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 News & Web Pages
Forget prompt engineering: 'Loop engineering' is all the rage now
1+ day, 7+ hour ago (336+ words) Claude Code creator Boris Cherny says he doesn't "write the prompt anymore." Here's how loop engineering is changing coding....
GBase 8a Table Design and Modeling: Choosing Data Types, Partitions, Distribution Keys, and Replicated Tables
46+ min ago (336+ words) In a distributed analytical gbase database, many performance issues are baked in at the table design stage. Data types, partitioning, distribution keys, and replicated table strategies largely determine query cost down the line. This guide walks through these four core…...
How Developers and Institutions Can Run AI Models Without Exposing Their Data
1+ hour, 18+ min ago (31+ words) Note: This article is Adapted from the official Phala and Cluster announcement. Most people don't think about what "...
What Predictability Actually Measures (and Why Velocity Is the Wrong Question)
1+ hour, 51+ min ago (277+ words) Why I invented a metric I'd never heard of, and why the industry eventually caught up. I started using the term "predictability" in 2019, and I was pretty sure I was making it up. At some point I added a predictability…...
I built Open Code Nexus: A multi-agent workflow plugin for Open Code that prevents context loss and enforces two-stage code reviews.
1+ hour, 35+ min ago (274+ words) Hi everyone, I've been experimenting with multi-agent workflows for coding, and I kept running into the common issue of agents losing context or merging bad code without proper reviews. To solve this, I built Open Code Nexus, an open-source, shareable…...
Building a Memory Agent That Actually Forgets (And the Three Bugs That Taught Me Why That's Hard)
2+ hour ago (398+ words) By Nidhi: Built for the Global AI Hackathon Series with Qwen Cloud, Track 1: Memory Agent When I signed up for Track 1, I figured memory was basically a vector database problem. Store embeddings, retrieve similar messages, done. The first prototype worked…...
GBase 8a Table Design in Practice: Choosing Distribution Keys, Partitions, and Replicated Tables
2+ hour, 34+ min ago (152+ words) Many performance issues are baked in the moment a table is created. This guide systematically explains table design decisions in GBase 8a: how to pick distribution keys, when to partition, how to use replicated tables, and how to choose the right…...
I Built a World Cup 2026 Prediction Pipeline with Sportmicro, Python, and Git Hub Actions
3+ hour, 17+ min ago (438+ words) I wanted a football prediction project that felt closer to a real data product than a one-off notebook. So I built a pipeline that: The repo is here: A lot of sports prediction demos stop at one model and one…...
# Vector Search and RAG: A Primer
3+ hour, 39+ min ago (798+ words) A short learning path from a weekend project: I indexed my personal markdown notes (~800 chunks), tried a few local embedding models, stored the same vectors in four different backends, and wired up simple RAG. Not a production guide " just the…...
why a simple string match beat apple's nlembedding for local rag
4+ hour, 21+ min ago (1662+ words) how apple's nlembedding drove me crazy and how i built my own hybrid search engine recently, while working on my personal ai agent (pheronagent), i was focused on perfecting its memory and retrieval system. the system is simple: i feed…...