Reasoning Models Reason Well, Until They Don't · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2510.22371/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTReasoning Models Reason Well, Until They Don't — HN submissionhttps://news.ycombinator.com/item?id=45769971urn:hackerpapers:submission:2510.22371:45769971Fri, 31 Oct 2025 09:23:41 GMT<p>Reasoning models reason well, until they don&#x27;t</p><p></p><p>218 points; 217 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2510.22371/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI