#AI编程
9632 related articles
Claude Code + Skills: A Practical Walkthrough of Automated Web Test Case Generation
Learn how Claude Code's Skills mechanism automates Web test case generation in three stages — requirements splitting, test point extraction, and case output — in under 10 minutes.
AI Agents Tackle Particle Physics: How the LEBRON Framework Computes Electroweak Phase Transitions
Fermilab postdoc Isaac Wang presents LEBRON, an AI Agent framework for computing electroweak phase transitions. Covers four LLM failure modes in rigorous physics, auditor mechanisms, and why AI hasn't revolutionized theoretical physics the way it has math.
Anthropic Launches Developer Certification Program: A Three-Tier System Explained
Anthropic is building a developer certification program with three tiers: Developer Foundations, Architect Foundations, and Professional. Here's what it means for AI practitioners.
Running DeepSeek V4.1 Flash Locally on Mac Studio: How Far Can Local LLMs Really Go?
A 24-hour stress test of DeepSeek V4.1 Flash on Mac Studio M3 Ultra: 55B params, N-gram mechanisms, thinking mode trade-offs, and Deep SWE benchmark analysis.
MiniCPM5-2B Benchmarked: A 2B Model Scores 46.4 on SWE-bench
MiniCPM5-2B scores 46.4 on SWE-bench with just 2B parameters, beating 4B rivals. Supports 128K context, native tool calling, Apache 2.0 license, runs fully offline.
Building a Local AI Video Generator with GPT and Grok — Does It Actually Work?
A non-engineer blogger used GPT, Grok, and Cursor to build a local AI video generator from scratch — and actually ran the Will Smith spaghetti test. Here's what worked, what didn't, and why compute still wins.
NeoHorse-1-4B Hands-On Review: The Local Small Model That Trains Itself
NeoHorse-1-4B is a locally-runnable open-source model built on Coin 3.5, using recursive self-improvement training via live routing logs. Hands-on review inside.
Harness Engineering in Practice: A Deep Dive into Enterprise Multi-Agent Architecture
A deep dive into an enterprise multi-agent architecture using Harness Engineering: Vue frontend, FastAPI/ASGI backend, DeepSeek multi-model orchestration, MCP protocol for ERP integration, and sandbox container isolation.
Complete Guide to Building an AI Agent + Personal Knowledge Base with DeepSeek
A complete guide to building AI agents and private knowledge bases using DeepSeek R1 — covering RAG, workflows, Coze, Cherry Studio, and advanced agent patterns.
Getting Started with LangChain: From Core Libraries to AI Agent Development
LangChain is an open-source framework for building LLM-powered apps. Learn how LangChain Core, LangGraph, LangServe, and LangSmith work together for RAG and AI Agent development.
Building a Super Floating Ball with Doubao Work: A Full AI-Powered Development Walkthrough
A content creator built a fully functional desktop floating ball app using Doubao Work AI Coding tool — no code written, just natural language. Full walkthrough inside.
The Real Bottleneck in AI Coding Isn't the Model — It's Closed-Loop Verification
The real bottleneck in AI coding isn't model capability — it's closed-loop verification. Plus a detailed comparison of Codex, Claude Code, and GLM subscriptions.
Beginner's Guide to Building AI Agents and Private Knowledge Bases
A beginner's guide to building AI Agents and private knowledge bases — covering real learning barriers, RAG architecture, toolchains, and a practical roadmap from zero.
Vercel's Agent Evolution: From Failure to Double the Score with a File System Approach
Vercel's CSO Andrew recaps how internal data agent D0 went from a multi-agent failure to doubling evals scores with a file system approach, and how it inspired the new open-source EVE framework.
Enterprise AI Agent in Practice: A Dual-Track Strategy with Low-Code and Hardcore Frameworks
A dual-track enterprise AI Agent framework: low-code platforms (Coze/Dify/n8n) and code frameworks (LangChain/LangGraph/CrewAI), covering MCP protocol, nine smart job roles, and four real-world projects.
OpenSpec in Practice: Taming AI Code Generation with Spec-Driven Development (SDD)
AI code goes off-rails after 30 minutes? Learn how OpenSpec uses Spec-Driven Development (SDD) to make AI-generated code trackable, verifiable, and deliverable.
Getting Started with LLM Development: Alibaba Cloud Model Studio Setup and API Key Configuration
A hands-on beginner's guide to LLM development: covers Alibaba Cloud Bailian registration, real-name verification, API Key creation, and free quota management for RAG and Agent development.
9 Hands-On Projects to Build a Skill Agent: The AI Advancement Roadmap for Test Engineers
A 9-project roadmap from hand-crafted Prompts to a full-pipeline Skill Agent, covering test case generation, performance testing, and Web/mobile automation for QA engineers.
One Developer, 49 Automated Tasks: Solo Skills Open-Sources 26 AI Agent Skills
Korean solo developer open-sources Solo Skills on GitHub: 26 of 49 AI agent skills, compatible with Claude Code and Codex. Core value is turning hard-won lessons into agent guardrails.
Cursor Launches Projects: Reimagining AI Coding Workflows with a Coordinator Agent
Cursor's new Projects feature replaces fragmented chats with a persistent thread and coordinator agent that proactively dispatches subagents — a shift toward multi-agent autonomous AI coding.