Notes#
This is where I write regular blog posts that don’t fit under Books or Apps.
Most of the time, I’ll write about technical topics. Sometimes, I’ll also share everyday stories or my personal opinions on things I notice. From longer essays to short memos, this is where I keep what I want to publish and revisit.
What you’ll find here#
- Tech notes: debugging logs, troubleshooting, concept summaries, and quick tips
- Personal notes: daily life, observations, thoughts, and opinions
Subcategories#
- Essays: reflections, opinions, observations, retrospectives, and direction-setting posts (the default bucket in Notes)
Note#
- Posts may be revised and improved over time.
- You can browse the list from the left sidebar.
Latest Posts
Hunting Down an Active-User Crash — Bots, Illusions, and an Indexing Collapse
When the Google Analytics active-user graph fell off a cliff, I chose to peel the data back layer by layer instead of trusting the number. A record of telling bot traffic from real readers, diagnosing an indexing collapse after a domain migration, and putting the sitemap on an index diet.
Why Do Coding Agents All Design Alike? — Research and Decisions Behind Choosing a Design Stack
An essay on why web designs produced by coding agents look similar and slightly unpolished, surveying the skills, MCP servers, and harness guidelines that address this, and walking through the decisions that shaped an actual project's design stack.
LLM Wiki, Opened Up — The 'Automatic Memory' Myth and a Schema That's Just a Few Lines
A record of actually applying Andrej Karpathy's LLM Wiki to my repository and what I learned. I correct the myth that it's 'automatic memory that updates itself,' show that the heart of the pattern is really 'a schema that's just a few lines,' and walk through how I brought it into my repository.
What Do Feature Flags Actually Solve? Single-Branch Collaboration and the Myth of Google-Style Trunk Development
An essay examining whether feature flags can fix the problems of having everyone push directly to a single shared branch. It lays out what feature flags actually solve, what they don't, and the real conditions that make Google-style trunk-based development work.
I Thought AWS Bedrock Was Just Relaying Models — Turns Out It Runs Them Directly
A record of digging into how AWS Bedrock serves external LLMs like Claude and GPT. It is not a dedicated-line relay but direct hosting, with cryptographic sealing and zero operator access protecting the model assets.
An AI Tools Knowledge Map — Lining Up the Materials for Process-Improvement Consulting
To reach a level where I can consult on improving work processes with AI, I organized today's AI tools by category and noted what each one is and how it can be used. From chatbots to coding tools, autonomous agents, and managed AI platforms — a living knowledge map I plan to review often.
I Decided to Call Them Harness Skills — Breaking the Illusion of Doing Well and Opening Up My Harness
A story that began with a question: what should we call tools like LLM Wiki and GStack? With no standard term available, I named them 'harness skills,' reflected on how confidence in my own harness became a trap for growth, and then surveyed the most widely loved harness skills.
An Agent That Keeps Working After the Laptop Closes: Remote Development with Lightsail, Hermes, and Discord
A practical record of moving an AI agent from a local laptop to an always-on remote environment with AWS Lightsail, Hermes Agent, Discord, and a Docker sandbox. It covers the architecture, security posture, and setup process for continuing development work from mobile.
How Product Development Processes Should Change in the Age of AI Agents
An essay on how product teams should handle code changes created directly by planners using AI agents, with a focus on intent transfer, review, and harnesses.