https://hackerpaper.kaipfister.de/p/2607.05147/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49303073urn:hackerpapers:mention:2607.05147:49303073Fri, 14 Aug 2026 18:54:28 GMT<p>Deepseek&#x27;s DSpark does dynamically adjust speculated token count per user/completion. https://arxiv.org/abs/2607.05147 But they do so to maximise total throughput, I don&#x27;t think there&#x27;s reason to do that for batch=1.</p><p><a href="https://hackerpaper.kaipfister.de/p/2607.05147/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AIhttps://news.ycombinator.com/item?id=48892597urn:hackerpapers:mention:2607.05147:48892597Mon, 13 Jul 2026 13:45:36 GMT<p>Some of the most exciting engineering work is happening in the DS4 repo - and I&#x27;m watching it almost like a sports game. When the DSpark paper came out[1] the next day we had folks attempting to implement, working together, validating their failures. Eventually their work being synthesized into a PR[1] that admits performance is not ideal. Something antirez alluded to in one of his videos (speculative decoding is a great boon, but mostly for large labs hosting and serving many requests at once, and maybe not so effective for local inference). There&#x27;s recent work into &quot;directional steering&quot;[3]…</p><p><a href="https://hackerpaper.kaipfister.de/p/2607.05147/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI