Think Again Networks and the Delta Loss · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1904.11816/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTThink Again Networks and the Delta Loss — mentioned by atrudeauhttps://news.ycombinator.com/item?id=45517307urn:hackerpapers:mention:1904.11816:45517307Wed, 08 Oct 2025 15:33:34 GMT<p>Very cool to see the effectiveness of recurrence on ARC. For those interested in recurrence, here are other works that leverage a similar approach for other types of problems: Language modeling: Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach https://arxiv.org/pdf/2502.05171 Puzzle solving: A Simple Loss Function for Convergent Algorithm Synthesis using RNNs https://openreview.net/pdf?id=WaAJ883AqiY End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking https://arxiv.org/abs/2202.05826 Can You Learn an Algorithm?…</p><p><a href="https://hackerpaper.kaipfister.de/p/1904.11816/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL