"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2308.03825/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMT"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models — HN submissionhttps://news.ycombinator.com/item?id=37139871urn:hackerpapers:submission:2308.03825:37139871Tue, 15 Aug 2023 22:05:25 GMT<p>Characterizing and Evaluating In-the-Wild Jailbreak Prompts on LLMs</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2308.03825/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CR"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models — HN submissionhttps://news.ycombinator.com/item?id=37066337urn:hackerpapers:submission:2308.03825:37066337Wed, 09 Aug 2023 17:59:31 GMT<p>Do anything now Understanding jailgbreak prompts in modern LLMs</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2308.03825/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CR