https://hackerpaper.kaipfister.de/p/2310.02238/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=40156273urn:hackerpapers:mention:2310.02238:40156273Thu, 25 Apr 2024 11:47:20 GMT<p>There was one where they tried to remove Harry Potter... Who&#x27;s Harry Potter? Approximate Unlearning in LLMs https://arxiv.org/abs/2310.02238 See also The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported https://arxiv.org/abs/2403.12082v1</p><p><a href="https://hackerpaper.kaipfister.de/p/2310.02238/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=37989403urn:hackerpapers:submission:2310.02238:37989403Mon, 23 Oct 2023 18:11:31 GMT<p>Who&#x27;s Harry Potter? Approximate Unlearning in LLMs [pdf]</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2310.02238/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=37976878urn:hackerpapers:submission:2310.02238:37976878Sun, 22 Oct 2023 16:40:07 GMT<p>Who&#x27;s Harry Potter? Approximate Unlearning in LLMs</p><p></p><p>2 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2310.02238/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL