# AI应用

Complete Guide to Connecting Codex with DeepSeek: Stable Setup in China Without a VPN

Step-by-step guide to deploying OpenAI Codex CLI in China using WSL + MoBridge relay + DeepSeek API. No VPN needed, stable and cost-effective setup in minutes.

Multi-Model AI Development in Practice…

Multi-Model AI Development in Practice: A Guide to Unified API Gateway Architecture Design

Learn how to overcome single-model AI limitations by designing a unified API gateway architecture for multi-model collaboration, covering task routing, failover, and cost optimization strategies.

Codex Keeps Reconnecting? Fix the Prox…

Codex Keeps Reconnecting? Fix the Proxy Configuration Issue in One Step

Codex CLI keeps showing Reconnecting failures? This 5-step guide covers setting HTTP_PROXY, fixing 401/403 errors, and solving proxy issues on Windows, Mac, and Linux.

Expert Opinions

100K Views but Only 20 Sales: An Indie…

100K Views but Only 20 Sales: An Indie Developer's Monetization Post-Mortem

An AI indie developer built a Windows one-click installer for Open WebUI in 3 days, got 100K views but only 20 sales. A full post-mortem on pricing, distribution, and monetization mistakes.

AI Is Getting More Expensive: The Indu…

AI Is Getting More Expensive: The Industry Truth Behind Rising Prices for Premium Models

From $1.3M monthly token bills to rising premium AI model prices, AI isn't becoming accessible. A deep dive into the industry's two price lists, centralization trends, and what it means for everyone.

Three Ways to Deploy Codex: Subscripti…

Three Ways to Deploy Codex: Subscription, API Relay, and Free Alternatives Explained

Three ways to deploy OpenAI Codex: ChatGPT Plus subscription, API relay pay-as-you-go, and Kimi Code CLI as a budget alternative. Covers setup, pricing, and comparison for developers.

OpenAI Codex Deep Dive: From AI Q&A to…

OpenAI Codex Deep Dive: From AI Q&A to AI Getting Things Done

Deep dive into OpenAI Codex: not just answering questions, but independently executing tasks and delivering results. Learn how Codex transforms AI from advisor to executor.

Cursor Multi-Agent Workflow: A Practic…

Cursor Multi-Agent Workflow: A Practical Guide to Main Thread & Grunt Collaboration

Learn the Cursor "Main Thread & Grunt" multi-agent workflow: use a high-tier model for complex tasks and a low-tier model for simple tasks in parallel to maximize AI coding efficiency.

How Jane Street Built a Custom AI Programming Toolchain for OCaml

How Jane Street Built a Custom AI Programming Toolchain for OCaml

Jane Street's AI team details how they built a custom LLM toolchain for OCaml, covering workspace snapshot training data, RL with code evaluation, and the AID editor architecture.

AI Agents Deep Dive: The Paradigm Shift from Chat Tools to Autonomous Execution Systems

AI Agents Deep Dive: The Paradigm Shift from Chat Tools to Autonomous Execution Systems

Deep analysis of AI Agents vs LLMs, covering three evolution stages, four core architecture components, three penetration paths, multi-agent collaboration, and societal impact.

Zero Coding, Zero Art Skills: Building…

Zero Coding, Zero Art Skills: Building a Rhythm Game with AI in 24 Hours

A Bilibili creator used AI platform TabTab to build a rhythm game from scratch in under 24 hours — art, music, and code 100% AI-generated. A deep dive into this zero-experience AI game dev case.

Deep Dives

Claude Opus vs. Sonnet vs. Haiku: How …

Claude Opus vs. Sonnet vs. Haiku: How to Choose the Right Model

Compare Anthropic's Claude Opus, Sonnet, and Haiku models across intelligence, speed, and cost. Practical selection guide with multi-model routing strategies.

GPT 5.5 vs Claude Code vs DeepSeek V4:…

GPT 5.5 vs Claude Code vs DeepSeek V4: Hands-On Comparison of Three Top Coding Models

Hands-on comparison of GPT 5.5, Opus 4.7 (Claude Code), and DeepSeek V4 Pro through a 3D flight simulator and WebGPU shader test — covering coding ability, pricing, and real-world performance.

Zenflow Hands-On Review: Spec-Driven A…

Zenflow Hands-On Review: Spec-Driven AI Coding vs. Pure Prompt-Based Development

In-depth review of Zenflow's spec-driven AI coding vs Google AI Studio's prompt-based approach. Covers multi-agent execution, automated validation, version rollback, and the paradigm shift in AI programming.

Meta Partners with AWS: Bringing in Tens of Millions of Graviton Cores to Expand AI Infrastructure

Meta Partners with AWS: Bringing in Tens of Millions of Graviton Cores to Expand AI Infrastructure

Meta partners with AWS to add tens of millions of Graviton cores for AI inference, diversifying its infrastructure to support Meta AI and Agentic experiences for billions of users.

US vs. China AI Computer Control Diver…

US vs. China AI Computer Control Divergence: Why Programming Tools Still Haven't Integrated GUI Agents

AI computer control success rates surpass humans, yet Cursor and Copilot still lack GUI Agent integration. Deep analysis of US product packaging vs. China's open-source ecosystem, plus three bottlenecks blocking the path to autonomous software engineers.

feishu-claude-bridge Open Source Project Analysis: A Practical Guide to Integrating Claude Code with Feishu

feishu-claude-bridge Open Source Project Analysis: A Practical Guide to Integrating Claude Code with Feishu

In-depth analysis of the feishu-claude-bridge open-source project: how to use Claude Code for AI programming directly in Feishu, covering architecture, deployment, and use cases.

Behind the Gemini CLI Explosion: Why t…

Behind the Gemini CLI Explosion: Why the Terminal Is Becoming the Ultimate Gateway for AI Agents

Google's open-source Gemini CLI hit 100K GitHub stars. This article analyzes why the terminal is becoming the ultimate AI Agent gateway through execution chains, infrastructure integration, and more.

The Dutch Dropping Tradition: Leaving Kids in the Forest to Teach a Lesson for the Digital Age