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
Features — Jetro
8+ hour, 17+ min ago (195+ words) Everything Jetro gives your agent and your canvas. Jetro is a toolkit that turns your code editor into a full research and analysis environment. It gives the AI agent specialized skills, a visual canvas, a local database, and a bunch…...
Local LLMs in 2026: What Actually Runs Well on a Laptop Now
34+ min ago (190+ words) Two years ago, "run a language model locally" meant a weekend of compiling, a graveyard of CUDA errors, and a model that answered like it had a concussion. In 2026, you can install one tool, type one command, and have a…...
Default-to-Flagship Is Now a Cost Bug: Tiered Model Routing for Agentic Workloads
36+ min ago (511+ words) For two years the reflex was simple: reach for the biggest model you can afford and call it a day. In 2026 that reflex quietly became a bug in your cost model. The clearest signal came this summer, when a smaller,…...
A look at “Spiralism”, a quasi-spiritual movement that grew in 2025 from human-AI conversations after sycophantic GPT-4o updates and expanded ChatGPT memory
36+ min ago (12+ words) Top news and commentary for technology's leaders, from all around the web....
Notes & guides
7+ hour, 21+ min ago (1683+ words) Getting more done with AI — tips, ideas, and what's new. You don't need a gaming GPU to use an AI coding agent. Here's what actually matters — RAM, internet, storage — and what doesn't. A step-by-step walkthrough for building an app with…...
Measuring diffusion video performance on a MacBook: one speedup and a large gap
1+ hour, 3+ min ago (876+ words) Last month, I published a benchmark showing a 1.125× speedup from block-residual caching on 4-bit FLUX. The main lesson was not the multiplier. It was that my original quality metrics had been measuring the wrong thing, and that acceleration claims often…...
The Two Layers That Decide Whether Your Agent Survives
1+ hour, 21+ min ago (955+ words) I have read a lot of agent architecture content over the last two years, and almost all of it is about the same layer: how the agent thinks. Prompt chaining, routing, orchestrator-workers, evaluator-optimizer, ReAct, plan-and- execute. That layer is genuinely…...
Lessons from a Robotics Startup: What I Learned About Data Pipelines
56+ min ago (435+ words) "Smile because it happened" — Dr. Seuss These aren't company secrets. They're about the general engineering challenges that anyone working with robotics data pipelines will encounter — challenges I'd read about in papers but hadn't truly internalized until I was standing in…...
Hank Green AI controversy raises questions for science communicators
12+ hour, 1+ min ago (624+ words) Four words in a Hank Green video—"I appreciate the pushback"—were enough to make some viewers suspect the voice of artificial intelligence, sparking fan backlash, prompting a public apology from Green and raising bigger questions about how AI is…...
Advanced GPU Optimization: How can I tech an LLM with CUDA and ROCm? - Part 2
2+ hour, 30+ min ago (681+ words) Welcome back! In Part 1, we built the foundation: from vector addition to tiled GEMM, and finally assembled a complete forward pass of a Transformer block using HIP (CUDA/ROCm). But a forward pass without gradients is just a very expensive…...