#AI编程
9513 related articles
Why Is x86's Undefined Instruction Called ud2? The History Behind the Number
Why does x86's undefined instruction carry the number 2? This article traces the history behind ud2's naming, its opcode, and how compilers use it to mark unreachable code.
LangChain Agent Web Scraping: DIY vs. Managed API — A Practical Comparison
DIY scraping vs. managed APIs for LangChain Agents: compare Playwright/bs4 self-builds against Firecrawl and context.dev on cost, anti-bot maintenance, and when to switch.
Codex vs. Claude Code: A Beginner's Guide to AI Coding Agents
Codex vs. Claude Code: which AI coding agent should you use? This guide compares both tools and walks beginners through GPT account setup, virtual number platforms, US App Store switching, and subscription cost-saving tips.
Pi-chat in Practice: Connecting External Tools to AI Agents via MCP Protocol
Learn how to integrate external tools into AI Agents using MCP protocol with Pi framework. Covers pi-mcp-adapter setup, .mcp.json config, Extension Factory initialization, and a live 12306 train ticket query demo.
AI Large Model Engineering Careers Decoded: Algorithm Research vs. Engineering Deployment — Which Path Is Right for You?
AI large model jobs split into algorithm research and engineering deployment. Learn the skill requirements, core competencies like RAG and Multi-Agent, and why Harness architecture is the 2026 interview differentiator.
Build an AI Daily Digest with Hermes Agent: Auto-Delivered at 8 AM Every Day
Step-by-step guide to building a multi-source AI creator daily digest with Hermes Agent, combining websearch, curated channels, and platform signals for automated 8 AM delivery to enterprise WeChat.
Harness Engineering: A New Paradigm for Agent Development
Harness Engineering is emerging as the next paradigm in agent development, encompassing context engineering, tool calling, memory, planning, and safety into a unified infrastructure layer.
Building a Multi-Agent AI Team with Coze: From Concept to Practice
A complete guide to building multi-Agent AI teams with Coze — covering the 3 types of Agent products, Coze's core modules, multi-agent collaboration, Skill Store, and custom workflows.
5 VS Code AI Coding Assistants Compared: Roo Code, Copilot, Cline, and More
Deep comparison of 5 VS Code AI coding assistants: Roo Code leads in flexibility but burns tokens, Copilot offers great value for beginners, Cline and Kilo Code balance power and ease, Augment Code is the premium all-rounder.
Coze Multi-Agent Collaboration in Practice: Build Your AI Team from Scratch
A practical guide to Coze (扣子) 3.0: multi-agent collaboration, agent types, Skill Store, Coze Coding, and workflows — build your AI team from scratch.
How to Write a Resume for an AI/Agent Engineer Role? Key Strategies Explained
A practical guide to writing a resume for AI/Agent Engineer roles at high-growth startups, covering key skills, project quantification, and tech stack alignment.
Docket: Building Per-Commit Evidence Trails for AI Agent-Generated Code
Docket builds per-commit evidence trails for AI agent-generated code, making every AI commit traceable, auditable, and verifiable — a pragmatic step in AI coding governance.
Promptyx Expands: From Prompt Engineering to Context Engineering
Promptyx is expanding from prompt engineering into context engineering. Learn the difference between the two and what this evolution means for AI app development.
Anthropic Reveals: Houthi Forces Used Claude Code to Develop Missile Guidance Software
Anthropic reveals Houthi forces used Claude Code to help develop missile guidance software, raising urgent questions about AI dual-use risks and safety governance.
Resurf: The Personal Context Manager That Feeds Your Data to AI
Resurf is a personal context app for Apple devices that saves notes, links, images, and PDFs, then feeds them to AI via MCP and CLI. Local storage with iCloud sync keeps your data private.
Cognition Launches SWE-2 Coding Model: Near Top-Tier Performance at 64% Lower Cost
Cognition releases SWE-2, a coding model post-trained on Kimi K3 with RL. Scores 50% on FrontierCode, nearly matching Fable 5.1 at 64% lower cost and 1/4 the price of GPT-6 Astra.
Vibe Coding 5 Mobile Games with Claude Code: Ad Monetization Beats Subscriptions
An indie dev built 5 iOS casual games with Claude Code vibe coding. His verdict: AdMob ads plus ASO optimization outperform subscriptions for casual games.
RiftPoint: A Rust-Powered Multiverse Checkpointing Solution for LangGraph
RiftPoint is an open-source LangGraph checkpointer backed by a Rust engine that uses multiversal branching to avoid full state copies, cutting memory and performance costs for concurrent agent paths.
OpenCode: The Open-Source Coding Agent That Hit 150K GitHub Stars
OpenCode is an open-source TypeScript coding agent with 150K+ GitHub stars. Learn about its features, advantages, and use cases for AI-powered development.
Learning AI Agent Development from Scratch: An Open-Source Tutorial Worth Bookmarking
Haozhe-Xing/agent_learning is a systematic, hands-on open-source tutorial for learning AI Agent development from scratch, with daily arXiv paper tracking built in.