Yuan

X search sucks

@manateelazycat 同时开 60 个 codex 的场景是？

这两年我买的投资回报最好的装备列表 1. AMD 顶配台式机，买之前只想拥有，担心用不完性能，买完后发现，同时跑 60 ～ 90 个 codex 真的太香了 2. Vivo 折叠屏手机，日常用屏幕很窄，单手操作方便，展开 AI 后 AI 编程，出差和旅游能高效处理工作，不需要平板和笔记本，最佳搭子是豆包语音输入法 3. Nuphy 矮轴机械键盘，手感超好，长时间打字不累，虽然现在手写代码少了，但是偶尔和推友聊天，还是很享受 4. 坦克 500 混动，各种皮实，怎么开都不会坏，城市纯电开，旅游三把锁哪里都可以去 5. AT 胎和氮减，这次西藏之行，发现百路驰 AT 胎太静音了，堪比公路胎，氮减在山路连续过弯，可以拉的住坦克这种 3 吨的车，安全感满满 这些装备给我节省了很多时间，让我生活更幸福 你买过哪些幸福感满满的装备？一起和大家分享吧😁

@manateelazycat 最近用 ds 爽的飞起。但是审美实在不行，写出来的前端没眼看

梁圣这次让 DeepSeek V4 系列永久降价，其实最难受的并非 Claude 或者 GPT，甚至可以说对这两家的影响微乎其微，要用这两家的还是会用。 反而受到影响的是国内几家，比如Qwen、GLM、MiniMax 等。智商没多大差距，DeepSeek 还量大管饱。 当然这个优势看能延续多久。如果梁圣还像去年那种节奏去迭代，估计只能压1、2个月。 不过我认为不可能。毕竟现在梁圣融资了，有足够的市场来的钱去冲了😆 有 DeepSeek 最价值标的是用户的福音啊。 我现在就一个问题：梁圣什么时候把多模态也灰度给我。那么多用户都用了一个月了。🤡

🔥

@DanKulkov Man, welcome to China!

hi from China 🇨🇳

Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5, it scales from 355B params (32B active) to 744B (40B active), with pre-training data growing from 23T to 28.5T tokens. Try it now: chat.z.ai Weights: huggingface.co/zai-org/GLM-5 Tech Blog: z.ai/blog/glm-5 OpenRouter (Previously Pony Alpha): openrouter.ai/z-ai/glm-5 Rolling out from Coding Plan Max users: z.ai/subscribe

@0xTykoo 试试 pencil.dev

我去测评了一下市面上的专门用AI设计UI的产品： Google的stitch（专门设计UI用的）虽然上了没多久，但是我已经是重度使用者了。可惜今天又故障，不是第一次了，不得不找一下备胎。 Gemini给我推荐了四个我都去玩了一下， 第一张是uizard，简单的UI太简单了，复杂的又没有理解我的意图而且模版痕迹比较重，意图很容易被模版给吞掉，但是好处是这些里面的小模块都可以拖拽修改，这个作为新手UI玩家属于是美坏了，也是一种可控吧，可能是免费模型比较基础，但是你做的不好我又不想付费。 第二张是妙多AI，比较精确的实现了我的prompt的想法，在每个小模块都可以调的基础上给每个小模块prompt的功能，Google的stitch也是选一小块可以动嘴改，我最喜欢这个功能，只是stitch里框住以后改的乱七八糟，跟特别早openai生图还要框的那会一样糟。 第三张是Canva，明明是搞设计的平台做出来的UI机械的不行，感觉就和replit半年前差不多，就是UI设计感也没赶上，做app的能力也不如人意。 第四张是Figma，其实就像让他弄UI的，直接把一些功能给实现了，这四个里我最喜欢的是Figma，因为是有点惊喜在的，只不过总感觉有点过于麻烦他了，费token，因为我就想要个设计图。 作为一个纯用户的观察是感觉是本身UI设计做的好的Canva、Figma这俩特别想沾边vibe code app，让自己能部署出一个app出来。 如果用户直接对着 AI 说给我个 App，那中间画 UI 的过程就消失了。所以它们被迫往上下游延伸，想做一站式部署。 而反而Google、初创公司都是在想只切一个UI层，把这一点做到极致，往足够垂做。它们赌的可能是在相当长的一段时间里，人类还是需要中间态的。 我们需要看到界面，需要调整像素，需要确认视觉感受，然后才去写代码。 我当前阶段还是喜欢后者，Canva和Figma让我感觉有点焦虑过头了，谁会跑他们那里去做app呢，但我也不知道对不对，毕竟反过来说，做app也成内容创作的一种了，这么想其实也是合理的，只不过能不能把自己擅长的先做好一点。 最后就是希望我的Google stich速速修好，不要再故障了，不然我真的会订阅其他的。

pencil.dev is really cool

@dingyi 开源的 vibekanban.com

再来几个： - agentastic.dev - vibe-coder.com - ami.dev Ami 设计真好看。

We have open-sourced our new 𝕏 algorithm, powered by the same transformer architecture as xAI's Grok model. Check it out here:  github.com/xai-org/x-algo…

Introducing GLM-4.7-Flash: Your local coding and agentic assistant. Setting a new standard for the 30B class, GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight deployment option. Beyond coding, it is also recommended for creative writing, translation, long-context tasks, and roleplay. Weights: huggingface.co/zai-org/GLM-4.… API: docs.z.ai/guides/overvie… - GLM-4.7-Flash: Free (1 concurrency) - GLM-4.7-FlashX: High-Speed and Affordable

Today we’re announcing Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API. ✅ Multi-provider by default ✅ Useful for real-world workflows ✅ Extensible without fragmentation Build agentic systems without rewriting your stack for every model: openresponses.org

Introducing json-render AI-generated UI. Deterministic output. 1. Define your component catalog 2. AI steams JSON 3. Render interactive UI Let users prompt dashboards, widgets and apps - safely constrained to components and actions you define

crazy

The reason why DeepSeek could challenge so-called frontier labs' hegemony with 1/10 of the budget isn't just about 'cheap labor' or 'luck.' It's about this exact scientific rigor. They stopped 'alchemizing' and started doing 'physics.' If your CTO is still just yelling 'add more GPUs,' show them Zeyuan's tutorial and watch them sweat!

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently. So, here goes.

GLM-4.7 is here! GLM-4.7 surpasses GLM-4.6 with substantial improvements in coding, complex reasoning, and tool usage, setting new open-source SOTA standards. It also boosts performance in chat, creative writing, and role-play scenarios. Default Model for Coding Plan: z.ai/subscribe Try it now: chat.z.ai Weights: huggingface.co/zai-org/GLM-4.7 Tech Blog: z.ai/blog/glm-4.7

Open models year in review What a year! We're back with an updated open model builder tier list, our top models of the year, and our predictions for 2026. First, the winning models: 1. DeepSeek R1 (@deepseek_ai): Transformed the AI world 2. Qwen 3 Family (@AlibabaGroup): The new default open models 3. Kimi K2 Family (@Kimi_Moonshot): Models that convinced the world that DeepSeek wasn't special and China would produce numerous leading models. Runner up models: MiniMax M2 (@minimax_ai), GLM 4.5 (@Zai_org), GPT-OSS (@OpenAI), Gemma 3 (@GoogleAI), Olmo 3 (@allen_ai) Honorable Mentions: Nvidia's (@nvidia) Parakeet speech-to-text model & Nemotron 2 LLM, Moondream 3 VLM (@moondreamai), Granite 4 LLMs (@IBMResearch), and HuggingFace's (@huggingface) SmolLM3. Updated Tier list: Frontier open labs: DeepSeek (@deepseek_ai), Qwen (@AlibabaGroup), and Kimi Moonshot (@Kimi_Moonshot) Close behind: Z.ai (@Zai_org) & MiniMax AI (@minimax_ai) (notably none from the U.S. here and up) Noteworthy (a mix of US & China): StepFun AI (@StepFun_ai), Ant Group's (@AntGroup/ @TheInclusionAI Inclusion AI, Meituan (@Meituan_LongCat), Tencent (@TencentHunyuan), IBM (@IBMResearch), Nvidia (@nvidia), Google (@GoogleAI), & Mistral (@MistralAI) Then a bunch more below that, which we detail. Predictions for 2026: 1. Scaling will continue with open models. 2. No substantive changes in the open model safety narrative. 3. Participation will continue to grow. 4. Ongoing general trends will continue w/ MoEs, hybrid attention, dense for fine-tuning. 5. The open and closed frontier gap will stay roughly the same on any public benchmarks. 6. No Llama-branded open model releases from Meta in 2026. Read the full post on @interconnectsai -- link below.

Introducing shadcn/create – Build your own shadcn/ui Customize Everything. Pick your component library, icons, base color, theme, fonts and build something that doesn’t look like everything else. Now available for Next.js, Vite, TanStack Start and v0.

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask: "What do you think about xyz"? There is no "you". Next time try: "What would be a good group of people to explore xyz? What would they say?" The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".