https://hackerpaper.kaipfister.de/p/2510.25941/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=48225102urn:hackerpapers:mention:2510.25941:48225102Thu, 21 May 2026 16:10:53 GMT<p>https://arxiv.org/html/2510.25941v1 You can get it to reproduce content but it’s a game of cat and mouse. Were it not for the alignment to avoid direct reproduction it would taken far more often. &gt; RECAP consistently outperforms all other methods; as an illustration, it extracted ≈3,000 passages from the first &quot;Harry Potter&quot; book with Claude-3.7, compared to the 75 passages identified by the best baseline.</p><p><a href="https://hackerpaper.kaipfister.de/p/2510.25941/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=46005299urn:hackerpapers:submission:2510.25941:46005299Fri, 21 Nov 2025 15:11:28 GMT<p>Recap: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2510.25941/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL