) can be watermarked ...
Ascii can't but I guess most of the text on the internet is unicode which easily can be.
biased word choice