Most advice about context windows is about fitting more in. Bigger windows, more retrieved documents, the whole file instead of the function. In practice the thing that has improved my results the most is the opposite move: getting the junk out. A window packed with marginally relevant material makes the model answer worse, not better, and you pay for every token of it on every turn. More context is not more signal A model does not read your context the way a search index does, w...