Loading video...

Video Failed to Load

Go Home

Still baffled as to why people are sleeping on this. Implementing this strategy is what allowed me to bump my monthly earnings to $13,000 a year ago A simple concept shared by OpenAI co-founder Andrej Karpathy recently exploded to 21 million views. Stop treating AI as just a coding...

24,597 views • 2 months ago •via X (Twitter)

47 Comments

emelu's profile picture
emelu2 months ago

claude is basically your assistant

Bober_smart's profile picture
Bober_smart2 months ago

Yes, a personal assistant

Hussain Hashim | Building SundayBack's profile picture
Hussain Hashim | Building SundayBack2 months ago

@Bober_smart right? it's crazy how many people overlook this. i've noticed even small tweaks in AI strategy can make a huge difference in earnings. what's the strategy you're using?

Bober_smart's profile picture
Bober_smart2 months ago

Many have not yet realized that a new era has arrived

Hussain Hashim | Building SundayBack's profile picture
Hussain Hashim | Building SundayBack2 months ago

@Bober_smart totally agree, the pace of change is wild. what's been the biggest surprise for you?

Moysha's profile picture
Moysha2 months ago

The real advantage is not the model, it's the system around it

Bober_smart's profile picture
Bober_smart2 months ago

The system indeed plays a very important role in this chain

Amsterdam's profile picture
Amsterdam2 months ago

Thanks, my friend. It looks amazing

Bober_smart's profile picture
Bober_smart2 months ago

🤝bro

MAX's profile picture
MAX2 months ago

This is a much better use of AI than just coding.

Bober_smart's profile picture
Bober_smart2 months ago

Yes, that works much better

shmidt's profile picture
shmidt2 months ago

very cute concept

Bober_smart's profile picture
Bober_smart2 months ago

I'm glad you liked it, my brother

Nitesh's profile picture
Nitesh2 months ago

this second-brain setup is seriously underrated

Bober_smart's profile picture
Bober_smart2 months ago

This is actually alpha now

pulmencr's profile picture
pulmencr2 months ago

Once the knowledge base starts compounding, going back to an empty chat feels pretty primitive

Bober_smart's profile picture
Bober_smart2 months ago

Yes, development is a key goal

Gipp 🦅's profile picture
Gipp 🦅2 months ago

is there any lag when searching your wiki after feeding in a ton of new pdfs?

Bober_smart's profile picture
Bober_smart2 months ago

I didn't encounter any glitches

MopOzeu's profile picture
MopOzeu2 months ago

The short guide helps a lot

Bober_smart's profile picture
Bober_smart2 months ago

I am happy to help as many people as possible

me_cool_off's profile picture
me_cool_off2 months ago

Karpaty is a genius

Bober_smart's profile picture
Bober_smart2 months ago

True True

EagleVision's profile picture
EagleVision2 months ago

I can set this up in 5 minutes too?

Bober_smart's profile picture
Bober_smart2 months ago

You can set this up while you drink your coffee

Dekos's profile picture
Dekos2 months ago

Really cool strategy if it brings in that kind of money

Bober_smart's profile picture
Bober_smart2 months ago

Yes, that works perfectly

nofad's profile picture
nofad2 months ago

5 min setup and then you just drop files in. staring at a blank chat every day is so slow after that

Bober_smart's profile picture
Bober_smart2 months ago

Set it up once and forget about it

Sujoun🍌.eth🦍's profile picture
Sujoun🍌.eth🦍2 months ago

Brother am really need 1 key buyer am also per day 200_300 sell Claude Api key please really need 1 buyer

Bober_smart's profile picture
Bober_smart2 months ago

I'm sure you'll find it soon

Sujoun🍌.eth🦍's profile picture
Sujoun🍌.eth🦍2 months ago

Today scamed 19 keys

EugBass's profile picture
EugBass2 months ago

time to develop a third brain:)

MAIL's profile picture
MAIL2 months ago

best video i came across today. your strategy is alpha

ELG's profile picture
ELG2 months ago

Search and query your entire accumulated database whenever you want

Tony Tong | Founder | Ancient Systems x AI's profile picture
Tony Tong | Founder | Ancient Systems x AI2 months ago

A wiki that compounds still runs on whatever state you were in when you fed it. I wrote in 2017 that success means operating from an elevated state daily, decisions made from love, not whatever reactive mood shows up first. Feed it garbage input and it compounds that instead.

Biti8's profile picture
Biti82 months ago

Claude 💪

安叫兽|Bird🕊️ 🔶 BNB's profile picture
安叫兽|Bird🕊️ 🔶 BNB2 months ago

流程具体怎么跑的没说,光看收入数字有点悬

ih8y's profile picture
ih8y2 months ago

my brain is about to become a supercomputer

Insomnia's profile picture
Insomnia2 months ago

bro how you made it?

Kevinllll's profile picture
Kevinllll2 months ago

three folders works because raw stays raw. the wiki gets worse fast if the source disappears.

Ridark's profile picture
Ridark2 months ago

You have a unique terminal with an interesting approach, how did you actually make it look like this?

hitu's profile picture
hitu2 months ago

bumping earnings takes more

DeepRead.com's profile picture
DeepRead.com2 months ago

When you drop new material in, does Claude actually read the existing wiki to make connections, or does the compounding happen through your own linking over time? We built around that same question for Kindle highlights. A book opens as a shape you move through, chapter structure intact, because stripping the hierarchy turns a compounding argument into a pile of sentences.

360-Year Old Pensioner's profile picture
360-Year Old Pensioner2 months ago

Because it involves 30 hours of sitting down and figuring this fucking shit out and everybody has 10,000 fucking demands on their time. Also, obsidian is 96 bucks to get it to do that. It's a note app. It's a really neat note app, but I can also remember the notes that I wrote. I have a brain in my head that already associates everything for me.

FlowOps Daily's profile picture
FlowOps Daily2 months ago

Second brain with OpenAI makes the demo feel polished without overexplaining it.

vvtentt's profile picture
vvtentt2 months ago

Why did I go to bed so early yesterday? And didn't manage to catch this?

Related Videos

I genuinely don't understand why everyone isn't using this yet With the help of this concept, my business reached an income of $13,000 per month Andrej Karpathy noted: "The primary regret among engineers in my field right now is every AI conversation they failed to save. In 10 years, the people who started archiving in 2024 will leave the rest of us in the dust" co-founder of OpenAI, generated 25M views around a single concept: stop using AI just to code, and start using it to construct a second brain that remembers every article, PDF, transcript, and chat you have ever provided You simply direct Claude Code to a folder, throw any file into it, and Claude scans the content, connects it to existing records, and builds a living wiki. Your personal knowledge finally stacks up like compound interest instead of slipping away every weekend The stack: > Brew install obsidian⁠, ⁠mkdir ~/vault⁠, ⁠cd ~/vault⁠ > Launch claude inside that directory and enter: "init a knowledge vault with CLAUDE.md as the rules, /raw for sources, /wiki for your pages" > Place any file into ⁠/raw⁠ (a YouTube transcript, meeting notes, a 400-page PDF, or a tweet screenshot) and enter "ingest" > Claude constructs a wiki page, links it to 5 existing documents automatically, and updates ⁠CLAUDE.md⁠ with any fresh patterns it spots in your thinking style > Never launch a blank Claude chat window again. Every prompt runs through your vault, and every reply cites your own materials with dates and links It takes 5 minutes to set up, letting your knowledge compound from that night onward The harsh truth most people will scroll past: in 10 years, the engineers who adopted this in 2024 will recall every book, podcast, and meeting with solid proof. You will remember virtually nothing. Karpathy has already made his decision, and you are still falling behind Check the article below for the complete step-by-step walkthrough Save this to your bookmarks before you waste another Monday

Bober_smart

16,519 views • 15 days ago

this is f*cking insane. andrej karpathy: "the biggest regret of every engineer in my field right now is every AI conversation they never saved, and in 10 years the ones who started saving in 2024 will be running circles around the rest of us" andrej karpathy, co-founder of openai, pulled 16M views on one idea: stop using AI to write code, use it to build a second brain that remembers every article, pdf, transcript and conversation you ever fed it you point claude code at a folder, drop anything into it, and claude reads it, cross-links it with everything already there, and writes it into a living wiki. your knowledge finally compounds instead of leaking out of your head every friday the stack: → brew install obsidian, mkdir ~/vault, cd ~/vault → run claude in that folder and type "init a knowledge vault with CLAUDE.md as the rules, /raw for sources, /wiki for your pages" → drop any file into /raw (youtube transcript, meeting notes, 400-page pdf, screenshot of a tweet) and type "ingest" → claude writes a wiki page, links it to 5 existing ones automatically, updates CLAUDE.md with any new pattern it noticed about how you think → never open a blank claude chat again. every question goes through the vault, every answer cites your own sources with dates and links 5 minutes to set up. compounding knowledge from that evening forward the ugly part most will scroll past: in 10 years the engineers who started this in 2024 will remember every book, every podcast, every meeting with receipts. you will remember none of them. karpathy already picked which side he is on and you are still not on his full step-by-step is in the article below bookmark this before you waste another monday

mojesko

467,339 views • 16 days ago

I still don’t understand why people keep building a Claude second brain by hand when these 10 repos already built the whole system They turn your Claude sessions into a wiki, let Claude read and write your vault from your phone, and one of them comes straight from Obsidian’s own CEO 01 llm-wiki → your Claude Code and Codex sessions become a searchable wiki, with an MCP server to query it 02 llm-wiki-claude-skill → one skill file teaches Claude to ingest sources, answer from them, lint the wiki and compile it into clean pages 03 obsidian-skills → Obsidian’s own CEO teaches Claude how Obsidian really works 04 llm-wiki → a Claude Code plugin with init, ingest, compile, query and lint, where every change is committed to git 05 obsidian-dev-second-brain → your tickets, sprints and project docs live in the vault as notes, and Claude keeps them in sync with the code 06 obsidian-mcp-server → 14 tools to read, write, search and surgically edit notes, tags and frontmatter 07 mcpvault → safe vault access with a read-only mode, and Obsidian doesn’t even need to be running 08 obsidian-claude-code-mcp → connect Claude Code to your open vault with one /ide command 09 obsidian-web-mcp → reach your vault from your phone or any MCP client, with OAuth and a Cloudflare Tunnel 10 obsidian-mcp → a git-backed vault with 18 tools, running locally or on AWS Lambda Nobody is going to build your second brain for you, and every chat you close without one is knowledge thrown away. Bookmark this, pick one repo from 01 to 05 and ingest your first source tonight. A month from now you have a wiki, and everyone who skipped it is still opening a blank chat.

Ryven

10,722 views • 14 days ago

I still don't get why people bother creating a second brain for Claude from scratch when these 10 repositories already provide complete systems They process your sources, organize them into a wiki, verify every single claim, and one of them even operates entirely on your personal machine 1. obsidian-skills-> rightarrow The CEO of Obsidian personally shows Claude the inner workings of Obsidian 2. claude-obsidian-> rightarrow Simply drop any source in, and Claude will read, link, and file it into a unified, connected graph of standard Markdown files that you control 3. obsidian-second-brain-> rightarrow Claude Code retains memory of you across different sessions, featuring 48 commands operating entirely within your Obsidian vault 4. karpathy-llm-wiki-> rightarrow Features a single installation line, followed by ingestion, querying with citations, and linting—all usable within Claude Code, Cursor, Codex, or OpenCode 5. second-brain-> rightarrow Takes raw sources as input and outputs linked wiki pages for easy browsing inside Obsidian 6. second-brain-os-> rightarrow The complete package: includes a 77-page guide, a starter vault, 18 skills, 72 commands, and 6 subagents (four of which are read-only) 7. llm-wiki-> rightarrow Utilizes a two-tier memory system: 10 to 20 rules loaded by Claude during every session, alongside 50 to 200 wiki pages fetched strictly when needed 8. vouch-> rightarrow Agents suggest modifications for your approval, where any claim lacking an explicit source is treated as an error 9. ai-second-brain-> rightarrow Transforms your historical interactions from ChatGPT and Claude into a linked Obsidian vault, which then becomes a wiki 10. LLM_Wiki_SecondBrain-> rightarrow Runs the entire pipeline locally without any cloud APIs (recommended 32 GB of RAM) I recommend adding this to bookmarks and never doing this manually again

Bober_smart

39,281 views • 16 days ago