A quick overview of how @akshaan built Trending Topics on Farcaster. 

1. Casts are selected and preprocessed daily. 
2. Model categorizes thousands of casts with a prompt. 
3. Topics are post-processed, merged and winners are picked

It costs about $1/day and runs in < 1 hour.

Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

Each day, a few thousand of the best performing casts are selected and pre-processed. 

All of the text content is turned into structured JSON that can be fed into the model as a prompt. 

Right now, we're classifying 1-5% of all casts.

We love to hear how you select the casts for analysis. 

I'm running a similar process, and so far, using the OpenRank score, but wonder if there's a better way.