297 related articles

Tongyi Qianwen Qwen-Image-3.0 image generation model gets a comprehensive upgrade: supporting 4,500-token ultra-long instructions, pixel-level detail rendering, 12-language knowledge understanding, and ancient painting restoration. This article analyzes its three core capabilities.

Alibaba open-sources a 2.4 trillion parameter Qwen model and launches the Qwen Token Plan. Chinese models surge, Kimi K3 tops global rankings, and China's AI is reshaping the global competitive landscape.

Upgraded Cursor and can't find the classic file tree? Learn two quick methods to switch back from Agent mode using the Open Edit Window button or File menu.

Learn how to use Codex for AI-powered programming with natural language prompts — from generating origami assets to building a gesture-interactive portfolio site. No coding required.
Windows Terminal: A Modern Command-Lin…
A deep dive into Windows Terminal, Microsoft's open-source project featuring GPU-accelerated rendering, multi-tab panes, JSON customization, and WSL integration.

Modern Web Guidance is an agent skill & CLI tool that injects modern Web standards into AI coding assistants like Claude Code and Copilot CLI, replacing outdated polyfills with Baseline-validated solutions.

Vibe Coding is an AI-driven development paradigm that requires no coding skills. Use natural language to guide AI through design, development, and testing. Learn the 4-step workflow using Gemini, Figma Make, and Claude Code.

Cursor designer Rio: AI compresses build loops dramatically, but risks flooding the world with mediocrity. From Glass UI principles to the migration of craft — why human agency, taste, and responsibility remain software's true core.

How one self-hoster achieved 21 concurrent Plex streams, tackled bandwidth and disk I/O bottlenecks, and built Manifold — a custom React dashboard combining netdata and MQTT.
Handwritten C/CUDA Inference Engine: P…
A deep dive into a handwritten C/CUDA inference engine for Qwen 35B on RTX 5090 (Blackwell), covering quantization, FlashAttention kernels, and memory optimization.

Chrome's Modern Web Guidance offers 100+ expert-reviewed guides to help AI Agents adopt modern web practices, fixing training data lag and legacy pattern recommendations with semantic search and Baseline compatibility checks.

An electronics engineering student who hates hardware wants to pivot to backend dev, facing a dilemma between a "guaranteed" degree and a third-tier BCA. We break down the degree vs. skills tradeoff, how to explain gaps, and self-study paths.

Deep dive into OpenClaw multi-agent AI programming workflows: context layering, CMUX parallel terminal management, work trees, and manager-perspective debiasing for scalable AI dev automation.
wigolo: A Zero-Cost MCP Tool That Give…
wigolo is a local-first open-source MCP tool that gives AI coding assistants like Cursor and Claude Code free web search, fetch, crawl, and research capabilities — no API keys, no cloud, $0/query.

A non-programmer tests AMD Ryzen AI Halo by deploying local AI models to tackle a real dev task. After testing Ollama and Qwen3, the verdict: AI amplifies developers, it doesn't replace them.

A 1-billion-token deep dive into GPT-5.6 Solar Max reveals qualitative leaps in coding stability, Skills compliance, and frontend design. Includes version selection guide.

A hands-on guide to installing and configuring the OpenAI Codex IDE extension, covering its three working modes and Agent demo. Supports VS Code, Cursor, and Windsurf.

UFM Pro is a free dual-panel file manager for Android and Android TV, featuring D-pad navigation, AES-256 local encryption, built-in FTP/SFTP server, RClone cloud support, and a GPL v3 open-source version.

Hands-on test of a conversational AI Agent completing a full interior design workflow — from blank floor plan to layout, renderings, storyboard animation, and presentation deck — using only natural language.

Hands-on test of ChatCut AI video editor: Codex plugin support, auto filler removal, MG animation & subtitle generation. Full workflow test on a 3min 20sec video.