From Mole CLI to Mole for Mac: What I Learned
【2026-08-16】How Mole grew from an open-source Mac cleaner CLI into a native app, and what I learned about safe cleanup, quiet design, and building for real users.
Tw93 · Product engineer, open source creator, and writer
You Don't Know Embodied AI: From a Tiny Robot Dog to Optimus
【2026-06-07】In April, I built a small robot dog with an STM32, ASRPRO, ESP32-C3, servos, and 3D-printed parts. Once it could hear a command, walk a few steps, and call a cloud model, embodied AI stopped being a broad idea for me. It became serial ports, PWM, space, motion, control frequency, actuators, failed samples, and manufacturing constraints.
You Didn't Know GEO: AI Visibility Principles, Practices, and Trade-offs
【2026-05-01】Friends told me AI was recommending my projects unprompted. I hadn't done anything special, so I spent an hour structuring my content for AI readability. What I did, what works, and what to skip.
You Don't Know AI Coding: A Non-Engineer's Guide to Getting Started, Scenarios, and Practice
【2026-04-26】A practical Claude Code guide for product, business, and operations folks. Not about prompt engineering, more about how to actually use it: how to write CLAUDE.md, how to build Skills, when to use Plan mode, and which tasks actually fit Claude Code.
How I Turn Learning Into a Workflow in the AI Era
【2026-04-06】Before AI, learning was slow but joyful. Now I treat it like a workflow: collect, filter, outline, draft, refine, publish. Here is how that process actually works.
You Don't Know LLM Training: Principles, Pipelines, and New Practices
【2026-04-03】Most people think model upgrades mean bigger parameters. But the real differences you feel day-to-day usually come from the back half of the training pipeline. This piece follows the full chain from pretraining through distillation and deployment, with a focus on how data engineering, system recipes, post-training, reward design, and agent training together shape the final product. Improvements usually come from a combination of weights, the training pipeline, and deployment decisions, not just scale.
The Death of the Manual Programmer
【2026-03-30】My title reworks the name of a song by Omnipotent Youth Society that I loved twelve years ago. The song is about something different, but that feeling of watching a familiar world slowly get replaced does feel similar.
You Don't Know AI Agents: Principles, Architecture, and Engineering Practices
【2026-03-21】After studying Claude Code's architecture, I realized I still didn't understand agents well enough. Our team had already deployed agents in several projects, but I hadn't put that experience together. I went back through the literature, open-source implementations, and my own code to work through control flow, context engineering, tool design, memory, evaluation, and security.
You Don't Know Claude Code: Architecture, Governance, and Engineering Practices
【2026-03-12】I'm sharing what I've learned from six months of using Claude Code across two accounts. It covers context management, Skills, Hooks, Subagents, prompt caching, and CLAUDE.md design, with a focus on making collaboration more reliable and easier to control and check.
Installing OpenClaw Isn't the Same as Using It
【2026-03-07】Watching people flock to Tencent Tower to get OpenClaw installed today gave me a lot to think about. Many big tech companies are aggressively pushing non-technical frontline employees to install this AI tool, and I've even seen people online offering home installation for 500 RMB. Everyone's desperately searching for uses for it, demanding results, and trying to prove this thing is too important to miss. The whole thing feels like people living in different technological worlds, folded into the same place.