Because we have LLMs, we Can and Should Pursue Agentic Interpretability · HackerPapers discussions

Because we have LLMs, we Can and Should Pursue Agentic Interpretability · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2506.12152/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTBecause we have LLMs, we Can and Should Pursue Agentic Interpretability — HN submissionhttps://news.ycombinator.com/item?id=44494845urn:hackerpapers:submission:2506.12152:44494845Mon, 07 Jul 2025 21:28:40 GMT<p>Because We Have LLMs, We Can and Should Pursue Agentic Interpretability</p><p></p><p>4 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2506.12152/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI