https://hackerpaper.kaipfister.de/p/2203.08913/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=40184002urn:hackerpapers:mention:2203.08913:40184002Sat, 27 Apr 2024 22:02:28 GMT<p>No. RAG is about finding relevant documents/paragraphs (via KNN lookups of their embeddings) and then inserting those documents/paragraphs into the input context, as sequences of input tokens. What I&#x27;m talking about is different: https://arxiv.org/abs/2203.08913</p><p><a href="https://hackerpaper.kaipfister.de/p/2203.08913/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=31448360urn:hackerpapers:submission:2203.08913:31448360Fri, 20 May 2022 14:58:29 GMT<p>Memorizing Transformers</p><p></p><p>179 points; 32 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2203.08913/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG