https://hackerpaper.kaipfister.de/p/2305.15408/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=41563330urn:hackerpapers:mention:2305.15408:41563330Tue, 17 Sep 2024 02:11:46 GMT<p>I think you&#x27;re misrepresenting the study. It builds upon previous work that examines the computation power of the transformer architecture from a circuit-complexity perspective. Previous work showed that the class of problems that a &quot;naive&quot; Transformer architecture could compute was within TC0 [1, 2] and as a consequence it was fundamentally impossible for transformers to solve certain classes of mathematical problems. This study actually provides a more realistic bound of AC0 (by analyzing the finite-precision case) which rules out even more problems, including such &#x27;simple&#x27; ones as modular…</p><p><a href="https://hackerpaper.kaipfister.de/p/2305.15408/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=36232326urn:hackerpapers:submission:2305.15408:36232326Wed, 07 Jun 2023 19:37:22 GMT<p>Towards Revealing the Mystery Behind Chain of Thought: A Theoretical Perspective</p><p></p><p>5 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2305.15408/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG