I'm Writing Articles Myself Again, and Some Thoughts on GPT-5.4
I’ve gone back to writing articles “myself” again. The reason I say “myself” is: Actually, my recent articles were all …
· 3 min read
Latest Posts
View all →
Does Self-Hosting an LLM Really Let You Use It Without Limits?
Self-hosting an LLM does not magically remove constraints. The real question is where the breakeven point sits between hardware, operations, and API …
· 7 min read
The Mathematical Trap of Big Model Coding Plan Packages: Can Promised Usage Be Delivered Under Concurrency Limits?
Calculating the actual usable volume of big model Coding packages from the perspective of concurrency limits and throughput, revealing the gap between …
· 4 min read
Private Cloud for Small Companies
Many friends want to know: What is the internal server situation and infrastructure of our small software development company? Internal development …
· 1 min read
Efficient and Cost-Effective: My AI Agent Workflow Choice
Sharing my efficient and cost-effective workflow using OpenCode + Gemini 3 Flash
· 2 min read
Coding Performance and Model Cost-Effectiveness Analysis
How to choose programming models in January 2026.
· 1 min read
Configuring Claude Code Python UV Hooks and Skills
Troubleshooting Guide: Using Hooks to Force Claude Code to Use uv for Python Dependency Management
· 3 min read
Running Claude Code in a VM for Automated Testing and Development
Recently, I verified an effective AI development method that doesn’t affect the existing workflow. Here’s a summary. Why Choose VM + …
· 2 min read
Hugo Admin - A Lightweight Hugo Blog Management Interface
When managing a Hugo blog, you often need to switch back and forth between the terminal and editor. To simplify this process, I developed hugo-admin, …
· 2 min read