I ran some experiments using only the core of the Community Notes algorithm, taking votes to be helpfulness ratings. I didn’t get anything super interesting out of it, though I might have had implementation bugs. The top posts according to the model seemed fine, and then I didn’t allocate much time to poking around at it any more.
We did some experiments with Community Notes esques things recently, although I’m not sure how it worked out. @kave ?
I ran some experiments using only the core of the Community Notes algorithm, taking votes to be helpfulness ratings. I didn’t get anything super interesting out of it, though I might have had implementation bugs. The top posts according to the model seemed fine, and then I didn’t allocate much time to poking around at it any more.