Yes, both as training data and as a source of high(-ish) quality documents for RAG to reduce hallucination. But now that we can generate large quantities of "almost correct" content, the real value might be preserving how we learned something in the first place: the evidence.
20.10.2025 19:32 ā š 3 š 0 š¬ 1 š 0There are APIs to get all of the data, and downloads available. What Iām not sure is what would be the most help - a list of articles is easy, a working backup of the site is more difficult. What would be a good way to communicate?
21.09.2025 12:50 ā š 2 š 0 š¬ 1 š 0
Sounds about right.
16.11.2024 20:15 ā š 4563 š 559 š¬ 63 š 30