SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2511.08983/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving — mentioned by ianjbutlerhttps://news.ycombinator.com/item?id=49474824urn:hackerpapers:mention:2511.08983:49474824Fri, 28 Aug 2026 05:52:02 GMT<p>&gt; These researchers wanted methods based on human input to win and were disappointed when they did not.[1] This was/is basically a strawman though. Like maybe &quot;human input winning&quot; was desirable for chess masters but for computer science wonks? Not the point or the disappoint. It&#x27;s always neats and scruffies fighting about using some kind of recognizable method (logic) instead of magic (ML). &gt; breakthrough progress eventually arrives by an opposing approach based on scaling computation by search and learning. More to OP&#x27;s point I think: nowadays when someone wants to beat you over the head…</p><p><a href="https://hackerpaper.kaipfister.de/p/2511.08983/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL