EasyChen (@easychen) profile picture

方糖气球( https://xitter.gq/t.co/8hHNDAV7Px )博主,80后大叔,萌物控。做原型、敲代码、写吐槽小说、制四格漫画。无业,玩独立开发,偶尔卖课为生。信息流诸多日本语、二次元、R18内容,关注需谨慎。

重庆
Joined March 2007
Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)Photo by EasyChen (@easychen)
猫の伸びからしか得られない栄養がある。
63
5,700
242
51,451
985,376
ゴジラ、襲来。 ニャジラ、就寝。
🤖 Made with AI
Readers added context they thought people might want to know
AIで生成された画像です。 OpenAIが提供するチェッカーで、ツールを使用した事を意味するシグナル(SynthID)が検出されています。 openai.com/ja-JP/research…
1,973
86,837
2,296
678,370
16,479,181
EasyChen retweeted
欢迎!Cindy 现在完全可以替代 Hermes,而且在我自己常用的领域都比 Hermes 做得更好。如果还有不如 Hermes 的地方,欢迎大家反馈,我们会马上改进。
Replying to @DashHuang
今天打算从hermes迁移到cindy
91
5
7
158
58,825
EasyChen retweeted
Fucking what the hell @NousResearch I am uninstalling all your bloatware garbage copypasta software. Fuck this attitude problem y'all have picked up. Deleting hermes no utility i get from the defunct garbage is worth my support. What a joke.
This team is a literal joke of a team: Its been exactly 2 hrs since I've started rage hating my favorite open source lab ever. They destroyed there rep with this one.
15
14
1
441
29,240
EasyChen retweeted
如果你打算用 GPUI 之前可以看看这篇
感谢分享,我说一下我在上一个版本 baocut 用 GPUI 踩的坑。 GPUI 挺好的,性能好,跨平台,AI 友好,但也有坑: 1. UI 复杂一点的话大概率你要 fork 一份改一下,有些功能原生支持不了,但也不是大问题 2. Accessibility 支持不太好,要支持一些键盘操作会比较麻烦(也可能我用法不对) 3. Rust 编译资源消耗很大 每次编译,无论是 CPU 占用还是磁盘占用,都巨大,对于我这样用 Mac Mini M4 16G + 1T 硬盘的来说简直太痛苦了,不敢并行多开编译任务,磁盘空间永远不够用(后来我把编译结果默认放到移动硬盘缓解了一点) 4. 编译时间很长,不支持热更新。 这点很要命,这意味着你如果改一点 UI 代码,要重新编译,然后要等少则几分钟多则十几分钟,这时间无论对于 agent 还是对于人来说都是很大的时间成本,加上不能随便多任务,会拖慢你的开发速度 5. agent 验证 UI 不算太友好 codex、claude code 都可以借助 computer use 去验证 GPUI 的结果,但一个是慢,另一个相对成本也不低。 --- 后来我之所以换回 Electron,就是因为 Electron App 对于 Agent 相对友好,编译快、热更新,UI 改动很快看到效果,然后 Electron App 还能跑到 agent 内置的浏览器中,agent 验证起来很快,都不需要用 computer use 去打开 electron app。 至于网页渲染性能不够好的问题,我把原来一些需要复杂渲染的部分,都用 rust 编译成了 wasm,这样在浏览器运行也可以保证高性能。 以前 rust 做的转录、tts 模块也都以 worker 进程的形式保留下来了,electron 需要用到的时候可以直接起 rust 编译出来的进程(Codex 也是类似),和这些进程通信,后台的性能也比纯 TypeScript + Node 要好不少。 有兴趣的话可以看代码库:github.com/jimliu/baocut
24
6
1
56
23,827
EasyChen retweeted
不,并没有解决。在 MacOS 上 agent-desktop 后台处理问题的通过率只有 20%,Codex 有 33%,最高的是 Cua Driver 的 58%,也就是 Cindy 的 Computer Use 所采用的方案。
这个刚开源的工具,终于解决了所有AI 操作电脑会抢走鼠标的问题! 以前让 AI 帮你点电脑软件,它一动你就不能动鼠标,只能在旁边干等着(除了 codex) 现在 Vercel 开源了 agent-desktop,直接给 Claude Code、Codex、Cursor 这些 AI 装上了操作整台电脑的手和眼: 1. 后台静默干活,你在前台正常用鼠标办公,它在后台自己点别的软件,完全不抢鼠标焦点 2. 多个 AI 同时开工,1 台电脑里能同时跑多个 AI,各用各的虚拟光标,互不打架 3. Mac、Windows、Linux 三大系统都能直接用 为什么它能不抢鼠标呢? 以前的工具要不停截屏,靠大模型看图猜按钮位置,再移动你的鼠标去点,既慢又费额度,窗口挪一下还容易点歪 但 agent-desktop 完全不看截图,它直接读取系统的无障碍接口,相当于拿到了软件里所有按钮和输入框的编号清单,在后台按编号直接点,根本不用动你的物理鼠标! 有老哥直接在 1 台 Mac 上同时开了 16 个 AI 操作 16 个软件(见图 1),一个按计算器算账,一个写旅行备忘录,一个设提醒事项,还有查词典、翻日历、贴便签、跑终端的,16 个 AI 各带一个光标同时干活,是不是相当离谱? github.com/vercel-labs/agent…
42
10
3
170
35,644
EasyChen retweeted
:Python 社区迎来了一个新的包管理器 :(看着十几种包管理器方案)这有什么奇怪的 :它是 pnpm
experimental: pnpm v12.4 can install Rust and Python dependencies too. So in a multi-language repository you get js packages, crates, and pypi packages downloaded concurrently. pnpm.io/blog/releases/12.4
34
21
4
320
57,278
EasyChen retweeted
我的合伙人 @xdanger 二十多年前就是受 DHH 的 Ruby on Rails 介绍视频的影响,从 Windows 平台换到的 Mac。他今天捐了 100 万美元给到 Omacom 基金会,用实际支持来让这个世界有更多改变。 今天的 Mac OS 已经失去了当年那种独特和前卫的气质。开发个软件还要每年交 99 刀,上架 App Store 还有各种苛刻的限制和 30% 的苹果税,这一切都在 AI 时代显得格格不入。期待有更多的革新者出现,打破沉闷无聊的旧世界。
99
38
15
699
159,280
EasyChen retweeted
刚发现 PayPal 偷偷改政策了,不让自己选卡片的默认结算货币了? 现在会用很差的汇率结算,每次都会多扣 5% 左右,对于使用全币种以及非银联信用卡的人来说非常坑。Apple ID 绑定了 PP 支付的朋友们,记得去改一下自动扣款里每个条目的结算选项。
120
7
4
116
47,262
誰でも簡単にチップチューン(ピコピコ音楽)が作れる【EASY 8BIT EDITOR】を公開しました。自動作曲機能がついているので、テイストを調整してSHUFFLEボタンを押すだけでもOK!ミックスも楽しめます。ゲームやYouTube・WebサイトのBGMに! amix-design.com/tl/tool-s-8b…
15
586
49
2,576
322,710
Some of you guessed right. 👀 Owl Alpha on @OpenRouter — that's us. Since going live, it has reached Top 3 globally by daily volume — and #1 on Hermes Agent, #2 on Claude Code, #3 on OpenClaw by monthly volume. Thank you to everyone who tested and used Owl Alpha during stealth — you helped shape what's coming next. Owl Alpha will be retiring soon. But this isn't an ending — stay tuned!
56
69
44
984
172,009
EasyChen retweeted
Anthropic
120
1,297
159
14,742
782,683
EasyChen retweeted
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/D… 🤗 Open Weights: huggingface.co/collections/d… 1/n
1,645
7,415
2,421
45,272
10,178,766
EasyChen retweeted
claude —dangerously-skip-permissions
28
150
30
2,344
173,294
EasyChen retweeted
We ran Qwen3.6-35-A3B GGUF performance benchmarks to help you choose the best quant. Unsloth ranks first in 21 of 22 model sizes on mean KL divergence, making them SOTA. GGUFs: huggingface.co/unsloth/Qwen3…
47
74
9
793
74,888
We're delighted to announce that MiniMax M2.7 is now officially open source. With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 (57.0%). You can find it on Hugging Face now. Enjoy!🤗 huggingface:huggingface.co/MiniMaxAI/Min… Blog: minimax.io/news/minimax-m27-… MiniMax API: platform.minimax.io/
Readers added context they thought people might want to know
The MiniMax M2.7 model weights are publicly available, but under a license prohibiting commercial use without authorization. This does not meet the Open Source Initiative's definition of open source, which requires allowing commercial use. License: huggingface.co/MiniMaxAI/Mini… OSI: opensource.org/osd
289
728
288
5,506
1,623,333
EasyChen retweeted
‼️Do not npm install or deploy anything right now Supply chain attack on axios 1.14.1 - even if you don’t use axios it may be a nested dep. Pin versions or wait until this is resolved
Replying to @npmjs
@npmjs @GHSecurityLab there is an active supply chain attack on [email protected] which pulls in a malicious package published today - [email protected] - someone took over a maintainer account for Axios
161
1,748
228
8,820
1,640,078
The Next.js Adapter API is now stable - the result of over a year of collaboration with Netlify, OpenNext, and other platform partners. We are deeply committed to developers running Next.js on Cloudflare. Looking forward to building our official adapter on this new foundation.
Next.js 16.2 introduces a stable Adapter API, built with Netlify, Cloudflare, OpenNext, AWS, and Google Cloud. But the API is only part of the story. Next.js is used by millions of developers across every major cloud, and making it work well everywhere is on us. Here are our commitments. nextjs.org/nextjs-across-pla…
43
94
30
1,485
226,789
🔥 Introducing LongCat-Next: A Discrete Native Autoregressive Multimodal Model LongCat-Next integrates language, vision, and audio into a unified discrete autoregressive model, extending Next-Token Prediction to native multimodality and delivering industrial-strength performance across diverse multimodal domains. 🔑 Key Features: ⚙️ 68.5B total params, 3B active, LongCat-Flash-Lite MoE backbone, excels at seeing, painting, and speaking in a unified discrete autoregressive framework. 🧩 Discrete Native Autoregression Paradigm (DiNA): We introduce DiNA, a unified paradigm that extends next-token prediction from language to native multimodality, internalizing diverse modalities into a shared discrete token space. 🌐 Discrete Native Any‑Resolution Vision Transformer (dNaViT): A unified visual tokenizer and de-tokenizer that encodes images into discrete IDs with semantic completeness, enabling both understanding and generation at any resolution. This approach overcomes the performance ceiling of discrete vision modeling in understanding tasks and enables to reconcile the conflict between understanding and generation. 👀 Visual Understanding: Fine-grained visual perception for complex tasks such as OCR, Charts, GUI interpretation, and document analysis, and advanced STEM reasoning capabilities. 🎨 Visual Generation: Generation under 28x compression ratio at arbitary resolution with competitive performance, especially in text rendering. 🎧 Speech: Strong audio comprehension capabilities, low-latency and intelligent audio-to-audio interaction, as well as speech synthesis featuring customizable voice cloning. 📄 Paper: github.com/meituan-longcat/L… 🔗 GitHub: github.com/meituan-longcat/L… 😊 HuggingFace: huggingface.co/meituan-longc… 💻 demo: longcat.chat/longcat-next 📖 blog: longcat.chat/longcat-next/in…
9
69
16
428
49,145
Building agent skills from scratch is a grind. We've been there. So we built the fix — and open-sourced all of it under MIT. PDF, Excel, PPTX, DOCX, and more. Use it, fork it, PR it. Intelligence with everyone. Github Repo → github.com/MiniMax-AI/skills Try online → agent.minimax.io
23
116
14
1,129
140,942