#legacy code refactoring
85 related articles
Is Chasing the Latest AI Models Worth …
·2 min
Is Chasing the Latest AI Models Worth It? A Big Tech Engineer's Honest Question — and a Rational Answer
A 10-year big tech data engineer asks: why chase the latest AI models? This deep dive analyzes the three core motivations behind AI tool upgrades and helps you find the right model selection strategy.
Read more →
·2 min
GPT-5.6 Sol XHigh Real-World Test: The Coding Capability That Changed a Claude User's Mind
A long-time Claude user was genuinely impressed by GPT-5.6 Sol XHigh. We break down the model's coding performance, shifting AI assistant competition, and how to rationally choose the right coding AI.
Read more →
·2 min
The Complete TypeScript Guide: How JavaScript's Superset Came to Dominate Modern Web Development
TypeScript is Microsoft's JavaScript superset that catches errors at compile time via static type checking. Explore its core benefits, ecosystem, and trade-offs.
Read more →
·3 min
Arcaide: Understanding Codebase Structure Through Multi-Level Call Graph Visualization
Arcaide is a code comprehension tool based on multi-level call graphs, helping developers explore function calling relationships from macro to micro, speed up onboarding, assess change impact, and identify technical debt.
Read more →
·5 min
The Complete OpenCode Tutorial: Installation, Commands, and Advanced Practice
Systematically learn the OpenCode AI programming tool: covering both desktop and WSL installation, core commands, model and rule configuration, MCP integration, and Agent Skills.
Read more →
·2 min
GPT-5.6 Triple Model Integration in Cursor: Sol Scores 67.2% on CursorBench
OpenAI's GPT-5.6 models Sol, Terra, and Luna are now available in Cursor IDE. Sol scores 67.2% on CursorBench, covering real-world tasks like code completion and cross-file refactoring.
Read more →
·4 min
OpenAI Build Week Kicks Off: Turning Your Ideas Into Reality with Codex
OpenAI launches Build Week, a global developer event centered on Codex AI coding tool, featuring live sessions and community events to help developers ship ideas fast.
Read more →
·3 min
GPT-5.6 Revealed: What a 54% Token Efficiency Boost in Agentic Coding Actually Means
Sam Altman revealed GPT-5.6 boosts token efficiency 54% in agentic coding — meaning near-halved API costs, longer work chains, and faster responses. A deep dive into the technical implications for developers.
Read more →
·3 min
GPT-5.6 Sol Ultra Rumors Decoded: How Codex's Programming Capabilities Could Evolve
Rumors of GPT-5.6 Sol Ultra integrating into Codex are circulating in tech communities, but OpenAI hasn't confirmed anything. We analyze the real trends: context understanding, reasoning, and agentic workflows.
Read more →
·7 min
Gemini CLI: The AI Development Powerhouse in Your Terminal, Ending Tool Fragmentation
Gemini CLI is Google's open-source AI terminal tool that deeply integrates Gemini model capabilities into the command line—supporting code generation, file operations, Shell execution, and MCP protocol extensions, with 1,000 free daily requests.
Read more →
·6 min
From Vibe Coding to AI Engineering: A Complete Practical Guide to Codex and Claude Code
An in-depth analysis of the practical use of Codex and Claude Code, comparing Vibe Coding and AI engineering, covering Super Power plugins, Spec-Driven Development, and Chinese LLM integration strategies.
Read more →
·5 min
Claude Drives the sqlite-utils 4.0 Release: The Real Cost and Collaboration Methodology of AI-Assisted Refactoring
Developer Simon Willison used Claude to ship sqlite-utils 4.0: 37 prompts, 34 commits, $149 API cost — revealing coding agents' real capabilities, cross-model review, and agentic engineering best practices.
Read more →
·5 min
Claude Sonnet 5 Integrated with Devin: Enhanced Coding Performance with 30% Lower Quota Consumption
Anthropic's Claude Sonnet 5 launches on Devin Desktop and CLI, delivering frontier-level coding performance while reducing quota consumption by ~30% compared to the previous generation.
Read more →
·7 min
The C Readability Crisis: Engineering Reflections Behind Clever Tricks
Why do C programmers keep creating readability disasters? An in-depth look at macro abuse, fancy pointer tricks, and over-nesting—and how coding standards, static analysis, and code review protect maintainability.
Read more →
·3 min
Kimi K2.7 Code Hands-On: How Does High Speed Mode Feel in Practice?
Hands-on test of Kimi K2.7 Code in High Speed mode across two real projects: a frontend interactive lab and an e-commerce microservice. Speed is noticeably improved, with strong responsiveness for legacy codebases and frontend-backend integration.
Read more →
·6 min
10 Billion Tokens in Practice: An In-Depth Review of Codex's Long-Horizon Engineering Capabilities
Creator Ajiang burned 10B Tokens on Codex to migrate cc-haha from Tauri 2 to Electron. A deep dive into Codex's long-horizon engineering, Computer Use, costs, and practical advice for developers.
Read more →
Reviving Legacy SOAP APIs: Building a …
·2 min
Reviving Legacy SOAP APIs: Building a JSON and MCP Wrapper for Spain's Cadastre API
A developer built a modern JSON wrapper and MCP integration for Spain's 2003-era SOAP Cadastre API, enabling AI assistants to query land registry data directly.
Read more →
·3 min
Cursor & Claude Code Enterprise Training: AI Coding Tool Division of Labor and Practical Methodology
How can R&D teams truly leverage AI coding tools? This article breaks down Cursor vs. Claude Code division of labor, an eight-step framework, and how to build reusable AI collaboration assets.
Read more →
·3 min
Claude Fable 5 Deep Dive: An AI That Works 9 Hours Straight — Are Programmers Really Being Replaced?
Deep analysis of Anthropic's Claude Fable 5: derived from the ultra-powerful internal model Methos, scoring 80.3 on SWE Bench Pro crushing GPT 5.5, tested working autonomously for 9.5 hours straight.
Read more →
·4 min
AI Agent Development Learning Roadmap: A Complete Four-Stage Plan from Zero to Production
A systematic AI Agent development learning roadmap covering LLM fundamentals, ReAct paradigm, memory & tool calling, and multi-agent collaboration across four stages with project suggestions.
Read more →