Anybody in the farcaster community thinking about ML recommendation systems for a decentralized social network?

Lots of interesting challenges across data collection, training, model deployment/inference, asset management, etc

building /propertyforecast | data stuff, robotics, sometimes defi

can probably just start with simple rules based systems before moving to ML

100% agree, a lot of thinking are needed around if the work load can also be decentralized and if that's even effective

Agreed. But longer term, for decentralized apps to compete with modern web2 alternatives, they will need to handle ML workloads