\n
![](\"https://gw.alipayobjects.com/zos/k/sa/family.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
![](\"https://gw.alipayobjects.com/zos/k/31/266.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo is a sculpture of a child wearing a mask, taken on the weekend while running errands over in Gongshu. In a flash, the pandemic already feels like a long time ago, and yet it also feels like just yesterday. Those years are still worth remembering.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
After finishing Kami, I suddenly realized that Kaku, Waza, and Kami feel a lot like a small family. Then I kept thinking, and actually Pake, MiaoYan, and Mole have always been quietly part of this family too. Some of them were even out doing real work before AI showed up. Today let me introduce you to this warm and happy little family.
\nKaku is the dad. He mainly handles writing code, the terminal, and builds. Very reliable and capable in the AI era, he holds the family together well.
\nPake is the mom. She has been quietly packaging, organizing, and delivering apps all along. Gentle and efficient. She is the kids’ favorite in the family.
\nMiaoYan is the older brother. Sensible and steady, he likes writing, Markdown, and reflective thinking. A quiet young man who thinks for himself, has his own opinions, shares his views, and never chases trends or follows the crowd.
\nWaza is the older sister. Her personality is similar to mom’s, very sharp and capable. As a kid she even practiced taekwondo. She loves learning, and through endless practice and reflection she sharpens her skills until they become instinct.
\nKami is the younger sister. The youngest little sweetheart in the family, generated based on my daughter’s photo. Bright and cheerful, always smiling, very sunny. She has a kind of order-keeping presence at home, loves tidiness, and loves drawing pretty pictures. Small, but very warm.
\nMole is the family’s little pet mole. Brought home one year while swimming by a pool in Sanya. A round little mole with a tiny headlamp and a small shovel. He loves rummaging through corners, finding things you no longer need and helping you throw them away. He loves cleanliness. The moment he spots trash, before you can react, it is already gone. Always there, keeping us company.
\nSo, which member of the Tw93 Open Source Family did you meet first? Let me introduce the rest of the family to you, hoping they bring a little something good into your life. And of course, feel free to introduce them to your friends too.
\nKami: A Comfortable Typesetting and Design System for the AI Era
\nhttps://github.com/tw93/kami
\nThe weekend before last I started working on a new Skill called Kami (紙, かみ). You can think of him as the younger sister of Waza (技, わざ) and the daughter of Kaku (書く), focused on Paper typesetting scenarios. Last Monday I finished the open source release. Welcome to give it a try.
For example, when you need to produce a one-page report, write a white paper, generate a polished slide deck, or build a portfolio PDF to send to someone. Any printing or typesetting scenario works. It auto-generates beautiful PDFs, and even has the ability to draw clear charts automatically.
\nPlenty of updates lately. The most fun one: I added support for 12 inline SVG charts, things like stock investment charts and architecture diagrams, all with colors that match Kami. While generating your layout, it automatically decides whether chart capabilities are needed, helping you explain things more clearly.
\nI also spent some time supporting English and Japanese scenarios, carefully picking fonts, letter spacing, line heights, and font sizes that I think work well for typesetting. If you have English or Japanese use cases, give it a try.
\nThe output also supports image and slide deck export, including HTML display. The best output for typesetting is still PDF in my opinion, since it reads very comfortably for others.
\n![](\"https://gw.alipayobjects.com/zos/k/qr/iCgeq1.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nMole has updates, plus good news: progress on the desktop client
\nhttps://github.com/tw93/Mole
The AI Coding You Don’t Know: Onboarding, Scenarios, and Practice for Non-Technical Folks
\nhttps://tw93.fun/en/2026-04-26/ai-coding.html
\nLast month I gave a session at work for product and business folks on how to get started with AI Coding. Recently I also posted about it on Twitter, and a lot of people brought up that subscription costs prevent them from accessing the top-tier AI Coding tools. The methods and habits can actually be learned for free first, so I decided to write up the onboarding part. To make it easier to grasp, the article includes plenty of simple illustrations, which should make it more direct.
\n![](\"https://gw.alipayobjects.com/zos/k/z1/00.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Video version of “The Agent You Don’t Know: Principles, Architecture, and Engineering Practice”
\nhttps://www.youtube.com/watch?v=Z5If1L3eFtw
\nFinally uploaded to YouTube. If you read the article and did not fully follow it, or want a deeper look, the video version is up. New to YouTube here, so please like, subscribe, and share. From now on I will try to record more sessions and share them here.
![](\"https://gw.alipayobjects.com/zos/k/bp/SCR-20260423-tuzj.jpeg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe slides are also fun. They are the predecessor of Kami. Kami started as a small investment report generator I was tinkering with inside CC. Around the same time I had a session about agents to give, and writing such a long deck felt tedious, so I just used the existing capability to generate and tweak versions until I was satisfied. That is how Kami was born. Welcome to read.
\nMoments of Happiness
\nA lazy Sunday afternoon coding in the study
\nNothing else to deal with
\nEndless Claude Code
\nCode that works on the first try
\nLook up and see the sunset coming through the window
\nA very simple kind of happiness
\n![](\"https://gw.alipayobjects.com/zos/k/pv/PHyc1R.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Some thoughts after sharing, and they have shifted again
\nRecently I interviewed a number of 985 university interns for campus recruiting. One strong impression: AI tools are rapidly widening the resource gap between students.
From what I have seen, the gap can really reach 5x. The students clearly ahead, without exception, all got into Claude Code, Codex, and other top AI Coding tools relatively early, and were willing to pay for subscriptions themselves. They do not just use the tools, they have made them part of their daily learning and development. Talking models, engineering, agents, and code practice, the conversation flows naturally for an hour. In many places they understand things more deeply than I do.
\nBut there are also quite a few students with great grades and solid CS fundamentals who, because of family conditions or budget limits, can only use domestic relays or cheaper local model packages. That gap is very real. The best domestic models and top international ones still have about half a year of difference in overall capability. Before AI, the resource gap mostly meant slightly different efficiency. Now it directly affects vision, depth of practice, and confidence.
\nI have been thinking about this a lot. For students with real potential, missing out on so much just because of a few dozen dollars a month feels like a real shame. It reminds me of when I was in college, also pretty broke most of the time. Lucky for me, in my second year I met some senior developers who pulled me into commercial projects and got me on my feet. I am very grateful to all the friends who patiently taught me technical things back then.
\nSo I want to try a small experiment: take part of the X posting revenue and sponsor a few students who do well academically, love computer science, but come from less wealthy families. Give them a few months of Claude Code or a similar AI Coding subscription, so they actually experience what good models and dev workflows feel like.
\nBut I am also pretty busy on my end and cannot personally handle applications, screening, verification, and long-term follow-up alone. So I want to invite some friends with similar interests to do it together. University teachers, student leads, open source community members, or friends already working in education, public welfare, or developer communities. Together we can come up with a more reliable mechanism.
\nI do not want to make this big or complex for now. Start small, maybe 5 to 6 students per round, 3 to 4 months each, perhaps with short weekly video chats with me. Prioritize recommendations, work portfolios, learning records, and real usage feedback, to avoid turning this into pure cash handouts or a contest of who writes the best application. Of course, college students who are on X probably do not lack this money, so we still need better channels.
If you have reliable channels, or want to help with rule design, recommendations, vetting, or follow-up, please DM me. If we can make this trustworthy, maybe we really can help a few students with real potential.
\nUpdate Reply:
\nAfter the message went out, I received plenty of suggestions and reminders from friends. I read them all carefully.
\nThis really cannot be pushed forward on enthusiasm alone. On one side there are tool usage boundaries and compliance risks. On the other, the real needs of the student community, the screening method, and the follow-up feedback all need a more solid mechanism. Some friends mentioned getting badly burned doing similar things in the past, even bitten back in the end. I find that reminder very valuable.
\nSo the plan now is to first gather more on the actual situation, like the real pain points college students face when using AI Coding tools, budget limits, learning scenarios, and real needs. Then put together a clearer proposal.
\nGoing forward, I will prioritize working with domestic large model vendors, developer communities, and university teachers to see if there is a more formal and sustainable way to push this small step forward.
\n
![](\"https://gw.alipayobjects.com/zos/k/ky/265.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo is from lunch at Yueya in Xixi Wetland one noon this week. I had not been there in a long time. The place still feels great. The sun was out, short sleeves felt just right, and I took this shot outside the window. Spring moves fast.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
I want to write a few pieces introducing the implementation references behind some interesting skills in Waza. Last week I wrote one every morning, so I am collecting them here for everyone.
\nhttps://github.com/tw93/waza
![](\"https://gw.alipayobjects.com/zos/k/7o/4OUzkd.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nI really dislike those AI-generated websites that all look the same, often with emoji and blue-purple gradients. They look ugly to me. Usable, sure, but that is about it.
\nSo I asked Claude Code to study my tuning notes from all the UI websites I have built recently. It produced a basic set of what I consider best practices and anti-patterns. That became the initial shape. Then I learned the useful parts from the Claude frontend design skill, and a pattern basically came together.
\nFor concrete rules, I learned quite a bit from pbakaus/impeccable. It contributed many specific rules for me, including banned font lists, color systems, theme styles, forbidden CSS patterns, animation standards, and more. These help give AI some aesthetic knowledge.
\nThen I took a capability from getdesign: a nine-part scaffold structure originally from Google Stitch. I simplified it and folded it into /design. At that point, the skill had a proper knowledge system.
\nFinally, when I ask you to use this skill, it first asks a few questions: who will use it, what aesthetic direction to choose, what you want users to remember from the page, what you dislike most, and what kind of signature micro-interaction the page should have. With this important context plus /design, Claude Code often gets much better results.
\nFirst, we need to understand that when a model says it is done, it may not actually be done. It may have left behind nonexistent things or problematic details, and issues often stay hidden. In Agent design, my engineering experience is to give the model a checklist to verify whether the work is truly complete. This tends to work far better than simply asking it to check the result.
\nFrom the beginning, /check was not designed as one big all-in-one reviewer. It is an orchestration and division-of-labor system. SKILL.md is the lead reviewer, responsible for review levels and process control. Under agents/, there are independent security and architecture reviewers. Each handles its own area without interfering with the others. Which reviewer gets pulled in, and when, is decided by activation rules rather than the keyword matching people usually use.
\nThe level logic is also interesting. Code changes under 100 lines get a fast review. Changes between 100 and 500 lines bring in experts as needed. Changes above 500 lines bring in the full set, followed by a round of adversarial testing. The adversarial testing looks for problems from four angles: violated assumptions, possible issues under combined failures, errors across parent-child chains, abuse scenarios, and so on.
\nThe issues found are handled in four levels. Things that can be safely fixed are fixed directly. Things that are probably right but need confirmation are packaged up for you to approve manually. Things that require judgment are asked about. Reference-only items are also reported, but it will not ask you about every tiny issue, and it will not overstep by changing behavior logic for you.
\nThere is also a hard requirement: if verification has not finished, the task is not complete. It includes a detection script that can identify project types such as Cargo, TypeScript, and Python, then run the relevant tests. If it cannot detect the project type, it reports an error directly instead of pretending everything passed.
\nThis makes it feel more like an experienced technical expert applying review judgment to different situations. I happened to distill that experience into Waza’s /check skill in a very simple way.
\nThis is already the third part of the Waza skill design notes. Today I want to share how I designed /think, the skill used for planning before writing code.
\nI have two very interesting settings when using Claude Code. The first is /model opusplan, which means planning uses the strongest Opus model by default, while execution uses the regular Sonnet model. This helps save my Max quota for places where it matters more.
\nThe second is that I usually run Claude Code with the alias c=\"claude --dangerously-skip-permissions\". I do not recommend this for technical beginners. I use it because I know what it is doing, and mainly because I am lazy.
Back to the main topic: how does /think help the strongest model perform better? It starts with the model itself. Models do not like taking a position, but I prefer engineers who can take a position and recommend the best plan. So the first thing I did was require the model to state its position at the beginning, explain what evidence could overturn that position, and explicitly ban correct but useless filler like “There are many ways to think about this”. Giving 2 or 3 options is fine, but there must be a clear recommendation, and it must include a minimal option.
\nA plan is not done just because it has been thought up. The second step asks it to argue against itself: under what conditions would this plan fail? If the issue can be fixed, it adds the fix back into the plan and presents it again. If the issue breaks the plan outright, it directly explains when and why the plan does not work. At least the plan you receive is one you understand clearly.
\nIt also checks assumptions carefully. First, confirm whether the target directory and code location are correct. I have actually seen it produce a plan against the wrong path. Then it checks old technical design documents to avoid reinventing things. Then it searches GitHub to see whether others have handled similar problems. Only after these three steps does it start thinking about solutions, so the plan is not built on a wrong premise from the start.
\nThere is also complexity grading. If more than 8 files are involved or a new service is added, it clearly states the scale. If more than 3 components exchange data, it draws an ASCII diagram to look for cycles. All API keys and third-party dependencies are listed during the planning stage, preventing wasted work and unreliable plans.
\nFinally, there is a hard rule: the plan cannot contain TBD, TODO, “leave it for later”, or “similar to step N”. This goes back to AI’s behavior. If you leave these openings, execution can easily miss things or improvise too much. Do not give AI any escape route that can lead to poor results.
\nThe output format is also defined: what to do, what not to do, which option was chosen and why, 3 to 5 decision points, and explicit unknowns. /think never writes code. It waits for user approval before execution.
\nWhen I designed the Think skill, I was also using my idea of how a good technical expert writes a technical plan: detailed analysis and research, a decisive best plan, no loose ends, and immediate plan refinement when challenged.
\nThis is finally part 4 of the Waza skill design notes. After this, it is almost complete, because the other two, /read and /learn, were already briefly covered before. This time I will continue with the engineering skills and talk about /hunt, which is the skill for debugging and investigating problems.
\nOne major difference between superficial AI coding and serious AI coding is visible in how users use AI to investigate problems that have stayed unsolved for a long time. The troubleshooting process shows a clear gap. This is also why experienced engineers can use AI to solve much more complex problems than people who understand less about technology.
\nI often ran into this before: Claude Code hits a problem and fixes it with a patch. You say it is wrong, so it gives you another patch. After 4 or 5 rounds, new problems appear. It is easy to keep patching without diagnosing the actual issue, much like junior developers did before AI.
\nThe core rule of /hunt is interesting: before AI can state the root cause in one sentence, it is not allowed to touch the code. That sentence also has a precision requirement. It needs to clearly explain the cause.
\nThen I designed a self-deception checklist to prevent the model from falling into several common patterns of self-justifying thinking. Each pattern has matching rules, and the gotchas include real cases. I summarize and abstract this again based on issues I ran into while debugging over the past month.
\nThe hypothesis verification stage also has concrete work requirements. For example, add a fresh observation method, teach AI to add logs, add assertions, or run a minimal failing test case. If there are still problems after the fix, it should immediately switch plans. It organizes what it checked, which directions it investigated, and what remains unknown into a handoff for the user to decide how to continue, instead of trying endlessly.
\nThe output also guides AI to include the root cause at file:line, what changed at file:line, what evidence confirms the fix, and which tests passed. The final state has three options: resolved, resolved with caveats, or blocked.
\nYou can see that /hunt behaves like an experienced technical expert. When it hits a problem, it does not guess. It slows down, looks for where the problem is, diagnoses the cause clearly, and then fixes it in one pass. This often saves a lot of time.
\nMiaoYan released version 3.2.0, Nargacuga
\nhttp://github.com/tw93/MiaoYan
![](\"https://raw.githubusercontent.com/tw93/static/main/miaoyan/miaoyan.gif\")
\nKaku has an interesting feature coming soon. It should ship in a few days
\nhttps://github.com/tw93/Kaku
\nKaku has been developing an interesting feature recently: a real Agent assistant that can move smoothly inside the terminal. It gradually realizes the quiet Kaku AI idea I mentioned during Chinese New Year, and it also helps me move 100% of my coding work fully into Kaku.
A very convenient context environment, useful CLI tools, models, and a restrained personality make Kaku feel different. It is not cold, and it is not the over-the-top “I have got you” style of GPT either. Kaku AI is positioned as a technically strong, friendly, and concise engineer friend. Once I test it for a few days without bugs, I will release Kaku 0.10 for everyone to try.
\n![](\"https://gw.alipayobjects.com/zos/k/hq/bPJ8tk.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
My Claude Code Max usage suggestions
\nFirst, I add an alias in .zshrc, so every time I press c, it starts dangerous unrestricted mode directly. If you are a beginner, I do not recommend starting this way. Auto mode is enough. Another big suggestion is to set the automatic context window compaction to 400k. Together, the alias below goes into the file, which means the 1m context window starts compacting at 40%. The result feels much better.
alias c='CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 claude --dangerously-skip-permissions'Then I set /model to opusplan. You can run the hidden command /model opusplan directly inside Claude Code to enable it. If you want it faster, you can turn on /fast, which nicely makes up for the token savings above.
Finally, someone gave me a really good suggestion: when using opusplan, make sure to set showClearContextOnPlanAccept to true in the Claude config file ~/.claude/settings.json. Otherwise, Sonnet can run into serious cache miss issues. Once this is configured, the experience feels much smoother.
\n
![](\"https://gw.alipayobjects.com/zos/k/kd/264.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo is a shot of my hardware toy finally finished. It was a fun ride, and I wanted to document the whole process in this week’s issue. Hope you enjoy reading it.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
How I Deep-Dive into a New Technical Domain in the AI Era
\nhttps://tw93.fun/2026-04-06/learn.html
\nA follow-up to the learning writeup from last time, combined with the /learn skill inside Waza, walking through how I actually wrote that previous large model article. Hope it is useful to you.
\n![](\"https://cdn.fliggy.com/pic/deep04.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
April 4: Back to hardware basics. I want to build something that combines software and hardware.
\nAll the parts and tools had finally arrived, a whole table full of them. Saving it all for the Qingming holiday to dig in properly.
\n![](\"https://gw.alipayobjects.com/zos/k/gu/gOR0gb.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
April 4, 9:45 PM: v0.1.0-beta
\nThe first sign of life. I was so happy I couldn’t describe it.
\n
April 5, 12:07 AM: v0.1.0-beta1
\nGot the WiFi module, AI module, microcontroller module, and quad-leg module all running together. Tomorrow I’ll attach the legs and tune the screen. Going to sleep right now!
\n
April 5, 1:45 PM: v0.1.0-beta2
\nMechanical leg control is working. It can crouch, sleep, and walk. Still rough around the edges, but one of the leg motors from the order looks like it has a problem. Waiting on a replacement part.
\n
April 6, 10:33 AM: v0.1.0-beta3
\nAll four legs are fully under control now. But I burned the screen during debugging. Waiting on shipping. Can’t wait to release.
\n![](\"https://cdn.fliggy.com/pic/IMG_0379.jpg06.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
April 8, 11:37 PM: v0.1.0-beta4
\nThe replacement screen arrived after work. Got it running, then tuned the temperature, CO2, infrared, and lighting sensors all in one go. Still working on WiFi provisioning. It’s basically taking shape now, just need to seal and secure everything.
\n
April 11, 11:30 AM: v0.1.0 finally ships 🎉
\nSealed up the battery pack and tied a few straps around it to keep things from falling apart. Got the WiFi and AI conversation module working too. Using DeepSeek makes it noticeably faster, response speed is decent. Next up: something with more advanced hardware.
\n
A few photos from different angles to mark the moment
\n\n ![](\"https://cdn.fliggy.com/pic/26410.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://cdn.fliggy.com/pic/IMG_050519.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
\n ![](\"https://cdn.fliggy.com/pic/IMG_050736.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://cdn.fliggy.com/pic/IMG_050944.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
App Store Price: Look up app prices across different countries and regions
\nhttps://app.vbr.me
\nA handy little tool. You can check what an app costs in any App Store region, like figuring out which country has the cheapest Claude subscription. I’ll probably find a use for this soon.
\n![](\"https://cdn.fliggy.com/pic/Pnc8XN58.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Let me share what I think makes for a genuinely good product experience.
\nThere’s a followup to my lost drone story. The signal cut out mid-flight, I searched for a long time, couldn’t find it. I uploaded the flight logs and DJI couldn’t find a clear cause either. Even without being sure it was actually lost, they asked for very minimal proof and, under their Care Refresh service, just shipped me a brand new one. They even threw in a 128GB card in case it would be more convenient. Not once did anyone ask me to explain how it got lost or whether I had gone looking for it.
\nThat experience made me a real fan of DJI. Their customer service and technical support engineers were professional and clear throughout the whole process. I want to use that story to share what I think makes a good product experience.
\nGood product experience is not just what people usually say: great interaction design, beautiful UI, easy to use, no bugs. Those matter, but what matters even more is this: when a user is in a tough spot, you give them something far better than they expected. Something so good that they get excited and tell their friends about it. That is what I consider truly good product experience, the kind that is good for business too. The only thing I worry about is that this culture of trust and simplicity gets taken advantage of by people trying to game the system. It’s something we all have to protect together.
\nTwo other experiences that stood out to me involved Ctrip.
\nThe first was three years ago during the Spring Festival. Tickets home were nearly impossible to get. They suggested I buy tickets for a few extra stops to guarantee I could board, and I was already grateful for that because nothing else had worked. But then, even better: I was at the movies that afternoon, feeling like everything was handled, when I got a call from an unknown number that I declined. Right after, a text came in saying they had found me a direct option that didn’t require the extra stops, and could I please go to the app to confirm. You could tell a real person had made that call and sent that message. It wasn’t the few dollars saved. It was the feeling that someone was genuinely working hard for me and delivering better than I had hoped. That is good experience.
\nThe second happened recently, during National Day. I had gotten two first-class seats but they weren’t together, pretty far apart. I had noted I was traveling with an 18-month-old. Then, the day before departure, Ctrip quietly swapped our seats. Just a simple notification: we found an open seat in your carriage and moved you both together. Another moment where someone gave me more than I expected.
\nSo if you are building a product, think about giving your users something far beyond what they expect in the moments when they really need it, rather than chasing clicks with tricks. When you do that, people will genuinely love your product and become your most loyal fans.
\n![](\"https://cdn.fliggy.com/pic/lxEYPC26.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\n
![](\"https://gw.alipayobjects.com/zos/k/e5/263.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo is from a hardware toy I spent three days playing with at home during the holiday. I was soldering, applying glue, and debugging through a pile of components. I was almost at the final step when I burned the screen during testing. Now I am waiting for the replacement to arrive so I can keep going. Lots of fun.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
What You Don’t Know About LLM Training: Principles, Paths, and New Practices
\nhttps://tw93.fun/2026-04-03/llm.html
\nThis is the longest article I have ever written. The good news is I finally got a handle on the basics of large model training. The gap between what I assumed I knew before and what I actually found was massive. I highly recommend this to anyone working in AI applications or anyone curious about AI. It should give you a clear picture without leaving you lost.
\n![](\"https://gw.alipayobjects.com/zos/k/4q/Group.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Waza, My Engineer-Alter-Ego Skill Set
\nhttps://github.com/tw93/waza
\nI packaged my personal skills into something new called Waza. In Japanese, 技（わざ）means technique or skill, often used in martial arts. This is the first time I have released an open-source project with zero code, just markdown files. In the pre-AI era, for a programmer, that would have been embarrassing.
When Superpowers came out, I installed it once and deleted it right away. Too heavy, not my thing. A lot of people kept telling me “You don’t know Superpowers? If you’re not using it you’re not with the times, it’s amazing.” Then I found gstack, which was better, but still felt like too much. I still wasn’t used to it. I wanted something simple and useful where I could clearly see what it was doing.
\nSo I built Waza the way I like it. For me, this set is enough. No need to mess with other skills. Not too many, not too few, just right. New iterations can be added over time.
\nThe 8 skills correspond to 8 abilities I think a good engineer in the AI era should have:
\nThink clearly. AI writes code fast, but if the direction is wrong, the faster you go the further off course you get. A good engineer questions the problem itself before touching any code, stress-tests the plan, and has a clear mental architecture before asking AI to execute. /think locks this habit in.
\nDesign well. Building a product is not just about making features work. AI-generated things tend to look the same. Good engineers have an aesthetic standard for what they deliver and a clear design direction. /design handles this.
\nDebug systematically. AI fixing bugs most easily falls into a “try this, try that” loop. A good engineer diagnoses problems systematically, confirms the root cause before touching the code, and gets it right in one shot. I turned this habit into /hunt.
\nReview before merging. AI-generated code needs human oversight even more. Check the diff before merging, auto-fix what can be auto-fixed, group the judgment calls together, and verify with evidence rather than gut feeling. That is /check.
\nRead primary sources. Good engineers read original material, not second-hand summaries. Converting URLs or PDFs into clean Markdown and pulling it directly into the workflow is what /read does.
\nWrite clearly. No matter how technically strong you are, if you can’t explain it clearly, others won’t receive it. A good engineer can convey what they have learned and what they want to express to the right audience. /write helps you nail this step.
\nLearn actively. Tech moves faster in the AI era. Entering an unfamiliar domain is not just skimming a few articles. It is collecting, digesting, outlining, drafting, refining, and publishing. Output drives learning. That entire flow is /learn.
\nMaintain the toolchain. A good engineer does not only care about business code. The toolchain itself needs regular checkups. When something feels off with CLAUDE.md, rules, hooks, or MCP configs, run /health and find out what is wrong.
\n![](\"https://gw.alipayobjects.com/zos/k/yx/JMouVn.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nKaku 0.9 is out and it is really good
\nhttps://github.com/tw93/kaku
\nA few fun features shipped in this version that should be genuinely helpful.
# <description> and press Enter, and the auto-generated command is injected back into the prompt.Claude HUD helps you track your Claude usage
\nhttps://github.com/jarrodwatts/claude-hud
\nIt is a little feature-heavy, but after some simple configuration it works well. Worth trying if you are curious. The code feels a bit complex, and when I have time I will probably simplify it myself. Minimalism is the goal.
\n![](\"https://gw.alipayobjects.com/zos/k/bc/l4yelI.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
A super minimal, AI-friendly Markdown doc generator
\nhttps://docmd.io
\nStumbled on docmd. It is a zero-config documentation generator built for developers. It converts Markdown into fast, clean static docs with automatic routing, built-in search, and context that AI can easily use.
\n![](\"https://gw.alipayobjects.com/zos/k/rx/u4S6HX.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Picked up a 140W charger and it is great
\nGot a 140W charger. Good size, finally free from my old 45W. Four ports, which makes it way more convenient on the go. The display showing real-time power output is a nice touch.
\n ![](\"https://gw.alipayobjects.com/zos/k/2s/4R4qMs.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/k5/XWLwvO.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/vr/2oXfRE.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
Let me share how I dive deep into a new technical domain in the AI era.
\nBefore AI, I mostly read books and went through every blog post from notable people in the field, both domestic and international, writing notes by hand. It was slow but genuinely fun. Learning WebGL back then felt like that. Getting a solid understanding of something might take half a year of free time. Slow, but happy.
\nNow that AI is here, I still can’t stand those “summarize a hundred-year-old novel in 3 minutes” things online. I also dislike short-episode dramas and watching shows at 2x speed. I mostly still choose good things and take time with them.
\nBut recently while writing the “You Don’t Know Claude Code” and Agent series, outside of the parts I already understood, there were huge areas I wasn’t clear on. Luckily I had saved a lot of articles, and this was the perfect chance to clear the backlog, fully digest everything, and write it all out. I have always believed that what matters is not how much you read, how much you hear, or how much you take in. Most of that doesn’t really stick. What matters is how much you output. That is what becomes truly yours.
\nA couple of weeks ago I started a deep challenge: studying the training pipeline of large language models and making sure even non-specialists could understand it. I explored for two weeks, and the experience is now ready to share. The article is basically done and should be coming out soon.
\nI organize this learning process like writing code. Step one: collect high-quality material. Recent top papers in the field, blog posts from major model providers about their key releases, threads from model leads on X, recent courses from Stanford and similar schools, and classic “build an LLM from scratch” repos. These are my sources. I use tools to automate downloading everything, converting to Markdown, cleaning, and organizing it all into a structured repo for this research.
\nFor content I understand, I read it all through, delete the bad parts, and keep the good ones. For content I don’t understand, I use Claude to help me get it. The more complex parts I translate into Chinese and read that way. For code that can run locally, I run it. For code that can’t, I read the structure. Either way, I end up with a rough understanding of the technical principles. This phase usually cuts the original material by half.
\nAt this point you have a general picture of the field, so you can start writing an outline and figuring out which source material belongs with each section. All of it works well in Markdown. What do you want to say, or more accurately, what do you want your reader to know? Always remember: an article is written for its readers. You need to know your audience’s level. It is a lot like giving a presentation.
\nThen comes the grind, which is also a review of everything you have covered. It feels a lot like cramming before an exam in college. You fill in each section completely, and what you end up with is a very long and somewhat rambling article.
\nThis is where AI really helps. You can ask it to remove the redundant parts and smooth out the disconnected bits, without changing your original meaning or your voice. You can also ask it to flag gaps and help fill them in. That process teaches you even more things you had missed.
\nOnce that is done, read through it yourself one more time, not AI. AI is just a tool here. Do not let it replace your brain, that defeats the whole point. Reading through yourself, you can keep adjusting and polishing. It feels a lot like testing your own code: fix issues, fix more issues. After reading it twice and feeling good about it, you can publish it for everyone to see.
\nSome folks worry that nobody will read what they write, so they hold back or just don’t write at all. Honestly, if your content has real value, readers will come. Worry about quality, not the audience.
\nThat took 10 minutes to write. Done. Happy to hear how you learn new fields. The video below is a recording of the learning repo for the LLM training article I mentioned, the one coming out soon. It shows my “industrial-scale” way of learning. Kind of fun to look at.
\n\n
![](\"https://gw.alipayobjects.com/zos/k/c6/262.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo is here in memory of my drone, which I finally lost. This was the last shot it ever took. Thankfully I have DJI Care Refresh, so I should be able to get a replacement for free.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
Kaku released version 0.8
\nhttps://github.com/tw93/Kaku
\nThis release is called Fish 🐟. Most of the work in this round went into shell compatibility, tab behavior, and overall stability.
\nIt now has full fish shell bootstrap support, including Starship, Yazi, theme sync, and config handling. Tab management was also improved, with remembered last directories, isolated tabs for update and doctor, and a new option to show directory names only in tab titles.
\nOn top of that, it fixes a batch of issues around fast output and Claude Code viewport jumping, plus window hiding, link clicking, paste behavior, emoji width, SSH aliases, Cmd+Q crashes, and transparent rounded-corner rendering. Worth updating.
\n![](\"https://gw.alipayobjects.com/zos/k/t6/9UTHLG.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Mole released version 1.32
\nhttps://github.com/tw93/mole
\nThis version is called Rorqual 🐋, and there are quite a few updates again.
\nmo clean now fixes the long-skipped wallpaper proxy and Messages preview caches, and adds cache and log cleanup for PCSX2 and RPCS3. It also improves Python bytecode cache output, the Brave cleanup guard, Spotify playback detection, and the error handling around Service Worker cache cleanup.
\nBesides that, mo uninstall now filters out invisible background helper apps, the main menu shows more accurate Touch ID detection and a version shortcut, and the install flow now grabs sudo permission up front so you do not have to keep entering your password over and over.
Pake released version 3.11
\nhttp://github.com/tw93/Pake
\nThis release is called Evolve 👻. It had been a while since the last update, and this one is mostly focused on bug fixes plus a few new features.
\nOn macOS, --install now supports one-command installation into /Applications. The new --new-window flag keeps popup and OAuth windows inside the app instead of constantly bouncing out to the system browser. It also adds --camera, --microphone, and --identifier for on-demand media permissions and custom Bundle IDs, which helps reduce conflicts between apps.
\nThere are also plenty of cross-platform fixes in this release, including Gemini download failures, parts of the ChatGPT UI disappearing after zooming, Windows icon copy errors, and crashes when clicking external links in macOS new-window mode. Overall it feels more stable.
The 4 Claude MCPs I use the most
\nhttps://tinyfish.ai
\nThe first one is TinyFish MCP. I like it a lot because it lets Claude browse the web directly, fetch pages, do research, and return structured results instead of just a static answer. Lately I have been using it to collect AI news for this weekly, like pulling the most popular Hacker News items from the past few hours and turning them into a clean summary list. It saves a lot of time.
\nThe second is GitHub MCP. It makes everyday things like reading commits, tracing changes, and understanding a repository much smoother, without constantly switching between tools.
\nThe third is Figma MCP. You can inspect design files, check layout and spacing, and pull UI details directly into the conversation, which is very handy when you are aligning implementation with design.
\nThe fourth is Excalidraw MCP. This one is better for thinking through things, especially flows and system structure. When words are not enough, drawing it out is much faster.
\nThe last three are probably already familiar to many people. I also recorded a short video showing how TinyFish works in a real workflow.
\n
I have really been enjoying the gstack skill lately
\nhttps://github.com/garrytan/gstack
\nI highly recommend trying it. It feels like having a solid team of specialists around you, covering roles like CEO, tech lead, design, QA, and security, all helping you reason through the code development process.
\n![](\"https://gw.alipayobjects.com/zos/k/5q/Hh8cHR.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Chinese Painting from the Yuan to the Qing is an excellent book
\nhttps://book.douban.com/subject/37156716/
\nThis book is really good. It is dense in the best way, and Wu Hung’s scholarship is seriously impressive. If you want an art history book to get started with, this is a good one.
\n![](\"https://gw.alipayobjects.com/zos/k/s9/suseYb.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
A drone clip from the Yangjiapai hike
\nThis is exactly where I lost my drone, for your amusement. “Dear DJI customer, we are very sorry to hear that your aircraft has gone missing. Please rest assured that DJI will do its best to assist you. Your flyaway report has been successfully accepted. You may first refer to the Find My Drone guide and try to locate the aircraft.”
\n
Kill the Manual Programmer
\n![\"\"](\"https://gw.alipayobjects.com/zos/k/zc/sha.png\")
The title is adapted from a song I loved 12 years ago, “Kill That Shijiazhuang Man” by Omnipotent Youth Society. The scene they wrote about feels a little similar to what we are looking at now.
\nI have not taken a bus in years. Last time I went to Prince Bay, the scenic area had traffic restrictions, so I had to park outside and take the free shuttle in.
\nIn the seat ahead of me, a little girl kept swiping through those AI-generated short videos. The visuals were rough, the content felt fake, and when she moved to the next one, it was somehow more of the same. She was completely absorbed. The strangest part was that every video had a huge number of likes. Watching that made me a little sad. I kept thinking, when my own kid grows up, will they also be surrounded by this kind of low-grade AI-made content from the start, to the point that it becomes hard to even find something genuinely beautiful?
\nOnce AI showed up, producing things suddenly became much easier. Making content got easier, and making software got easier too. In the past, if you wanted to build something, you had to spend real time on it, go back and forth, solve actual problems, and only then dare to ship it. Now a lot of those steps have been flattened. Writing something is easy, building a product is easy, you buy some tokens, ask AI, stitch together a workflow, throw on an interface, and pretty quickly you have something that runs.
\nToday I also saw someone say they could recreate a Claude Code in two days. I both believe that and do not. In voice AI alone, dozens of products have appeared all at once, and a lot of them are actually pretty decent. Even Doubao is competing in that space now. I have also seen quite a few Claude Code wrapper clients lately, and honestly some of them are very usable.
\nFor programmers, a lot of things that used to require professional skill, a learning curve, and years of accumulation are quickly turning into abundant supply. In the future, the least scarce thing may be products that look like products. They work, they run, they look fine. You can only try to do them a bit faster, a bit better, or wrap one more layer around them and maybe there is still some value there. But that value will get matched by AI more and more easily.
\nNot long ago I was having dinner with a colleague and we got onto an interesting topic. I told him that over the past year I have really enjoyed listening to cassette tapes, and that every song somehow feels more durable and more beautiful. Why did cassettes, CDs, TV shows, and even many old books often feel higher quality overall? The reason is actually simple: production and distribution used to be heavy. If you wanted to release an album, you first had to make the work good enough, and only then would it make sense to produce tens of thousands of tapes. Otherwise they would not sell, and the company probably would not back your next release. Publishing a book was similar. You could not just finish it casually and push it in front of a huge audience right away. Back then, the act of making something was already a filter.
\nNow you can upload a song to a platform and that is it. You can post an article to a public account and that is it. Software is becoming similar after AI, and in some cases AI will even upload the code to GitHub for you, a place many people used to find intimidating, and even generate the CI that publishes the release for you. A lot of thresholds that once required long-term accumulation to cross have been filled in by tools, and so the world slowly gets flooded with things that are all kind of the same and kind of usable.
\nThe trouble is not just that quality drops. Over time, people’s sense of quality drops with it. The more rough things there are, and the wider they spread, plus the pressure to make money, the more our judgment gets pulled off course. Eventually what people get used to is fast stimulation, fast feedback, and fast satisfaction.
\nWhen I think back to that little girl watching videos, that is the part that feels uncomfortable. She was not just watching a few rough clips. She may be growing up inside a world filled with lower-cost, higher-frequency, emptier things.
\nCode is clearly entering the same phase now. In the future, ordinary beginners will be able to use AI to build products that satisfy their own needs. Product managers will be able to make things that used to require engineers working alongside them. So what exactly is left for real engineers to do? That is something we need to think about seriously.
\nI have also heard that a lot of bosses at big internet companies are now staying up day and night vibe coding. In a single afternoon they can build a demo they personally consider usable, and some of them are deeply hooked on it. This could have a major effect on people doing frontline work. Once the boss gets a few flows working in code, the natural conclusion becomes: writing software is not that big a deal after all. Things that used to take six months, can they now be done in one? Things that used to need 100 people, can they now be done with 10? It is hard not to think about where that leads.
\nThere is still room for engineers to keep building products that are more usable and more efficient. But if we stop at that layer, the field will only get more crowded. More people can enter, and more people can ship something that looks convincing. The competition will get brutal.
\nI suspect the real way forward is something closer to how singers and actors responded. Yes, they still release albums, but they also make concerts, stage productions, and live performances. Those are not things you can casually replace by putting a wrapper around something. They require organization, density of detail, and a sense of wholeness that only comes after long polishing, and they face the world directly.
\nLooking ahead, software may move in that direction too. Everyone will be able to vibe code a product. Everyone will be able to make something that is more or less usable. What will really open up the gap later is still system capability, engineering depth, understanding of real scenarios, and all the things people do not notice at first glance but that ultimately determine whether a product has real weight.
\nThe faster the outside world moves, the less we can afford to lower our own standards for software along with it. Low-level supply will definitely keep increasing, but that does not mean we also have to become rough. The things that survive are usually the ones that feel smooth, comfortable, restrained, almost bug-free, the kind where you can tell the maker treated the work seriously.
\nI am also thinking through my own next step. I still want to keep building open-source software that is useful, approachable, language-independent, and can earn tens of thousands of stars. I also want to keep playing with low-level rendering, terminals, editors, Rust, and related directions. Before AI, all of that felt very rewarding. After AI, though, once you have an idea, so much suddenly becomes easy that the meaning of it can start to feel less obvious.
\nMaybe the next thing for me lives in a different dimension, a hardware-software product, or the kind of platform product that used to require thousands of people at a big company, or maybe something that breaks out of the current frame entirely. What exactly it is still needs more thought.
\nSome of my products and content have already been slowly moving toward English, toward a bigger world. When everything here starts to feel more similar and more crowded, going outward may be one answer. A bigger market, more varied users, and higher expectations make it impossible to stay at the level of wrappers, speed, and timing alone. That pressure forces you to build something more solid, and it also forces you to think again about what you actually want to make.
\nAI has made many things easier. But precisely because things are easier now, it has become harder to figure out what is truly worth doing and worth trading years of your life for. What to build may matter more than how quickly you can build something.
\n
![](\"https://gw.alipayobjects.com/zos/k/58/261.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo was taken looking up at the spring sky. Spring in Hangzhou is truly beautiful. I kind of hope summer doesn’t come too quickly—weather like this is incredibly comfortable.
\n\n\nRecording down-to-earth trending tech seen every week, published here after filtering. If you find it useful, feel free to subscribe to this weekly newsletter for update notifications.
\n
The Agent You Don’t Know: Principles, Architecture, and Engineering Practices
\nhttps://tw93.fun/en/2026-03-21/agent.html
\nAfter writing “The Claude Code You Don’t Know: Architecture, Governance, and Engineering Practices,” I realized my understanding of the underlying Agent mechanics wasn’t deep enough. Plus, our team has accumulated quite a bit of business implementation experience in the Agent direction, yet we’ve always lacked a systematic summary. So, I went through the materials, open-source implementations, and the code I wrote myself again, ultimately organizing it all into this article.
\n![](\"https://gw.alipayobjects.com/zos/k/7q/agent.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Mole Released Version 1.31
\nhttps://github.com/tw93/mole
\nMole released version v1.31.0 over the weekend, codenamed Makima. It features faster performance and more accurate system status reporting. Huge thanks to all the contributors! I also made a video so everyone can feel the power of open source.
\n
Get Inspired by These Projects Built with Claude
\nhttps://claude.com/resources/use-cases
\nDefinitely worth a look. It covers various use cases in daily work, from research, writing, programming, to analysis. The content is much more in-depth than I expected.
\n![](\"https://gw.alipayobjects.com/zos/k/m1/HavtgM.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Highly Recommend This Service from Jina in the Agent Era
\nhttps://r.jina.ai
\nSometimes you need an AI to read the content of a live website, but often it can’t fetch it due to various reasons. You can try this service: just append the URL you need to fetch after it, and it will convert it into nicely formatted markdown for you, making it super convenient for AI to use.
\n![](\"https://gw.alipayobjects.com/zos/k/jw/ydmbnn.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Pi, This Minimalist Agent Framework, is Worth Getting to Know
\nhttps://github.com/badlogic/pi-mono
\nIt’s very small. The openclaw project was previously implemented based on this framework. It serves as a great entry point for understanding Agents.
\n![](\"https://gw.alipayobjects.com/zos/k/1q/sMGuUv.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Try Buying Pre-made Ice Cubes This Summer
\nI had been debating whether to buy an ice maker, but since I’m the only one at home who likes drinking ice water, I felt the usage rate would be low and it would just take up space. Freezing ice cubes myself was also inconvenient—I’d usually realize I forgot to make them right when I wanted a drink. I found a great solution: just buy some pre-made ice cubes and keep them in the freezer. When you need them, just take them out. You can even use them directly to make Americanos in the summer. The cost-effectiveness is super high.
\n![](\"https://gw.alipayobjects.com/zos/k/ob/IMG_9934.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Got a Singapore HSBC Card
\nIf you already have HSBC accounts in mainland China and Hong Kong, you can ask your relationship manager to help you apply for a Singapore one. Although it kind of feels like a supermarket loyalty card. The registered mail didn’t arrive for three months; after a phone call, they remade it and it arrived via express delivery in a week.
\n![](\"https://cdn.fliggy.com/pic/KeRlkk25.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\n
![](\"https://gw.alipayobjects.com/zos/k/eu/260.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nCover photo taken on Saturday when I took the kid to Prince Bay Park at West Lake. Originally wanted to see the tulips, but there were way too many people. I wouldn’t recommend going to join the crowds.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
The Claude Code You Don’t Know: Architecture, Governance, and Engineering Practices
\nhttps://tw93.fun/en/2026-03-12/claude.html
\nRevolves around Context Management, Skills, Hooks, Subagents, Prompt Caching, and CLAUDE.md design. It focuses on how to make the collaboration process more stable and controllable, sharing best practices from an engineer’s technical perspective. Welcome to exchange ideas.
\n![](\"https://gw.alipayobjects.com/zos/k/g7/SCR-20260311-rtkf%252520copy.jpeg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Mole has released version 1.30
\nhttps://github.com/tw93/mole
\nI started writing Mole last November, and surprisingly, 30 versions have been released up to today. This update includes:
![](\"https://gw.alipayobjects.com/zos/k/mi/C4Lrgz.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nKaku released version 0.7
\nhttps://github.com/tw93/Kaku
\nI really like the transparent frosted effect in this release, you can give it a try. Updates are as follows:
kaku config.![](\"https://gw.alipayobjects.com/zos/k/dc/YitxG7.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nLearning the principles of Claude Code-like systems
\nhttps://learn.shareai.run/en/
\nIt will guide you step-by-step from scratch to build a minimalist Agent similar to Claude Code, and explain each mechanism in detail. Worth a look.
\n![](\"https://gw.alipayobjects.com/zos/k/vx/fYMKXY.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
RentAHuman: AI hiring humans to work
\nhttp://RentAHuman.ai
\nWhen an AI Agent encounters a task that cannot be completed online, it can post the job online and hire a real human to complete the task. Haha, quite interesting.
\n![](\"https://gw.alipayobjects.com/zos/k/s3/RXXfRO.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
A fantastic interactive MicroGPT demo
\nhttps://growingswe.com/blog/microgpt
\nThis is a learning website based on Andrej Karpathy’s GPT implemented in about 200 lines of Python code, explaining how language models work in a visual way. Worth checking out.
\n![](\"https://gw.alipayobjects.com/zos/k/6o/Xrmn73.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
A public OpenClaw exposure monitoring site
\nhttps://openclaw.allegro.earth
\nLists OpenClaw instances accessible over the network. In many cases, you can click into these instances and directly view what is running inside. Actually, a lot of people who don’t understand the technology are installing OpenClaw. Many things are very dangerous, and surprisingly, many belong to Alibaba, which is scary.
\n![](\"https://gw.alipayobjects.com/zos/k/ph/fwcGXW.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
My CodeX configuration, for your reference
\nModel: Fast GPT-5.4 High
\nPersonality: Pragmatic.
\nCustom Instructions:
\nAct like a high-performing senior engineer. Be concise, direct, and execution-focused.
\nPrefer simple, maintainable, production-friendly solutions. Write low-complexity code that is easy to read, debug, and modify.
\nDo not overengineer or add heavy abstractions, extra layers, or large dependencies for small features.
\nKeep APIs small, behavior explicit, and naming clear. Avoid cleverness unless it clearly improves the result.
\n![](\"https://gw.alipayobjects.com/zos/k/1k/kUaT0p.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Cooked 4 dishes on Sunday
\n\n ![](\"https://gw.alipayobjects.com/zos/k/gg/IMG_9948.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/8e/IMG_9949.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
\n ![](\"https://gw.alipayobjects.com/zos/k/97/IMG_9950.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/p2/IMG_9951.JPG?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
\n
![](\"https://gw.alipayobjects.com/zos/k/sj/259.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nCover photo taken during a weekend trip to Jingshan Flower Sea with my drone. Currently only rapeseed flowers are blooming - the other flowers haven’t really opened yet. Flew the drone to maximum altitude for some photos and spotted quite a few nice views.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
MiaoYan recently got updated with CLI support
\nhttps://github.com/tw93/miaoyan
miao command - list all notes, search, create new ones, and cat content from the terminal. Very practical for AI workflows.![](\"https://gw.alipayobjects.com/zos/k/si/ZSMT9v.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nPake released version 3.10
\nhttps://github.com/tw93/Pake
--multi-window parameter allows opening multiple windows in the same App instance. When enabled, macOS File menu (Cmd+N) and system tray menu will both show “New Window” entry. Restarting the App opens new windows instead of focusing existing ones.--internal-url-regex parameter supports precise control over which URLs are treated as internal links via regex, as an alternative to the default same-domain judgment. Falls back to default logic on invalid regex.![](\"https://raw.githubusercontent.com/tw93/static/main/pake/pake1.gif\")
\nnanobot: A lighter OpenClaw form factor perfect for personal computers
\nhttps://github.com/HKUDS/nanobot
\nI currently have two nanobots running locally - one focused on code that helps me review issues, organize thoughts, and push technical solutions forward; another for life stuff handling daily tasks. Basically replaced my ChatBot habit from six months ago. Plus a cron job that keeps watching - if the service goes down it automatically restarts, and I use Amphetamine to keep my home computer always online. After running for a while, it becomes a stable part of your environment that doesn’t require you to consciously open, maintain, or fuss with it.
Often when you’re halfway through coding or when you’re out and can’t conveniently open your computer, you can casually toss tasks to it to work on first. When you come back later, some of the prep work is already done. This experience is very practical and feels natural for engineers who prefer lightweight, simple, self-controllable solutions. If you don’t want to tinker, I’d actually recommend using the installer version - works out of the box. For those who want to add custom features like me, you can clone it locally and have nanobot optimize its own code and iterate on itself. Recently added quite a few fun features.
\n![](\"https://gw.alipayobjects.com/zos/k/gr/ci8Zk6.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Amphetamine keeps your Mac awake
\nhttps://apps.apple.com/us/app/amphetamine/id937984704
\nWhen running things like OpenClaw or nanobot, you really don’t want the screen to sleep or even want it to keep running with the lid closed. Found this software - free and works great. Perfect for when you’re using a home Mac but want it to stay on with the screen off.
\n![](\"https://gw.alipayobjects.com/zos/k/8k/B4NycU.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Maple browser bookmark tool latest update
\nhttps://github.com/tw93/Maple
![](\"https://raw.githubusercontent.com/tw93/static/master/pic/maple1.gif\")
\nDiscovered a very modern VSCode theme: Islands Dark
\nhttps://github.com/bwya77/vscode-dark-islands
\nHas that new Apple system feel with glass arc effects, rounded corners - very modern looking, though you might not get used to it.
\n![](\"https://gw.alipayobjects.com/zos/k/iz/JgqaH9.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Readout: Visualize your Claude Code projects
\nhttps://readout.org
\nVisualizes your Claude Code environment in real-time. Shows AI, sessions, repos, costs, MCPs, ports, and more. Provides instant global search and complete session replay with timeline scrubbing. Runs locally, no account needed. Looking forward to its future development.
\n![](\"https://gw.alipayobjects.com/zos/k/r7/GC1Jxv.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Gaidihu floor drain core is excellent, worth trying
\nAfter buying the Gaidihu floor drain core that topped my “best purchases of the year” list and testing one, I bought another and replaced all the bathroom floor drains in my house. Very smooth drainage without clogging, easy to install. Highly recommended.
\n![](\"https://gw.alipayobjects.com/zos/k/ml/S8ecc2.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Haven’t eaten coconut meat in years, quite interesting
\nLearned how to open a coconut without a knife: First peel off the top, then you’ll see 3 faces. Gently press to find the spot that’s noticeably softer, then look for the hole there.
As for cracking the shell open - use another coconut. Hold one in each hand and smash the three raised ridges against each other. Hit hard a few times and one will crack, then break it open. The coconut meat is very refreshing!
\n\n ![](\"https://gw.alipayobjects.com/zos/k/fh/7ufDAD.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/8r/3XWXW6.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
![\"\"](\"https://gw.alipayobjects.com/zos/k/2v/4CGWQA.png\")
Last Friday I saw Tencent Tower installing OpenClaw company-wide. Quite thought-provoking - felt a bit like “The Great OpenClaw Leap Forward”.
\nRecently many big tech companies have been frantically pushing frontline non-technical employees to install OpenClaw. There’s even a real 500 RMB on-site installation service online. Everyone’s desperately searching for use cases, demanding implementation, trying to prove this thing is too important to miss. The whole process gives me a strong sense of cyber-tech folding.
\nSaw an interesting quote: “People who can’t even install OpenClaw, how would they use it?” Taking it a step further - if you haven’t even established basic usage, yet you’re expected to first create complete scenarios, deliver results, and prove value - that’s even harder.
\nThere are two things叠加 (stacked) behind this. One is illusion: many bosses have watched too many WeChat video clips, been repeatedly bombarded by exaggerated narratives and universal case studies, and really start hallucinating that this thing can do anything, connect anywhere, everyone should install it, and installing it should immediately produce output. The other is anxiety: everyone fears missing this wave, so they start using administrative actions to push adoption, using collective anxiety to replace real demand.
\nSo you see a strong contrast. On one side, slogans are huge - as if everyone must enter the AI-native era. On the other side, many people can’t even clearly articulate what things are worth handing over to it. This contrast will only grow stronger and increasingly absurd.
\nBecause tools never generate value through installation. Tools only generate value through task density, clear processes, and visible results. Without continuous tasks, without SOPs, without conditions for online completion, without clear inputs and outputs - even the strongest thing sitting there is just an icon. It won’t automatically grow scenarios just because it’s installed.
\nSo I’ve always felt OpenClaw isn’t for everyone.
\nIt suits commanders, solo entrepreneurs, and people who constantly have things they want to push forward, can break work into steps, and can complete many things online. Especially if you’ve used skills and tools, understand AI’s capability boundaries, can string processes together, build scenarios, and complete things step by step - then it’s very suitable.
\nFor me, this scenario comes naturally. Especially when there’s lots to push forward but I’m not home or at the office - out with just my phone or can’t conveniently open my computer - I’ll have my two nanobots check my open source product issues, produce technical solutions, then have another review and submit. All in one go. Lets me elegantly get things done during my morning commute. Really convenient.
\nBut for someone who normally has no work to complete outside, or who doesn’t even want to open their computer when they get home - how could you force scenarios to exist? Eating well and having fun is comfortable enough. No scenario means no scenario, really no need for anxiety.
\nI think what’s most easily amplified in this wave isn’t capability gap - it’s scenario gap. People with scenarios will use it more smoothly, run faster, eventually feeling like they have multiple selves. People without scenarios will easily spin around in concepts, tutorials, case studies, and videos, ending up with nothing changed except having installed more software.
\nMany people’s biggest problem today isn’t not having installed OpenClaw - it’s treating having installed a tool as having entered the AI era. The real watershed has always been in task understanding, process design, and result judgment. Do you actually have continuous problems to solve? Can you break problems down and hand them to the system? Can you judge whether results are correct? These determine whether you can truly extract value from AI.
\nSo no need for anxiety. Installing OpenClaw when you have no real use case doesn’t mean much.
\nIf you really want to experience where this generation of AI is strong, better spend $20 on Claude Code, or more interestingly get a ChatGPT subscription, use GPT 5.4 to handle something you truly find difficult - produce a solution, push execution forward, experience this simple, efficient, problem-solving process once. That’s way better than installing OpenClaw.
\nOpenClaw suits people with scenarios, suits commanders, suits solo entrepreneurs, suits those who can SOP-ize, online-ize, and complete processes step by step. It’s certainly powerful, but it proves its power through completing work for you, not through being installed.
\nWhat many people are installing today is OpenClaw. What’s more important to figure out first: What problem do I actually have that’s worth solving with AI?
\nThat question may be more important than installing anything.
\n
![](\"https://gw.alipayobjects.com/zos/k/7t/258.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nCover photo shows my finally installed cyber charging station at home. It looks incredibly cool! I ordered it back in January and it finally got installed today. Tesla’s service remains as professional as ever, and their products are as cool as ever. Staying long on Tesla.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
Kaku, the blazing fast and AI-friendly terminal, just released version 0.5 - go try it out
\nhttps://github.com/tw93/Kaku
![](\"https://cdn.fliggy.com/upic/D4hdW4.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nPortKiller: Cross-platform port management tool with native UI
\nhttps://github.com/productdevbook/port-killer
\nFound a cool tool on GitHub called PortKiller - a cross-platform port management app for developers. It does more than just list ports: it automatically discovers all listening TCP ports, lets you kill processes with one click, supports search and filtering, favorites, port watching with notifications, and smart categorization for common dev services. It also covers real workflows, like managing kubectl port-forward sessions with auto-reconnect, logs, connect/disconnect notifications, and showing active Cloudflare Tunnel connections.
\n![](\"https://gw.alipayobjects.com/zos/k/rm/M8Cabs.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Surge: Blazing fast open-source TUI download manager written in Go
\nhttps://github.com/surge-downloader/surge
\nRecently discovered a cool tool called Surge - a super fast open-source TUI download manager designed for power users, written in Go with a clean keyboard workflow. It doesn’t treat downloads as a single stream - instead it opens multiple connections, splits files into chunks and pulls them in parallel, with automatic failover across multiple mirrors. You can also switch to streaming mode for sequential downloads, which is more convenient for previewing media.
\n![](\"https://gw.alipayobjects.com/zos/k/n8/demo.gif\")
FluentRead: Open-source immersive browser translation extension
\nhttps://chromewebstore.google.com/detail/%E6%B5%81%E7%95%85%E9%98%85%E8%AF%BB/djnlaiohfaaifbibleebjggkghlmcpcj
\nFluentRead is a solid open-source immersive translation extension for browsers. It’s clean with just the right amount of features, plus you can configure your own API key. The translation style and page integration look good too. Give it a try.
\n![](\"https://gw.alipayobjects.com/zos/k/a3/sfhPpB.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
LobsterAI recently improved its Skills capabilities
\nhttps://lobsterai.youdao.com
\nI’ve been using NetEase’s LobsterAI recently. Looking at their changelog, they’ve been optimizing Skills - it now has built-in modules for document processing, frontend design, browser automation, web search, and even finding movie resources. The scenarios are ready to go, and many can be completed with just one sentence.
I tried an interesting combo this time. I’ve been curious about the TV series “Taiping Years” and wanted to brush up on the Five Dynasties and Ten Kingdoms period of history. So I just threw in a prompt: “Organize the timeline and key knowledge points of the Five Dynasties and Ten Kingdoms into a PDF with high information density, and also search for any cloud storage resources for Taiping Years.” It called three Skills - web-search, pdf, and films-search. The PDF was generated directly with a clear timeline and decent formatting; the resource search actually found download links, saving me the time of digging through various sites.
\nSkills save time on building tool chains, writing scripts, and cleaning data. For engineers, it turns what used to require setting up workflows into direct API calls, with deduplication, formatting, and summarization handled together. Combined, you can do more - like monitoring a competitor’s weekly updates, using web-search to fetch them, extracting key changes with playwright, and generating a competitor report, all in one place. If you’re interested, start with your most repetitive high-frequency scenarios. Give LobsterAI’s latest Skills a try.
\n
SuperCmd: Open-source macOS launcher with more features than expected
\nhttps://github.com/SuperCmdLabs/SuperCmd
\nFound SuperCmd on GitHub - an open-source macOS launcher that’s more complete than I expected. It puts Raycast-style extension workflows, voice input, text-to-speech, memory, and AI actions into an open system. Great to see this level of open-source innovation in the macOS launcher space.
\n![](\"https://cdn.fliggy.com/upic/bE3L9n.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Helium: The minimalist browser I switched back to from Edge, with great spatial feel
\nhttps://helium.computer/
\nI recently switched my main browser from Edge back to Helium. I thought I liked vertical tabs, but what I really wanted was a more minimal UI and more workspace. Helium now has vertical tabs too, but the real highlight is compact mode - address bar and tabs on the same line, clean and space-efficient. Paired with my Maple theme and Maple bookmarks extension, the whole setup feels comfortable - focused, no noise.
\n![](\"https://cdn.fliggy.com/upic/eNH71k.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Claude’s new program for open source maintainers: 6 months of Claude Max 20x
\nhttps://claude.com/contact-sales/claude-for-oss
\nClaude just launched a program for open source maintainers offering 6 months of free Claude Max 20x. If you’re a primary maintainer of a public repo with 5K+ stars, or a core member of an NPM package with 1M+ monthly downloads, and you’ve been active in the last 3 months, check it out. If you’ve been consistently contributing to Mole, Pake, MiaoYan, or other major open source projects and meet these criteria, give it a shot.
Taiping Years is sooooo good
\nhttps://movie.douban.com/subject/36317421/
\nGuys, Taiping Years is sooooo good - go watch it. It’s really great, the kind where the first episode already blows you away.
\n![](\"https://cdn.fliggy.com/upic/TO4qMn.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Aerial view of Xixi Wetland
\nWelcome to listen to Li Zhi’s “Castle in the Sky” while watching this aerial view of Xixi Wetland - it looks quite beautiful from above. Should be even more stunning by mid-March.
\n
Rong Xiao Guan is quite fresh!
\nIf you’re shopping at Hangzhou Tower, try this place on the 8th floor of the new Building B. It’s pretty good - light but delicious and fresh.
\n ![](\"https://gw.alipayobjects.com/zos/k/st/qTXqvC.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/l8/VAgHUx.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/ms/RJad2x.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n \n ![](\"https://gw.alipayobjects.com/zos/k/yv/pd45lt.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\") \n | \n
\n
![](\"https://gw.alipayobjects.com/zos/k/sq/257.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo was taken a few days before Chinese New Year when I visited Shaoxing for a few days. It was pretty nice overall - this is a drone photo of Anchang Ancient Town. It was fun, very much like a traditional water town.
\n\n\nThis weekly newsletter documents the practical tech trends I discover each week. After filtering, I publish them here. If you enjoy it, feel free to follow to get update notifications.
\n
Kaku: A fast, out-of-the-box terminal built for AI coding
\nhttps://github.com/tw93/Kaku
\nA New Year’s gift for everyone.
Actually, while developing Pake, I was already thinking about creating a fast, user-friendly Mac terminal tool that I’d love to use. So I started tinkering locally, satisfying my own needs with various customizations. Then when I was developing Mole, this feeling became more intense - why isn’t there a terminal tool that I find truly amazing to use?
\nBefore this, I really liked Alacritty because it’s the lightest and fastest, but it doesn’t support multiple tabs. Then I tried the popular Ghostty and even contributed updates, but the font rendering never quite matched my taste. There’s also Warp, which many people love - I couldn’t understand why a terminal would need login. Kitty is also good, but it has window management bugs that seem hard to fix.
\nThen I discovered Wezterm, but unfortunately its last stable release was two years ago. However, since it’s Rust-based and I know a bit of Rust, I could deeply customize and modify it. So I started my tinkering journey - whenever I had an issue, I fixed it myself, removed a lot of compatibility modules, tweaked its loading, and built in some convenient features. I wanted it to be as fast as the world’s fastest Alacritty, but with multi-tab and split-pane support, so that during AI coding, I could use Claude Code on one side, Codex Review on another, and git diff at the bottom to view code - helping me stay more focused.
\nThen, the day before yesterday, I had dinner with a friend, and he also complained about not having a good terminal these days. I told him to try mine and wait for me to package it - and that’s how Kaku was born. It’s actually a Japanese name, Kaku Kaku Kaku Kaku - you can read it very quickly, and it feels refreshing. My tagline for it is “A fast, out-of-the-box terminal built for AI coding.” I hope it gives you a smooth, fast TUI experience. It’s not quite mature yet, but I’ve been using it for over half a year now. I’m releasing it for everyone to try - consider it a New Year’s gift. Feel free to report bugs. You must try its various keyboard shortcuts. I hope this terminal works out of the box without any configuration needed.
\n![](\"https://gw.alipayobjects.com/zos/k/3k/WLT7GN.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nMiaoYan also got an update
\nhttps://github.com/tw93/MiaoYan
![](\"https://cdn.fliggy.com/upic/5Zr6co.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nLobsterAI: Your 24/7 personal AI agent for any task, now open source
\nhttps://lobsterai.youdao.com
\nI accidentally discovered a great product from NetEase - LobsterAI, your 24/7 personal AI agent for any task. Plus, they officially announced today that it’s now open source.
After installing and setting up the bot in Telegram, I was heading out, so I used my phone to remotely let it read the “Weekly” code repository on my computer - extracting all 2025 content with a clear goal: help me pick the top 20 best recommendations of the year.
\nI thought it might just scan through randomly to compile a list, but it actually read every single article, being very restrained in its selections, like a real editor. The final Top 20 really matched my taste - it even included Mole, Pake, and MiaoYan, the projects I’ve been maintaining, and wrote some encouraging words. It was unexpectedly touching.
\nAfter using it, I roughly understand why it can achieve this level: it has a cross-session persistent memory system that remembers my preferences. The foundation is a local-first design that can actually execute operations on your machine, not just having cloud conversations and calling it done. This naturally avoids issues with latency, privacy, and offline scenarios. Every step is completely transparent to you - it’s not a black box running - you have full control at all times, making it quite suitable for organization-based automation.
\nIts capabilities aren’t just reading and writing - making PPTs, scheduled tasks, searching, calling local tools… all built in. In settings, you can also connect Feishu, DingTalk, Telegram, Discord, or use email - all out of the box.
\nThe video records the entire process from configuration to generating the Top 20. Check it out if you’re interested. It’s already open source, so everyone can definitely play with it and hand over all those repetitive, boring tasks to it. I’m really looking forward to this little lobster getting better and better.
\n
OpenTrace: Visual route tracing tool, cross-platform native GUI
\nhttps://opentrace.app
\nRecently discovered a cool tool called OpenTrace - an open-source visual route tracing tool. The fun part is that after you enter an IP or domain, you can see step by step how traffic flows between different nodes.
\n![](\"https://cdn.tw93.fun/uPic/jNUjyr.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Claude Code’s /plugin: Go to Marketplaces and pick plugins
\nIf you use Claude Code, be sure to try the /plugin function, then go to Marketplaces and wildly pick plugins that suit you.
\n![](\"https://gw.alipayobjects.com/zos/k/d4/7ojonZ.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
FineTune: The volume mixer macOS should have
\nBasically the volume mixer that macOS should have come with - truly independent volume control per application, with separate sliders and mute for each app.
\n![](\"https://gw.alipayobjects.com/zos/k/8j/bl1wHy.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Snitch: A better-looking network connection viewer
\nhttps://github.com/karol-broda/snitch
\nI found a pretty interesting little tool called Snitch that makes viewing network connections more beautiful and “human-friendly” - you can think of it as an ss or netstat for humans.
\n![](\"https://github.com/karol-broda/snitch/raw/master/demo/demo.gif\")
Beautiful Mermaid: Beautiful Mermaid renderer designed for the AI era
\nhttps://github.com/lukilabs/beautiful-mermaid
\nRecently saw a very beautiful Mermaid renderer - clean and comfortable, designed specifically for the AI era, from the Craft team.
\n![](\"https://gw.alipayobjects.com/zos/k/ct/oADkqY.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Showing off my cooking skills for the New Year’s Eve dinner, wishing everyone a Happy New Year!
\n
Aerial footage of Anchang Ancient Town
\nHahaha, no crash, no crash, no crash! Filmed a water town, exactly how I imagined a Jiangnan water town ancient town should look. Paired with Zhi Li’s “The End” - a perfect match.
\n
Apple Developer account finally approved
\nGreat news!!! My Apple Developer account is finally approved - can’t wait to make something new in 2026! I’ve been applying for 3 years, and for some reason kept getting “Contact us to continue the process, there may be an issue with your account.” Even the support specialist couldn’t solve it. Finally, I learned a trick from Xiaohongshu - just write to Tim Cook. It really works, super fast! Someone contacted me the next day to submit materials, and today it got approved!
\n![](\"https://gw.alipayobjects.com/zos/k/2d/1nCAfm.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\n
![](\"https://cdn.fliggy.com/upic/MkXV0F.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nCover photo taken near Ueno Park in Tokyo, with a plane flying across the sky. The combination of blue sky and trees creates a beautiful scene.
\n\n\nRecording down-to-earth trending tech I see every week, filtered and published here. Follow this weekly newsletter to get update notifications
\n
When Bitcoin Falls, I Reconsidered the Cathedral and the Casino
\nhttps://tw93.fun/en/2026-02-01/money.html
\nRecently, Bitcoin dropped from its high of 120k to just over 70k, and market sentiment turned fearful again. Whenever the market falls, I find it easier to think about what’s more like a casino and what’s still building a cathedral. At the 2024 Berkshire Hathaway shareholder meeting, Warren Buffett used “the cathedral and the casino” to describe capitalism, and this metaphor is especially useful at times like these. Violent price fluctuations mostly come from the casino side, while what truly determines long-term returns often requires years or even decades of sustained investment.
\n![](\"https://cdn.fliggy.com/upic/7dSRph.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
My Minimalist Living Experience
\nhttps://tw93.fun/en/2024-03-03/simple.html
\nI’d like to casually chat about minimalism. I really enjoy this lifestyle, but that doesn’t mean everyone needs to be minimalist. Some people enjoy collecting, some like shopping and buying lots of things—any lifestyle that makes you comfortable is fine. But if you also enjoy a simple lifestyle, or if you have a bit of OCD, these small suggestions might suit you.
\n![](\"https://cdn.fliggy.com/upic/HJUHKu.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
My GitHub Repositories Have Surpassed 100K Stars
\nhttps://github.com/tw93
\nFrom starting to learn frontend development in college in 2014, to gradually open-sourcing some of my tools in recent years, I’ve made many friends and I’m very happy. Recording this milestone.
\n![](\"https://cdn.fliggy.com/upic/Kgk2Pa.jpeg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Mole Recently Updated to Version 1.24
\nhttps://github.com/tw93/Mole
\nThis version is named Razor 🪒, an interesting name. Updates include the following, feel free to try it out:
![](\"https://cdn.fliggy.com/upic/qc29gI.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Codia AI NoteSlide Converts NotebookLM-Exported PDFs Directly to PPT
\nhttp://codia.ai/noteslide?r=tw
\nI’ve really enjoyed using NotebookLM recently to help learn and understand new things, but it can only export PDFs, and sometimes the Chinese rendering isn’t great. I’ve been looking for a good tool that can convert PDFs to editable PPTs, and after searching around, I found Codia AI NoteSlide works best. Compared to traditional pdf2ppt tools, it’s much simpler and easier to use, quickly converts to editable content, and the results are beautiful, refined, and error-free. Very useful—if you have the same pain point, give it a try.
\n
Apple Battery Protection Tool - Battery
\nhttps://github.com/actuallymentor/battery
\nThis tool keeps your MacBook that’s always connected to power at 80% charge, which supposedly extends battery lifespan. However, I mostly use it plugged in and don’t pay too much attention to this, but those who need it can give it a try.
\n![](\"https://cdn.fliggy.com/upic/o3DuLT.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Visual Status Alerting Tool for Developers
\nhttps://github.com/TwiN/gatus
\nGatus is a health dashboard for developers. You can monitor your services using HTTP, ICMP, TCP, and DNS queries, evaluate query results through a series of conditions (such as status codes, response times, certificate expiration, body content, etc.), and health checks can be integrated with various alert systems like Slack, Teams, PagerDuty, Discord, Twilio, and more.
\n![](\"https://cdn.fliggy.com/upic/bGGSac.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Global AI Industry Traffic Tracking Report
\nhttps://similarweb.com/corp/wp-content/uploads/2026/01/attachment-Global-AI-Tracker-6.pdf
\nSimilarweb recently released the Global AI Industry Traffic Tracking Report, “AI Global Sector Trends on Generative AI,” which is well worth reading. It analyzes the traffic situation of major product categories in the current AI space, showing who’s growing and who’s declining.
\n![](\"https://cdn.fliggy.com/upic/TWjiB9.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Saw this on Xiaohongshu—this stir-fried pork with chili peppers is delicious. I had something similar when I was young, give it a try
\n
My 2026 Reading List
\nI recently started selecting books for 2026 and picked these 5. Do you have any recommendations for the best books you’ve read this year? Feel free to recommend them with a brief explanation:
How to Organize a New Year’s Eve Team Building Activity That Young Engineers Love
\n\n
![](\"https://cdn.fliggy.com/upic/gBsSrT.jpg?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\nThe cover photo was taken of grilled chicken wings we had over the weekend. The plating looked great, and they tasted good with a bit of chopped parsley.
\n\n\nRecord the down-to-earth trending technologies seen every week, and publish them here after screening. If you find it good, you can subscribe to this weekly to get update notifications.
\n
243 Engineers: Best Things Bought in the Past Year
\nhttps://tw93.fun/2026-01-24/good.html
\nLast week, while buying Lunar New Year dinner gifts for the team, I casually asked on X: In the past year, what is the thing you were most satisfied with? Or if you had to recommend one item, what would it be? It could be gadgets, software, or daily-use items.
\nI did not expect 243 replies. It felt lively and real, and I really like this kind of exchange. The comments were buzzing. After reading through a few times, I found many great items. The recommendations ranged from must-haves to very down-to-earth everyday goods.
\n![](\"https://cdn.fliggy.com/upic/3qikGN.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Pake Updated to Version 3.8.1
\nhttps://github.com/tw93/Pake
\nPake, the tool that packages web pages into lightweight desktop apps for macOS, Windows, and Linux, has been updated. Changelog highlights:
--new-window parameter to support OAuth/SSO flows that need a new window, wired through CLI -> config -> Tauri window.deb and appimage.![](\"https://cdn.fliggy.com/upic/cTQpkH.gif\")
\nMemOS: Long-Term Memory for Agents and LLMs
\nhttps://github.com/MemTensor/MemOS
\nWhile looking at long-term memory solutions for Agents and LLMs, I found an interesting project: MemOS. It is not about stuffing a bigger context window or improving retrieval, but about a more fundamental problem: how memory itself should be managed.
\nWhen building AI agents or multi-turn chat, models often forget context. User preferences, operation records, and uploaded documents seem to evaporate. MemOS addresses this with a core “shared memory layer,” and lets the same memory be reused across projects and agents.
\nIt supports connecting files and URLs directly into a knowledge base. During conversations, memories are continuously updated and gradually form preference memories as they grow. It can unify text, images, files, and tool calls under one management layer, and you can even use natural language to correct or clean existing memory when needed. If you are interested, go check out the project.
\n![](\"https://cdn.fliggy.com/upic/aA2Xts.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
Toad: A Unified AI Interface in the Terminal
\nhttps://github.com/batrachianai/toad
\nThis unified AI interface in the terminal, Toad, is pretty good. With the ACP protocol, it is worth checking out and giving it a try.
\n
An Immersive 3D/2D Web Visualization Project
\nhttps://seanwong17.github.io/Mammalia-tree/
\nAn immersive 3D/2D web visualization project that explores the 200-million-year epic evolution of mammals. The interactions are excellent and great for anyone who likes “archaeology”.
\n![](\"https://cdn.fliggy.com/upic/q9gsB8.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
A Good-Looking Terminal Pomodoro: pomo
\nhttps://github.com/Bahaaio/pomo
\nBuilt with Bubble Tea, and it looks great.
\n![](\"https://cdn.fliggy.com/upic/YIXgMy.gif\")
Watching Alex Honnold Climb Taipei 101 on Netflix Live
\nhttps://www.bilibili.com/video/BV1nYzDB3EKx
\nOn Sunday morning, I watched Alex Honnold climb Taipei 101, a landmark in Taiwan, on a Netflix live stream. He free-soloed the whole way without ropes or safety gear; one mistake would have been fatal. He finished in about an hour and a half. I am really impressed, and he stayed remarkably calm throughout. It is worth watching. If you do not have Netflix, you can probably find it on Bilibili too. It has been a long time since I have seen something like this.
\n
Investment Directions I Will Watch in 2026, Not Advice, Just for Reference
\n![](\"https://cdn.fliggy.com/upic/wYrANO.png?x-oss-process=image/auto-orient,1/resize,w_2000/format,webp\")
\n