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

The GitHub Blog
github.blog > changelog > 2026-09-04-new-api-endpoint-provides-privacy-safe-star-history-data

New API endpoint provides privacy-safe star history data - GitHub Changelog

9+ hour, 34+ min ago   (89+ words) New API endpoint provides privacy-safe star history data The GitHub Blog Track repository star growth over time with the new star history REST API endpoint without exposing stargazer identities. Earlier this year, stargazer listing endpoints were restricted to admins and…...

t.co
yiyihum.github.io > SciLaws-Bench

SciLaws-Bench??? Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

1+ hour, 19+ min ago   (364+ words) We took 118 open problems out of 381 scientific papers — the kind a research community is still arguing about — and asked frontier models to find the law twice: once from the measurements science already has, and once inside a world whose law…...

Portal ERP
portalerp.com > za > noticia > sas-interns-apply-data-to-support-local-students

SAS interns apply data to support local students

8+ hour, 4+ min ago   (383+ words) This summer, interns at global data and AI leader SAS had the chance to help the Boys & Girls Clubs of Wake and Johnston Counties through a Data for Good project demonstrating how data, technology and community service can come together…...

DEV Community
dev.to > pmdroid > my-agents-dont-get-to-vibe-207p

My Agents Don't Get to Vibe 🤖

36+ min ago   (428+ words) Hey tech adventurers! 👋 I use coding agents a lot. Probably an irresponsible amount. My current favorite is Grok Build. 🤖❤️ But I don't want my workflow tied to one agent. Models change, shiny new robots appear, benchmarks go brrrr, and everyone…...

DEV Community
dev.to > jamilxt > ai-agents-failed-to-prove-fermats-last-theorem-then-they-got-a-shared-to-do-list-h0k

AI Agents Failed to Prove Fermat's Last Theorem. Then They Got a Shared To-Do List

1+ hour, 44+ min ago   (751+ words) On September 4, Anthropic published something that sounds like a headline from a decade in the future: the first complete, computer-checked proof of Fermat's Last Theorem, written by a team of Claude agents working largely autonomously over 11 days. Thirteen million lines…...

DEV Community
dev.to > natuworkguy > ollamas-cloud-suffix-isnt-a-label-its-a-silent-instruction-i-bypassed-it-ce4

Ollama's -cloud suffix isn't a label, it's a silent instruction. I bypassed it.

2+ hour, 39+ min ago   (762+ words) I never built:31b. I built:31b-cloud. I asked for:31b-cloud. Ollama went looking for something else, didn't find it, and told me so, using a name that existed nowhere on my machine, in my registry, or in my head. TL;…...

Windows Latest
windowslatest.com > 09/05/2026 > microsoft-is-adding-an-ai-powered-canvas-to-excel-that-turns-workbook-data-into-interactive-dashboards

Microsoft is adding an AI-powered Canvas to Excel that turns workbook data into interactive dashboards

11+ hour, 52+ min ago   (545+ words) In July 2026, Microsoft added as many as six Copilot features to Excel, and I am not even considering the third-party integrations. Now, there’s another one coming, and it’s called Copilot Canvas, which might actually be useful. By the looks of…...

DEV Community
dev.to > uridovoicenote > dictation-is-not-long-form-transcription-i-tried-five-tools-before-writing-my-own-5505

Dictation is not long-form transcription — I tried five tools before writing my own

3+ hour, 43+ min ago   (707+ words) Dictation is writing with your mouth: you say a sentence, look at the screen, fix it. Transcribing long-form audio is a different problem — you talk for fifteen minutes without looking at anything, and you want the whole text afterwards. Almost…...

mint
livemint.com > opinion > ai-agents-agentic-ai-children-and-ai-childhood-personal-accountability-agency-decision-making-ai-assistants-11788425568662.html

Growing up agentic: childhood sans consequences

3+ hour, 21+ min ago   (381+ words) With another intelligence now occupying the space between intention and outcome, how will agentic-natives develop personal accountability and agency? Now the agents can handle our email, make travel plans, track agendas, replenish supplies, do useless shopping, and execute projects. To…...

DEV Community
dev.to > mno_tao_236ab4649edf4cf9f > what-local-ocr-should-mean-in-a-web-application-1ai7

What “local OCR” should mean in a web application

3+ hour, 50+ min ago   (680+ words) “Runs in your browser” is easy to put on a landing page. It is harder to make it a property of the whole OCR pipeline. Here is the approach I use for a browser-only OCR tool. For an image or…...