leopardracer's banner

leopardracer

@leopardracer • 11,040 subscribers

Researching AI, Crypto & Emerging Tech Sharing insights before they become headlines

Shorts

3-month-old Shopify store is printing $412,000 a month, and the whole thing runs on Claude. Shopify connected directly to Claude on May 4th. You type the order. The store updates. Products, descriptions, ads, collections - all from a chat window. He didn’t hire a developer. Didn’t pay a copywriter. Didn’t touch an ad agency. Store setup - $0. 40 product descriptions - $0. Full ad campaign - $0. First month - $412,000. 605% growth. 4,086 orders. Now Shopify is offering him $250,000 in capital to scale faster. He opened the app to check his stats. Got a new order before he finished reading them. Then went back to configuring his BMW M3. Most people are still paying $15,000/month for a team to do what Claude does for $20. $412,000 a month. A BMW on the side. 3 months. Do the math.

3-month-old Shopify store is printing $412,000 a month, and the whole thing runs on Claude. Shopify connected directly to Claude on May 4th. You type the order. The store updates. Products, descriptions, ads, collections - all from a chat window. He didn’t hire a developer. Didn’t pay a copywriter. Didn’t touch an ad agency. Store setup - $0. 40 product descriptions - $0. Full ad campaign - $0. First month - $412,000. 605% growth. 4,086 orders. Now Shopify is offering him $250,000 in capital to scale faster. He opened the app to check his stats. Got a new order before he finished reading them. Then went back to configuring his BMW M3. Most people are still paying $15,000/month for a team to do what Claude does for $20. $412,000 a month. A BMW on the side. 3 months. Do the math.

698,487 views

THIS MAN HASN’T OPENED HIS TASK MANAGER IN A WEEK AND HIS ENTIRE LIFE IS STILL ON TRACK he dumped everything into one folder before bed and closed his laptop woke up to a system that had already sorted every note and flagged every stalled project and assigned every task his coworkers are still living in their inboxes the only difference is one folder called CAPTURE and claude running at 8pm every night every idea goes in and claude files it and nothing requires a decision and nothing gets lost

THIS MAN HASN’T OPENED HIS TASK MANAGER IN A WEEK AND HIS ENTIRE LIFE IS STILL ON TRACK he dumped everything into one folder before bed and closed his laptop woke up to a system that had already sorted every note and flagged every stalled project and assigned every task his coworkers are still living in their inboxes the only difference is one folder called CAPTURE and claude running at 8pm every night every idea goes in and claude files it and nothing requires a decision and nothing gets lost

313,569 views

SOMEONE BUILT A PERSONAL AI DASHBOARD WITH CLAUDE DESIGN AND OPUS 4.7 AND IT FEELS LIKE A PERSONAL OS

SOMEONE BUILT A PERSONAL AI DASHBOARD WITH CLAUDE DESIGN AND OPUS 4.7 AND IT FEELS LIKE A PERSONAL OS

316,181 views

I HAVEN’T OPENED A SINGLE BOOK THIS MONTH. CLAUDE READ 34 OF THEM FOR ME I built a vault in Obsidian, connected Claude and added Notebooklm went to sleep woke up with flashcards, mind maps, and an AI that answers from my own notes only my friends are still highlighting pdfs manually the only thing separating us is one setup: claude + obsidian + notebooklm every idea captured. every book processed. zero knowledge lost if this is the setup you’ve been looking for - like & bookmark so you don’t lose it

I HAVEN’T OPENED A SINGLE BOOK THIS MONTH. CLAUDE READ 34 OF THEM FOR ME I built a vault in Obsidian, connected Claude and added Notebooklm went to sleep woke up with flashcards, mind maps, and an AI that answers from my own notes only my friends are still highlighting pdfs manually the only thing separating us is one setup: claude + obsidian + notebooklm every idea captured. every book processed. zero knowledge lost if this is the setup you’ve been looking for - like & bookmark so you don’t lose it

251,765 views

My Grok Bot + Kimi K3 Made $2,200 While I Was Away I gave them the job, closed the laptop, and came back to this agents were doing the research, checking the numbers, passing work to each other, and Kimi K3 was deciding what needed to happen next I wasn’t sitting there moving results from one chat to another, I wasn’t writing the next prompt, and I wasn’t the guy keeping everything moving RESEARCH was finding the information ANALYSIS was turning it into something useful VERIFY was catching bad numbers and old data KIMI K3 was keeping the whole thing together The crazy part is that I wasn’t even there I set the goal, the agents took the work, and the system kept going while I was away $2,200 later, I came back to the result Maybe the biggest upgrade with AI isn’t making it smarter Maybe it’s finally getting it to stop waiting for us to tell it what to do next

My Grok Bot + Kimi K3 Made $2,200 While I Was Away I gave them the job, closed the laptop, and came back to this agents were doing the research, checking the numbers, passing work to each other, and Kimi K3 was deciding what needed to happen next I wasn’t sitting there moving results from one chat to another, I wasn’t writing the next prompt, and I wasn’t the guy keeping everything moving RESEARCH was finding the information ANALYSIS was turning it into something useful VERIFY was catching bad numbers and old data KIMI K3 was keeping the whole thing together The crazy part is that I wasn’t even there I set the goal, the agents took the work, and the system kept going while I was away $2,200 later, I came back to the result Maybe the biggest upgrade with AI isn’t making it smarter Maybe it’s finally getting it to stop waiting for us to tell it what to do next

15,710 views

THIS IS WHAT YOUR SECOND BRAIN SHOULD LOOK LIKE most people dump notes into obsidian and call it a second brain it’s not a second brain it’s a second drawer karpathy just dropped the pattern that changes this and it’s called the llm wiki every time you add a source ai reads it, extracts key claims, updates every connected note and flags contradictions your obsidian stops being an archive and starts being alive save this and show it to someone still using notion as a second brain full breakdown in the article ↓

THIS IS WHAT YOUR SECOND BRAIN SHOULD LOOK LIKE most people dump notes into obsidian and call it a second brain it’s not a second brain it’s a second drawer karpathy just dropped the pattern that changes this and it’s called the llm wiki every time you add a source ai reads it, extracts key claims, updates every connected note and flags contradictions your obsidian stops being an archive and starts being alive save this and show it to someone still using notion as a second brain full breakdown in the article ↓

123,618 views

I wrote one article. Someone built a data center. No GPUs. Just $599 boxes. Jensen Huang is having a bad year. The new AI data center doesn’t need NVIDIA. It needs a Costco membership and a good Wi-Fi router.

I wrote one article. Someone built a data center. No GPUs. Just $599 boxes. Jensen Huang is having a bad year. The new AI data center doesn’t need NVIDIA. It needs a Costco membership and a good Wi-Fi router.

232,395 views

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

53,328 views

Someone in China watched my guide. Now they have a room full of Mac Minis. I don’t know how many people lost their jobs.

Someone in China watched my guide. Now they have a room full of Mac Minis. I don’t know how many people lost their jobs.

128,628 views

GEMMA 4 26B ON AN RTX 4060 WITH A 248K TOKEN CONTEXT WINDOW 20 tokens per second and a context window so large you can feed it entire codebases, books and research papers in a single prompt this is not a cloud api and not a server rack, this is a regular consumer gpu running locally with llama.cpp and q4_k_xl quantization 248k context on an 8gb vram card was not supposed to be possible and here it is just running on someone’s desk the article below covers exactly which tools and configs make this kind of setup work in 2026 ↓

GEMMA 4 26B ON AN RTX 4060 WITH A 248K TOKEN CONTEXT WINDOW 20 tokens per second and a context window so large you can feed it entire codebases, books and research papers in a single prompt this is not a cloud api and not a server rack, this is a regular consumer gpu running locally with llama.cpp and q4_k_xl quantization 248k context on an 8gb vram card was not supposed to be possible and here it is just running on someone’s desk the article below covers exactly which tools and configs make this kind of setup work in 2026 ↓

56,772 views

THIS ENGINEER SKIPPED 7,862 WORDS OF AI ROADMAP AND SHIPPED ON A WEEKEND a Pi Zero 2W, an IMX500 camera and a solar panel, that's the whole stack inference runs on-chip so there's no cloud, no latency and no monthly bill Spotted Dove at 0.95, King Parrot at 0.88, runs forever on sun code is open source and the 3D files are free, you just print the case and buy the parts and it works better than most paid wildlife monitoring services out there full video: code (open source): 3D print files: solar power board: save this so you actually have everything in one place when you decide to build it

THIS ENGINEER SKIPPED 7,862 WORDS OF AI ROADMAP AND SHIPPED ON A WEEKEND a Pi Zero 2W, an IMX500 camera and a solar panel, that's the whole stack inference runs on-chip so there's no cloud, no latency and no monthly bill Spotted Dove at 0.95, King Parrot at 0.88, runs forever on sun code is open source and the 3D files are free, you just print the case and buy the parts and it works better than most paid wildlife monitoring services out there full video: code (open source): 3D print files: solar power board: save this so you actually have everything in one place when you decide to build it

63,096 views

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

23,629 views

THIS MAN HASN’T HAD A SINGLE ORIGINAL IDEA IN 8 WEEKS. CLAUDE HAS ALL OF THEM BEFORE HE WAKES UP he gave claude his obsidian vault on a saturday by monday it found a link between two notes written 6 weeks apart in different folders he turned that connection into his best-performing post his competitors are still organizing folders and writing morning pages and brainstorming in notion the only difference is one file called CLAUDE.md every note = fuel and every morning = synthesis and every week = ideas compounding faster than he can publish them this is not a tool anymore and this is not even an assistant this is a second brain that studied you for 2 months straight bookmark & like this or lose it forever

THIS MAN HASN’T HAD A SINGLE ORIGINAL IDEA IN 8 WEEKS. CLAUDE HAS ALL OF THEM BEFORE HE WAKES UP he gave claude his obsidian vault on a saturday by monday it found a link between two notes written 6 weeks apart in different folders he turned that connection into his best-performing post his competitors are still organizing folders and writing morning pages and brainstorming in notion the only difference is one file called CLAUDE.md every note = fuel and every morning = synthesis and every week = ideas compounding faster than he can publish them this is not a tool anymore and this is not even an assistant this is a second brain that studied you for 2 months straight bookmark & like this or lose it forever

27,938 views

$4,277,574,722. That’s the CS2 skin market right now. No central bank. No SEC. No taxes. And most people playing the game have no idea this market exists. The ones who do - don’t play. They trade. In 2026, Claude does the trading for them. Bookmark this. You’ll want to come back when you’re ready to stop playing and start earning.

$4,277,574,722. That’s the CS2 skin market right now. No central bank. No SEC. No taxes. And most people playing the game have no idea this market exists. The ones who do - don’t play. They trade. In 2026, Claude does the trading for them. Bookmark this. You’ll want to come back when you’re ready to stop playing and start earning.

31,073 views

THIS GUY NAVIGATES HIS MIND PALACE WITH HAND GESTURES AND IT LOOKS INSANE deep learning, machine learning, anthropic, openai all floating in 3d space and he just waves his hand to move through the graph this is what karpathy was describing when he said knowledge should compound and connect instead of sitting in flat markdown files your second brain should feel like a place you can walk through not a search bar you type into

THIS GUY NAVIGATES HIS MIND PALACE WITH HAND GESTURES AND IT LOOKS INSANE deep learning, machine learning, anthropic, openai all floating in 3d space and he just waves his hand to move through the graph this is what karpathy was describing when he said knowledge should compound and connect instead of sitting in flat markdown files your second brain should feel like a place you can walk through not a search bar you type into

15,297 views

I built my own AI hedge fund for $100. No Bloomberg terminal. No Wall Street connections. Just Python, Polymarket API, and a pairs trading algorithm. Sharpe ratio: 1.84.

I built my own AI hedge fund for $100. No Bloomberg terminal. No Wall Street connections. Just Python, Polymarket API, and a pairs trading algorithm. Sharpe ratio: 1.84.

26,276 views

HE FIXED A BROKEN $5 MP3 PLAYER WITH ONE PROMPT. SAME MODEL WITH OPENAI CODEX BUILT A CUSTOM OS his process: → bought cheap MP3 player on AliExpress → threw it away due to brutal Bluetooth stuttering → hit by a sudden shower thought → cracked open the case to check the chip → one year: garbage in a drawer the AI version: → showed the microchip to OpenAI Codex → Codex dumped firmware and analyzed binaries → built a custom OS fixing all Bluetooth bugs → remapped clunky navigation from left-right to up-down → result: instant, flawless performance the hardware is the same. the output is 10× bigger.

HE FIXED A BROKEN $5 MP3 PLAYER WITH ONE PROMPT. SAME MODEL WITH OPENAI CODEX BUILT A CUSTOM OS his process: → bought cheap MP3 player on AliExpress → threw it away due to brutal Bluetooth stuttering → hit by a sudden shower thought → cracked open the case to check the chip → one year: garbage in a drawer the AI version: → showed the microchip to OpenAI Codex → Codex dumped firmware and analyzed binaries → built a custom OS fixing all Bluetooth bugs → remapped clunky navigation from left-right to up-down → result: instant, flawless performance the hardware is the same. the output is 10× bigger.

15,617 views

THIS ENGINEER USES HIS HANDS AS A REMOTE CONTROL. CLAUDE MADE THAT POSSIBLE he opened claude and described the idea and got the full code he strapped sensors to his hands and walked outside and the drone followed every move his colleagues are still reading arduino documentation the only thing separating them is one conversation with claude every flex is a command and every gesture is a signal and zero remote needed save this so you don’t forget how to set it up

THIS ENGINEER USES HIS HANDS AS A REMOTE CONTROL. CLAUDE MADE THAT POSSIBLE he opened claude and described the idea and got the full code he strapped sensors to his hands and walked outside and the drone followed every move his colleagues are still reading arduino documentation the only thing separating them is one conversation with claude every flex is a command and every gesture is a signal and zero remote needed save this so you don’t forget how to set it up

16,382 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

THEY RAN STATE OF THE ART AI ON A 26 YEAR OLD IMAC WITH ZERO INTERNET not a demo. not a benchmark a real answer in near instant time on hardware older than most people reading this your subscription money is going to a data center that doesn't need it the future already runs locally on dead hardware from 1999 bookmark this before you pay for another month of cloud AI you don't need

THEY RAN STATE OF THE ART AI ON A 26 YEAR OLD IMAC WITH ZERO INTERNET not a demo. not a benchmark a real answer in near instant time on hardware older than most people reading this your subscription money is going to a data center that doesn't need it the future already runs locally on dead hardware from 1999 bookmark this before you pay for another month of cloud AI you don't need

2,764,696 views • 3 months ago

THIS DEVELOPER HASN’T PAID AN API BILL IN 3 MONTHS. HIS AGENTS RAN 10,000 TIMES FOR FREE he built a local AI lab under his desk two GPUs 32GB VRAM zero rate limits his agents loop 400 times if they want to his coworkers are still watching the usage dashboard the only thing separating them: llama.cpp + llama-swap every prompt stays on his machine every experiment costs $0 zero invoices bookmark & like this before your next API bill hits

THIS DEVELOPER HASN’T PAID AN API BILL IN 3 MONTHS. HIS AGENTS RAN 10,000 TIMES FOR FREE he built a local AI lab under his desk two GPUs 32GB VRAM zero rate limits his agents loop 400 times if they want to his coworkers are still watching the usage dashboard the only thing separating them: llama.cpp + llama-swap every prompt stays on his machine every experiment costs $0 zero invoices bookmark & like this before your next API bill hits

543,272 views • 3 months ago

ANDREJ KARPATHY IS THE GODFATHER OF MODERN AI He doesn’t use Notion. He doesn’t use Roam. He doesn’t use Obsidian plugins. He built his own second brain from scratch. I copied him exactly. The result: → 378 notes → 1,854 nodes → 3,856 edges → One custom 3D knowledge galaxy that thinks back at you This isn’t note-taking. This is a second nervous system. Click any node - AI surfaces every hidden connection. Zoom out - you see your entire mind as a universe. Zoom in - you see why Fischer beating Spassky in 1972 connects directly to your trading edge today. ChatGPT forgets you in 2 hours. This remembers everything. Forever. Notion users are building filing cabinets. Roam users are building spreadsheets. Obsidian users are building graveyards. I built a galaxy. The gap between people who consume knowledge and people who compound it isn’t talent. It’s architecture. Karpathy knew this before anyone. Now you do too.

ANDREJ KARPATHY IS THE GODFATHER OF MODERN AI He doesn’t use Notion. He doesn’t use Roam. He doesn’t use Obsidian plugins. He built his own second brain from scratch. I copied him exactly. The result: → 378 notes → 1,854 nodes → 3,856 edges → One custom 3D knowledge galaxy that thinks back at you This isn’t note-taking. This is a second nervous system. Click any node - AI surfaces every hidden connection. Zoom out - you see your entire mind as a universe. Zoom in - you see why Fischer beating Spassky in 1972 connects directly to your trading edge today. ChatGPT forgets you in 2 hours. This remembers everything. Forever. Notion users are building filing cabinets. Roam users are building spreadsheets. Obsidian users are building graveyards. I built a galaxy. The gap between people who consume knowledge and people who compound it isn’t talent. It’s architecture. Karpathy knew this before anyone. Now you do too.

455,907 views • 3 months ago

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

248,390 views • 2 months ago

3 guys. Same apartment. $1.5 billion paid out by Roblox in 2025. They figured out the code doesn’t matter anymore. Roblox has 380 million monthly users. $1.5B paid to creators last year. Up 31% from the year before. The top 1,000 creators averaged $1.3 million each. The wall that kept everyone out was always Luau - Roblox’s custom programming language. You needed to learn it. Most people never did. Claude writes Luau. And it connects directly to Roblox Studio via MCP. One developer built a full mining tycoon - currency system, shop, rebirth mechanics, persistent data - in 2 hours. Zero scripting experience. Every line of code generated by AI. These guys live together. They share a kitchen and a game engine. And they claim to make millions doing exactly this. The barrier is gone. The window is open. Most people still haven’t noticed.

3 guys. Same apartment. $1.5 billion paid out by Roblox in 2025. They figured out the code doesn’t matter anymore. Roblox has 380 million monthly users. $1.5B paid to creators last year. Up 31% from the year before. The top 1,000 creators averaged $1.3 million each. The wall that kept everyone out was always Luau - Roblox’s custom programming language. You needed to learn it. Most people never did. Claude writes Luau. And it connects directly to Roblox Studio via MCP. One developer built a full mining tycoon - currency system, shop, rebirth mechanics, persistent data - in 2 hours. Zero scripting experience. Every line of code generated by AI. These guys live together. They share a kitchen and a game engine. And they claim to make millions doing exactly this. The barrier is gone. The window is open. Most people still haven’t noticed.

336,130 views • 4 months ago

THIS CHINESE DEVELOPER’S NEURAL NETWORK VISUALIZATION IS EXACTLY HOW YOUR OBSIDIAN VAULT SHOULD WORK every node connects to every other node and the whole thing gets smarter the more data flows through it, same way a real knowledge system should work but almost nobody builds it like that most people throw everything into folders and tags and call it a second brain but what they actually built is an archive that gets harder to use every month claude reads across everything you ever captured and finds the connection you need right when you need it here’s how to build the version that actually compounds ↓

THIS CHINESE DEVELOPER’S NEURAL NETWORK VISUALIZATION IS EXACTLY HOW YOUR OBSIDIAN VAULT SHOULD WORK every node connects to every other node and the whole thing gets smarter the more data flows through it, same way a real knowledge system should work but almost nobody builds it like that most people throw everything into folders and tags and call it a second brain but what they actually built is an archive that gets harder to use every month claude reads across everything you ever captured and finds the connection you need right when you need it here’s how to build the version that actually compounds ↓

231,513 views • 3 months ago

THIS AMERICAN DEVELOPER SPENT WEEKS DEBUGGING TIMEOUT ERRORS IN OLLAMA. THEN HE LOOKED UNDER THE HOOD LM Studio is just llama.cpp Ollama is just llama.cpp so he cloned llama.cpp from source, pulled Qwen 3.6 35B off Hugging Face, set up asymmetric KV quantization and got a local server running on 127.0.0.1:8080 plugged it into VS Code, connected it to OpenClaw, 53 tok/s on an M1 Max with 262K context zero wrappers, zero timeout errors, zero API fees bookmark & like this before your next timeout error hits full breakdown of my raw llama.cpp setup ↓

THIS AMERICAN DEVELOPER SPENT WEEKS DEBUGGING TIMEOUT ERRORS IN OLLAMA. THEN HE LOOKED UNDER THE HOOD LM Studio is just llama.cpp Ollama is just llama.cpp so he cloned llama.cpp from source, pulled Qwen 3.6 35B off Hugging Face, set up asymmetric KV quantization and got a local server running on 127.0.0.1:8080 plugged it into VS Code, connected it to OpenClaw, 53 tok/s on an M1 Max with 262K context zero wrappers, zero timeout errors, zero API fees bookmark & like this before your next timeout error hits full breakdown of my raw llama.cpp setup ↓

238,950 views • 3 months ago

There are teenagers making more with AI girlfriends than most engineers make coding. Let that sink in.

There are teenagers making more with AI girlfriends than most engineers make coding. Let that sink in.

208,723 views • 4 months ago

the entire “grind YouTube for 3 years and build a personal brand” industry just got nuked by a 19 year old with a Discord account $80,000/month. no camera. no editing. no algorithm. no audience. no ads. no brands. no content. 20+ servers. Claude-written bots. $5 Railway hosting. PayPal does the rest. the most insulting part is he didn’t need an audience to do it. no posts. no thumbnails. no parasocial nonsense. just bots that work, running on a platform with 771M users and zero gatekeepers. the gap isn’t IQ. it’s that he didn’t ask for permission. the “build a personal brand first” crowd is going to pretend they didn’t see this one.

213,380 views • 4 months ago

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

223,397 views • 4 months ago

THIS GUY OPENED OBSIDIAN AND SAW HIS ENTIRE KNOWLEDGE AS A NETWORK AND HE BUILT IT IN 90 DAYS one note at a time and one link at a time now the graph shows him what he actually thinks about and not what he assumed he cared about six months ago he had 200 isolated notes sitting in folders nobody visits today every idea he has connects to something he wrote in the past a thought from january becomes context for a decision in may without him remembering january even happened his coworkers are still searching for files by name and finding nothing useful the only difference is he stopped filing and started linking his notes are not stored they are connected like & bookmark this if you’ve been using obsidian as a filing cabinet this whole time

THIS GUY OPENED OBSIDIAN AND SAW HIS ENTIRE KNOWLEDGE AS A NETWORK AND HE BUILT IT IN 90 DAYS one note at a time and one link at a time now the graph shows him what he actually thinks about and not what he assumed he cared about six months ago he had 200 isolated notes sitting in folders nobody visits today every idea he has connects to something he wrote in the past a thought from january becomes context for a decision in may without him remembering january even happened his coworkers are still searching for files by name and finding nothing useful the only difference is he stopped filing and started linking his notes are not stored they are connected like & bookmark this if you’ve been using obsidian as a filing cabinet this whole time

144,589 views • 3 months ago

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 ↓

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 ↓

81,925 views • 2 months ago

Skinport takes 8%. Steam takes 15%. CSFloat takes 5%. Every platform takes a cut. The only way to win is to buy cheaper than everyone else. Claude built me a bot that finds underpriced skins across 15,000 listings in seconds. $6K/month. Zero playtime. Bookmark this. Fees don’t matter when your buy price is right.

Skinport takes 8%. Steam takes 15%. CSFloat takes 5%. Every platform takes a cut. The only way to win is to buy cheaper than everyone else. Claude built me a bot that finds underpriced skins across 15,000 listings in seconds. $6K/month. Zero playtime. Bookmark this. Fees don’t matter when your buy price is right.

136,861 views • 4 months ago

THIS PERSON READ A 134-PAGE BOOK IN 15 MINUTES AND DIDN'T HIGHLIGHT ONCE BUT REMEMBERS ALL OF IT he dropped the PDF and waited 15 min he got 25 atomic notes with a full flashcard deck, auto-generated, auto-linked and ready to review his friends still re-read the same books and forget everything the gap isn't intelligence, it's infrastructure bookmark & like this full vault setup

THIS PERSON READ A 134-PAGE BOOK IN 15 MINUTES AND DIDN'T HIGHLIGHT ONCE BUT REMEMBERS ALL OF IT he dropped the PDF and waited 15 min he got 25 atomic notes with a full flashcard deck, auto-generated, auto-linked and ready to review his friends still re-read the same books and forget everything the gap isn't intelligence, it's infrastructure bookmark & like this full vault setup

95,425 views • 3 months ago

Anthropic engineer just built a second brain that reads 3 files instead of 5,000, and cut the token bill 40% no orchestrator, no plugin, just a router file, an index, and code that scores before the model ever opens anything point claude at a flat folder of notes and every question reads all of them, that’s the default and it’s expensive this breakdown turns that exact pattern into a system anyone can run CLAUDE.md → index.md → nodes → edges → retrieval as code → memory → ship it twelve steps, one shared rule, evidence lives in the index, the model reads three files while the notes folder still holds thousands the stale index test, one line drifts and the whole graph quietly turns back into the pile it was built to escape, no exceptions save it and watch, then read the article below

Anthropic engineer just built a second brain that reads 3 files instead of 5,000, and cut the token bill 40% no orchestrator, no plugin, just a router file, an index, and code that scores before the model ever opens anything point claude at a flat folder of notes and every question reads all of them, that’s the default and it’s expensive this breakdown turns that exact pattern into a system anyone can run CLAUDE.md → index.md → nodes → edges → retrieval as code → memory → ship it twelve steps, one shared rule, evidence lives in the index, the model reads three files while the notes folder still holds thousands the stale index test, one line drifts and the whole graph quietly turns back into the pile it was built to escape, no exceptions save it and watch, then read the article below

37,304 views • 1 month ago

THIS AI DEVELOPER RUNS 120B PARAMETER MODELS LOCALLY AND HIS MACBOOK PRO CAN’T EVEN OPEN THEM he bought a DGX Spark, gave it the model, went back to his desk by end of day the inference was done, tested, committed his team is still waiting for the cloud GPU queue to free up the only thing between them is 128GB of unified memory in a box smaller than your lunch one Spark is a datacenter node, two Sparks is your own cluster bookmark this and send it to whoever is still paying for cloud GPUs

THIS AI DEVELOPER RUNS 120B PARAMETER MODELS LOCALLY AND HIS MACBOOK PRO CAN’T EVEN OPEN THEM he bought a DGX Spark, gave it the model, went back to his desk by end of day the inference was done, tested, committed his team is still waiting for the cloud GPU queue to free up the only thing between them is 128GB of unified memory in a box smaller than your lunch one Spark is a datacenter node, two Sparks is your own cluster bookmark this and send it to whoever is still paying for cloud GPUs

85,726 views • 3 months ago

THIS GUY HIT HIS DAILY CLAUDE LIMIT BUILDING A KNOWLEDGE GRAPH. THE SYSTEM KEPT RUNNING WITHOUT HIM he opened obsidian at 6am and claude had already read everything new connections, a brief, one question worth thinking about today his coworkers are still copy-pasting context into every session he stopped doing that 3 months ago one markdown file changed how he works with claude forever Bookmark & like it if you’re tired of starting from zero every session

THIS GUY HIT HIS DAILY CLAUDE LIMIT BUILDING A KNOWLEDGE GRAPH. THE SYSTEM KEPT RUNNING WITHOUT HIM he opened obsidian at 6am and claude had already read everything new connections, a brief, one question worth thinking about today his coworkers are still copy-pasting context into every session he stopped doing that 3 months ago one markdown file changed how he works with claude forever Bookmark & like it if you’re tired of starting from zero every session

87,564 views • 3 months ago

THEY RAN A LOCAL AI MODEL ON A RASPBERRY PI THAT COSTS LESS THAN $300 no cloud no subscription no data center device smaller than your wallet output on a 27 year old iMac I tested local ai this week on a macbook and a phone the hardware keeps getting cheaper and the models keep getting smarter bookmark this if you’re still paying $20 a month for something your $300 raspberry pi can do

THEY RAN A LOCAL AI MODEL ON A RASPBERRY PI THAT COSTS LESS THAN $300 no cloud no subscription no data center device smaller than your wallet output on a 27 year old iMac I tested local ai this week on a macbook and a phone the hardware keeps getting cheaper and the models keep getting smarter bookmark this if you’re still paying $20 a month for something your $300 raspberry pi can do

73,534 views • 3 months ago

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below

28,047 views • 1 month ago

SOMEONE IS BUILDING THE BEST SECOND BRAIN IN 2026 AND IT LOOKS LIKE THIS not a better notion template, not a cleaner folder structure, not another zettelkasten variation a living system where every idea has an orbit and new information changes the gravity of everything around it Karpathy described exactly how to build this and the answer was simpler than anyone expected, stop retrieving and start compounding the article explains the whole thing in 15 minutes ↓

SOMEONE IS BUILDING THE BEST SECOND BRAIN IN 2026 AND IT LOOKS LIKE THIS not a better notion template, not a cleaner folder structure, not another zettelkasten variation a living system where every idea has an orbit and new information changes the gravity of everything around it Karpathy described exactly how to build this and the answer was simpler than anyone expected, stop retrieving and start compounding the article explains the whole thing in 15 minutes ↓

41,928 views • 2 months ago