English

Starting from the simplest "one star, one pixel" rendering, eight failures and 600 million stars later, the Milky Way slowly emerged from a real star catalog.

Step two isn't better prompting. It's externalize first, reuse second. This post explains how Skills carry work knowledge, the three parts of a good Skill, and how to organize them so agents find the right one.

After weeks of severe insomnia, I used AI to build an iOS app that exported HealthKit data and ran multivariate regression to find the root cause—late-night AI-assisted intense multitasking. This post explores how AI provided end-to-end execution support and why certain things still require human judgment.

Querying layout results takes one line of code on iOS, Android, Qt, and Flutter. On the web, it requires triggering a full-page reflow. This isn't because browser engineers are incompetent. CSS made a deliberate architectural choice in 1994 toward declarative layout, which has a higher ceiling but hides intermediate state. Facebook paid hundreds of millions of dollars in 2012 for not understanding this trade-off. SwiftUI and Jetpack Compose prove that declarative and observable can coexist through proper layering. The lesson applies to all system design: good abstractions let you choose which layer to work at; bad abstractions glue all layers together and leave you no choice.

An LLM's default output is consensus: correct but mediocre. Deep Research is really Wide Research. We found a systematic way to pull LLMs out of consensus using personal cognitive context. One year of experimentation, with controlled evidence.

The gap between using AI and using AI well is 10x. That gap comes from how you work, not which model you use. This post walks through a complete workflow example and a Three Tiers framework to explain why you should switch from ChatGPT to agentic tools like Cursor.

A real-world case study of directing AI to add SEO summaries to 300 articles in two minutes, breaking down five key decisions: choosing the right execution environment, building tests before work, letting agents handle corner cases, divide and conquer, and outcome-oriented prompt writing.

OpenClaw went viral for the same reason DeepSeek did — not a technical breakthrough, but bringing a niche power-user experience to the masses. This post skips setup tutorials and instead dissects its memory system, Skills mechanism, and the fundamental ceiling of chat-based AI interfaces, helping you decide whether to adopt it and how to extract its core ideas into your own workflow.

Analyzes the four-step attrition ladder in AI learning and proposes using engineering platforms to eliminate configuration, experimentation, and deployment friction. Introduces AI Builder Space's unified API, one-click deployment, and MCP automation.

Why handing translation to Claude Code works better than calling APIs directly - leveraging the agentic loop, evaluation-first mindset, and the ecosystem's runtime layer to achieve outcome certainty over process certainty.