The Mathematics Search Engine
Mathematics News & Resources
4Mathematics is a specialist search engine for Mathematics. Discover the latest math news and mathematical content. Part of the 4SEARCH network of topic specific search engines.
Latest Articles
My GPU Database Lost to a Single CPU Thread. The Bug Was One Constant, 128x Too Small
12+ min ago (700+ words) Summer Bug Smash: Smash Stories 🐛🛹 This is a submission for DEV's Summer Bug Smash: Smash Stories powered by Sentry. I maintain a GPU SQL engine — a DuckDB community extension that runs aggregates and GROUP BY on Apple Silicon via Metal....
Benchmarks Don't Build Great Products. Engineers Do.
4+ min ago (1021+ words) The AI industry has a benchmark problem. Not because we have too many benchmarks. Because too many companies treat them like trophies instead of tools. A benchmark's primary job is to make your product better. Publishing the score is secondary....
Applied Sciences, Vol. 16, Pages 8342: A Novel Lightweight Transformer-Free Neuro-Scattering Mamba-KAN Architecture for Respiratory Sound Classification
13+ min ago (445+ words) Automated pulmonary auscultation demands rapid and reliable anomaly detection. Contemporary deep learning frameworks frequently face deployment barriers due to their reliance on memory-intensive Transformer mechanisms and high-cost processing hardware. Addressing this limitation, the present study introduces the Neuro Scatter Mamba…...
Why Spreadsheet Translation Is Really a Data-Integrity Problem
16+ min ago (559+ words) A translated spreadsheet is successful when the people receiving it can use it with the same confidence as the original....
Pangaea Data uses AI platform to identify untreated and under-treated patients
1+ hour, 14+ min ago (339+ words) Biotech organisation’s platform uses Microsoft AI Azure, Fabric, Text Analytics for Health and Azure OpenAI By Kasturi Datta | 21 August 2026 Biotech organisation Pangaea Data has built an AI platform on Microsoft AI Azure and Microsoft Fabric that helps clinicians identify untreated…...
Latest News In AI Chips - Cloudera NVIDIA Partnership Boosts Apache Spark Performance
3+ hour, 9+ min ago (187+ words) Recent advancements in AI chips have been exemplified by Cloudera's partnership with NVIDIA, which introduces native GPU acceleration for Apache Spark 4.1 within Cloudera Data Engineering. This integration, facilitated by the NVIDIA CUDA-X library cuDF, promises up to fourfold faster processing…...
Error Feedback, Gradient Compression, and Why Adam Breaks It
46+ min ago (424+ words) That guarantee is why error feedback shows up in every low-precision training recipe, including the one I wrote. It is also why I never questioned it. The guarantee is real, it is provable, and it holds under SGD. The code…...
I Ran a 284B-Parameter LLM From 3.2GB of RAM — in Plain C
52+ min ago (913+ words) DeepSeek-V4-Flash has 284 billion parameters and takes up about 160GB on disk. My laptop does not have 160GB of RAM. It doesn't even have 32GB. It ran the model anyway. Peak memory: 3.23GB. With a GPU and a bit more headroom, it generates at…...
ox-alpha vs GLM-5.2 - AI Model Comparison
3+ hour, 28+ min ago (14+ words) OpenCode Related comparisons. Other model pairs to check....
Hy-MT2-30B-A3B vs Aion-3.0 - AI Model Comparison
12+ hour, 2+ min ago (82+ words) OpenRouter Hy-MT2-30B-A3B vs Aion-3.0: side-by-side summary Hy-MT2-30B-A3B and Aion-3.0 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration. Hy-MT2-30B-A3B, from tencent, has a 8,192-token context window and is priced…...