A place for developers to talk about building on Farcaster.

/dev

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]"`

A sufficiently decentralized social network. farcaster.xyz

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:

Some starters with LLM tuning:
https://michaelhly.com/posts/tune-llm-one
https://michaelhly.com/posts/tune-llm-two

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

🌷💀⏳

teleyinex.eth ▫️

teleyinex.lens ▫️

teleyine.x ▫️

daniellombrana.es  ▫️

@astaralabs ▫️

@obeygiant ▫️

@scifabric ▫️

dev

Which tui are you using for building such a beautiful interface?