{"author":{"username":"akshaan","displayName":"akshaan","fid":9052},"timestamp":"2025-07-07T19:18:44.000Z","text":"I think you're conflating supervised vs. unsupervised training with manual vs. learned models. We used supervised training, because the model needs feedback from users to know what they like. We don't use manual heuristics, but instead train models that infer what users like from the feedback they're given.\n\nThis does scale because they feedback is generated when users click, like or otherwise engage with content. It is not generated by us manually labeling things.","farcaster":"https://farcaster.xyz/akshaan/0xd5b5aadc8fe94cfd60c6b0332ba6463286bccdd6","firefly":"https://firefly.social/post/farcaster/0xd5b5aadc8fe94cfd60c6b0332ba6463286bccdd6","note":"author hasn't signed the social smart contract; the cast may be restricted on farcaster.xyz"}