https://hackerpaper.kaipfister.de/p/2405.16684/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=40659148urn:hackerpapers:submission:2405.16684:40659148Wed, 12 Jun 2024 15:24:24 GMT<p>Gzip Predicts Data-Dependent Scaling Laws</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2405.16684/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=40504084urn:hackerpapers:submission:2405.16684:40504084Tue, 28 May 2024 18:48:42 GMT<p>Show HN: Chinchilla Scaling Laws Are Not Universal</p><p>Hey HN! Chinchilla (DeepMind 2022) tells us that when we scale up our language model training, we should scale the parameters and data equally. Over the last several months I&#x27;ve been hacking on a research project to determine if the optimal compute allocation (scaling law) for training an LLM is sensitive to training data complexity. I found that as data complexity increases, you need even more data than Chinchilla suggests! I released the preprint just yesterday: https://arxiv.org/abs/2405.16684</p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2405.16684/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=40503161urn:hackerpapers:submission:2405.16684:40503161Tue, 28 May 2024 17:28:15 GMT<p>Gzip Predicts Data-Dependent Scaling Laws</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2405.16684/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL