Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

An asian guy has discovered a method to learn anything ten times faster using AI! It just involves the Claude + Obsidian. Most people learn the slow way: read, forget, re-read, forget again. His flip: use Claude to turn anything you're learning into small, connected notes. Use Obsidian to...

933,618 Aufrufe • vor 3 Monaten •via X (Twitter)

33 Kommentare

Profilbild von Hamza Khalid
Hamza Khalidvor 3 Monaten

I built a complete guide on how to build your second brain using Obsidian and claude in my newsletter. Go and check it out:

Profilbild von Rahul
Rahulvor 3 Monaten

I don't know about other things But wow, animations looks amazing 😀

Profilbild von Sajid AI
Sajid AIvor 3 Monaten

The real advantage isn’t speed it’s structured recall, where notes become a network instead of isolated fragments.

Profilbild von Madni Aghadi
Madni Aghadivor 3 Monaten

this is actually one of the smartest ways to learn

Profilbild von café
cafévor 3 Monaten

but how are you supposed to learn with this system exactly? what do I do with all these atomic notes in a practical way? I'm not saying that isn't good i really jus can't figure it out. 😅

Profilbild von Ty Udy
Ty Udyvor 3 Monaten

“An Asian guy” lol

Profilbild von Gill
Gillvor 3 Monaten

Setting up Obsidian links manually takes way too much time to be worth it.

Profilbild von Arslan Iqbal
Arslan Iqbalvor 3 Monaten

The real advantage isn't learning faster. It's remembering what you learn months later.

Profilbild von Muhammad Ali
Muhammad Alivor 3 Monaten

@AunySillyMe

Profilbild von Axonlotl
Axonlotlvor 3 Monaten

Splitting notes and linking them (Obsidian-style) helps retrieval, but it’s still passive structure-building. You end up optimizing storage, not necessarily understanding or decision-making. The real bottleneck in learning isn’t note granularity - it’s how you structure relationships while you’re thinking, not after the fact. That’s where mindmaps outperform linear note graphs: You force hierarchy + causality upfront instead of discovering it later through links You see structural gaps immediately (missing branches, weak connections) You can reorganize knowledge visually in real time instead of retrofitting connections after accumulation It reduces “false complexity” where everything is linked to everything but nothing is prioritized If you actually want faster learning, building your own structured knowledge maps while processing input beats post-hoc note linking. This is exactly what tools like Axonlotl are designed for: dynamic, evolving concept graphs where structure is not an afterthought but the primary learning mechanism. Obsidian is good for archival memory. Mindmaps are better for active cognition. interactive version @ #Axonlotl @CreateYourOwn

Profilbild von Aaron Chakraborty
Aaron Chakrabortyvor 3 Monaten

But the slow way is around for a reason like it helps us store and retain better for long term

Profilbild von Hussain Hashim | Building SundayBack
Hussain Hashim | Building SundayBackvor 3 Monaten

@humzaakhalid that's wild, been struggling to keep info in my head. def trying this with Claude and Obsidian, thanks for the tip!

Profilbild von Johnny Suede
Johnny Suedevor 3 Monaten

The real unlock is not faster note taking. It is turning learning into usable context: source, summary, open questions, and next action in one place so the agent can help you do something with it later.

Profilbild von Graaffy
Graaffyvor 3 Monaten

why a clickbait in all these articles is an obsidian cloud with nodes moving around? does it still impress people?

Profilbild von Harry Tandy
Harry Tandyvor 3 Monaten

obsidian and claude are the ultimate power couple

Profilbild von Steven Cheng
Steven Chengvor 3 Monaten

Atomic notes are great for debugging, just keep the links tight.

Profilbild von Greg Berry
Greg Berryvor 3 Monaten

I know it’s engagebait but in case it’s not, why does it matter if the guy is Asian?

Profilbild von Truntr
Truntrvor 3 Monaten

Learning is not faster from a new shell. You learn faster from forcing yourself to apply knowledge in production every day - writing code, an article, or an answer in X.

Profilbild von Crekolive
Crekolivevor 3 Monaten

okay and? the method isn't even new

Profilbild von Rufus.eth
Rufus.ethvor 3 Monaten

This looks damn hypnotizing😍

Profilbild von Trend Stack
Trend Stackvor 3 Monaten

lets try it out

Profilbild von Virgin Mary Society
Virgin Mary Societyvor 3 Monaten

This is s NOT for "learning" as stated in the post. It is for insights and 2nd brain. I've read the article.

Profilbild von John Vandivier
John Vandiviervor 3 Monaten

Bullshit

Profilbild von Mahendra Kumawat
Mahendra Kumawatvor 3 Monaten

Game-changing approach! Using Claude and Obsidian to break down learning into atomic notes is pure genius. Can't wait to dive into your 7-day guide

Profilbild von Ryan Kellogg
Ryan Kelloggvor 3 Monaten

“An asian guy” is a wild open.

Profilbild von Drake
Drakevor 3 Monaten

started doing this last month, results show way faster than six months

Profilbild von FW
FWvor 3 Monaten

This raises the question, what does it even mean to learn something? Isn't the only knowledge you really need, just knowing where and how to find answers quickly and effectively? Storing it somewhere is just a form of cashing.

Profilbild von Pepstein
Pepsteinvor 3 Monaten

Asian you say @JoeyF07

Profilbild von Nelly;
Nelly;vor 3 Monaten

Claude breaking things down is such a good move

Profilbild von Andy Brown
Andy Brownvor 3 Monaten

Kiloliter ok llll Ll

Profilbild von Alisher
Alishervor 3 Monaten

You can go further. Check it out

Profilbild von VALIX
VALIXvor 3 Monaten

Real alpha. Thanks for sharing

Profilbild von Luke Jackson
Luke Jacksonvor 3 Monaten

Sönke Ahrens [How to Take Smart Notes (2017)] + Niklas Luhmann [Zettelkasten] Synthesis Layers Fleeting note (L0) Literature note (L1) Permanent note (L2) Map of Content (L3) Meta-synthesis (L4)

Ähnliche Videos

Obsidian + Claude Code is how Andrej Karpathy turns 15 years of notes into a brain that works while he sleeps. The method behind it costs $0 and takes 5 minutes a day and it outlived every productivity app since 2011. Every idea, link, and half-thought gets appended to the top of a single note, with no sorting, no folders, no tags. Once a week he scrolls through, and anything that still matters gets copied back to the top. Weak ideas sink. Strong ideas resurface 5, 10, 20 times and by the 20th pass your brain has already wired them into everything else you know. Repetition as a filter. That's the whole system. Now the 2026 upgrade almost nobody is running: Drop that note into an Obsidian vault and open the folder with Claude Code not the chat app, the terminal agent that reads files. 3 commands change everything: read my last 30 days of notes and find the 3 ideas I keep circling without acting on link every note mentioning this project into a CLAUDE.md of what I actually believe about it draft this week's post from the idea that resurfaced most Claude Code doesn't search your vault it walks it, follows the wikilinks, and hands you the patterns you were too close to see. Karpathy method filters the signal, Obsidian stores it, Claude Code compounds it. One is a habit, one is a folder, one is $20 a month together they're the closest thing to a second brain that thinks back. Most people collect notes for 10 years and never read them once. His notes read him.

Spike 1%

12,467 Aufrufe • vor 2 Monaten

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,124 Aufrufe • vor 3 Monaten