https://hackerpaper.kaipfister.de/p/2405.14577/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=40710557urn:hackerpapers:mention:2405.14577:40710557Mon, 17 Jun 2024 20:15:55 GMT<p>I would not say it’s impossible… my lab is working on this (https://arxiv.org/abs/2405.14577) and though it’s far from mature - in theory some kind of resistance to downstream training isn’t impossible. I think under classical statistical learning theory you would predict it’s impossible with unlimited training data and budget for searching for models but we don’t have those same gaurentees with deep neural networks.</p><p><a href="https://hackerpaper.kaipfister.de/p/2405.14577/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=40465249urn:hackerpapers:submission:2405.14577:40465249Fri, 24 May 2024 11:59:26 GMT<p>Representation noising effectively prevents harmful fine-tuning on LLMs</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2405.14577/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL