Orchestrating ideas with Code & AI Craft: Let's go on a trip together. The companion of the journey is the musubi. https://xitter.cf/t.co/f8o9ukHWme All views are my own

Joined August 2014
拾一 retweeted
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax. - 100-500× faster than mermaid.js - 6× smaller bundle - No dependencies - Easy to theme - Responsive to device width In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now. Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
281
878
172
11,274
608,064
Hey Japanese learners! I built a font that renders Furigana or Romaji above Kanji, with ligatures to support words. You can apply it anywhere to get furigana notations for free. Give it a try, and I hope it will be helpful :) furifont.antfu.me/
113
1,119
179
6,717
316,073
As you invite more agents to our work, and create software factories to be more productive than ever, you’ll soon outsource everything to an agent, even the thinking. The work you will do will feel frictionless, it will feel amazing on the surface, but once you go a bit deeper, it’ll feel extremely shallow. It won’t reflect the struggles you went through, your decisions, and ideas. It will no longer remind you of you and the work you aspire to. You will turn into just another extremely efficient producer of things, but not a creator like you were before. Invite friction to your work.
96
158
34
1,847
63,828
拾一 retweeted
100% 同意。 现在已经没有必要再使用臃肿大公司的软件了。 现在已经没有必要再使用那些几年后就会转手出售用户群和数据的初创公司的软件了。 至少作为独立软件制作者的我,不会出售用户数据,因为已经有良性的用户付费支持的结构,有良性的发展资金来源,使得软件可以长久发展。
This is the BEST time to support small creators and independent software. There’s no need anymore to use software from bloated corporations. There’s no need anymore to use software from startups who are just flipping their user base and data a few years later. Support small teams or individual people who have a track record of delivering value and sticking with what they say, not only because their livelihood depends on it but also because they’re in it because they truly are passionate about it. Support small teams wherever you can and where it makes sense 🧡
1
10
2,803
Replying to @zane_os
tibo 的28天计划看着像个笑话 大家要的是他展现他还能否勃起,他一直在炫耀自己的内裤牌子多高级
15
8
4
361
12,883
拾一 retweeted
怎么能少了《数学之美》
Opus 5.5眼中的《物理之美》 提示词: 生成一个视频,展示物理之美,要有电影感,高级感,一镜到底
7
2
31
7,595
I wanted to quickly create a short video with Opus 5.5 about the history of AI, from "Attention is all you need" to AGI. No stock footage, no image or video generators: every frame is rendered from code. This 3-minute film was made 100% in code by Claude in Claude Code: ~7,400 lines of React/TypeScript (Remotion), every image drawn in SVG and Canvas, an open-source TTS voice, and a score synthesized in Python. No stock footage. No image generators. Id say pretty cool! Tookl about 1h and 7% weekly rates.
161
185
34
2,722
205,238
拾一 retweeted
Hi Anthropic team, I’m writing because I feel hurt and helpless about how ordinary Chinese users are being treated. I understand that you may choose not to officially offer Claude in China. But could you please reconsider how you enforce that policy? Having accounts banned after paying for a subscription, without receiving a refund, leaves people feeling like they never mattered as customers. I need to ask something painful: are Chinese users being discriminated against? Is being Chinese itself a reason to be treated with suspicion, even when someone has done nothing harmful? I don’t want to believe that about a company whose product I love, but it’s hard not to feel that way when innocent people lose access without understanding what they personally did wrong. I don’t represent the Chinese government or Chinese companies competing with you. I don’t agree with their actions either. I have no power over their decisions, and I never chose to be caught in the middle of these conflicts. Please don’t hold ordinary people responsible for things completely outside our control. You can decide not to support a region officially. I’m asking you to please avoid sweeping bans that hurt innocent users, and to give people a meaningful chance to have their circumstances reviewed. Our nationality alone cannot tell you our intentions or how we use Claude. Behind these accounts are real people who care about what you’ve built. To me, Claude is something I sincerely want to keep using. It hurts to support a product and then feel that the people behind it don’t want you there, regardless of who you are or what you’ve actually done. Could you please give ordinary Chinese users a legitimate path to use Claude? If an account is banned, could you explain the specific reason and offer a real opportunity to appeal? The refund matters too. If you won’t restore access, please return the money for the subscription time we can no longer use. But what I want most is to be allowed to stay. Please look at us as individuals and give us a fair chance.
395
86
30
1,582
296,201
At the top of my AGENTS.md: - NEVER write unit tests after you write code. - Highly prefer E2E tests as the sole testing mechanism. Use them to verify complex features work. At the end of E2E tests, produce a verifiable and repeatable artifact. - If you must test a system in isolation, FIRST write all the ways it could fail, THEN write the code.
leave it to your boy opus to add 10 unit tests to ensure a constant string contains various substrings
83
244
32
5,554
1,268,066
拾一 retweeted
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
2,042
4,749
1,662
48,702
8,415,440
你可以过度用眼,但必须学会暴力恢复。
335
1,889
20
14,400
1,032,325
Installed macOS 27 on a MacBook and I'm not sure if this is some kind of twisted joke or just incompetence. The contrast of window controls (for both active and inactive windows) is so bad that even a sugar-jolted 25-year old can tell.
39
5
10
307
77,016
拾一 retweeted
Lody 开源了! 我们通过 @loro_dev 第一天就构建了面向团队的、本地优先的 workspace,coding agent 的控制面是我们的第一步。我们真正要解决的是团队数据 context 的共享,通过 agent 帮助团队和个人真的理解 context。 AI 已经能够帮助我们完成大大小心的任务,沉淀各类文档,但还无法让我们真的理解它做了什么,团队其他人做了什么。只有理解了才有掌控感,这就是 Lody 想去完成的,我们通过本地优先让你掌控了自己的数据,我们进一步希望通过 Lody 让你掌控自己的作品。 我们开源了客户端和 CLI 端,更多的更新和博客会逐步开放!如果你对我们做的事情感兴趣,欢迎 star,保持关注! github.com/LodyAI/Lody
59
55
31
388
155,274
来,作为一个 deepseek harness 喷子,我来告诉你它到底在捣鼓什么: 在 Claude Code、Codex 这类产品里,通常是: 固定 Agent 内核 + 可以添加的 Skills、Tools、MCP、Hooks 而 DeepSeek Harness : 极小的 Cordis 内核 + 模型供应插件 + 工具插件 + Agent Loop 插件 + 上下文插件 + 会话插件 + 存储插件 + 沙箱插件 + 权限插件 + 调度插件 + UI 插件 说人话:你在 CodeX 里面添加再多 skill,你也改不了 CodeX 读文件时候的内秉工作流(因为那是 Tibo 的研发同事在写软件时硬编码设定的)。 但是在 deepseek harness 体系下,你可以随时插拔它的核心插件,从而控制修改 loop 中的每一个具体检查点的运作方式。 既然你可以,那么 Agent 自身也可以抽插自己。deepseek 团队解决了两个核心问题,Agent 自己抽插自己的时候,怎么才能不把自己给抽或者插坏了。毕竟这玩意是个软件。 于是,他们提出一种“时间可组合性”的特性。让这些插件和传统软件中的插件不一样:它们在被添加的时刻,就铺好了自己的“退路”。保证在消失时干干净净,不会弄崩程序,减少心智负担。 来如未来。这叫时间倒流。 同时,插件还要声明自己依赖于什么服务。这样,当它依赖的服务被拔开、挪走的时候,它也不会像传统软件那样暴毙,报错。而是变为不可用,等待新的提供者,然后自动激活自愈。 小触角,小等待,小重连。四通八达小自愈。这叫空间。 然后他们认为自己发明了一种“时空软件学”。就给论文起了个关于时空的高大上的名字。 总而言之,他们把没有发明新的 harness,而是把乐高积木拆成更原子化的东西,再重新拼起来,发布了一下。发布的同时告诉你,看,这有一个 harness 哦,但是,它不一样,你可以任意拆下它最小的一部分,改造一下,再装回去。而且装配的过程中,它不会坏哦。一切都是热插拔的哦。 你们他妈的是不是脑子坏了,老子没事干非要把那一个个该死的螺丝拧下来再换个更炫酷的型号拧上去是吧?
181
62
16
611
196,174
Replying to @__oQuery
GPT 5.6 把我整个C盘都清空了,GPT还是慎用吧。 Fable 把我整个D盘都清空了,外国模型还是慎用吧。 GLM 5.2 真的把我的数据库给清空了,我真服了,国产模型也慎用吧。 Kimi K3 把我整个电脑都炸了,我真是服服的了。所有AI慎用吧。 还是人工处理最好。真的(认真脸)
4
1
14
13,044
I decided to stop buying SaaS. AI changed which software is worth building. We built our own ATS in a weekend, then a CRM and knowledge system. Saying bye to adapting someone else's workflow has never felt so good. I wrote about it here: cali.so/en/blog/we-decided-t…
1
1
7
1,665
smooth cloudy text effect copy code here: arlan.me/vault
11
10
280
10,611
3 年如同白驹过隙,LobeHub 80k Star 了🥳
33
3
3
41
8,584
拾一 retweeted
7月份股票的不断下跌 𝕏已经变成我的情绪垃圾桶了 什么分析复盘完全都不想做了 无念也无意义 🙂
50
1
68
18,411
拾一 retweeted
Replying to @SpaceXAI
What the hell is this response?!?!? So you basically admit you were storing customer data without their knowledge???? This is illegal in every developed country. And there’s 0 chance you DONT know this considering it’s literally standard practise in the industry So it means you did it deliberately. What, so you had more training data? Question is, were the cursor team doing this or was it the Grok team? Or both? Either way this is beyond the craziest thing I’ve seen this year and you all have lost all credibility
41
44
5
1,207
69,411