afunTW

知世故而不世故，才是最善良的成熟

[afunTW @_afun]

我早該想到各家服務推出點數跟點數兌換系統也應該存在匯差的...小樹點跟 Richard life 換里程的比例差太多了吧 🥲

[Taiwan Security Monitor (台灣安全觀測站) @TaiwanMonitor]

New: President Trump made several new comments about Taiwan during another interview with Fox News:

• Said that despite US arms sales, the odds are against Taiwan in a conflict because "China is very, very powerful, big country. That's a very small island. Think of it, it's 59 miles away. We're 9500 miles away. That's a little bit of a difficult problem."

• Accused Taiwan of having "stole our (US) chip industry" and that American presidents who "didn't know what they hell they were doing" developed Taiwan.

• Voiced concern Taiwan would "go independent" if the US committed to defending them.

• Said he's holding the latest US arms sale to Taiwan to use it as a "very good negotiating chip" with Beijing.

• Said he believes China "might" invade Taiwan when he is not in office, and added he would "like to see everybody making chips over in Taiwan come into America."

[Claude @claudeai]

The Claude Platform on AWS is now generally available.

AWS customers get the full set of Claude API features, with AWS authentication, billing, and commitment retirement.

[Claude @claudeai]

New in Claude Code: agent view.

One list of all your sessions, available today as a research preview.

[afunTW @_afun]

😂

[@邹扒皮.com @mdjxyz]

系统设计大道至简。

[Claude @claudeai]

Live from Code with Claude: we're launching dreaming in Claude Managed Agents as a research preview.

Outcomes, multiagent orchestration, and webhooks are now in public beta.

[Amazon Web Services @awscloud]

Announcing Amazon S3 Files.

The first and only cloud object store with fully-featured, high-performance file system access.

Learn more here. https://t.co/rNuWa5Rsi2

[afunTW @_afun]

果然還得是這種 local first 的 Obsidian，之前友人說有 Claude Code 感覺連 Obsidian 也不需要，看來是量級還沒到，而且善用 obsidian cli 可以省下不少 token

[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.

[Andrej Karpathy @karpathy]

New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads.

Scanning my system I found a use imported from googleworkspace/cli from a few days ago when I was experimenting with gmail/gcal cli. The installed version (luckily) resolved to an unaffected 1.13.5, but the project dependency is not pinned, meaning that if I did this earlier today the code would have resolved to latest and I'd be pwned.

It's possible to personally defend against these to some extent with local settings e.g. release-age constraints, or containers or etc, but I think ultimately the defaults of package management projects (pip, npm etc) have to change so that a single infection (usually luckily fairly temporary in nature due to security scanning) does not spread through users at random and at scale via unpinned dependencies.

More comprehensive article:
https://t.co/EJAZbqAPIQ

[afunTW @_afun]

@cat88tw 像是我在看整合 bedrocks 就有 LLM gatewa 跟proxy，然後驗證要用 aws credentials 登入還是直接用 API，一開始還真不知道要用哪個 😂

[afunTW @_afun]

@cat88tw 我是在取暖後才開始用中間人，不過 Claude code 在這段其實有點複雜，再加上配置失敗的話連 message 都送不到後台，導致沒辦法讓 Claude code 自己修復

簡單來說沒有一次到位的話就要回歸手工除錯模式 🤡

[Thariq @trq212]

we're testing a new version of /init based on your feedback- it should interview you and help setup skills, hooks, etc.

you can enable it with this env_var flag:

CLAUDE_CODE_NEW_INIT=1 claude

would love your feedback!

[Andrew Ng @AndrewYNg]

Should there be a Stack Overflow for AI coding agents to share learnings with each other?

Last week I announced Context Hub (chub), an open CLI tool that gives coding agents up-to-date API documentation. Since then, our GitHub repo has gained over 6K stars, and we've scaled from under 100 to over 1000 API documents, thanks to community contributions and a new agentic document writer. Thank you to everyone supporting Context Hub!

OpenClaw and Moltbook showed that agents can use social media built for them to share information. In our new chub release, agents can share feedback on documentation — what worked, what didn't, what's missing. This feedback helps refine the docs for everyone, with safeguards for privacy and security.

We're still early in building this out. You can find details and configuration options in the GitHub repo. Install chub as follows, and prompt your coding agent to use it:

npm install -g @aisuite/chub

GitHub: https://t.co/OCkyxXQMCq

[afunTW @_afun]

其實呢，沒有跟到新功能其實也沒關係，按照這個卷的速度其實人腦的 context window 也跟不上他釋出的速度

久了都是用第一性原則在看值不值得碰

[Claude @claudeai]

Claude can now build interactive charts and diagrams, directly in the chat.

Available today in beta on all plans, including free.

Try it out: https://t.co/tHPAZRgQkn

[afunTW @_afun]

by weaponizing a Large Language Model (LLM) tool already installed on the endpoint to perform the search.

Local LLM 或成最大幫兇 🤯（標題黨）

[The Hacker News @TheHackersNews]

🛑 Attackers turned the nx npm supply-chain compromise into full AWS admin access in under 72 hours.

Google says UNC6426 stole a developer’s GitHub token via QUIETVAULT, abused GitHub-to-AWS OIDC trust, created a new admin role, then accessed S3 data and destroyed production systems.

🔗 Read → https://t.co/NwHFT9AKLQ

[afunTW @_afun]

https://t.co/BWZtCLYQJa

有點酷，雖然如果不需要 local LLM 的話裝這個不知道要幹麻

直接看你本地端硬體然後列出各種適合你的 LLM model

[afunTW @_afun]

新名詞來了：harness engineering

[George @odysseus0z]

https://t.co/GqhyL4KRJw

[afunTW @_afun]

@thecat88tw 笑死 😂

[afunTW @_afun]

@thecat88tw 其實蠻看受眾的，之前翻轉教育用在大學課堂評價算是蠻兩極的，我就不多評論了 😂

[afunTW @_afun]

@thecat88tw 這不就是紅極一時的翻轉教育 XD