Yeah collecting your data and running your own algorithms are going to be opt in by default. All peertube instance would have to do is send information described all the videos and you’re local machine will pick it out for you

yeah i saw that stats when i looked at my videos, but i didn’t know if that would be worth collecting since its guarded not readily accessible. i guess an instance can use it for recommendations of local videos. right now im just trying to profile both the watcher(locally) and videos