Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2506.11022/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSecurity Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox — mentioned by jvbotelhohttps://news.ycombinator.com/item?id=49018887urn:hackerpapers:mention:2506.11022:49018887Thu, 23 Jul 2026 09:20:47 GMT<p>There is also this paper that says that this AI loop makes the security worse getting almost 40% rise of vulns after just 5 iterations https://arxiv.org/html/2506.11022v2</p><p><a href="https://hackerpaper.kaipfister.de/p/2506.11022/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SESecurity Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox — HN submissionhttps://news.ycombinator.com/item?id=45461358urn:hackerpapers:submission:2506.11022:45461358Fri, 03 Oct 2025 10:47:00 GMT<p>Security Degradation in Iterative AI Code Generation</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2506.11022/">Paper and source history</a>. A submission is not an endorsement.</p>cs.SE