Specialized search for programming

Curated, developer-focused results

4Programming is a search engine built for programmers. It prioritizes technical relevance by combining multiple indexes, code-aware ranking, and AI systems. Use it to find code examples, documentation, libraries, tools, tutorials, and services — faster and with fewer irrelevant results than general-purpose search engines. Part of the 4SEARCH network of topic specific search engines.

Latest News & Web Pages

Open Router
openrouter. ai > poolside > laguna-xs-2. 1-20260625

Laguna XS 2. 1 - API Pricing & Providers

1+ hour, 39+ min ago  (394+ words) Laguna XS 2. 1 is the latest coding agent model in the 33 B-A3 B category from Poolside(opens in new tab) and a step forward from their Laguna XS. 2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact…...

Symbols: d05.S0,u11.S0,z74.S0,a33.S0,fq7.S0,qbpr.si
NPower User
nokiapoweruser. com > google-gemini-arena-leak-gemini-3-5-pro-vs-claude-fable-5

Google Is Cooking: New Gemini Models Drop in Chatbot Arena Leaks

1+ hour, 1+ min ago  (482+ words) The artificial intelligence arms race is moving incredibly fast, and Google is turning up the heat. A viral benchmark leak sparked by developer Harshith on X reveals that Google's unreleased, stealth-tested models are fundamentally shifting expectations around front-end design, code…...

Symbols: btc-usd,eth-usd,xrp-usd,sol-usd
Tech Times
techtimes. com > articles > 319542 > 20/26/0702 > new-gemini-flash-checkpoint-surfaces-lm-arena-gemini-4-incremental-update. htm

New Gemini Flash Checkpoint Surfaces on LM Arena: Gemini 4 or Incremental Update?

37+ min ago  (268+ words) The Gemini 3. 5 Flash generation " the current production model, and the baseline against which this new checkpoint is being compared " outperforms Gemini 3. 1 Pro on Terminal-Bench 2. 1 (76. 2% vs. 70. 3%), MCP Atlas (83. 6% vs. 78. 2%), and GDPval-AA agentic evaluation (1, 656 Elo vs. 1, 317 Elo), while generating tokens at roughly…...

Symbols: nasdaq:gemi,nasdaq:googl
Google News
devops. com > z-ai-debuts-zcode-to-compete-with-github-copilot-cursor-and-anthropic

Z. ai Debuts ZCode to Compete With Git Hub Copilot, Cursor and Anthropic

12+ min ago  (376+ words) By: James Maguire on July 2, 2026 Chinese AI developer Z. ai has introduced ZCode, a desktop application that automates software development tasks, positioning the platform to compete with established coding platforms from Anthropic, Git Hub and Cursor. The company built ZCode, which…...

Symbols: nyse:ai
Cyber Security News
cybersecuritynews. com > hackers-use-mapbox-dead-drop-c2

Hackers Use Mapbox Dead-Drop C2 and Python RAT to Target Vulnerability Researchers

3+ hour, 38+ min ago  (624+ words) Security researchers have uncovered a long-running campaign that turns trusted proof-of-concept exploits into weapons against the very people who study vulnerabilities for a living. The operation, tracked under the name Choco Po C, hides a fully functional Python remote access…...

The Decoder
the-decoder. com

Anthropic says it cut 80 percent of Claude Code's system prompt because Fable 5 models "want a smaller system prompt"

34+ min ago  (190+ words) the-decoder. com Anthropic says it cut 80 percent of Claude Code's system prompt because Fable 5 models "want a smaller system prompt" Anthropic says it has cut 80 percent of the system prompt for Claude Code. Tariq Shihipar, a member of technical staff…...

Symbols: cert-in,nasdaq:nvda,nasdaq:goog,nasdaq:googl,nasdaq:spcx
@phoronix
phoronix. com > news > Linux-AI-Attribution-Again

Linux Kernel Developers Again Discussing AI Agent Attribution - Potentially Dropping It

1+ hour, 45+ min ago  (232+ words) When AI/LLM agents are used in the creation of Linux kernel patches, the policy for a while now has been that it should be specified using an "Assisted-by" tag as part of the patches/commits. But Linux kernel developers…...

Symbols: abxx.ne,btc-usd,nasdaq:arm,eric-b.st
Tech Times
techtimes. com > articles > 319534 > 20/26/0702 > chatgpt-pro-splitting-three-gpt-56-benchmark-reveals-luna-terra-sol-pro. htm

Chat GPT Pro Is Splitting Into Three: GPT-5. 6 Benchmark Reveals Luna, Terra, Sol Pro

1+ hour, 38+ min ago  (449+ words) Chat GPT Pro has always meant one thing: access to the single best model Open AI ships. That simplicity appears to be ending. The standard GPT-5. 6 Sol cleared 28. 7% of those problems at its highest reasoning setting. With what the paper…...

Symbols: nasdaq:goog,nasdaq:googl,nasdaq:meta,spax.pvt
TFOT
thefutureofthings. com > 28986-how-emerging-tech-startups-build-scalable-infrastructure-without-owning-data-centers

How Emerging Tech Startups Build Scalable Infrastructure Without Owning Data Centers

1+ hour, 9+ min ago  (324+ words) The mythology of startup success often centers on product ingenuity, market timing, and venture capital. However, beneath every fast-scaling software is infrastructure, which is the decisive factor. In the early internet era, scaling meant racks of physical servers, climate-controlled rooms,…...

Symbols: cnq.to,enb.to,tsx:bip.un,bip.un
Tribune Online
tribuneonlineng. com > top-free-ui-ux-component-libraries-you-dont-have-to-pay-for > amp

Top free UI/UX component libraries you don't have to pay for

8+ hour, 13+ min ago  (616+ words) You don't need to buy expensive, pre-designed templates to limit the creativity in building a digital product. In today's world of product design and development, the key to speed and uniformity is using free, open-source libraries of components." Structured design…...

Symbols: gtag.js,data.ts,btc-usd,uhs-ii