https://hackerpaper.kaipfister.de/p/2506.22760/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=44841634urn:hackerpapers:mention:2506.22760:44841634Fri, 08 Aug 2025 20:59:26 GMT<p>From the paper: &gt; Most language models face a fundamental tradeoff where powerful capabilities require substantial computational resources. We shatter this constraint with Jan-nano, a 4B parameter language model that redefines efficiency through radical specialization: instead of trying to know everything, it masters the art of finding anything instantly. Fine-tuned from Qwen3-4B using our novel multi-stage Reinforcement Learning with Verifiable Rewards (RLVR) system that completely eliminates reliance on next token prediction training (SFT), Jan-nano achieves 83.2% on SimpleQA benchmark with…</p><p><a href="https://hackerpaper.kaipfister.de/p/2506.22760/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL