Install
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
Jumia Product Analysis WithExcel Dashboards
42+ min ago (393+ words) Introduction Big E-commerce organisation like Jumia handle large datasets that are vital... Tagged with datascience, analytics....
Modern GLSL Shader Development in Zed & VS Code: Zero Setup, Real-Time Diagnostics
2+ hour, 4+ min ago (171+ words) Writing GLSL shaders often feels like stepping ten years back in time compared to modern web or... Tagged with gamedev, shader, glsl, vulkan....
AMD Local LLM Setup on Windows/Linux: ROCm Overrides & Vulkan vs. HIP Benchmarking
2+ hour, 21+ min ago (117+ words) The Problem with Local AI on AMD Hardware Running models locally with tools like Ollama or LM Studio on AMD GPUs often leads to two roadblocks: Uncertainty over whether to run Vulkan backends or ROCm/HIP backends for maximum tokens…...
My PR got merged into the Harvard CS249r ML Systems book 🎉
2+ hour, 38+ min ago (184+ words) PR #1962 — feat(staffml): add recent-papers section to About page Repo: harvard-edge/cs249r_book — 28.4k ⭐, the open-source textbook for Harvard CS249r covering ML Systems, Agentic AI, and Physical AI. What I did: Spotted issue #1792 (StaffML improvement suggestions) Scoped my work to just the recent-papers section…...
USAspending API, No API Key: Federal Contract Awards
3+ hour, 11+ min ago (658+ words) USAspending.gov publishes federal award data through a public REST API that requires no authentication. There is no signup, no key header, no quota form. You POST JSON, you get JSON. Exactly one filter is required: filters.award_type_codes. Omit it and…...
Types of Context Rot in Harness Engineering
4+ hour, 18+ min ago (1353+ words) That set of degradations has a name: context rot. And it's not one problem. It's five distinct failure modes that combine, compound, and get worse the more you naively pile things into a bigger and bigger context window. By the…...
Your AI Doesn’t Need a Better Prompt. It Needs a Better Reading System
37+ min ago (352+ words) The most expensive AI failures rarely look like model failures. The answer sounds polished. The summary is plausible. The …...
Beyond zstd: A Lossless Compressor That Pushes the Pareto Frontier
45+ min ago (971+ words) Cold storage is cheap. Reading it back is not. MIT-licensed, block-adaptive compression: often faster decode than zstd at the same …...
Don’t Start with a Model. Start with the Problem.
49+ min ago (34+ words) I still pick the business problem first. Then the stack. This is the five-of-everything I hand working engineers who want next year to ship — not …...
Your RAG Pipeline Can Be Fast and Still Be Wrong: A Developer's Guide to Embedding Evaluation
5+ hour, 28+ min ago (1309+ words) Hello, I'm Shrijith Venkatramana, and I'm building LiveReview — a blast-radius aware AI code review... Tagged with ai, webdev, programming, productivity....