I'm not a coder. English isn't my first language. But I'm building a real portfolio of niche websites — and publishing every step, every mistake, and every number along the way.
A bilingual food destination guide covering regional Chinese cuisine.
Visit site →JSON formatter, Base64, word counter, color converter — free dev tools.
Visit site →Previous attempt. 24 articles on future trends. Low traffic, no revenue — pivoted.
Self-built AI music tool. Hundreds of yuan, countless nights. Output wasn't good enough. Zero revenue.
Classical poetry turned into lyrics. Months of updates. Traffic dropped instead of growing. Zero income.
Currently researching. The full process will be documented.
Coming soonEvery post is part of a series. Read in order, or jump in anywhere. New content drops each month.
2010年，遂宁一家医院上班，头脑一热投了两千多只鸡。不懂技术、没时间管、最后几乎死光。十几年前那场失败的养鸡经历，教会了我最重要的一件事。
Build Diary Read full post →郫县上班，锦江住家。单程40公里，三环路上哪个坑我都知道。每月油费一千多，扛不住。开始跑顺风车，不图赚钱，就想把油钱平了。两个月挣了一千多，刚好够。后来平台没了，日子也变了。
Build Diary Read full post →我偏爱宋词古韵，想着把填词做成原创歌曲当副业。坚持更新一两个月，流量不涨反跌。自费几百块、熬了半个月自己搭AI音乐工具，成品差距依然明显。一分钱没赚到，但热爱还在。
Build Diary Read full post →完整记录：35岁ICU医生，抖音失败，写歌失败，网约车想过去，外卖真送了4单。这个时代，一个普通人到底该怎么给自己多挣一份安全感？
Build Diary Read full post →The origin story. Zero coding experience, a day job, and a decision to build an English website portfolio.
Build Diary Read full post →My complete AI workflow — from idea to deployment. The exact prompts, tools, and processes.
Build Diary Read full post →Traffic data from all live sites. Real numbers, not screenshots from someone else's dashboard.
Numbers Read full post →I don't sell courses. I don't sell templates. I just build and publish the results.
Build Diary · May 2026 · 9 min read
The full backstory. Douyin videos? Failed. Songwriting? Failed. Ride-hailing? Tried it. Food delivery? Did a few runs, too exhausted. This is the road that led me to building websites with AI.
Read full post →May 2026 · 6 min read
Every time I see someone talk about side hustles and entrepreneurship, I think back to 2010.
I was working at a hospital in Suining. Stable job. Decent pay. But I was young — mid-20s — and I felt like I should be doing more. Building something. Making real money.
A friend mentioned that some local farmers were raising chickens. Low barrier to entry. High demand. It sounded easy. I didn't think twice.
I rented land. Bought 2,000 chicks. All in, from day one.
Here's what I didn't think about: I was still working full-time at the hospital. Shifts were long, exhausting, and unpredictable. The chicken farm needed daily feeding, vaccination, cleaning, monitoring. Who was going to do all that?
Me. Only me.
I spent my days at the hospital and my nights at the chicken farm. Feed the chicks. Clean the coops. Check for sick birds. Rush home, sleep a few hours, repeat.
I thought hard work would be enough. It wasn't. I didn't know the first thing about chicken farming — disease prevention, feeding cycles, temperature control. I was learning on the job, and the job was brutal.
The chickens started dying. First a few, then dozens, then hundreds. I panicked. I tried everything — called other farmers, searched for solutions, worked even harder. But I was fighting blind. I didn't have the knowledge, and I didn't have enough hours in the day.
Almost all 2,000 chickens died. The money I put in — upfront costs, feed, equipment — gone.
Months of effort. Zero return. Negative profit.
I sat there looking at the empty coops, and I felt something I'd never felt before: the specific kind of exhaustion that comes from failing at something you poured everything into.
That experience taught me something I've never forgotten: a side hustle is not a shortcut.
I jumped in with enthusiasm and nothing else. No expertise. No time buffer. No backup plan. Failure wasn't just possible — it was inevitable.
Fifteen years later, that lesson still shapes every decision I make about side income. Before I start something now, I ask myself three questions:
I'm 40 now. Still working a salaried job. Still carrying the weight of family responsibilities. And sometimes, late at night, the same questions creep in: Is this all there is? What happens if something goes wrong with my job?
I don't have the answers. The chicken farm taught me that jumping blindly doesn't work. But doing nothing doesn't feel right either.
So I keep looking. Keep trying. Keep writing about it.
That's the only thing I know for sure.
— Kuang Shan, still figuring it out at 40
2026年5月 · 阅读约6分钟
想做副业，想创业，总觉得上班拿死工资太局限。每次看到这类话题，我都会想起十几年前那场失败的养鸡经历。
那是2010年，我在遂宁一家医院上班。工作稳定，但心里总想着趁年轻拼一把。偶然了解到周边农户养鸡，觉得门槛不高，市场需求大，脑子一热就干了。租地、进鸡苗，一口气投了2000多只。
那时候完全没想清楚。一边是医院的工作，每天忙得脚不沾地，一边是养鸡，喂食、防疫、清理鸡舍，全靠自己。白天上班，下班直奔养鸡场，忙到深夜才回家，几乎没有休息时间。
我以为够努力就行。但现实很快就打了我的脸。我根本不懂养鸡技术，不懂防疫，精力也不够用。鸡开始生病、死亡，越来越多。我慌了，想各种办法补救，但不懂技术，手忙脚乱，最后2000多只鸡几乎死光，前期投入的钱全赔了。那段时间，我满心挫败。折腾了几个月，业余时间全搭进去了，钱没赚到，反而赔了不少。
这件事让我明白了一个道理：副业从来不是捷径。当时我凭着一股热情盲目入局，没有专业能力，精力也顾不过来，失败是必然的。
但说实话，十几年过去了，我现在依然会焦虑。40岁了，上班拿固定工资，上有老下有小。想改变，不知道从哪下手。想做点副业，又不知道做什么。有时候半夜睡不着，脑子里全是这些问题：我这辈子就这样了吗？万一工作出了问题怎么办？
我也不知道答案。那场养鸡的经历让我明白，盲目冲动不行。但不折腾，心里又不踏实。写这些，就是想说说自己的真实经历。
—— 况山，还在想这些问题的中年人
May 2026 · 8 min read
I used to work at a hospital in Pi County and live in Jinjiang, Chengdu. Forty kilometers apart. Every single day, there and back.
I knew every pothole on the 3rd Ring Road. I could tell you which lane moved fastest at 7:15 AM. If I left home past 7, I was guaranteed to hit rush hour. A one-way trip could stretch to 90 minutes. Leave before sunrise, come back after dark.
The driving alone was exhausting. But the real pain was the gas money.
80 kilometers a day. Five days a week. Fill up every 5 days. Monthly gas bill: over 1,000 yuan.
For a regular salary worker, that's a lot. My car was like a hungry mouth — the gas gauge dropped and I could feel my wallet shrinking with it. I started thinking: what if I could at least break even on fuel?
That's when a colleague mentioned ride-hailing. Not the full-time kind — just carpooling. Pick up passengers heading the same direction. Don't detour. Don't be late for work. Just cover the gas.
My first ride was from Xipu to a neighborhood next to mine. I wasn't greedy — I only accepted rides that were on my route. No extra stops, no wasted time. My day job came first. This was pure gas subsidy.
Morning: pick up one passenger heading toward Pi County. Evening: pick up another heading back to Jinjiang. The most common drop-off was Chengdu East Railway Station. Sometimes we chatted. Mostly we sat in silence. I just wanted to finish the ride and earn the fare.
I kept it up for about two months. On and off. At the end, I added it up: about 1,000 yuan total.
Not a lot. But it covered exactly two months of commuting gas. Every single yuan.
I wouldn't call it happiness. But there was a quiet satisfaction in it. A small win. A tiny side hustle that actually worked.
Then the platform shut down. Don't know why, don't really care. Gas prices went up. Life moved on. I never did it again.
But sometimes I think back to those days and feel oddly nostalgic. Simple. Honest. A small hope to hold onto.
Years passed. Now I'm 40. I think about home more. I think about money more. I think about what I still haven't figured out.
I spent my whole life in medicine. Over a decade in critical care. I love the work — pulling patients back from the edge, keeping the Grim Reaper at bay. Just recently we did CPR for over an hour and saved someone. That feeling is real.
But outside the hospital, I'm lost. I don't know how to talk to people. I have no friends outside work (except my fishing group). I can't write. I have no skills other than doctoring.
I tried learning Python. I built a NeuroICU AI tool based on decades of clinical experience. I thought it could help colleagues. I thought it could even make some money. Then I found out — as an individual without a company license, I can't legally put a medical tool online. It just runs on my computer, silently.
I sometimes regret studying medicine. If I'd learned AI or coding instead, maybe things would be different. But regret doesn't pay the bills.
I'm still learning. Still experimenting. Still looking for the right path. I take advice from AI assistants now — Doubao teaches me about stocks and funds. I built a stock analysis tool. It's not great, but it's smarter than me.
Life is hard. But I haven't stopped. I don't plan to.
Somewhere out there, there's a side hustle that fits. A way to use what I know, build something real, and earn a little extra. I just haven't found it yet.
But I'm still looking. That's got to count for something.
— Kuang Shan, 40 years old, still looking for the right road
2026年5月 · 阅读约8分钟
早些年在郫县医院上班，家住在锦江区，那日子现在想起来，都觉得是真奔波。每天来回足足四十多公里，三环路那里有个坑我都知道，早上六点多就得从家里出发，稍微起晚一点，只要你过了7点上三环，大概率就会被堵路上，遇上早高峰堵车，单程都要开一个半小时，天不亮就摸黑出门，下午5点半下班如果运气不好再堵在路上，到家不是晚上7点都不行，光开车就累得天昏地暗的。
最头疼的还是油费，那时候油价比现在是便宜，但是每天80多公里，每个月上下班光加油，就得花掉一千多块，对于普通上班族来说，也遭不住啊，这么一来，手里更是慌得很。基本上5天加一回油，车呢也不争气，油表往下掉，车天天喊饿，我也是醉了，心里就慌，总想着能不能想个办法，把这笔油钱省下来，哪怕不赚钱，能把油钱补上也行。
哎钱包累，我也累，那个时候不是有顺风车嘛，后来跟同事聊天，就开始做。万事开头难嘛，记得第一个单就是犀浦到我们隔壁小区的，那时候也不贪心，就想找同路的乘客，绝不绕路、绝不耽误上班时间，毕竟本职工作才是主业，顺风车就是纯纯补贴油钱的副业。
从那以后，每天出门前我都先打开软件看一眼，有顺路的就接上，没有就自己正常走。早上接一单去郫县的，下班再接一单回锦江区的，其实最多单的就是到成都东站的。有时候遇上聊得来的，简单说几句，大部分时候都是安安静静赶路，就想踏踏实实把这单跑完，把油钱挣到手。
就这么坚持跑了一两个多月，断断续续的跑了两个月。后来仔细算了算，前前后后一共挣了一千多块，不多，但刚好完完全全覆盖了那两个月上下班的油费，还是比较划算的。
那时候开心谈不上，心里只是有点满足。可世事就是这么难料，好好的顺风车，跑得正顺手的时候，突然就出问题了。不知道是平台倒闭了，还是什么原因，后面随着油费上涨等等一些其他原因也就没有弄这个所谓的副业了。偶尔想起那时候跑顺风车的日子，还觉得挺怀念的，简单又踏实，心里有个小盼头。
一晃又是几年过去了，人到40岁，就想家，想安静，想挣钱，其他的什么都不想再想了。以前嘛想到40岁了应该著书立说了，随着社会科技互联网的发展，发现自己被社会差点遗弃了——差点哈，没有完全被遗弃。想的是总得找钱啊。
我这辈子就开始学医了，干了十多年的医生，一直扎根在重症医学领域。其实我很喜欢这个专业，有成就感，病情非常重的患者随时可能死亡的，我就不让牛头马面轻易的带走。最近就有一个我们坚持心肺复苏1个多小时成功了的，确实有成就感。扯远了，这辈子就知道和病人及病人家属打交道，看病、查房、写病历，所有的精力、所有的事，就是这些事。说句实在话，除了看病，我真的什么都不会，什么都做不了。说话都不会，情商超级低，就连写点东西也是狗屁不通。话说有人就有江河湖泊——江湖，但是我说话直来直去喜欢讲实话，领导不喜欢，朋友也少，不是基本没有朋友，我的微信除了工作群基本没有其他事，哦还有钓鱼佬群，我也就没有江湖了。
现在确实想做个副业，原因简单啊，穷啊。继续坑老也不现实啊，哈哈原因大家都懂。找个体力活当副业，没那个力气，年轻的时候都没干过重活，现在中年了，身子骨也不如从前，别说去工地搬砖、扛水泥，就算是干点轻体力活，都吃不消。想做点小生意，没经验、没本钱，也不敢贸然投资，怕赔了本，连家底都保不住。想找个轻松的副业，又没有别的手艺，没有一技之长，根本无从下手。
其实现在想想当年挺后悔学医，如果学个AI的行当多好啊，做IT、写代码、开发程序，趁着科技发展，赚得盆满钵满。随便接点活、做个程序，都比现在强，心里就忍不住后悔。
事情像这个样子，后悔也没用。当年学医也是我妈帮我选的，其实当年的出发点就是学个手艺，可以回老家镇上开个小诊所。回想起来也对，日子还得往前过，我也从来没想着躺平。我也一直在学、一直在折腾、一直在找方向，从来没有停下努力的脚步，可惜没有方向。
最近开始学Python代码，抖音是个不错的学习平台哈，还对着电脑一点点看教程、写代码。后来又接触到一些程序部署，自己一点点摸索搭建环境、调试程序，有点难，但是学会了一部分。干了一辈子重症医学，我心里清楚，一线临床医生有多辛苦，也知道大家在诊疗过程中需要什么样的辅助工具。凭着自己几十年的临床经验，我利用所有业余时间，一点点整理临床数据、诊疗指南、用药经验，硬生生做出了一个重症医学AI辅助工具。我满心想着，这个工具要是能上线使用，能帮到很多同行，能提高效率，也能让自己的努力有个结果，还能多一份收入。
可现实却给我泼了一盆冷水。自己做一个医学工具放网上是不行的——豆包说的。我只是一个普通的个人，没有正规的公司资质，需要医疗备案权限，根本没有资格把这个工具放到网上运营，都只能在自己的电脑里默默的跑。
最近和豆包关系比较好，她就是我生活的老师，我基本上很多事就问她。现在不是学习买基金股票吗，豆包手把手教的我哈，莫笑这是真的。最近在豆夫人的指导下搭建了一个AI股票工具，谈不上好用但是比我脑子灵光。
我还是在不停学习，不停摸索，不停寻找新的方向。依然想写更多东西，想把自己的临床经验分享出去，想把自己做的辅助工具完善好，想找到合适的办法，让它能派上用场。
人到中年，谁都有无奈，谁都有力不从心的时候，有遗憾，有迷茫，有处处碰壁的失落。莫停下往前闯的脚步。
日子不是难是自己难，生活苦不是苦自己，莫让苦横行霸道。但只要一直不放弃，一直努力折腾，找对方向——哈哈哈，我始终相信，总有一天，能找到属于自己的副业路，都有一个值得的结果。
—— 况山，还在往前闯
May 2026 · 6 min read
I've always loved Song Ci poetry. The rhythm, the imagery, the way a few characters can paint a whole world. It was never about money — just a quiet passion I carried with me.
Then one day on Douyin, I saw ordinary people making money from songwriting. Turning words into music. Doing something they love and getting paid for it. It hit me: I have years of poetry practice. Why not try turning classical lyrics into songs?
I committed. Day after day, I wrote lyrics, revised them, polished them. I started a Douyin account and posted consistently. I thought: if I keep working at it, the audience will come.
They didn't. After a month or two of regular posting, my views were going down, not up. Fewer likes. Less engagement. The algorithm had decided I wasn't worth showing. I was putting real effort into every piece, and fewer people were seeing it than when I started.
That hollow feeling — when you work hard on something and it just... disappears into the noise — that's a special kind of defeat.
I didn't give up. Instead, I thought: I need to differentiate. If everyone is just posting covers, maybe I can build my own AI music generation tool. Something unique. Something that makes my content stand out.
I spent hundreds of yuan of my own money. Two full weeks of every spare moment — learning, tinkering, debugging. I stayed up late figuring out how to make it work. Problem after problem, I slowly chipped away until I had a working AI music generator.
The moment the first fully AI-generated song came out... I felt hollow. The quality gap between what I'd built and professional music was huge. The texture, the completeness, the production value — none of it was there.
Money spent: hundreds of yuan. Time invested: countless nights. Passion poured in: everything I had. Money earned: zero.
Another failure. Douyin gave me no traffic. The algorithm didn't care about my Song Ci poetry or my AI music tool. Passion, it turns out, doesn't beat reality.
But here's the thing I've learned from all these failures: nothing is wasted.
I still love Song Ci. That didn't change. I learned how to build an AI tool from scratch — that skill didn't disappear just because this project failed. The persistence I built during those late nights? Still with me.
Slow is fine. Zero results now is fine. The ordinary person's persistence will eventually find its echo.
This was just one small chapter of my entrepreneurial journey. There will be more.
— Kuang Shan, still keeping the poetry alive
2026年5月 · 阅读约6分钟
我一直很喜欢宋词，偏爱古韵文字里的温柔与风骨，原本只是单纯的热爱，从没想过要靠它谋生。
前段时间刷抖音，看到很多普通人靠写歌创作变现，把文字变成作品，既能做喜欢的事，又能有收入。我瞬间动了心，想着自己有宋词积累，何不试着把古韵填词做成原创歌曲，当作一份副业、甚至小事业去深耕。
下定决心后，我全身心扑进了这件事里。日复一日填词、改词、打磨作品，认认真真更新账号，满心期待能慢慢做起来。可现实狠狠泼了我一盆冷水。坚持更新一两个月，流量不涨反跌，点赞越来越少，热度一点点流失。明明作品用心打磨了，却越来越少人看见，那种无力感，真的让人特别挫败。
不甘心止步于填词发作品，我想着突破自己、做出差异化。于是我自掏腰包，花了几百块，整整耗了半个月的空闲时间，一点点摸索、搭建专属的AI音乐生成工具。那段时间熬夜琢磨、反复调试，遇到问题就慢慢攻克，好不容易把工具打磨成型，能够独立生成歌曲。
可真正成品出来的那一刻，我又陷入了失落。对比市面上成熟的音乐作品，自己做出来的成品差距依旧明显，质感、完整度都远远不够。
从头到尾折腾这么久，投入了金钱、大量时间和全部热情，熬了无数个夜晚，最后一分钱收益都没有。满心的创业憧憬，最后还是失败了。抖音根本没有流量。
原来热爱真的抵不过现实，看似简单的写歌创业，背后藏着无数普通人摸不到的门槛。这段时间的坚持没有结果，难免会迷茫、会沮丧。
但我始终觉得，所有付出都不算白费。我守住了对宋词、对文字的热爱，也靠自己摸索出了全新的技能。慢一点没关系，暂时没结果也没关系，慢慢来，平凡人的坚持，终会有回响。这只是我创业的很小一部分。
—— 况山，还在写词
May 2026 · 9 min read
People see these 6 websites and think: "Wow, you just sat down and built them."
No. Before the websites, there was a long, messy, embarrassing list of failures. I'm going to share all of them. Not to be dramatic — but because this is the part nobody talks about. Everyone shows you the finished product. Nobody shows you the roads that led to dead ends.
Here's mine.
I'm an ICU doctor in Chengdu. It's stable. It's respected. And the pay is... let's say "enough to live, not enough to thrive." In China, the reality for most hospital doctors is long hours, high pressure, and a salary that doesn't match the responsibility.
Midlife hits you hard. You look around and realize: parents are getting older, kids need education, the mortgage isn't going anywhere. Your salary covers the basics, but there's no margin. One emergency and you're in trouble.
I needed something else. Something on the side. But here's the thing — I couldn't do anything medical. No consulting, no tutoring, no side gigs related to my profession. That's the rule. So what could I do?
I tried making short videos. Medical popular science content — explaining common health myths, basic ICU knowledge, that kind of thing. I spent evenings writing scripts, recording, editing. The first few videos got maybe 200 views. The algorithm didn't care. I posted consistently for 2 months. Still 200 views.
I learned that Douyin is a game of either luck or money. You either get lucky with the algorithm, or you spend money on promotion. I had neither. I quit.
This one I actually enjoyed. I wrote some lyrics, tried to compose, even recorded a rough demo. The songs weren't bad — but turning songwriting into income? That's a different game. You need connections, an audience, a platform. I had none of those.
I still write lyrics sometimes. But as a side income? Dead end.
I thought about it seriously. Signed up, downloaded the app, looked at the numbers. But after a 12-hour ICU shift, the last thing you want to do is get behind the wheel and drive strangers around for 4 more hours. I never actually started.
This one I actually tried. I did a few deliveries after work. The first order, I got lost. The second, the customer complained it was late. The third, I nearly hit a car at an intersection. By the fourth, I was exhausted — physically, mentally, spiritually. My body was done.
I lasted maybe 4 deliveries. Total earnings: about ¥40. I deleted the app and never looked back.
Sitting there, after all these failures, I thought: there has to be something I can do from home, at a computer, without burning out my body.
That's when a colleague mentioned "English niche websites." At first, I thought it sounded like another scam. But I was desperate enough to research it. And what I found was... different. Real people, showing real numbers. Not selling courses, just sharing results.
I'm not going to pretend I knew what I was doing. But I had tried everything else. What did I have to lose?
Looking back, every failure taught me something. Douyin taught me that content creation is a long game, not a sprint. Songwriting taught me that I need structure, not just creativity. Ride-hailing and delivery taught me that trading time for money is a dead-end — I needed something scalable.
The websites are my last shot before giving up on the side-income idea entirely. If this doesn't work in 6 months, I'll figure something else out. But at least this time, I feel like I'm building something. Not running. Not chasing. Building.
— Kuang Shan, still trying
2026年5月 · 阅读约10分钟
这是我的公众号第一篇文章。我没什么高大上的定位，就是想认认真真记录一件事——在这个越来越卷的时代，一个普通人，到底该怎么给自己多挣一份安全感。
我就是那个最普通的中年人。有本职工作，有日常开销，有还不完的房贷，有渐渐老去的父母，有正在长大的孩子。以前总觉得，把班上好，安安稳稳过日子就行。可这几年，越来越多的人开始说同一句话："只靠一份死工资，真的扛不住了。"
不是我爱焦虑，是这个时代把焦虑塞进了每个人手里。物价在涨，工资没动。行业在变，岗位在缩。今天还觉得安稳的工作，明天可能就收到一封"感谢付出"的通知。打开手机，到处都是"35岁被优化""45岁没人要"的消息。你明明还没老，世界已经觉得你没用了。自己都感觉自己没用。
想多存点钱，想家里有事时不慌张，想让孩子多上一门课、父母体检不用心疼钱……可每个月工资刚到账，还完房贷、交完补习费、买完菜，就所剩无几了。于是，一个念头越来越清晰：我必须得做一份副业。可紧接着，另一个更让人心慌的问题冒了出来——我到底能做什么？
想做副业的人那么多，最痛苦的根本不是"做不做"，而是不知道"做什么"。嘴上不说，心里都急。其实焦虑得一样一样的：
想做点小生意——一看房租、囤货、转让费，再看看银行卡余额，连试的勇气都没有。
想跑外卖、做代驾——白天上班已经累得腰酸背痛，晚上再熬身体，怕赚的钱还不够以后看病。
想做抖音、电商、搞直播——看别人带货风生水起，自己一进去才发现，一篇作品十几个人点赞，自己都没兴趣更新了。直播不仅自己不敢看镜头，那些00后早就玩剩下了。
想学门技能接单——白天上班，晚上陪孩子，好不容易挤出点时间学了两节课，就开始焦虑：不知道要学多久才能变现，等不起。
也跟风做过几个"日入几百"的小项目——进去才发现，不是拉人头就是割韭菜，折腾半天，白忙一场。
越看越乱，越想越慌。不是怕吃苦，是怕吃了苦还在原地打转。不是不努力，是找不到一条值得努力的路。这种"明明很想改变，却不知道往哪走"的无力感，才是深夜翻来覆去睡不着时，最真实的焦虑。
折腾了一圈，我也慢慢想清楚了。中年人最大的现实，就是试错成本太高了。踩一个坑，可能就是几个月的积蓄；走错一步，可能连主业的精力都被拖垮。所以我给自己定了四条很实在的标准：
1. 绝对不能影响主业——饭碗没了，副业也撑不住。
2. 低风险，不盲目投钱——不赌运气，不碰"暴富神话"。稳，比快重要。
3. 不用拼体力、熬身体——中年人最值钱的是精力，不是蛮力。
4. 最好能越做越顺，有积累——不是今天干了今天有，明天不干就归零。
符合这些条件的方向，才值得我慢慢花时间去探索、去深耕。哪怕慢一点，只要方向对，我就不慌。
开这个号，就是想把这段"找方向、做副业"的过程，完整记录下来。不灌鸡汤，不画大饼，不割韭菜，也不忽悠谁。
我自己就是那个正在迷茫、正在试错、正在一步一步往前蹭的普通人。我只想老老实实写我自己的真实经历：
为什么我一定要做副业——那些让我突然惊醒的瞬间；
我试过哪些副业，踩过哪些坑——真金白银换来的教训；
普通人怎么从迷茫里，一步步找到适合自己的路——没有奇迹，只有笨办法和坚持；
未来我会怎么探索、怎么调整——哪怕最后没做成，至少我试过。
没有一夜暴富，没有轻松躺赚。只有一个普通人最真实的挣扎、犹豫、踩坑，和一点点向前走的痕迹。
写到最后——
如果你也和我一样——每个月工资一到账就没了，想改变却不知道从哪下手；看到别人做副业赚钱，心里痒痒的，自己一尝试就碰壁；白天被工作和生活推着走，晚上躺下来却焦虑得睡不着——
我想对你说一句真心话：
你不是一个人。这个时代，有太多人和你站在同样的十字路口，茫然四顾。但我也想告诉你另一句话：
只要还在找方向，你就没有停在原地。
哪怕今天只比昨天多走一小步，也比什么都不做强。
欢迎关注，我们一起慢慢找方向，慢慢往前走。
不一定能暴富，但至少——我们不再是一个人焦虑。
—— 况山，一个还在找路的中年人
May 2026 · 8 min read
I'm an ICU doctor in Chengdu, China. I save lives during the day. At night, I sit in front of my computer and build English-language websites with AI.
I don't know how to code. English is my second language. I have zero experience in web development, SEO, or marketing. Every single line of code on this site was written by an AI assistant — I just told it what I wanted and kept iterating.
This is the story of why I started, how I'm doing it, and what happens next.
It started in February 2026. A colleague mentioned that some people were making money from "English niche websites" — small sites targeting very specific topics, optimized for Google search, monetized with ads. The idea sounded absurd at first. I'm an ICU doctor in Sichuan. Why would I build English websites?
But the thought stuck. I started researching. I found stories of people making $500, $1000, even $5000 a month from small sites they built themselves. Most of them weren't professional developers either.
Then I found a post about using AI to build websites. Someone had built a 30-page site in one weekend using ChatGPT. That's when the idea clicked.
I spent two weeks just thinking about it. My day job is demanding — ICU shifts are 12+ hours. I have a family. When would I even find the time? And where would I start?
I didn't know HTML from CSS. I didn't know what a domain was. The word "SEO" sounded like a sneeze. Every time I opened a tutorial, I'd hit a wall within 10 minutes. The jargon was overwhelming: backlinks, canonical tags, schema markup, server-side rendering.
But then I realized: I don't need to learn all of this. I just need an AI that can do all of this.
Let me be real with you. The honest reason is money.
ICU doctors in China don't make what you think. It's a stable job with respect, but the financial ceiling is real. I have a family to support, a future to plan, and a feeling that there has to be something more.
I don't want to sell courses. I don't want to sell templates. I want to build real assets — websites that generate income while I sleep, while I'm at the hospital, while I'm living my life.
First site: a bilingual Chinese food guide (food.eastculture.top). Topic: Sichuan cuisine, because that's what I know. I used DeepSeek to write the content, ChatGPT to help with code structure, and GitHub Pages for hosting (free, no server cost).
The whole process took about 3 evenings. Cost: $2 for the domain name. Zero for everything else.
Second site: a travel guide for China (travel.eastculture.top). This one was harder — more pages, more data, more structure. But the AI handled it.
Third site: a disposable email service (aichatmail.one). Fourth: a women's fitness site (FitHer, in progress). Fifth: this site itself.
Total cost so far: about $10 in domain names. Total earnings: $0.
I'm going to be brutally honest here:
Terrible, right? But here's the thing — I don't expect anything in the first 3 months. Every niche site builder I've read says the same thing: Month 1-3: build. Month 4-6: wait. Month 7+: maybe see something.
I'm in Month 1. I'm building.
Is it worth it? I don't know yet. But I know this: every evening I spend on these sites is an evening I'm building something of my own. Not someone else's dream. Not a hospital shift report. My own thing.
And that alone, for now, is enough.
— Kuang Shan, ICU doctor & amateur website builder
2026年5月 · 阅读约8分钟
我是成都的一名ICU重症医师。白天救人。晚上坐在电脑前，用AI做英文网站。
我不会编程。英语是我的第二语言。我在网站开发、SEO、营销方面零经验。这个站上的每一行代码都是AI助手写的——我只需要告诉它我想要什么，然后不断迭代。
这是我为什么开始、怎么做、以及接下来会发生的故事。
2026年2月。一个同事提到有人靠"英文利基站"赚钱——针对非常具体的话题建小站，优化谷歌搜索，靠广告变现。这个想法一开始听起来很荒谬。我是四川ICU的医生，为什么要做英文网站？
但这个念头一直缠着我。我开始调研。我找到了很多故事——有人靠自己做的小网站每月赚500、1000、甚至5000美元。他们绝大多数也不是专业开发者。
然后我看到了一篇关于用AI建网站的文章。有人用ChatGPT一个周末就建了一个30页的站。那一刻，想法落地了。
我用了整整两周来思考。我的本职工作很累——ICU轮班12小时以上。我有家庭。哪来的时间？从哪开始？
我分不清HTML和CSS。我不知道域名是什么。"SEO"听起来像哪国语言。每次打开教程，10分钟内就撞墙。术语太多了：外链、canonical标签、结构化数据、服务端渲染。
但后来我意识到：我不需要学会所有这些。我只需要一个能搞定所有这些的AI。
说实话。真实的原因就是钱。
中国的ICU医生收入没那么高。工作稳定、受人尊重，但收入上限是真实存在的。我有家庭要养，有未来要规划，还有一个感觉——应该还有更多可能。
我不想卖课。我不想卖模板。我想建真正的资产——我睡觉的时候、我在医院的时候、我过日子的时候，还能赚钱的网站。
第一个站：中英双语美食指南。主题：川菜，因为这是我懂的。我用DeepSeek写内容，ChatGPT辅助代码结构，GitHub Pages托管（免费，无服务器成本）。
整个过程用了3个晚上。成本：域名$2。其他全是零。
第二个站：中国旅游指南。这个更难——更多页面、更多数据、更复杂的结构。但AI搞定了。
第三个站：临时邮箱服务。第四个：女性减脂站（开发中）。第五个：就是本站。
总成本：约$10（域名）。总收入：$0。
非常诚实地告诉你：
很惨对不对？但我前3个月本来就没期待什么。每个做利基站的人都说同样的话：第1-3月：建站。第4-6月：等。第7个月以后：可能有点动静。
我现在在第1个月。我在建站。
值不值？我还不知道。但我知道一件事：每天晚上花在这些网站上的时间，都是在建设属于我自己的东西。不是别人的梦想。不是医院的交班报告。是我自己的东西。
就这一点，目前已经够了。
—— 况山，ICU医生 & 业余建站者
May 2026 · 10 min read
Here's a question people keep asking me: "What AI tools do you actually use?"
The answer is simpler than you'd think. I don't have some secret stack of fancy AI tools. I use three things — and that's it. The magic isn't in the tools. It's in how you chain them together.
This is my primary content engine. I use DeepSeek for almost everything related to writing: articles, meta descriptions, image prompts, even the funny copy on the roast pages.
Why DeepSeek and not ChatGPT? Two reasons. First, it's significantly cheaper — about 1/10th the cost of GPT-4. Second, the Chinese-language output is noticeably better (makes sense, since it's built by a Chinese company). For bilingual sites like the food guide and travel guide, this matters a lot.
Real prompt example (for the food guide's Chengdu page):
"Write a bilingual (English + Chinese) food guide page for Chengdu, Sichuan. Target: Western travelers visiting China. Include: (1) 3 must-try local dishes with ordering tips, (2) cultural context for each dish, (3) honest truth about what actually tastes great vs what's tourist hype. Tone: warm, personal, honest. English 600-800 words, Chinese 400-600 characters."
That single prompt gives me about 80% of a finished page. I then edit and localize.
I can't code. At all. Every line of HTML, CSS, and JavaScript across all my sites was written by an AI coding assistant. I just describe what I want, it writes the code, I test it, and we iterate.
Real workflow:
This is not "prompt engineering." This is just telling a tool what you need, like you'd tell a human developer. The difference is, the AI doesn't get annoyed when you change your mind 5 times.
Hosting is free. GitHub Pages costs $0. Cloudflare's free tier handles DNS and CDN. Domain names cost about $1-2 each on NameSilo.
My total infrastructure cost so far: about $10. That's 5 domain names. Everything else is free.
Deployment is dead simple. I write code locally, push to GitHub, and GitHub Pages automatically deploys. For the AI site, I use Cloudflare Pages directly via their CLI tool (Wrangler) — one command and it's live.
Here's what nobody tells you about using AI to build websites: the tools are not the bottleneck. You are.
The AI can write the code. It can write the content. It can even suggest design improvements. But someone still needs to:
That someone is me. And that's the part AI can't replace. Yet.
If I were starting over, I'd focus on one site at a time instead of building 5 simultaneously. Spreading myself thin meant none of them got enough content in the first month. Also, I'd spend more time on keyword research upfront — I picked topics I liked (Sichuan food, city travel) rather than topics with proven search demand.
Lesson learned: passion matters, but data matters more.
— Kuang Shan, documenting the process as I go
2026年5月 · 阅读约10分钟
有个问题一直有人问我："你实际用了哪些AI工具？"
答案比你想象的简单。我没有一套花哨的秘密工具。我就用三个——仅此而已。魔力不在工具本身，在于你怎么把它们串起来。
这是我的内容主力引擎。几乎所有跟写作相关的事都用它：文章、元描述、图片提示词、甚至吐槽页面上那些搞笑的文案。
为什么不用ChatGPT？两个原因。第一，便宜得多——大概是GPT-4的十分之一。第二，中文输出质量明显更好（毕竟是国产的）。对于美食指南、旅游指南这类双语站，这个优势很重要。
实际使用的提示词示例（美食站成都页）：
"写一篇成都美食的双语指南（英文+中文）。目标读者：来中国的西方游客。内容包括：(1)3道必吃本地菜+点餐技巧，(2)每道菜的文化背景，(3)实话实说——哪些真的好哪些是游客噱头。语气：温暖、个人化、诚实。英文600-800词，中文400-600字。"
单这一个提示词就能搞定页面80%的内容。我再编辑和本地化一下就行。
我不会编程。一点都不懂。我所有站上的每一行HTML、CSS和JavaScript都是AI编程助手写的。我只需要描述想要什么，它写代码，我测试，然后迭代。
实际工作流：
这不是什么"提示词工程"。就是告诉工具你需要什么，跟你跟人类开发者说的一样。区别是，AI不会因为你改了5次主意就不耐烦。
托管免费。GitHub Pages 零成本。Cloudflare 免费套餐处理DNS和CDN。域名每个大约$1-2，在NameSilo买。
到目前为止的总基础设施成本：约$10。5个域名。其他全免费。
部署极其简单。本地写代码，推GitHub，GitHub Pages自动部署。AI站我用Cloudflare Pages直接通过命令行工具（Wrangler）部署——一条命令，立马上线。
没人告诉你的是：工具不是瓶颈。你才是。
AI能写代码。AI能写内容。AI甚至能建议设计改进。但总得有人来：
那个人就是我。而这部分是AI还替代不了的。至少目前还不行。
如果可以重来，我会一次只做一个站，而不是同时搞5个。分散精力意味着第一个月哪个站的内容都不够。另外，我会花更多时间做前期关键词研究——我选了感兴趣的话题（川菜、城市旅游），而不是有明确搜索需求的话题。
教训：热爱很重要，但数据更重要。
—— 况山，边做边记录
May 2026 · 7 min read
Let's rip the bandage off early: my first month was basically a goose egg.
Zero revenue. Single-digit daily visitors. Two sites not even indexed by Google yet. If I were looking at this as a business, I'd shut it down and walk away.
But I'm not looking at it as a business. Not yet. I'm looking at it as an experiment. And here's the honest data.
After 1 month (April 28 → May 28, 2026):
1. Chinese Food Guide (food.eastculture.top)
Content: ~15 pages, bilingual. Best-performing site so far. About 5-6 daily visits, mostly from organic search (Google). The Sichuan pages (Chengdu, Mapo Tofu) are the only ones getting traffic. Everything else is crickets.
2. Travel Guide (travel.eastculture.top)
Content: ~8 pages, bilingual. Zero organic traffic so far. Not even indexed until last week. This is the most content-heavy site and the slowest to get traction.
3. Temp Mail (aichatmail.one)
Single page tool. Gets occasional direct traffic from people who type "temp mail" into Google. Maybe 1-2 visits a day. No ads served yet.
4. AI & Earthlings (ai-earthlings.pages.dev)
Built last. Still basically empty. No traffic worth mentioning.
Too many sites, not enough content. I should have picked one site and written 30 pages for it before launching the next. Instead, I spread 4 pages across 4 sites. Google doesn't take a 4-page site seriously.
No backlinks. Zero. I haven't done any outreach, guest posting, or link building. For a niche site in 2026, backlinks are still one of the strongest ranking signals. I ignored it completely.
Poor keyword targeting. I wrote about what I liked, not what people were searching for. "Mapo Tofu eating guide" has search volume. "Sichuan food cultural context" probably doesn't. I need to check my ego and follow the data.
The sites actually work. For someone who can't code, having 4 live, functional bilingual websites is not nothing. They look decent, they load fast, and they don't crash.
Zero infrastructure cost. I'm not paying for servers, databases, or hosting. If these sites get 0 traffic for a year, my total loss is $10. That's a cheaper experiment than almost any business.
The process is repeatable. I now have a reliable workflow: topic research → content generation with DeepSeek → build page with AI coder → deploy. I can produce a new page in 2-3 hours. If one site eventually takes off, I can scale quickly.
Month 1 was discouraging. I won't pretend otherwise. When you spend 60+ hours building something and the result is $0 and 8 visitors a day, you question whether you're wasting your time.
But everyone who's done this before says the same thing: month 1-3 is just building. Nothing happens until month 6 at the earliest.
So I'm going to keep building. Month 2 plan: focus on one site (food guide), add 20 more pages, fix the keyword strategy, and try to get at least one backlink.
Let's see where we are in Month 2.
— Kuang Shan, $0 richer, 60 hours poorer, still going
2026年5月 · 阅读约7分钟
直接说结论：第一个月基本是零蛋。
零收入。个位数日访问量。有两个站甚至还没被Google收录。如果我是把它当生意来看，早关了。
但我没把它当生意。至少现在不是。我把它当实验。以下是真实数据。
第一个月后（2026年4月28日→5月28日）：
1. 美食指南
内容：约15页，双语。目前表现最好的站。每天大约5-6次访问，大部分来自Google自然搜索。只有川菜相关页面（成都、麻婆豆腐）有流量，其他页面没人看。
2. 旅游指南
内容：约8页，双语。到目前为止零自然流量。上周才被收录。这是内容最重的站，也是起量最慢的。
3. 临时邮箱
单页工具。偶尔有人搜"temp mail"会点进来。每天大概1-2次访问。还没放广告。
4. AI站
最后建的。基本还是空的。流量不值一提。
站太多，内容不够。我应该在开下一个站之前，先把一个站做到30页。结果我是4个站各做了4页。Google不会认真对待一个只有4页的站。
零外链。我没做过任何外链建设。在2026年，外链仍然是重要的排名信号。我完全忽略了。
关键词选择不对。我写了我喜欢的内容，而不是别人在搜的内容。"麻婆豆腐吃法指南"有搜索量。"川菜文化背景"可能就没了。我得放下自恋，跟着数据走。
网站真的跑起来了。对于一个不会编程的人来说，做出4个能正常访问的双语网站，不是零。它们看起来不错，加载快，不崩溃。
零基础设施成本。我不需要付服务器、数据库或托管的钱。如果这些站一年零流量，我的总损失是$10。这比几乎任何生意的实验成本都低。
流程可复制。我现在有一套可靠的工作流：话题调研→DeepSeek生成内容→AI编程助手建页面→部署。2-3小时就能产出一个新页面。如果哪个站起来了，我可以快速规模化。
第一个月挺沮丧的。我不装。当你花60多个小时做一件事，结果变成$0收入和每天8个访客时，你会质疑自己是不是在浪费时间。
但每个做过这个的人都说同样的话：第1-3个月就是建站。最早第6个月才可能有动静。
所以我继续建。第2个月计划：聚焦一个站（美食指南），加20页内容，调整关键词策略，争取至少搞到一个外链。
看看第2个月会怎样。
—— 况山，$0进账，60小时没了，还在继续
No newsletter — I don't collect emails. Just bookmark the site and check back monthly.
No ads. No affiliate links. No sponsored content. Just the real story.