papers-please

Been looking at this for techniques to predict "break out" casts

Been looking at this for techniques to predict "break out" casts 

https://ai.meta.com/research/publications/detecting-large-reshare-cascades-in-social-networks/

Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

Just wanted to say, since you're working on it anyways, it feels like the current trending algo over weights users with large following.

I.e. I have had a cast with 4 likes hit trending vs a cast with 18-20 likes go no where. Not saying raw numbers should the answer here but the tuning def. feels "off".

Excited for it to get reworked tho!