137 related articles
Qoder's Context Engineering in Practic…
Deep analysis of Qoder's (Tongyi Lingma international edition) context engineering architecture, including its four-layer retrieval engine, memory engine, context caching, and core product design.
Cursor + Claude 3.7 Sonnet Coding Test…
Hands-on comparison of Claude 3.7 Sonnet vs 3.5 in Cursor across four front-end tasks, revealing dramatic improvements in requirement understanding, UI aesthetics, and multimodal recognition.
The Right Way for Beginners to Build P…
Vibe Coding isn't just chatting with AI. Learn the Iterative Build Loop: Discuss, Document, Develop, Learn — with VS Code and Claude Code to build products from scratch.
35 Lines of Prompts Let Codex Auto-Opt…
An OpenAI employee used just 35 lines of prompts to have Codex analyze 30 days of work history, identify repetitive tasks, and generate reusable automated Skills. Combined with screen reading and long-term memory, Codex is becoming a proactive workflow optimization agent.
Tech FrontiersAnthropic releases Claude Opus 4.8 with three core improvements based on user feedback: better nuance understanding, more natural conversations, and stronger collaboration from coding to knowledge work.
Tech FrontiersOpenAI CEO Sam Altman announces a general-purpose AI model has solved a major open math problem. We analyze this milestone, the leap from specialized to general AI, and its implications for science.
BMad-Method: Building an AI Agile Deve…
Deep dive into BMad-Method, an open-source multi-agent framework simulating a full agile team—from business analysis to QA—supporting Claude Code, Cursor, and more.
Spring AI Agent Utils: A Java Agent To…
Deep dive into Spring AI Agent Utils toolkit covering Skill modules, Ask a User Question, To Do Write, Auto Memory, and multi-Agent orchestration — empowering Java developers to build powerful AI Agents.
Codex Comes to Windows: AI Agents Take…
OpenAI Codex for Windows now supports Computer Use, letting AI agents directly control your PC. With Chrome multi-tab background work and mobile remote control.
Codex Security Guide: Five Key Princip…
A detailed guide to OpenAI Codex permission management covering workspace setup, three permission modes, approval mechanisms, risk-level management, and five safety mantras for secure AI coding.
Web Studio: Open-Source Local AI Codin…
Web Studio is an open-source desktop AI coding workbench integrating Cloud Code, Gemini CLI, and Codex into a local-first app with multi-repo management, structured code review, and smart PR workflows.
Zen MCP: An Open-Source Tool That Lets…
Deep dive into Zen MCP, an open-source project that lets Claude Code orchestrate Gemini, O3, and other AI models via MCP protocol, with cost-reduction proxy setup guide.
Claude Opus 4.8 Deep Dive: A Comprehen…
Deep dive into Claude Opus 4.8's core upgrades: improved judgment, optimized honest feedback, and Fast Mode costs cut to one-third. Compared with DeepSeek and GPT-5.5 for AI coding and long-context reasoning.
WenzAgent Open-Source Framework: A Pra…
A detailed guide on deploying WenzAgent, an open-source multi-Agent management framework under Apache License, supporting LAN-based multi-device AI agent collaboration with Server-Client architecture.
Harness AI Engineering: A Practical Me…
Explore the Harness AI Engineering methodology for enterprise AI programming — solving code hallucinations, quality issues, and more with systematic human-AI collaboration.
Industry InsightsGlobal IT services firm Endava uses OpenAI Codex to build an Agentic Organization, compressing requirements analysis from weeks to hours. A deep dive into AI-driven software delivery transformation.
Cursor Major Update: A Complete Breakd…
Deep dive into Cursor's latest update: new cross-file Tab model, Background Agent for autonomous coding, Max Mode for all models, inline editing upgrades, and more AI programming features.
AI Agent Learning Roadmap: From Beginn…
A detailed three-month AI Agent learning roadmap covering LLM basics, ReAct paradigm, LangChain, memory mechanisms, tool calling, and multi-agent collaboration with practical project suggestions.
Claude Opus 4.8 Deep Dive: Honesty Mat…
Claude Opus 4.8 core upgrade: code bug oversight rate reduced 4x, model becomes more honest. Covers Dynamic Workflows parallel orchestration, Claude Code quota reset, effort control, and upcoming Miscells model.
ResearchGitHub is building a general-purpose accessibility AI Agent to automatically detect and fix software accessibility issues. Explore the technical challenges, human-AI collaboration, and industry impact.