Toolchain Performance Matters More Than Ever in the AI Era
AI coding is increasingly an agentic loop: write code, run validation, read failures, and fix again. In that loop, test, lint, and build performance directly shape engineering throughput.
AI
9 posts
The Next Step for Admin Platforms Is CLI and Skill
A reflection on why admin and configuration platforms should stop exposing their capabilities only through pages, and start turning operations into CLI commands and agent-readable skills.
gpt-image-2 Prompt Patterns: Commercial Covers And Miniature Visuals
Rewritten English prompt patterns for editorial information visuals, technology posters, brand concepts, and botanical knowledge cards.
gpt-image-2 Prompt Patterns: Technical Diagrams And Infographics
Rewritten English prompt patterns for turning architecture notes, technical mechanisms, and Mermaid flows into readable gpt-image-2 visuals.
Reusable gpt-image-2 Prompt Patterns
A growing collection of reusable gpt-image-2 prompt patterns, rewritten and tested in English with new example images.
In the AI Era, Developers Have the Freedom to Refactor
A reflection on Bun's move toward Rust, a small SolidJS-to-Vue migration, and why technical choices in the AI era are becoming less like permanent bets and more like decisions that can be revised.
AI Broke the Zero Marginal Cost Myth of the Internet
A reflection on why AI applications feel less like traditional internet products and more like on-demand production, where every useful answer, image, and agent run has a real cost.
DeepSeek API with SillyTavern: A No-GPU Setup
How to connect SillyTavern to DeepSeek through the official API or an OpenAI-compatible configuration, without a local GPU or large model downloads.
DeepSeek R1 with SillyTavern: Local Ollama Setup on Windows
A practical Windows setup for running DeepSeek R1 with Ollama and connecting SillyTavern to the local model service, covering model size, GPU requirements, API settings, and common problems.