Cast by jc4p
Show the cast this replies toappreciate the response and totally acknowledge the oversimplification! my issue (which i have no way of knowing it's a wild guess) is that the models are trained on global (and possibly handpicked) features, the vibe i get is there isn't clustering and then each cluster gets its own features
1 reply
the features are personalized to each user (so not global) but are hand-picked. The model does some implicit clustering based on the features we feed it, but we don't have explicit clustering of topics or users today. Something we're thinking about actively rn.
thank you so much h for sharing this!!! i know semi unrelated but for a diff engine recently i did clustering based on embeddings > max feature generation from each cluster using LLMs > calculate colinearalities > have top 5-7 features per cluster