Vingel @vingel

🎉 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🤗

keyboard_arrow_left Previous keyboard_arrow_right Next

服了，这大热天新加坡晚上还能停电两小时

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.

keyboard_arrow_left Previous keyboard_arrow_right Next

有什么需求跟我的 Agents 沟通去吧🙃

在10年美签快到期的倒数第二天，接到了紧急出差美国的需求 😂

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.

keyboard_arrow_left Previous keyboard_arrow_right Next

@janlay 潮汕以前很少离婚也很少二嫁的。

很多人现在觉得 AI 是万能的。但我更认同一句话：AI 不是万能的，但没有 AI 是万万不能的。

尝试了下在 MBP 96GB 内存下用 ds4 框架可以跑到 ds4: prefill: 20.89 t/s, generation: 20.87 t/s 的速度。

团队本身就是创业公司的第一个产品，其他的产品都是这个产品的衍生品。

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.

The enemy of truth is motivated reasoning.

以下这些 AI 服务都不续费了

Claude / Claw 这两单词打多了，我现在凭键盘肌肉记忆拼不出来 Cloud 这个词了。

🧵 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-… 🙋 PRs welcome. Issues welcome. Stars appreciated. #OpenSource #iOS #Linux #ARM64 #iSH #SystemsProgramming

夜深想起 Pressfield《The War of Art》里的"Resistance 内阻力"。 于个人来说内阻力可能只是一个伪命题，但放到组织中， 内阻力能具像化成路径依赖、立场、和山头。

optimizationarena.com/prediction-mar… 昨天用 Claude + Codex 去参加量化做市策略竞赛，尝试了快20个版本， 也才 46 名 🤣

我们最近搞的 Longbridge CLI 已经比较完善了，也为此增加了很多数据 API，目前已经有 40 多个子功能，涵盖各类投资参考信息。 以前 CLI 仅是程序员特有的工具，现在有了 AI 加持，人人都可以有一个专业的投资助理。 open.longbridge.com/docs/cli/

@UdOatnil 看着很棒，加油

AI 时代的飞书/钉钉为什么还没有出现？