胡泊Hubo

微信读书的官方 skills 出现在 beta 版了。 把这段话复制给 AI：下载 cdn.weread.qq.com/skills/weread-… 安装 skill

最近在做我的第一个产品，我发现开源的组件/设计没有一个能达到我审美的， 最终选择的方法还是在网上到处找设计师的作品找灵感，还真发现了一个不错的网站，分享给大家， 在这个网站里面搜索各种需要的组件都有非常棒的设计。 layers.to

superpowers 居然还有个中文版，狂揽 2.7k star，只能说6。。 github.com/jnMetaCode/sup…

baoyu-skills 新加了一个 Skill： 微信群聊总结 Skill：github.com/JimLiu/baoyu-s… 依赖于 wx-cli：github.com/jackwener/wx-c… 如何配置使用 wx-cli 请看项目文档，无法提供帮助。另外目前只是借助其读取数据，其他没任何关系。 Claude Code + Claude Opus 4.6 效果最佳

Fun interactive science app ideas | Part 3 Played around with generating 3D biological structures and made an app to explore them interactively UI Design GPT Images 2 Code Gemini 3.1 Pro More demos ↓

今天又搞了一个小红书爆款复刻的Agent，用时半小时，不说很完美，那也是完美。 1、先通过抓取爆款的内容（使用了云抓取Apify）里面的点赞，评论内容按不同内容分类，如需求，差评等，收藏，爆款量，图片及文字内容等数据； 2、拿到数据从内容，标题，图片设计，互动，时间等维护度全方向分析为什么会爆； 3、分析完成后，按这些结果数据，给我复刻出3-5个爆款内容，给给出他们的内容优势； 4、然后再给出对应的运营策略。

豆包输入法 Mac 版正式发布了，最强大免费的语音输入法。shurufa.doubao.com/pc

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

今天群里面讨论怎么样学习 Harness，Harness 工程我学习这两个： 1. github.com/walkinglabs/le… 通过这个了解每一个 Harness 的核心机制 2. github.com/badlogic/pi-mo… 学习这个框架的各个模块设计实现，不懂的就让 AI 去解读实现逻辑

We've published our internal manual for building agent skills. Skills require a new way of thinking for developers. research.perplexity.ai/articles/desig…

卧靠，这个好棒啊。 GPT image 2 + Gemini 3.1 pro生成的3D生物结构页面 有利于AI教育，我要复刻一下～

Vibe Code Application 3d Generation and Photo

I gave Codex one idea: A screen-time app for kids that doesn’t feel like a punishment. Then it helped turn that idea into Peekaboo, a gentle mobile app built around a tiny purple character with a sprout on its head. 🌱 The workflow was wild: 🎨 GPT Image 2.0 shaped the cozy visual world, mascot poses, sticker rewards, and app-store-style mockups 🧠 GPT-5.5 helped design the product logic: timers, breaks, rewards, parent moments, and kid-friendly microcopy 📱 Codex pulled it together into an interactive mobile app prototype with real screens, transitions, animations, and state Prompt below 👇

这个 html-in-canvas和 Three.js 做的动画太炫了 html-in-canvas 允许开发者将真实的、可交互的 HTML 和 CSS 直接渲染到 <canvas>（包括 2D、WebGL 和 WebGPU）中。

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons: 1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing. 2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM". The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc. 3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc. I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3). The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to... Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.

iOS simulator directly in Codex!

现在连教学视频都不用手搓了么...... Codex+HyperFrames就能完成所有教学视频制作的工作

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

发现一个很好用的视频下载工具。 支持 YouTube、TikTok、Instagram、Bilibili 等多个主流平台， 可直接解析并下载无水印视频。 除了单条下载， 还支持批量解析、音视频合并、图片解析， 实用性很强。 downloadhd.net