Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2512.18901/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTGabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models — mentioned by gcrhttps://news.ycombinator.com/item?id=47286704urn:hackerpapers:mention:2512.18901:47286704Sat, 07 Mar 2026 11:36:28 GMT<p>wait, SVD / zeroing out the first principal component is an unsupervised technique. The earlier difference-of-means technique relies on the knowledge of which outputs are refusals and which aren’t. How would SVD be able to accomplish this without labels? edit: the reference is https://arxiv.org/pdf/2512.18901 they are randomly sampling two sets of refusal/nonrefusal activation vectors, stacking them, and taking the elementwise difference between these two matrices. Then they use SVD to get the k top principal components. These are the directions they zero out. Seems to me that the top…</p><p><a href="https://hackerpaper.kaipfister.de/p/2512.18901/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI