https://hackerpaper.kaipfister.de/p/2605.09998/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49619356urn:hackerpapers:submission:2605.09998:49619356Wed, 09 Sep 2026 01:00:27 GMT<p>Continual Harness: Online Adaptation for Self-Improving Foundation Agents</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2605.09998/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=49262057urn:hackerpapers:mention:2605.09998:49262057Tue, 11 Aug 2026 17:59:24 GMT<p>How to prevent wasteful AI loops without a human in the loop to intercede in death spirals that burn token budgets? Not unique to this loop pattern. There was this from DeepMind a few weeks ago about online rewriting of agent prompt materials: &quot;Continual Harness: Online Adaptation for Self-Improving Foundation Agents&quot; (2026) https://arxiv.org/abs/2605.09998 .. https://news.ycombinator.com/item?id=48126112 Costed WASM opcodes would probably help prevent waste by enabling optimization of agent loops.</p><p><a href="https://hackerpaper.kaipfister.de/p/2605.09998/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=48126112urn:hackerpapers:submission:2605.09998:48126112Wed, 13 May 2026 19:11:10 GMT<p>Continual Harness: Online Adaptation for Self-Improving Foundation Agents</p><p></p><p>8 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2605.09998/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG