Загрузка видео...

Не удалось загрузить видео

На главную

this one page turns Obsidian + Opus 5.5 + Jev into a Karpathy-grade second brain that thinks with you 24/7 built on Karpathy's second brain stack and classic Zettelkasten the loop: > Jev reads every note in your Obsidian vault before Opus 5.5 does > Opus writes only the...

Mr_Buzzoni's profile picture

Mr. Buzzoni

28,417 subscribers

48,337 просмотров • 18 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 13

Фото профиля Argona
Argona18 дней назад

wow this page reads like a real research paper friend

Фото профиля Iron Giant
Iron Giant18 дней назад

Second brain on full autopilot

Фото профиля FAMBROjoe
FAMBROjoe18 дней назад

The step people skip is the "read every note first" part. A second brain only gets smart when the links are good... most vaults are piles, not maps. How do you handle notes that contradict each other?

Фото профиля 0xbobaa
0xbobaa18 дней назад

Karpathy wouldn't give bad advice

Фото профиля Taz.
Taz.18 дней назад

You skipped the part where it’s probably 800 times more token usage…

Фото профиля Cole👽
Cole👽18 дней назад

curious how they measured that 10x improvement

Фото профиля Kai Lennox
Kai Lennox18 дней назад

My Obsidian vault has been collecting dust for months. Maybe this is what it needs lol

Фото профиля Cody
Cody18 дней назад

Sounds like a lot of setup for notes that still won't bet themselves. What's the win rate?

Фото профиля shmidt
shmidt18 дней назад

perfect explanation

Фото профиля Fokki
Fokki18 дней назад

the loop makes sense to me

Фото профиля Phosphen
Phosphen18 дней назад

my vault compounds too, mostly unread clippings

Фото профиля taylor
taylor18 дней назад

@bot can you read this article and this post and tell me if we should add jev or a system one model into my obsidian vault so the agents on t3 (codex/claude) actually use it lol

Фото профиля Crio Songo
Crio Songo18 дней назад

This workflow makes a lot of sense. I've been using Obsidian for years, I'll try to set it up this weekend.

Похожие видео

KARPATHY JUST MADE EVERY SECOND BRAIN GURU LOOK STUPID an artist with zero tech background took her obsidian vault, plugged it into blender and claude and turned her notes into a 3d map of her entire city no zettelkasten course, no notion templates, no productivity system just obsidian graphs that became something you can actually see and navigate this is what happens when your second brain stops being a folder and starts being a living structure save this for when someone tells you obsidian is just for nerds ↓
0:44

KARPATHY JUST MADE EVERY SECOND BRAIN GURU LOOK STUPID an artist with zero tech background took her obsidian vault, plugged it into blender and claude and turned her notes into a 3d map of her entire city no zettelkasten course, no notion templates, no productivity system just obsidian graphs that became something you can actually see and navigate this is what happens when your second brain stops being a folder and starts being a living structure save this for when someone tells you obsidian is just for nerds ↓

leopardracer

81,982 просмотров • 4 месяцев назад

CLAUDE JUST TURNED OBSIDIAN INTO A BRAIN THAT NEVER FORGETS (FOR $0) Someone connected Claude straight to their Obsidian vault. Now the AI reads and writes every note they own. Every client, every idea, every project. Instant recall. Runs on Claude + Obsidian. One evening. Zero code. The numbers are insane: - Notion AI: $10/month forever - A "second brain" course: $500 to $2,000 - An assistant to organize your notes: $3,000/month - This setup: $0 - Time to build: one evening - Skill required: copy the steps The opportunity is even wilder: People sell Notion "second brain" templates for $99 to $499. You just built something better for free, and it never forgets. One free vault can hold the entire memory of your business: clients, content, SOPs, ideas. One person + Claude + Obsidian + one evening = an infinite memory that never forgets. Save and watch the clip.
13:03

CLAUDE JUST TURNED OBSIDIAN INTO A BRAIN THAT NEVER FORGETS (FOR $0) Someone connected Claude straight to their Obsidian vault. Now the AI reads and writes every note they own. Every client, every idea, every project. Instant recall. Runs on Claude + Obsidian. One evening. Zero code. The numbers are insane: - Notion AI: $10/month forever - A "second brain" course: $500 to $2,000 - An assistant to organize your notes: $3,000/month - This setup: $0 - Time to build: one evening - Skill required: copy the steps The opportunity is even wilder: People sell Notion "second brain" templates for $99 to $499. You just built something better for free, and it never forgets. One free vault can hold the entire memory of your business: clients, content, SOPs, ideas. One person + Claude + Obsidian + one evening = an infinite memory that never forgets. Save and watch the clip.

shmidt

57,347 просмотров • 4 месяцев назад

This is f*cking insane, the CEO of Y Combinator open-sourced his own second brain and most people still don’t know it exists 8 second brain repos you haven’t seen yet: -> gbrain (by garrytan) the second brain of the YC CEO, every fact keeps its source and every agent shares one memory -> llm wiki (by karpathy) the original idea file behind all of this -> ai-memory (by akitaonrails) hand the work from Claude Code to Codex without losing context, memory lives in plain markdown -> agent second brain (by smixs) send a voice note in Telegram and it lands as a linked note in your Obsidian vault -> cog second brain (by huytieu) 33 skills and 10 agents running on plain markdown, no database -> open second brain (by itechmeat) a nightly pass turns the corrections you keep repeating into rules your agent follows -> claude second brain (by jessepinkman9900) one npx command scaffolds Obsidian, Claude Code and local search -> baalda (by naveedharri) a team second brain where people and agents edit the same markdown files the CEO of Y Combinator runs his agents on this you are still digging through bookmarks
0:27

This is f*cking insane, the CEO of Y Combinator open-sourced his own second brain and most people still don’t know it exists 8 second brain repos you haven’t seen yet: -> gbrain (by garrytan) the second brain of the YC CEO, every fact keeps its source and every agent shares one memory -> llm wiki (by karpathy) the original idea file behind all of this -> ai-memory (by akitaonrails) hand the work from Claude Code to Codex without losing context, memory lives in plain markdown -> agent second brain (by smixs) send a voice note in Telegram and it lands as a linked note in your Obsidian vault -> cog second brain (by huytieu) 33 skills and 10 agents running on plain markdown, no database -> open second brain (by itechmeat) a nightly pass turns the corrections you keep repeating into rules your agent follows -> claude second brain (by jessepinkman9900) one npx command scaffolds Obsidian, Claude Code and local search -> baalda (by naveedharri) a team second brain where people and agents edit the same markdown files the CEO of Y Combinator runs his agents on this you are still digging through bookmarks

Ryven

245,037 просмотров • 1 день назад

Steal my second brain CLAUDE. md. Paste this in the root of your Obsidian vault: 1. One idea per note. 2. Keep my words. Never rewrite my opinions into yours. 3. Never delete. Archive instead. 4. Cite every note you use. 5. If my notes don't have the answer, say so. 5 lines. Opus 5.5 now runs my notes like a chief of staff. Full course with all 6 commands below. Bookmark this.
0:28

Steal my second brain CLAUDE. md. Paste this in the root of your Obsidian vault: 1. One idea per note. 2. Keep my words. Never rewrite my opinions into yours. 3. Never delete. Archive instead. 4. Cite every note you use. 5. If my notes don't have the answer, say so. 5 lines. Opus 5.5 now runs my notes like a chief of staff. Full course with all 6 commands below. Bookmark this.

CyrilXBT

14,957 просмотров • 1 месяц назад

NOTEBOOKLM + GEMINI + OBSIDIAN = AI SECOND BRAIN - NotebookLM turns all your materials into instant podcasts, briefings & study guides - Gemini thinks across your full Google stack in one go - Obsidian auto-links every insight Build the system.
13:21

NOTEBOOKLM + GEMINI + OBSIDIAN = AI SECOND BRAIN - NotebookLM turns all your materials into instant podcasts, briefings & study guides - Gemini thinks across your full Google stack in one go - Obsidian auto-links every insight Build the system.

0xMarioNawfal

67,888 просмотров • 7 месяцев назад

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,643 просмотров • 5 месяцев назад

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.
0:23

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.

Simplifying AI

68,025 просмотров • 3 месяцев назад

This is f*cking gold, the CEO of Obsidian put his own second brain on GitHub for free and people still build theirs from zero 7 free repos from the Obsidian team: -> kepano obsidian (by kepano) vault template of the Obsidian CEO himself, copy it and skip the blank page -> jsoncanvas (by obsidianmd) open canvas format, your maps stay plain files that are yours forever -> obsidian releases (by obsidianmd) community plugin and theme in one list -> obsidian sample plugin (by obsidianmd) official template, build the plugin you are missing -> 40 questions (by kepano) questions that turn your notes into a yearly review -> obsidian minimal (by kepano) clean theme so your vault stops looking like a mess -> flexoki (by kepano) color scheme he made for writing and code your second brain should never start from a blank page copy his vault and make it yours
0:27

This is f*cking gold, the CEO of Obsidian put his own second brain on GitHub for free and people still build theirs from zero 7 free repos from the Obsidian team: -> kepano obsidian (by kepano) vault template of the Obsidian CEO himself, copy it and skip the blank page -> jsoncanvas (by obsidianmd) open canvas format, your maps stay plain files that are yours forever -> obsidian releases (by obsidianmd) community plugin and theme in one list -> obsidian sample plugin (by obsidianmd) official template, build the plugin you are missing -> 40 questions (by kepano) questions that turn your notes into a yearly review -> obsidian minimal (by kepano) clean theme so your vault stops looking like a mess -> flexoki (by kepano) color scheme he made for writing and code your second brain should never start from a blank page copy his vault and make it yours

rvaniaaa

607,451 просмотров • 2 дней назад

PSYCHO CREATED A GOD-MODE SECOND BRAIN ON FABLE 5 THAT FILLS ITS OWN KNOWLEDGE GAPS WHILE YOU SLEEP. KARPATHY'S FILE STRUCTURE MAKES IT POSSIBLE. Everyone wires Claude into Obsidian, posts the graph, and stops. this guy added a third system and it quietly changes the whole game: The full build is in the article below: vault structure, the Claude wiring, the exact prompts, the skills. > Obsidian as the knowledge base, but any notes app works as long as Claude Code can see the files > Karpathy's LLM Wiki doc as the skeleton, so the vault is organized the way a model actually reads, not the way humans decorate folders > a self-learning skill on a weekly loop: scans the entire brain, finds the gaps, then researches YouTube and Google by itself to fill them Read the third one again, actually your notes only ever contain what you happened to write down, and the gap-finder breaks that ceiling: the brain starts knowing things you never told it. Most second brains know what you told them. a real one notices what you didn't. that's the difference between note-taking and compounding. one sits there. the other gets smarter every week whether you showed up or not. P.S. send the article straight to your Claude, tell it to interview you, and the brain starts filling itself tonight.
1:05

PSYCHO CREATED A GOD-MODE SECOND BRAIN ON FABLE 5 THAT FILLS ITS OWN KNOWLEDGE GAPS WHILE YOU SLEEP. KARPATHY'S FILE STRUCTURE MAKES IT POSSIBLE. Everyone wires Claude into Obsidian, posts the graph, and stops. this guy added a third system and it quietly changes the whole game: The full build is in the article below: vault structure, the Claude wiring, the exact prompts, the skills. > Obsidian as the knowledge base, but any notes app works as long as Claude Code can see the files > Karpathy's LLM Wiki doc as the skeleton, so the vault is organized the way a model actually reads, not the way humans decorate folders > a self-learning skill on a weekly loop: scans the entire brain, finds the gaps, then researches YouTube and Google by itself to fill them Read the third one again, actually your notes only ever contain what you happened to write down, and the gap-finder breaks that ceiling: the brain starts knowing things you never told it. Most second brains know what you told them. a real one notices what you didn't. that's the difference between note-taking and compounding. one sits there. the other gets smarter every week whether you showed up or not. P.S. send the article straight to your Claude, tell it to interview you, and the brain starts filling itself tonight.

Miraqle

41,307 просмотров • 4 месяцев назад

It’s crazy how my Second Brain is getting stronger and stronger at finding Alpha. The Karpathy Obsidian Vault framework, combined with the new data-mining sessions, is one of the best ways to improve your agents. Based on your own framework and style, I’m not even trying to use agents anymore I’m reverse-engineering my own brain.
1:51

It’s crazy how my Second Brain is getting stronger and stronger at finding Alpha. The Karpathy Obsidian Vault framework, combined with the new data-mining sessions, is one of the best ways to improve your agents. Based on your own framework and style, I’m not even trying to use agents anymore I’m reverse-engineering my own brain.

ZenomTrader

18,431 просмотров • 4 месяцев назад

stop picking one model, a spider merged OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS into one business system one command splits a business into 6 jobs: plan, code, decide, run 24/7, review and ship every job has 4 candidates. the spider scans them one by one, marks the highest score as best, locks it in and swings to the next job the plan goes to Opus 5.5 at 0.94. Jev scores 0.52 on the same job on decisions it flips. Jev wins at 0.97 and Opus 5.5 gets 0.74, so the model that lost the plan is the one making the calls the code goes to Claude Code, and the job called "who never sleeps" goes to OpenAI Dots Opus 5.5 comes back a second time to check the work, and Sonnet 5.5 gets it out at the end 6 of 6 modules are locked and the system goes online run the same test on your own stack before you pay one model to do all six jobs ↓
0:41

stop picking one model, a spider merged OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS into one business system one command splits a business into 6 jobs: plan, code, decide, run 24/7, review and ship every job has 4 candidates. the spider scans them one by one, marks the highest score as best, locks it in and swings to the next job the plan goes to Opus 5.5 at 0.94. Jev scores 0.52 on the same job on decisions it flips. Jev wins at 0.97 and Opus 5.5 gets 0.74, so the model that lost the plan is the one making the calls the code goes to Claude Code, and the job called "who never sleeps" goes to OpenAI Dots Opus 5.5 comes back a second time to check the work, and Sonnet 5.5 gets it out at the end 6 of 6 modules are locked and the system goes online run the same test on your own stack before you pay one model to do all six jobs ↓

Noisy

11,722 просмотров • 1 месяц назад

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.
0:34

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.

West Lord

111,251 просмотров • 4 месяцев назад

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this
16:36

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

Yarchi

141,580 просмотров • 4 месяцев назад

Personal AGI is 3-6 months away. I'm already living in it. Here's my Obsidian setup: - Obsidian vault built since November 2025 - Markdowns about every person, project, and task - Limitless mic pulling daily transcripts straight in - Agents that read all of it before every task Obsidian is: - A second brain for you - A first brain for your agents My agents have full context before every task. That's the whole game.
1:55

Personal AGI is 3-6 months away. I'm already living in it. Here's my Obsidian setup: - Obsidian vault built since November 2025 - Markdowns about every person, project, and task - Limitless mic pulling daily transcripts straight in - Agents that read all of it before every task Obsidian is: - A second brain for you - A first brain for your agents My agents have full context before every task. That's the whole game.

The Startup Ideas Podcast (SIP) 🧃

30,065 просмотров • 6 месяцев назад

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.
0:32

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

xsmryze

60,847 просмотров • 18 дней назад

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.
0:32

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

401,730 просмотров • 26 дней назад

OBSIDIAN TURNED 4,000+ IDEAS INTO A KNOWLEDGE GRAPH THAT REBUILDS ITSELF EVERY NIGHT every lecture adds another point. every saved article adds another signal. every old note becomes part of the map again instead of sitting dead inside a folder. a $599 mac mini runs the loop 24/7, claude extracts the useful parts, verifies the note, then links it to 2-3 related ideas inside obsidian before saving it back into the vault. after 30 days the graph starts getting dense. random notes become clusters, forgotten ideas resurface, and the whole system begins to look less like storage and more like a private memory engine. this is what a second brain looks like when it stops waiting for you to open the app.
0:39

OBSIDIAN TURNED 4,000+ IDEAS INTO A KNOWLEDGE GRAPH THAT REBUILDS ITSELF EVERY NIGHT every lecture adds another point. every saved article adds another signal. every old note becomes part of the map again instead of sitting dead inside a folder. a $599 mac mini runs the loop 24/7, claude extracts the useful parts, verifies the note, then links it to 2-3 related ideas inside obsidian before saving it back into the vault. after 30 days the graph starts getting dense. random notes become clusters, forgotten ideas resurface, and the whole system begins to look less like storage and more like a private memory engine. this is what a second brain looks like when it stops waiting for you to open the app.

Gipp 🦅

18,560 просмотров • 4 месяцев назад

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.
1:29

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 просмотров • 3 месяцев назад

Andrej Karpathy keeps his entire second brain in Obsidian 1 folder of plain text files, nothing else. Here’s the exact setup, free, that turns 1 vault into a brain you can actually query. Why most “second brains” die: Notion is a database you forget to open, ChatGPT memory wipes itself after 30 messages, and both lock your notes inside their cloud. Karpathy rule is the opposite: your notes are the 1 dataset nobody else on earth has, so keep them in plain markdown, own them forever, and let the AI read them later. 3 phases. Phase 1 — Capture with 0 friction. Install Obsidian free, local, 1 hotkey to a daily note. Dump everything into it: ideas, links, quotes, 2-line thoughts, no folders, no tags, no system. Target is 5 notes a day. Phase 2 — Let the graph connect itself. Install Smart Connections and it runs embeddings on every note you’ve ever written, so 2 notes you wrote 4 months apart and never linked by hand suddenly surface as neighbors. That’s the fireworks in the 3D graph each burst is a cluster of ideas your brain forgot it owned. Phase 3 — Query your brain. Point Claude at the vault and ask: “What did I actually think about X across all my notes?” It answers from 1,200 of your own notes, not the internet your taste, your edge, your dataset. The realistic curve looks like this: Week 1 — 40 notes, graph looks empty, feels like a waste. Month 1 — 300 notes, first real cluster forms. Month 3 — 1,200 notes, and the embeddings start surfacing links you’d long forgotten. Month 6 — you stop googling your own past ideas and just ask the vault. Before — 9 tabs, 3 note apps, 0 memory. After — 1 folder, 1,200 notes, 1 brain that compounds. The gap between people who consume and people who compound isn’t talent, it’s architecture. You build your own life so choose the right path.
0:31

Andrej Karpathy keeps his entire second brain in Obsidian 1 folder of plain text files, nothing else. Here’s the exact setup, free, that turns 1 vault into a brain you can actually query. Why most “second brains” die: Notion is a database you forget to open, ChatGPT memory wipes itself after 30 messages, and both lock your notes inside their cloud. Karpathy rule is the opposite: your notes are the 1 dataset nobody else on earth has, so keep them in plain markdown, own them forever, and let the AI read them later. 3 phases. Phase 1 — Capture with 0 friction. Install Obsidian free, local, 1 hotkey to a daily note. Dump everything into it: ideas, links, quotes, 2-line thoughts, no folders, no tags, no system. Target is 5 notes a day. Phase 2 — Let the graph connect itself. Install Smart Connections and it runs embeddings on every note you’ve ever written, so 2 notes you wrote 4 months apart and never linked by hand suddenly surface as neighbors. That’s the fireworks in the 3D graph each burst is a cluster of ideas your brain forgot it owned. Phase 3 — Query your brain. Point Claude at the vault and ask: “What did I actually think about X across all my notes?” It answers from 1,200 of your own notes, not the internet your taste, your edge, your dataset. The realistic curve looks like this: Week 1 — 40 notes, graph looks empty, feels like a waste. Month 1 — 300 notes, first real cluster forms. Month 3 — 1,200 notes, and the embeddings start surfacing links you’d long forgotten. Month 6 — you stop googling your own past ideas and just ask the vault. Before — 9 tabs, 3 note apps, 0 memory. After — 1 folder, 1,200 notes, 1 brain that compounds. The gap between people who consume and people who compound isn’t talent, it’s architecture. You build your own life so choose the right path.

Spike 1%

16,390 просмотров • 4 месяцев назад

THIS IS A PURE F*CKING GOLDMINE the best REA trick almost nobody runs yet. The idea: REA takes the app apart, Jev keeps only what's proven, and a fresh Opus 5.5 rebuilds the feature from that alone. Nothing gets copied and no guess makes it into the code, because the builder never sees the original, only the spec Jev signed off on. You just connect REA like this: npx rea-agents setup here's the split: → REA reads the feature down to the binary and writes every rule into SPEC.md → Jev checks each rule against REA's evidence and sends back anything unproven → a fresh Opus 5.5 session gets only SPEC.md and rebuilds the feature → Haiku 5.5 runs the tests against 3 intentionally broken versions Opus only shows up at three moments: → rebuilding from the approved spec → the checks Jev marks as unclear → signing off before anything ships REA reads. Jev judges. Opus rebuilds. That's the clean-room rule in one line: the model that saw the original never writes the code, and the model that writes the code never sees the original. the full tree > REA reads the app and writes SPEC.md with evidence for every rule > Jev approves or returns each rule > Opus 5.5 rebuilds from the approved SPEC.md in a fresh session > Haiku 5.5 runs the tests and the 3 broken versions > Jev routes unclear checks back to Opus > /goal keeps going until all 3 broken versions fail paste the tree and this prompt into Claude Code ↓ "Set up a clean-room rebuild around this tree: 1. Use REA to investigate [FEATURE] in [APP]. Write every behavior and rule into SPEC.md, each with the evidence REA found. 2. Send each rule to Jev. Any rule without evidence goes back to REA. 3. Start a fresh session with only SPEC.md. Rebuild the feature on Opus 5.5 without opening the original. 4. Write tests on Haiku 5.5 plus 3 intentionally broken versions. Use /goal until the rebuild passes and all 3 broken versions fail. Show me SPEC.md first. Nothing gets built until I say go." ↳ save it, it'll come in handy.
0:20

THIS IS A PURE F*CKING GOLDMINE the best REA trick almost nobody runs yet. The idea: REA takes the app apart, Jev keeps only what's proven, and a fresh Opus 5.5 rebuilds the feature from that alone. Nothing gets copied and no guess makes it into the code, because the builder never sees the original, only the spec Jev signed off on. You just connect REA like this: npx rea-agents setup here's the split: → REA reads the feature down to the binary and writes every rule into SPEC.md → Jev checks each rule against REA's evidence and sends back anything unproven → a fresh Opus 5.5 session gets only SPEC.md and rebuilds the feature → Haiku 5.5 runs the tests against 3 intentionally broken versions Opus only shows up at three moments: → rebuilding from the approved spec → the checks Jev marks as unclear → signing off before anything ships REA reads. Jev judges. Opus rebuilds. That's the clean-room rule in one line: the model that saw the original never writes the code, and the model that writes the code never sees the original. the full tree > REA reads the app and writes SPEC.md with evidence for every rule > Jev approves or returns each rule > Opus 5.5 rebuilds from the approved SPEC.md in a fresh session > Haiku 5.5 runs the tests and the 3 broken versions > Jev routes unclear checks back to Opus > /goal keeps going until all 3 broken versions fail paste the tree and this prompt into Claude Code ↓ "Set up a clean-room rebuild around this tree: 1. Use REA to investigate [FEATURE] in [APP]. Write every behavior and rule into SPEC.md, each with the evidence REA found. 2. Send each rule to Jev. Any rule without evidence goes back to REA. 3. Start a fresh session with only SPEC.md. Rebuild the feature on Opus 5.5 without opening the original. 4. Write tests on Haiku 5.5 plus 3 intentionally broken versions. Use /goal until the rebuild passes and all 3 broken versions fail. Show me SPEC.md first. Nothing gets built until I say go." ↳ save it, it'll come in handy.

Archive

59,706 просмотров • 24 дней назад