AI & Agents
What I learned building an opinionated and minimal coding agent
Claude Code template for academics using LaTeX/Beamer + R
Conductors to Orchestrators: The Future of Agentic Coding
Introducing SkillsBench: The First Benchmark for Agent Skills
FlowBench：LLM-based Agents 工作流引导规划的再审视与基准测试
IronClaw is OpenClaw inspired implementation in Rust focused on privacy and security
Programming
How to write a good spec for AI agents
Beyond Pros and Cons: A Multi-Dimensional Trade-Off Analysis Framework for Software Architects
How to Fine-tune LLMs in VS Code with Unsloth & Colab GPUs
I Built a Self-Hosted Google Trends Alternative with DuckDB
Others
This CTO Says 93% of Developers Use AI, but Productivity Is Still 10%
人们只会做他们已经在做的事——Claude Code 背后的产品哲学
How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt