AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2410.09024/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTAgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents — mentioned by TaurenHunterhttps://news.ycombinator.com/item?id=42647324urn:hackerpapers:mention:2410.09024:42647324Thu, 09 Jan 2025 16:36:36 GMT<p>&quot;More Agents is all you need&quot; https://arxiv.org/abs/2402.05120 I could not find a &quot;Agents considered harmful&quot; related to AI, but there is this one: &quot;AgentHarm: A benchmark for measuring harmfulness of LLM agents&quot; https://arxiv.org/pdf/2410.09024 This &quot;Agents considered harmful&quot; is not AI-related: https://www.scribd.com/document/361564026/Math-works-09</p><p><a href="https://hackerpaper.kaipfister.de/p/2410.09024/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG