Given the full text of Wikipedia is undoubtedly part of the training data, what ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		fragmede 15 days ago \| parent \| context \| favorite \| on: So you wanna build a local RAG? Given the full text of Wikipedia is undoubtedly part of the training data, what would having it in a RAG add?

Zambyte 15 days ago [–]

High precision recall.

It may also be cheaper to update the source (Wikipedia) with new information than to update the model.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact