https://hackerpaper.kaipfister.de/p/2504.18565/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=46315767urn:hackerpapers:mention:2504.18565:46315767Thu, 18 Dec 2025 17:28:28 GMT<p>This is a really good report! I was particularly fascinated about the self-replication section [0]; I wasn&#x27;t aware of the RepliBench paper [1], and now that I skimmed through it, I&#x27;m quite concerned. It was clear to me before that there&#x27;s nothing particular stopping an AI from replicating, but seeing the already high success percentage at current levels of technology (e.g. 46% success of replicating itself onto compute) is very scary. [0] https://www.aisi.gov.uk/frontier-ai-trends-report#self-repli... [1] https://arxiv.org/abs/2504.18565</p><p><a href="https://hackerpaper.kaipfister.de/p/2504.18565/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR