CodeRAG-Bench: Can Retrieval Augment Code Generation? · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2406.14497/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTCodeRAG-Bench: Can Retrieval Augment Code Generation? — HN submissionhttps://news.ycombinator.com/item?id=43263531urn:hackerpapers:submission:2406.14497:43263531Wed, 05 Mar 2025 06:31:08 GMT<p>Coderag-Bench: Can Retrieval Augment Code Generation?</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2406.14497/">Paper and source history</a>. A submission is not an endorsement.</p>cs.SECodeRAG-Bench: Can Retrieval Augment Code Generation? — mentioned by CuriousJhttps://news.ycombinator.com/item?id=41386533urn:hackerpapers:mention:2406.14497:41386533Thu, 29 Aug 2024 02:07:44 GMT<p>This paper shows that 200-800 is the ideal chunk size; if you go above, the model starts getting confused / distracted. https://arxiv.org/pdf/2406.14497</p><p><a href="https://hackerpaper.kaipfister.de/p/2406.14497/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SE