#AI编程
9636 related articles
Agent Skill Routing: Retrieval vs. LLM vs. Two-Stage Architecture Compared
Retrieval or LLM for Agent skill routing? Compare coarse-filter vs. fine-select architectures on latency, accuracy, and cost — with 4 key production considerations.
AI Agent Developer Job Hunt Guide: 4 Standards to Land Your Offer This Recruiting Season
AI Agent developer fall recruiting guide: 4 standards to land your offer — solid basics, real project deployment, strong engineering, and surviving interview pressure.
30-Day AI Agent Roadmap from Zero to Freelancing: Concepts, Hands-On Builds, and Landing Projects
A 30-day AI Agent roadmap for beginners: grasp perception-decision-action-memory, build RAG, tool-calling, and workflow Agents, then deliver enterprise projects.
AI Large Model Learning Roadmap for Beginners: Three Stages from Prompt Engineering to Agent Development
A complete AI learning roadmap for beginners: from prompt engineering and API calls, to RAG knowledge bases, to Agent and multi-agent development — a 3-stage framework to go from zero to building real AI applications.
Xiaozhi AI Hardware Dev Board Review: Building a Voice Agent with Cloud Code
A hands-on review of an ESP32 AI dev board with transparent case, built-in speaker and mic. Covers city radio, Xiaozhi AI firmware, and building a voice agent with Cloud Code using LLM, TTS, and ASR.
Harness Engineering in Practice: Building Scalable Infrastructure for Production-Grade Agents
AWS expert Mike Chambers demos how to upgrade a local agent prototype into a production-scale system using Bedrock Agent Core and Strands SDK, covering memory, multi-tenancy, and observability.
Slowave: A Local Memory Layer That Lets Coding Agents Maintain Their Own Memory
Slowave is an open-source local memory layer for coding agents. It replaces standalone LLM judges with agent-driven reinforcement and decay, preventing context pollution over long-term use. Supports Claude Code, Cursor, Codex, and more.
The Real Cost of AI Agents: Input Tokens Are the Hidden Driver of Your Bill
Real-world data shows AI Agent input tokens outnumber output tokens 174:1, with cache hits accounting for 60% of costs. Identical-quality solutions can differ by 15x in price.
Has Claude Been Declining Since Version 4.6? A Two-Year User's In-Depth Critique
A two-year Claude user argues the model peaked at Opus 4.6, with each update bringing more verbosity, higher costs, and skill dependency. How should AI "progress" really be defined?
AI Agent Approval Workflows: How to Handle Edits and Retries
A deep dive into designing human-in-the-loop approval workflows for AI agents: reviewing exact requests, resuming execution, and handling edits and retries.
PS5 Linux Maintainer Quits: Are LLMs Eroding the Foundation of Open Source Collaboration?
The PS5 Linux port's core maintainer quit over a flood of LLM-generated, low-quality contributions. We examine how AI-assisted coding is straining open source trust and collaboration.
AI Agent Learning Roadmap: A Four-Stage Guide for Complete Beginners
A four-stage AI Agent learning roadmap for beginners: from core concepts and model deployment to RAG, LangChain, LoRA, and interview-ready projects.
Free Access to Mystery Model & DeepSeek V4 via Cline: Complete Setup Tutorial
Learn how to use DeepSeek V4 and the mystery "Niumai" model for free on Cline — covering IDE extension and CLI installation, account setup, and model selection.
Cline + VS Code in Practice: Generate a To-Do App from a Single Prompt
Cline is an autonomous coding agent inside VS Code. This hands-on guide shows how to generate a to-do app from one prompt and compares Claude, Ollama, and Groq integrations.
Complete Guide to Building Autonomous AI Agents with Spring AI + Skills
A complete guide to AI's evolution from chatbots to Agentic AI, and how to build autonomous decision-making agents using Spring AI, ReAct, and Agent Skills.
Cline Desktop App Launched: AI Coding Agent Breaks Free from the Editor
Cline, the open-source coding agent, launches a standalone macOS/Windows desktop app with task queuing, message forking, scheduled tasks, ClinePass subscription, and support for 256 API providers.
AI Agent in Practice: Understanding the Value and Real-World Applications of Intelligent Agents Through the Evolution of LLMs
From native LLMs to AI Agents: explore the four stages of LLM commercial deployment, the four core Agent capabilities, and a three-project hands-on roadmap for beginners.
AI Agent Learning Path Breakdown: A Complete Framework from Principles to Practice
A complete AI Agent learning path breakdown — from Agent principles, Prompt engineering, and RAG to multi-agent collaboration, tool invocation, and hands-on projects like knowledge base assistants and intelligent customer service bots.
AI Agent Fundamentals: The Three Core Components — Brain, Memory, and Tools
A beginner's guide to AI Agents: covering the three core components (brain, memory, tools), four stages of LLM deployment, and why Agents matter for real business use cases.
Boycotting Software That Doesn't Support Linux: One Developer's Philosophy of Choice
A Linux-only developer shares his philosophy of boycotting non-Linux software — without sacrificing productivity — and explains how coding agents like Claude Code are closing the gap with commercial tools.