Ian Chan

Wine, Coffee, Birding, Running, Music, Fashion。センスは知識からはじまる。

[Ian Chan @thisisrenn]

SCANDAL TOUR 2024 LUMINOUS at 広州

今度ドレスシャツ着てライブに行こうかなぁ

@scandal_band
#SCANDAL_LUMINOUS

[Ian Chan @thisisrenn]

@ValerieNoName If you're into custom Magic, check out this repository of Magic Set Editor styles I built: https://t.co/MHXfPO83Nj — feel free to give it a try for your custom sets or proxies.

https://t.co/9WuYKkNm7j

[Ian Chan @thisisrenn]

Magic Set Editor (MSE) 2003 Frame High Resolution Template
https://t.co/MHXfPO83Nj
Getting ready for some kitchen table Vintage Cube.

Features:
- Dual Color Hybird Artifacts
- Devoid
- Alpha Hybrid
- Extended Art

#mtg #mtgproxy

[Ian Chan @thisisrenn]

Magic Set Editor (MSE) 2003 Frame High Resolution Template
https://t.co/MHXfPO83Nj
Getting ready for some kitchen table Vintage Cube.

Features:
- Dual Color Hybird Artifacts
- Devoid
- Alpha Hybrid
- Extended Art

#mtg #mtgproxy

[Yifeng "Evan" Wang @ewind_dev]

非常激动地和大家分享，在 Fable 加持下，我终于做出了多年来设想中最极致的跨平台 UI 框架，这就是 PocketJS！

将 QuickJS 移植至内存仅 32MB 的索尼 PSP，结合标准版 SolidJS 和 Vue Vapor，配合编译期 tailwind 样式引擎，实现了 8MB 内存下 60fps 的流畅动画！

来拥抱裸金属 Modern Web 吧！

[Ian Chan @thisisrenn]

@japan_miyu_ ホンコン人じゃない？まあ、一応中国人だけど

[The Game Awards @thegameawards]

Meccha Chameleon has sold 5 million copies on Steam in 10 days.

[Cloudflare @Cloudflare]

Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds. https://t.co/o5GLomVUxb

[Ian Chan @thisisrenn]

@ValerieNoName My 2003 frame proxy.

[しふぉん | Shiho Kawahara @shiifoncake]

日立駅、朝。

[吊顶高松灯 @object_nullll]

鸽了两个周，UI 大改了，比之前好看很多，注册申请了苹果开发者，研究了很多如何签名和公证，现在终于可以面对大家了🫡

截图和功能介绍在评论区🧵

https://t.co/oBGb4SabGy

[Anita Chen @amanitahalo]

japan rail ridership map!
see how many people ride each segment of rail. includes almost all japanese rail operators.
https://t.co/GdUEjH6HcV

[渡边君 @JiaweiShen2568]

中国的一位女开发者
用ClaudeCode做了一个音乐电台Agent
起名叫Claudio
是一个24小时在线的AI电台主播
蒸馏了她十四年的歌单
从歌单、到界面交互、到审美，都很棒
Claudio的声音也很有磁性
会介绍音乐
会根据日程安排和时间选择播放什么音乐
整体非常有调性
让人看到“去APP化”、全民高定agent服务会是未来可能的方向
#ClaudeCode
#VibeCoding

[Ian Chan @thisisrenn]

@BDEgameowners That’s exactly why they call it a "master" set.

[AYi @AYi_AInotes]

这才是找工作的最高境界啊，

老哥为了自己找工作写的求职神器，

开源两天 github 直接干到 12K 星，

顺便给全行业送了个大福利，respect bro🫡🫡🫡

[nash_su - e/acc @nash_su]

继 Karpathy 大神后，YC 的 CEO @garrytan 也分享了自己的知识管理方法：
https://t.co/7iHMjfqr5e

Karpathy大神的：
https://t.co/Sxn9PR4TZ2

我将各自理论的核心架构、逻辑和概念可视化出来，方便大家看

[Andrej Karpathy @karpathy]

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.

I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:

1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable.
2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information.
3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy.
4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data.

So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :)

Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

[elvis @omarsar0]

Building a personal knowledge base for my agents is increasingly where I spend my time these days.

Like @karpathy, I also use Obsidian for my MD vaults.

What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers.

I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal.

You all get to benefit from that with the papers I feature in my timeline and on @dair_ai.

The papers are indexed using @tobi qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there.

I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip.

100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation.

But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close.

The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to.

Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them.

Work in progress. More updates soon. Back to building.

[axiaisacat @axiaisacat]

终于有人干了这件事 🔥

marknative：把 Markdown 直接渲染成 PNG/SVG，完全不需要浏览器、不需要 Chromium、不需要 DOM

以前的方案： Markdown → HTML → DOM/CSS → 浏览器截图

现在： Markdown → 自带布局引擎 → PNG Buffer（完毕）

服务端直接跑，零浏览器依赖
分页结果完全确定性，每次输出一模一样
批量渲染，速度快到飞起
三行代码搞定：

const pages = await renderMarkdown(markdown)
await writeFile('out.png', pages[0].data)

做文档生成、内容卡片、社交图片的同学，这个是真的香

地址👇

[Will Hu 🐯 @willlhhh]

仔细掰扯了下，原来阿里国际站搞了个骚动作：他们在 `/product-insights/` 这个目录下，一口气怼了将近 590 万个纯 AI 生成的页面。

最离谱的是什么？这些页面根本不是在卖 B2B 的机器设备，而是在疯狂蹭各种 C 端泛商业的长尾词。比如“史上最畅销漫画”、“怎么辨别汤坏没坏”……连页面上的作者简介和底下的评论都是 AI 捏造出来的。

这事儿有意思的地方在于，Google 刚刚在 3 月 25 号结束了最新的 Spam Update（垃圾内容算法更新）。按理说，这种“大规模内容滥用”绝对是精准打击对象。但魔幻的是，这 590 万个页面目前依然活得好好的，甚至流量还在涨。

一个 DR 92 的顶级老域名，仗着自己底子厚，直接骑在 Google 的算法底线上疯狂试探。

我实在太好奇这事儿的走向了。我已经在 Manus 上挂了个 Schedule Task，每天自动去扒 Ahrefs 和 Google 的数据，死死盯着这批页面的收录和流量变化。

我准备花30天时间，用这批连续追踪的数据，来算一笔账：
在 2026 年的今天，当内容和作者 100% 都是 AI 生成时，一个高权重网站的Google 页面收录量，页面排名，以及Traffic 之间，到底是个什么线性关系？

这可能是今年最值得拆解的 AI SEO 压力测试。

[Steve Schoger @steveschoger]

I put together a one hour video on how I've been using Claude Code as my primary design tool.

Packed with tons of 🔥 design tips.

[Google Cloud Tech @GoogleCloudTech]

https://t.co/Nhzbmwl85W