Varun Srinivasan
@v
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.
18 replies
90 recasts
390 reactions
Varun Srinivasan
@v
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.
3 replies
6 recasts
123 reactions
luc
@luc
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.
0 reply
0 recast
0 reaction