Would be cool to create embeddings for historical HN posts, and then use a users favorite posts to personalize the post selection by averaging the embedding vectors for a users favorite posts then doing a cosine similarity search to select stories most likely to be of interest to a user. Although it would be even better to use a users like history, but I’m not sure if/how those can be accessed. Speaking of, I’m curio…
This assumes that favorites have some kind of meaning. Favorites are public (IIRC) and I basically use them to track and share interesting/funny comments. Upvotes on the other hand, are private and are more inline with the things I care about.