https://hackerpaper.kaipfister.de/p/2311.09205/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49470557urn:hackerpapers:mention:2311.09205:49470557Thu, 27 Aug 2026 20:11:50 GMT<p>On narrow domains, it is very common for small models to match or outperform larger ones at a fraction of the parameter count. For example in language, this is called the “curse of multilinguality”. Small models that handle a single translation direction can easily outperform big ones that try to handle them all. https://arxiv.org/pdf/2311.09205 In any case, for most tasks the question is not “how many tasks can this model kind of do well” but “given time/cost constraints, what is the maximum level of quality we can achieve”. And for that, small models are usually very competitive.</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.09205/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL