Vingel retweeted
Our house in Toronto had this fancy glassed wine cellar, but we are not big wine drinkers.
Anyways, it had good climate control so here is my rack cellar.
Vingel retweeted
Anyone that works in AI is working the hardest they've ever worked in their lives. On the surface it's somewhat ironic (AI should give us back time!), but the reality is that it's the most fun, fascinating and empowering epoch in human history. The intelligence revolution.
Replying to @kentdebruin
I collected 70 different moats, and they're all still relevant
stephango.com/moats
Longbridge MCP is live on Claude - now on both ChatGPT and Claude🚀
140 tools: quotes, earnings, dividends, analyst estimates, shareholder...
We’ve also updated market data pricing for AI use: real-time US,HK market data is now free for every one.
claude.ai/directory/connecto…
Vingel retweeted
After 3-4 months of iteration, Open Minis — "possibly the best Agent app on your phone" — has stabilized into a mature architecture, now powering tens of thousands of users' daily workflows.
Today we're open sourcing all of it: the full iOS and Android code.
A real on-device AI agent: a native Linux shell, browser automation, extensible skills, persistent memory, and deep system integration.
Now, fork it, feel free to build your own on-device agent now. 🤗
github.com/OpenMinis/OpenMin…
Vingel retweeted
“So you spent $40K to run GLM 5.2 locally?”
“Yes, Dave”
“And you did all this to save $20 a month on Cursor”
“Thats right, Dave”
Vingel retweeted
🎉 很高兴,小小的 Minis 全球 App Store 获得 100 个 5 星好评啦!感谢用户的真诚认可(🥲 可没求过一次评价)!
同时,今天 Minis 1.9 版本也通过了审核,增加了 MCP、SOUL.md 等重磅更新,快去定义你的专属随身助理吧🤗
We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include:
Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work
Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency
Improved Architecture: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20%
Pure Open: An MIT open-source license — no regional limits, technical access without borders
Supporting long-horizon tasks starts with making long context engineering-usable: the model must maintain quality across long, messy coding-agent trajectories, not just accept more tokens. A 1M context is easy to claim, but much harder to keep reliable under real engineering pressure. To this end, we substantially expanded 1M-context training for coding-agent scenarios, covering large-scale implementation, automated research, performance optimization, and complex debugging. The result is a long-context system that is not only wide in scope, but solid in execution: a practical substrate for sustained engineering work.
This capability is reflected in GLM-5.2's performance on three long-horizon coding benchmarks. FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. On this benchmark, GLM-5.2 trails Opus 4.8 by only 1%, while edging out GPT-5.5 by 1% and Opus 4.7 by 11%. On PostTrainBench, where each agent is given an H100 GPU and evaluated by how much it can improve small models through post-training, GLM-5.2 outperforms both Opus 4.7 and GPT-5.5, ranking second only to Opus 4.8. On SWE-Marathon, an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services, GLM-5.2 still has room to grow, trailing Opus 4.8 by 13% while remaining second only to the Opus series. Across all three benchmarks, GLM-5.2 is the highest-ranked open-source model, showing that its 1M context has translated into practical long-horizon delivery capability.
Vingel retweeted
File over app
File over app is a philosophy: if you want to create digital artifacts that last, they must be files you can control, in formats that are easy to retrieve and read. Use tools that give you this freedom.
File over app is an appeal to tool makers: accept that all software is ephemeral, and give people ownership over their data.
In the fullness of time, the files you create are more important than the tools you use to create them. Apps are ephemeral, but your files have a chance to last.
The pyramids of Egypt contain hieroglyphs that were chiseled in stone thousands of years ago. The ideas hieroglyphs convey are more important than the type of chisel that was used to carve them.
The world is filled with ideas from generations past, transmitted through many mediums, from clay tablets to manuscripts, paintings, sculptures, and tapestries. These artifacts are objects that you can touch, hold, own, store, preserve, and look at. To read something written on paper all you need is eyeballs.
Today, we are creating innumerable digital artifacts, but most of these artifacts are out of our control. They are stored on servers, in databases, gated behind an internet connection, and login to a cloud service. Even the files on your hard drive use proprietary formats that make them incompatible with older systems.
Paraphrasing something I wrote recently:
> If you want your writing to still be readable on a computer from the 2060s or 2160s, it’s important that your notes can be read on a computer from the 1960s.
You should want the files you create to be durable, not only for posterity, but also for your future self. You never know when you might want to go back to something you created years or decades ago. Don’t lock your data into a format you can’t retrieve.
These days I write using an app I help make called Obsidian (@obsdmd), but it’s a delusion to think it will last forever. The app will eventually become obsolete. It’s the plain text files I create that are designed to last. Who knows if anyone will want to read them besides me, but future me is enough of an audience to make it worthwhile.
Vingel retweeted
You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.
Vingel retweeted
🧵 Announcing iSH ARM64 — native Linux on iPhone & iPad, open source.
A fork of @iSH_app that adds a same-architecture threaded-code interpreter (codename Asbestos) for AArch64 Linux on Apple Silicon.
1/ iSH ARM64 runs AArch64 Linux on ARM64. 3–30× overhead vs native, down from 15–100×.
2/ 48-bit virtual address space. Unlocked V8, Go, and Rust on iSH ARM64 now.
3/ Node.js 22 now runs on iOS. With --jitless injection.
npm install. npx. create-next-app. All working.
4/ Built for AI agent orchestration on iOS. iSH ARM64 shipped as the Agent Shell Sandbox inside OpenMinis — stably running Linux workloads for 10,000+ users.
5/ Compatibility: 205/205 tests pass. 18 categories — Core OS, Python, Node.js, Go, Rust, Perl, Ruby, SQLite, Git, SSH, Editors, Build tools, Media, Crypto, Signals, and more.
The code is open. The 10,000 users are production.
⭐ github.com/OpenMinis/ish-arm…
🙋 PRs welcome. Issues welcome. Stars appreciated.
#OpenSource #iOS #Linux #ARM64 #iSH #SystemsProgramming
Vingel retweeted
向大家介绍一下即将开源的新玩具 👇
Minis 一款纯手机本地运行的 AI Agent 应用📱
无需注册额外云端账号,无需添置任何新设备,连接你的 AI 订阅直接用你手上的就能完成Manus、OpenClaw的大部分任务。
✅ 本地虚拟技术 iSH(arm64)
✅ 本地 Browser use
✅ 与 iOS 集成: 分享、健康等
TF 链接见👇
这位博主贡献了一个有趣的观察:他发现自己跟Codex的对话特别像爱泼斯坦邮件的写作风格:去修饰化、极度简练、充满命令式且缺乏语法连接的断句风格。
正常的人类语言包含大量语法、敬语和逻辑连接词,这些都是为了克服人际交往中的“摩擦力”,为了说服对方或表达尊重。
但对于爱泼斯坦而言,他所处的权力结构已经把周围的人异化成了他意志的直接延伸。由于不需要协商,也不需要考虑对方的感受,他的语言就自动剥离了所有社交功能,退化为纯粹的触发机制。
当你面对 Codex 时,你处于同样的“绝对掌控”位置。AI 不需要被尊重,也不需要被说服,它只是你大脑的外部“延伸”。为了追求效率,你的大脑本能地抛弃了线性的、文学性的语言结构,转而采用一种碎片化的、关键词驱动的“脉冲式”表达。
正如麦克卢汉所说:我们塑造了工具,此后工具又塑造了我们。
Vingel retweeted
Telegram创始人帕维尔·杜罗夫(Pavel Durov)在谈及“如何区分顶尖人才与普通人才”时,分享了他在团队管理中的深刻观察。
他提到一个亲身经历:曾有两名Android工程师负责同一项目,却始终无法按时交付。“
起初我以为是人手不足,甚至考虑招聘第三名工程师。”
但深入观察后发现,其中一人不仅频繁拖延进度,还常常抱怨、逃避责任。
“当我做出解雇他的决定时,意外地发现根本不需要第三名工程师。”
杜罗夫总结道,这类员工制造的内耗,远比他能解决的问题更多,
“这违背直觉,因为人们总以为‘人多力量大’,但实际上,一个人的负面作用可能抵消整个团队的努力。”
更值得注意的是,与普通人才共事的挫败感。
“顶尖人才(A Players)能敏锐察觉到身边人的状态。”杜罗夫解释,当团队中出现一个总提错问题、持续拖后腿的人时,即使自己能力再强,也会因对方无法专注而感到压抑,“仿佛被无形的枷锁束缚,无法发挥真正的潜力。”
在他看来,顶尖与普通人才的核心差异,并非单纯的经验或勤奋,而是“持续专注的能力”。
“90%的普通人才(B Players)并非懒惰,而是难以长时间聚焦单一任务。”这种“无法深入钻研”的特质,让顶尖人才难以忍受——“与分心的人共事,就像在消耗自己的专注力,是对能力的浪费。”
杜罗夫的观察揭示了一个职场真相:真正的高效团队,需要每个成员都具备“深度专注”的核心能力。这不仅关乎个人成就,更决定着整个团队能否突破瓶颈,实现真正的“1+1>2”。对于追求卓越的企业而言,识别并留住这类“能沉下心做事”的顶尖人才,或许比盲目扩张更重要。
Telegram founder Pavel Durov on what separates A Players from B Players
“I can recall a few instances in my career where firing an engineer actually resulted in an increase in productivity,” Telegram founder Pavel Durov begins.
He gives an example of two Android engineers building an app that are having a hard time hitting deadlines:
“You think, ‘I probably have to hire a third engineer.’ But then you notice that one of [the engineers] is really weird — falling behind schedule, complaining, not assuming responsibility — and you ask, ‘What if I just fired this person?’ Then you fire this person, and in a few weeks you realize you never needed a third engineer. The problem was this guy who created more issues and problems than he solved. It’s so counterintuitive because in developing tech projects, you tend to think that you just throw more people into something and things get solved miraculously.”
Pavel continues:
“The other thing that people don’t realize is how demotivating working with a B Player is. Everyone can tell if the other engineer they’re working with is really competent. If the person is asking the wrong questions and they keep lagging behind, at a certain point if you’re an A Player, you get get this dissatisfaction and feeling that you are not able to realize your full potential and accomplish what you’re really meant to accomplish because of this person working next to you (or pretending to work next to you).”
Pavel reflects on what it is exactly that separates these B Players from A Players:
“In some cases it’s not because the person is lazy . . . It’s not about experience. More often it’s about natural ability and persistence. In 90% of cases, it’s just the inability to focus on one task for an extended period of time. Not everybody has this ability. So for people who do have this ability, it’s an insult to work alongside someone who is distracted and cannot go deep in the projects that they’re responsible for.”
Video source: @lexfridman (2025)



































