121 related articles

AI coding tools are changing development, but Vibe Coding hides risks in code quality and maintenance. This article explores Engineered AI Programming, compares Codex and Claude Code, and reveals real enterprise development paths.

A deep dive into three levels of AI programming: Vibe Coding for rapid prototyping, Plan Mode for structured development, and AI-engineered programming for enterprise-grade projects with SDD and Claude Code SuperPower.

In-depth comparison of Codex and Claude Code for enterprise AI development, covering Vibe Coding limitations, multi-Agent workflows, OpenRouter platform architecture, and programmer learning paths.

How can PhD students avoid coding skill atrophy when using AI programming assistants? This article proposes a layered delegation strategy with actionable advice for researchers.

OpenCalc is an open-source project that faithfully recreates the Windows 95 calculator with 100% new code, fixing original calculation bugs and adding history, undo/redo, with native Linux support.

Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Learn about its technical principles, performance gains, and value for long-context training and inference acceleration.

Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Explore its technical principles, performance gains, and value for long-context training and inference.

Deep dive into how Transformer² uses a unified Transformer architecture to integrate robot morphology design and motion control into one model, enabling task-driven end-to-end co-design for embodied AI.

OpenAI open-sources Codex Security components, bringing automated security detection to AI code generation. Analysis of its strategic value, developer impact, and the industry shift from capability to security.

OpenAI open-sources Codex Security components, bringing automated security detection to AI code generation. Analysis of its strategic significance and industry impact.

An in-depth analysis of the barriers Chinese users face accessing ChatGPT, an honest assessment of third-party mirror platforms' risks, and safer alternatives including official APIs and domestic LLMs.

Users report Grok 4.5 underperforms in Cursor vs. the official terminal. We analyze how system prompts, context management, parameters, and tool calling create AI coding tool integration gaps.

Spring AI 2.0 brings five core updates: mandatory upgrade to Spring Boot 4, Tools parsing moving up, a built-in Agentic mechanism, MCP switching to Streamable HTTP, and an on-demand tool Advisor.

Spring AI 2.0 brings five core updates: mandatory Spring Boot 4 upgrade, Tools parsing moved up, built-in Agentic mechanism, MCP switch to Streamable HTTP, and on-demand tool-loading Advisor.

Spring AI 2.0 brings five core updates: mandatory upgrade to Spring Boot 4, lifted Tools parsing, built-in Agentic mechanism, MCP switch to Streamable HTTP, and an on-demand tool-loading Advisor.

Frontier AI is going general: costs are dropping, general models are beating specialized ones in math and competitive programming, and multi-agent workflows are maturing fast.

Claude Code isn't just a chat AI—it can directly read projects, modify code, and run commands. This article compares Claude Code with ordinary AI across five dimensions: interaction, context, execution, memory, and tool calling.

From Vibe Coding to AI Engineering, explore Claude Code vs Codex tool selection, real enterprise boundaries of AI programming, and how to build maintainable AI-assisted development workflows.
Pumpkin: A High-Performance Minecraft …
Pumpkin is an open-source Minecraft server rewritten from scratch in Rust. Learn how it eliminates Java GC pauses, reduces resource usage, and its current limitations.

From the autocomplete nature of LLMs, tokens, and context windows to RAG vector databases, the MCP protocol, and AI agent loop design — this article uses vivid analogies to unpack the reality of AI engineering.