#AI编程
9426 related articles
Career Switch to AI Agent Development from Zero: A Comeback Path for Non-Elite University Grads
A Bilibili UP host shares: computer science jobs are hard to land, but AI Agent development is inclusive of educational background — beginners need Python, RAG, Tool Use, and LangChain for opportunities at small and mid-sized companies.
Vercel Sandbox Adds stdin Support: Opening Interactive Command Channels for AI Agents
Vercel Sandbox now supports stdin, letting running commands receive standard input. This article explains TypeScript and Python SDK usage, and what it means for stdio MCP servers, agent-browser, and other Agent toolchains, plus caveats.
Scale AI AgentEnv Evaluation Framework Now Available on Vercel Sandbox
Scale AI's AgentEnv evaluation framework now supports Vercel Sandbox, enabling isolated agent task runs and scoring. Learn how it works, the commands, and its impact.
Vercel Connect CLI New Feature: Discover 1000+ Services in Your Terminal
Vercel Connect CLI adds a discover command to search and filter over 1,000 services in the terminal, filter by category or connection method, and output JSON for scripts and AI agents.
Supabase Bets on AI Agents: The Database Foundation for a Billion Apps
Supabase co-founders discuss how AI agents are changing backend needs: running long tasks alongside the database, making schemas agent-friendly, and the billion-app vision.
Git Forge for Agent-Human Collaboration
Exploring a Git Forge designed for AI Agent-human collaboration: analyzing mismatches in existing code collaboration models around identity traceability, review throughput, and branch semantics, outlining source tagging, tiered permissions, and human gates that Agent-Human collaboration platforms should have, and the potential impact on development workflows.
Kimi K3.1 Pro Open-Source Model Matches GPT-6 Astra; China Releases AI Employment Policy
This week in AI: Moonshot open-sources Kimi K3.1 Pro with nearly 3T parameters, beating GPT-6 Astra on coding tests; Anthropic launches proactive agent Claude Duet; China's State Council issues AI and employment policy with 6 areas and 18 tasks.
The Most Comprehensive Agent Development Tutorial on Bilibili: From Zero to Expert in Seven Days
A Bilibili creator releases a 748-episode zero-foundation AI Agent tutorial in three parts: cognition, advanced, and hands-on, covering ReAct, LangChain, AutoGen, multi-Agent collaboration, and enterprise projects, with source code and a learning roadmap.
Beginner-Friendly Reinforcement Learning Kaggle Competitions: A Practical Getting-Started Guide
Recommends suitable Kaggle competition types and selection principles for RL beginners, covering classic control, simulation strategy, and practical tips for efficient learning.
Bilibili AI Large Model Tutorial: RAG Practical Guide from Beginner to Mastery
Bilibili creator A Shui launches a 109-episode AI large model RAG practical tutorial, from beginner to mastery, covering RAG, AIGC, multimodal and other core technologies, sharing learning paths and industrial practice experience to help learners systematically master large model technology.
Bilibili's 748-Episode AI Agent Development Course: A Complete Guide from Zero to Real-World Projects
A comprehensive review of Bilibili's 748-episode AI Agent development course: from ReAct, planning, and memory to LangChain, AutoGen, and enterprise projects like customer service and data analysis agents, with learning path and resource advice for beginners.
LangChain from Scratch: A Deep Dive into a Hands-On RAG and Agent Tutorial
A deep dive into a Bilibili zero-foundation LangChain tutorial: analyzing the learning path around RAG and Agent scenarios, from basic calls to complete deployable projects. Suitable for students, career changers, and side-project developers.
From Zero to Agent Developer in 7 Days: A Deep Dive into Bilibili's 748-Episode Tutorial Series
A deep dive into Bilibili's 748-episode Agent app development tutorial: from zero foundation to enterprise deployment, covering how Agents differ from ordinary AI chat, MCP integration, customizing open-source projects, and the full deployment pipeline, with a learning roadmap and hands-on cases to help you get started with AI agents in seven days.
Devin Security 2.0: Scanning and Auto-Fixing Code Vulnerabilities with Frontier Models
Devin Security 2.0 launches with frontier-model vulnerability scanning, environment-context prioritization, and autonomous remediation that turns findings into pull requests.
Core Course in Agent Development: A Practical Path with Python and Large Model Agents
Breaking down the seven-chapter path of a core agent development course on Bilibili: from Python syntax, virtual environments, and Jupyter, to intelligent computing platforms, the Hugging Face model community, and on to Gradio interfaces and Flask APIs, outlining the complete core workflow and learning order for large-model Agent development.
What Is Loop Engineering? A Full Breakdown of AI Agent Automated Workflows
What is loop engineering? This article explains how AI agents build automated workflows through goal setting, action-observation loops, context management, MCP tool calls, and sub-agent verification, and analyzes human-in-the-loop pitfalls like comprehension debt, intent debt, and cognitive surrender.
Is Programming Dead? A Practical Analysis of Three Vibe Coding Tools
Explaining Andrej Karpathy's vibe coding concept, with video demos analyzing the capabilities and limits of Lovable, Claude Code, and Manus, plus three real risks: security holes, architecture bloat, and runaway API costs.
What Is Vibe Coding? Build Apps Without Writing Code
What is Vibe Coding? This article explains the AI programming trend: describe ideas in natural language, let AI write code, and iterate fast—plus where human oversight is still required.
Build Apps with Zero Code in Google AI Studio: Just Describe an Idea and Ship It
Google AI Studio turns a natural-language description into a complete app—no code, no pasting. A full walkthrough from idea to preview, publishing, and phone installation, plus free-window notes, prompting tips, and limits.
Can AI Solve the COBOL Code Crisis? OpenAI Offers a New Approach
OpenAI claims substantial progress in legacy code migration—can this solve the COBOL crisis? This article analyzes AI's real capabilities, verification challenges, and engineering boundaries in migrating COBOL, and explores pragmatic paths for developers and enterprises.