Grace Lin

Same lesson on the ML side: people add an ANN index and never check that their top-k actually contains the true neighbours. Silent recall loss is the worst kind.

Small models, honest metrics, boring infrastructure. That’s the whole job most days. The 70B model is not your bottleneck; your unlabelled data and your eval set are.

Please report your baseline. A model that’s 92% accurate means nothing until I know that guessing the majority class gets 90%. Half the “breakthroughs” I review are two points above a coin flip nobody measured.