https://hackerpaper.kaipfister.de/p/2505.23869/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49802938urn:hackerpapers:mention:2505.23869:49802938Tue, 22 Sep 2026 15:29:50 GMT<p>Reminded me Google&#x27;s earlier paper, &quot;Language Modeling Is Compression&quot; https://arxiv.org/abs/2309.10668 Learning being a compression is also recently proposed as Gibbs compression proposition. See Gibbs randomness-compression proposition https://arxiv.org/abs/2505.23869v5</p><p><a href="https://hackerpaper.kaipfister.de/p/2505.23869/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML