Nathan

A gamer, a music lover

[Nathan @NathanZhong]

@Khazix0918 Fable 5还是unavailable

[Nathan @NathanZhong]

@op7418 支持你，声援一下！

[Nathan @NathanZhong]

香蕉已经不行了……

[Nathan @NathanZhong]

@nanshanjukr 宰客

[Nathan @NathanZhong]

@nanshanjukr 太认同了，obsidian是我用过最讨厌最不知所云的东西了。

[Nathan @NathanZhong]

👍

[宝玉 @dotey]

原推这个提示词风格很好看👍

----

一张极简风格插画，画面主体是【主体/物体】。使用干净纤细的线条描绘轮廓与结构，整体以黑白或低饱和色为主，只在局部加入少量鲜明色彩作为视觉重点。画面有大量留白，构图精致克制，现代杂志编辑插画风格，优雅、简洁、高级。不要复杂背景，不要写实摄影，不要厚重阴影，不要过多装饰。

----

主体/物体：一只安静坐着的猫

[Nathan @NathanZhong]

这是把知识工作拆成一条可自动运转的流水线，把“读—想—写—改—复用”从一次性对话，变成一个可持续迭代的知识仓库（raw → compiled wiki → Q&A/产出 → 回写 → 体检）。LLM 真正擅长的是“维护结构化语义层”（索引、摘要、链接、缺口、冲突）。我这就在我的Notion里加一层，概念卡片。

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Nathan @NathanZhong]

@wuhonganyyds @akokoi1 能用了，谢谢

[Nathan @NathanZhong]

@wuhonganyyds @akokoi1 太感谢您了！！！

[Nathan @NathanZhong]

@dotey 我的intel芯片mac到现在也不能用cowork，了；另外，cc的skill居然在客户端不能用。

[Nathan @NathanZhong]

赞👍

[VoxCat @VoxcatAI]

这种画风真的有无限可能！✨

尝试了这种极粗描边+赛璐珞平涂的“美式Q版”风格👇

(比例: )，[详细内容]。极具辨识度的2D扁平卡通插画风格，极粗的黑色轮廓线描边，手绘矢量感，Q版可爱人物造型，赛璐珞平涂上色（大色块，无渐变），高对比度配色。纯粹的插画作品，无任何游戏UI界面。

[Nathan @NathanZhong]

@yiko880509 @servasyy_ai 你用的这张参考图严格上就不算无骨画，工笔还是挺明显

[Nathan @NathanZhong]

@LZhou15365 👍

[Nathan @NathanZhong]

非常牛👍配上Opus 4.5，把一些支离破碎的组织沿革，图解得清清楚楚。

[Wang Shuyi @wshuyi]

skill 发布链接： https://t.co/ckXq3AfGfZ

[Nathan @NathanZhong]

@cc202201 @vista8 事实上Gemini也支持skill，把skill发给Gemini就能用。

[Nathan @NathanZhong]

@dotey 说句公道话，宝玉是授人以渔的教育家，始终以工程化的视角在AI前沿授业、解惑。我想批评者针对的是那些从不思考、只当二传手的人吧。

[Nathan @NathanZhong]

https://t.co/uF0cFzHdsA

现代犬种近一半的身体多样性早在石器时代中期（约1.1万年前）就已经存在，而不仅仅是维多利亚时代品种选育的结果。

从凶猛的狼到吉娃娃，这段“变身”旅程比我们想象的要漫长得多！🦴✨

[Nathan @NathanZhong]

A very good idea！

[Ethan Mollick @emollick]

Surprisingly good for the first try.

Nano banana pro: "create a map of the US where every state is made out of its most famous food (the states should actually look like they are made of the food, not a picture of the food). Check carefully to make sure each state is right."

[Nathan @NathanZhong]

还有哪些？

[宝玉 @dotey]

🍌 nano banana pro prompt (with gemini)

Dynamically generate a current weather card based on a given city name.

--- prompt ---

Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling.

The scene features soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadow effects. Weather elements are creatively integrated into the urban architecture, establishing a dynamic interaction between the city's landscape and atmospheric conditions, creating an immersive weather ambiance.

Use a clean, unified composition with minimalistic aesthetics and a soft, solid-colored background that highlights the main content. The overall visual style is fresh and soothing.

Display a prominent weather icon at the top-center, with the date (x-small text) and temperature range (medium text) beneath it. The city name (large text) is positioned directly above the weather icon. The weather information has no background and can subtly overlap with the buildings.

The text should match the input city's native language.
Please retrieve current weather conditions for the specified city before rendering.

City name:【上海】