林家圩子

发现这个世界,过好每一天

[林家圩子 @linxin]

Shanghai Station

[林家圩子 @linxin]

早，上海

[John Ternus @johnternus]

iPhone Duo
iPhone 18 Pro and iPhone 18 Pro Max
Apple Watch Series 12 and Apple Watch Ultra 4
AirPods 5

… and Joz

[spect @spectnfa]

You're not using Obsidian wrong. You're just missing the one folder that makes Claude actually fast against your notes.

Right now every question you ask reads your whole vault. 2,000 notes, hundreds of thousands of tokens, just to answer one thing. That's not a second brain, that's a pile you taught Claude to search blind.

A graph fixes this. One router, one index, nodes split by idea, edges that point where they need to. Claude reads 2-3 files instead of 2,000. Answers back in under a second, bill drops with it.

Wrote out the full 11-step system, from raw vault to working graph 👇

[unicode @unicodef1wn]

Your Obsidian vault burns 300,000 tokens to answer one question. A graph reads 3 files and answers in under a second

Ask AI one question in a flat vault and it reads every note. 2,000 files, hundreds of thousands of tokens, for one answer. Slow, expensive, still grabs the wrong file half the time.

A second brain is only as good as the graph underneath it, not the vault.

This breaks down the 11-step build:

router > index > nodes > edges, and the logic that lets Fable 5 open 2-3 files instead of the whole folder.

The result from one real build: cost drops sharply, answers come back faster on almost every question.

The graph view everyone screenshots is a poster. The index is the engine.

Save this before you rebuild your vault from scratch 👇

[林家圩子 @linxin]

千岛湖大桥

[Andrew Ng @AndrewYNg]

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.

Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.

The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!

Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.

The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.

When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.

AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.

External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.

With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!

I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).

[Original text: The Batch]

[Luna @LunaAI519]

此文喂给 codex 或者 cc，小白直接起飞！

[林家圩子 @linxin]

古猗园

[Vaishnavi @_vmlops]

MICROSOFT OPEN-SOURCED A PII DETECTION SDK

presidio detects and anonymizes sensitive data before it ever touches your model

the problem is real: names, emails, SSNs, credit cards, medical records all flowing through LLM pipelines unfiltered

presidio stops that

▫️ detects PII in text, images, and structured data
▫️ redacts, masks, or anonymizes before it hits the model
▫️ supports NLP, regex, rule-based, and transformer detection
▫️ runs on Python, PySpark, Docker, and Kubernetes
▫️ even handles DICOM medical images

in an era of GDPR, HIPAA, and AI compliance audits, this is infrastructure not optional

https://t.co/pcEkm4mMt7

[0xMarioNawfal @RoundtableSpace]

TOP FIVE GITHUB REPOSITORIES THIS WEEK

* ANDREJ-KARPATHY-SKILLS:
https://t.co/olDWqvuOUd

* HERMES-AGENT:
https://t.co/vE5UXyNY9U

* CLAUDE-MEM:
https://t.co/pAt8PQBOix

* EVOLVER:
https://t.co/qCzQihpooG

* GENERIC AGENT:
https://t.co/q1ziSnstXF

[林家圩子 @linxin]

海口喜来登

[王大锤 @boniusex]

https://t.co/iolyRhqhVe

[Sac @Saccc_c]

这是我见过最好的Claude Code+Obsidian的教学视频。

花一个小时看完，你将学会用 Obsidian 打造第二大脑——让 AI 记住你所有的想法，帮你挖掘规律、生成创意、落地执行。