https://hackerpaper.kaipfister.de/p/2505.03335/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=46907825urn:hackerpapers:mention:2505.03335:46907825Fri, 06 Feb 2026 01:23:44 GMT<p>https://arxiv.org/abs/2505.03335 Check out the paper above on Absolute Zero. Language models don’t just repeat code they’ve seen. They can learn to code give the right training environment.</p><p><a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43951985urn:hackerpapers:submission:2505.03335:43951985Sun, 11 May 2025 07:07:26 GMT<p>Absolute Zero: Reinforced Self-Play Reasoning with Zero Data</p><p></p><p>88 points; 19 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43946729urn:hackerpapers:submission:2505.03335:43946729Sat, 10 May 2025 16:06:18 GMT<p>Absolute Zero: Reinforced Self-Play Reasoning with Zero Data</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43935157urn:hackerpapers:submission:2505.03335:43935157Fri, 09 May 2025 09:30:43 GMT<p>Absolute Zero: Reinforced Self-Play Reasoning with Zero Data</p><p></p><p>3 points; 2 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43922339urn:hackerpapers:submission:2505.03335:43922339Thu, 08 May 2025 01:47:21 GMT<p>Absolute Zero: Reinforced Self-Play Reasoning with Zero Data</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43915814urn:hackerpapers:submission:2505.03335:43915814Wed, 07 May 2025 14:00:36 GMT<p>Absolute Zero: Reinforced Self-Play Reasoning with Zero Data</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=43914264urn:hackerpapers:mention:2505.03335:43914264Wed, 07 May 2025 11:12:33 GMT<p>Paper: https://arxiv.org/abs/2505.03335 Code: https://github.com/LeapLabTHU/Absolute-Zero-Reasoner Thread: https://xcancel.com/AndrewZ45732491/status/19199204597489092...</p><p><a href="https://hackerpaper.kaipfister.de/p/2505.03335/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG