Michael Huang (michaelhly)

Just shipped a tool to let hub runners generate a @farcaster training corpus for LLM tuning — zero network requests. If you have your hub synced, it should be 100x+ faster in pulling data out of your hub compared to RPC-based methods. Try it out with: `pip install "farglot[cli]"`

• 2 replies
• 0 recasts
• 1 reaction

I just shipped a transformer-based SocialNLP toolkit for @farcaster. This library can possibly help construct new ML-based feed algorithms based on text classification instead of relying on manual curation, recasts/reactions, and chronological ordering. Check it out: https://github.com/michaelhly/FarGlot

• 5 replies
• 4 recasts
• 19 reactions

https://github.com/tiangolo/typer

• 1 reply
• 0 recasts
• 1 reaction

Just shipped a tool to let hub runners generate a @farcaster training corpus for LLM tuning — zero network requests. If you have your hub synced, it should be 100x+ faster in pulling data out of your hub compared to RPC-based methods. Try it out with: `pip install "farglot[cli]"`

• 2 replies
• 0 recasts
• 1 reaction

Also there is a corresponding analyzer library to use your tuned models for cast classification to help with reputation ranking, spam detection, or auto-moderation: https://warpcast.com/michaelhly/0xb47dc6

• 1 reply
• 0 recasts
• 0 reactions

What about using a LLM backend to classify spam?

• 0 replies
• 0 recasts
• 0 reactions