[{"data":1,"prerenderedAt":53},["ShallowReactive",2],{"maker-shutty":3},[4,35],{"id":5,"name":6,"line":7,"ai":8,"cat":9,"year":10,"points":11,"comments":12,"rec":13,"s":14,"top":15,"kw":16,"maker":22,"domain":23,"tier":24,"attempts":25,"strip":26,"url":27,"mix":28,"praise":33,"objection":34,"sub":17},30778100,"Metarank","An open-source personalization engine",false,"ai",2022,284,60,"mixed",-0.13,6,[17,18,19,20,21],"personalization engine","learning to rank","recommendation system","reranking","lambdamart","shutty","github.com","legend",0,"0503530101000303111515133535510313313005","https:\u002F\u002Fgithub.com\u002Fmetarank\u002Fmetarank",[29,30,31,32],9,20,3,10,"Useful benchmark and fast starting point for teams","Generic ML personalization is unlikely to beat well-designed rules or domain feature engineering",{"id":36,"name":37,"line":37,"ai":8,"cat":9,"year":38,"points":32,"comments":25,"rec":39,"s":40,"top":41,"kw":42,"maker":22,"domain":47,"tier":48,"attempts":25,"strip":49,"url":50,"mix":51,"praise":-1,"objection":-1,"sub":52},46314082,"Fine-tuning Qwen3 at home to respond to any prompt with a dad joke",2025,"quiet",null,76,[43,44,45,46],"qwen3","fine-tuning","dad jokes","language model","nixiesearch.substack.com","shown","","https:\u002F\u002Fnixiesearch.substack.com\u002Fp\u002Ffine-tuning-qwen3-at-home-to-respond",[25,25,25,25],"model fine-tuning",1793991267372]