#AI编程
9636 related articles
RAG Knowledge Base: A Complete Guide from Fundamentals to Optimization
A complete guide to building a RAG knowledge base: covering vector databases, chunking, embedding models, retrieval strategies, re-ranking, and agent workflows to minimize LLM hallucinations.
MAGS Framework: Multi-Agent Auto-Formalization Provides Safety Guarantees for AI-Generated Code
MAGS is a multi-agent auto-formalization framework using Dafny as an intermediate representation to provide machine-checkable safety guarantees for LLM-generated code, achieving 100% success across 220 samples.
Tech FrontiersLiveReview: Free Risk-Aware Code Review That Auto-Approves Low-Risk PRs
LiveReview is a free, self-hostable AI code review tool that risk-scores every PR, auto-approving the lowest-risk 30-50% of changes, inspired by Meta's internal system.
27B Dense Model Tops Hugging Face All-Time Likes: Frontier-Level Agentic Ability on 16GB VRAM
A 27B dense model from Hangzhou tops Hugging Face's all-time likes chart. Quantized to 16GB VRAM, a single RTX 4090 delivers frontier-level Agentic performance locally.
Claude Code v2.1.276 Released: Fixes Proxy/Gateway 400 Error Regression
Claude Code v2.1.276 fixes a critical regression from v2.1.275 where all requests via proxy or gateway failed with a 400 error (Input tag 'advisor_20260301'). Upgrade now.
Andrew Ng on Agentic AI: Cutting Through the Hype to Find Real Value in Agent Development
Andrew Ng's Agentic AI course intro: separating hype from real value, exploring agent workflows in customer service, research, law, and healthcare, and why evals and error analysis define expert-level agent development.
Java 27 Deep Dive: How Default Changes Are Quietly Reshaping Production Environments
Java 27 has just 9 JEPs but changes key defaults: compact object headers on by default, G1 as unconditional default GC, Flight Recorder redaction, and built-in post-quantum TLS 1.3.
Anthropic Says Claude Is Helping Build Its Own Successor
Anthropic says Claude is helping build next-gen AI models. We break down what AI-assisted AI development means, the efficiency gains, safety risks, and industry trends.
ByteDance Trae Work Getting Started Guide: 11 Use Cases Explained
A hands-on guide to ByteDance's Trae Work AI agent — covering Work, Code, and Design sections across 11 use cases including PPT generation, data analysis, coding, and more.
TraeWork vs WorkBuddy: A Hands-On Comparison — How to Choose the Right AI Agent
Hands-on comparison of ByteDance's TraeWork and Tencent's WorkBuddy AI agents — covering cloud sandbox vs. local execution, features, pricing, and a same-prompt game dev test to help you choose.
Trae Work Full-Pipeline Workflow Review: From Topic Selection to Final Delivery in One Go
Trae Work full-pipeline workflow review: integrate info, build outlines, generate drafts, and create assets in one platform — with context lock to eliminate AI's goldfish memory.
Did AI Kill React Native? Starting with Shopify's Abandonment
Shopify dropped React Native for Swift/Kotlin, citing AI coding agents closing the native dev cost gap. A deep dive into OTA updates, React Native's real strengths and weaknesses, Meta's team exodus, and how AI is reshaping mobile development.
Vibe Coding for Beginners: Build Your First Software with AI — No Experience Needed
Can you build software with AI and zero coding experience? This guide breaks down Vibe Coding: solving real problems, personalizing software, and low-cost experimentation.
How People Use VMs to Repeatedly Register for Trae Free Credits — and Why It's Risky
A Bilibili tutorial claims virtual machines can "infinitely refill" Trae free credits. We break down the technical logic and analyze the compliance and security risks involved.
After Breaking My Hand: How I Code Productively Without Typing
A 160 WPM developer broke his hand and rebuilt his workflow with voice input, AI Agents, and Computer Use — and became more productive than ever. Real-world tips inside.
Plugin4Shell: Zero-Click RCE Vulnerability Allegedly Affects Top Four AI Coding Agents
Plugin4Shell is a reported zero-click RCE vulnerability affecting the top four AI coding agents. Learn how it works, why coding agents are targeted, and how to protect yourself.
How to Choose a Database for AI Agents? 5 Key Evaluation Criteria
What kind of database do AI Agents actually need? This article breaks down 5 key evaluation criteria — including branch isolation and serverless architecture — to help developers make smarter infrastructure choices.
Prompt → MCP → Agent → Skill: The AI Terminology Evolution Chain Explained in 5 Minutes
A clear guide to five core AI concepts — Prompt, MCP, Agent, Skill, and Cowork — and how they connect in a layered evolution chain from simple instructions to multi-agent teamwork.
Build a Local AI Agent with Python in 10 Minutes: Ollama + PydanticAI in Action
A hands-on guide to building a fully local AI agent with Python, Ollama, and PydanticAI in 10 minutes — covering model selection, tool functions, and conversation loops.
SJTU Open-Sources 'Hands-On AI': From API Calls to RAG and Agent Development
SJTU Professor Zhang Zhuosheng's team open-sources 'Hands-On AI' — a practical tutorial covering API calls, prompt engineering, RAG, and Agent development from scratch.