สาระยามเช้าจาก Microsoft Learn 🐱☀️
🌊 Data Lake: พื้นที่เก็บข้อมูลขนาดใหญ่สำหรับข้อมูลดิบทุกประเภท เช่น ไฟล์ Excel, รูปภาพ, Log, เอกสาร และข้อมูลที่ยังไม่ได้จัดระเบียบ
🏢 Data Warehouse: คลังข้อมูลที่มีการจัดโครงสร้างอย่างเป็นระเบียบ ข้อมูลถูกทำความสะอาดและจัดเก็บเป็นตาราง พร้อมสำหรับการวิเคราะห์และสร้างรายงานได้อย่างรวดเร็ว
🛶 Data Lakehouse: แนวคิดที่รวมข้อดีของทั้ง Data Lake และ Data Warehouse เข้าด้วยกัน สามารถเก็บข้อมูลดิบได้เหมือน Data Lake และจัดการข้อมูลให้พร้อมสำหรับการค้นหา วิเคราะห์ และ Query ได้อย่างมีประสิทธิภาพเหมือน Data Warehouse
The EU downsized plans for data centers to support AI, outlining a call for tenders that includes smaller-scale facilities than originally envisioned https://t.co/lCzqKX9WQR
Claude Code creator:
"100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too.
The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops"
in this interview he breaks down exactly how a system changes everything:
- the memory and context features that turn Claude into a second brain
- the knowledge architecture most users don't know Claude can build
- the integration layer that connects Claude to your actual workflow
- why typing one question at a time is the most expensive way to use Claude
if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
full guide in the article below
Karpathy said something you'll regret ignoring:
"Remove yourself as the bottleneck. Maximize your leverage. Put in very few tokens, and a huge amount of stuff happens on your behalf."
Loop engineering is the exact thing that does that.
In a hand-run session, the operator handles two things:
- deciding what the agent runs next
- and checking its output before the next step
Both are manual, and both decide how far the agent gets on its own without the operator.
Loop engineering moves both steps into the system.
A core operating structure surrounds the loop, and the diagram below depicts it.
- A schedule decides what to run
- Loop is the maker that produces the work
- A separate checker agent grades the output
- A file on disk holds the state they both read.
The loop runs until either done, max iterations, or an exhausted budget.
Here are some practical engineering considerations:
1) A model grading its own output justifies what it already did instead of catching where it failed.
That's why a separate checker's findings return to the maker as the next instruction. And the cycle repeats until the checker finds nothing left to fix.
2) A loop with no stop condition burns tokens, and the cost climbs fast once sub-agents and long runs add up.
That's why the exit must be set before the loop runs, not while it is running.
A simple exit could be:
↳ fix only the major issues, run one final pass, and stop after two loops, with "all tests pass and lint clean" as the rule that ends it.
3) State has to live on disk, not in context.
The model forgets everything between runs, so an MD file or a knowledge graph holds what is done and what is still open.
Each run reads it and writes back to it, which lets a loop pick up again after days.
4) The lower the verification bar, the safer the loop.
Boring, repetitive checks like a stale version string or a missing test are trivial to verify, so a loop runs them with little risk while the operator is away.
Judgment-heavy work is loopable too, but only as far as the checker can confirm the result.
Let's look at how an unattended loop fails in two ways.
1) It reports done when nothing is actually verified.
The separate checker exists to prevent it, but it merges code faster than anyone reads it, so over weeks, the team stops understanding its own codebase while every check stays green.
Green tests say the code passed the tests, not that anyone knows what shipped. Someone still has to read what the loop merges.
2) The checker keeps a running loop honest, but it only catches failures inside a run.
The harness around the loop, like the prompts, tools, and checks wrapped around the model, still drifts and breaks in production as models change.
That repair loop is usually run by hand based on observability traces.
My co-founder wrote a detailed walkthrough (with code) on making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it cannot recur.
Read it below.
Claude has 3 levels of automation.
Here's how to (actually) set each up:
Level 1: Skills in Claude Chat
On-demand. You start it.
Step 1: Connect your tools in Settings → Connectors.
Step 2: Describe the workflow. Claude writes the skill.
Step 3: Type one word. Get a finished output.
Level 2: Scheduled Tasks in Cowork
On a timer. Runs unprompted.
Step 1: Tell Cowork which skill to run and when.
Step 2: Answer a few questions. The task goes live.
Step 3: It runs itself. No terminal or code needed.
Level 3: Claude Code
Runs while you sleep.
Step 1: Install with one terminal command.
Step 2: Type /schedule and pick a time.
Step 3: Manage every run from the browser.
The decision rule:
- You start it → Skills in Claude Chat
- Timer-based → Scheduled Tasks in Cowork
- Laptop closed → Claude Code
Full setup guide
https://t.co/kQZZmboHIq
Repost ♻️ to help someone in your network.
P.S. Which level are you actually using right now?
Claude Code creator:
"50% of my engineering is done from my phone. I have a hundred agents running.
I also use /loop a lot. I don’t write the source code - I talk to an agent & it writes the code for me.
in 20-minute talk, creators of Claude Code reveal the best life hack they’ve discovered while using it.
Worth more than a $500 vibe-coding course
Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
this is one of the best workflows I've seen in a long time
in this video she breaks down exactly how most people are using Claude:
- the 14% you lose to CLAUDE.md before typing a word
- the automation workflows most users don't know exist
- the daily task pipelines that run without touching the keyboard
- the daily workflows Anthropic's own engineers automated first
if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
the guide is in the article below