Spike 1%'s banner
Spike 1%'s profile picture

Spike 1%

@SpikeCalls • 6,166 subscribers

AI dev

Shorts

166,700 neurons from a male fruit fly's brain are teaching a pair of silicone lips to talk. A steel frame, a silicone tongue, a row of motors under the jaw and a microphone pointed straight at the mouth, with no speaker anywhere. Air pushes through artificial vocal cords, the motors bend the lips and the microphone catches every sound it makes. If the pitch is off, the motors shift before the next try. Nobody coded the words: it finds each lip shape by trial and error and uses old sounds to guess new ones. Babies learn to talk the same way: babble, listen, fix, repeat. The new part is the brain in the corner of the screen, with 166,700 neurons and 125 million synapses packed into something smaller than a poppy seed. Scientists spent 10 years mapping every wire, and the job took 44 years of human labor. Male fruit flies already sing: they buzz 1 wing to court a female, and she hears the song through her antennae. That song never had a mouth until now. A trained linear readout turns its spikes into words and the mouth does the rest. You needed 86 billion neurons and 12 months to say "mama." The fly needs 166,700 and a microphone.

166,700 neurons from a male fruit fly's brain are teaching a pair of silicone lips to talk. A steel frame, a silicone tongue, a row of motors under the jaw and a microphone pointed straight at the mouth, with no speaker anywhere. Air pushes through artificial vocal cords, the motors bend the lips and the microphone catches every sound it makes. If the pitch is off, the motors shift before the next try. Nobody coded the words: it finds each lip shape by trial and error and uses old sounds to guess new ones. Babies learn to talk the same way: babble, listen, fix, repeat. The new part is the brain in the corner of the screen, with 166,700 neurons and 125 million synapses packed into something smaller than a poppy seed. Scientists spent 10 years mapping every wire, and the job took 44 years of human labor. Male fruit flies already sing: they buzz 1 wing to court a female, and she hears the song through her antennae. That song never had a mouth until now. A trained linear readout turns its spikes into words and the mouth does the rest. You needed 86 billion neurons and 12 months to say "mama." The fly needs 166,700 and a microphone.

2,483,807 просмотров

166,700 fruit fly neurons are flying a drone around my bedroom. 1 camera watches my open hand and that's the whole input. The panel in the middle is the brain running live 166,700 neurons, 25 million connections, the full reconstructed map of a fruit fly's head. Camera reads the hand, the brain fires, the output becomes throttle. Open palm and it climbs, fist and it holds, drop the hand and it comes down. 4 propellers the size of a coin hanging off a nervous system that belonged to an insect. The honest part this is a computational model, not a resurrected fly, the wiring is biological, the drone is mine, I built the bridge between them. I never wrote flight logic, no PID tuning, no gesture presets, I gave the neurons somewhere to send the signal and they found the ceiling. 11 seconds in, it holds altitude on its own. The fly is dead and it's still flying.

166,700 fruit fly neurons are flying a drone around my bedroom. 1 camera watches my open hand and that's the whole input. The panel in the middle is the brain running live 166,700 neurons, 25 million connections, the full reconstructed map of a fruit fly's head. Camera reads the hand, the brain fires, the output becomes throttle. Open palm and it climbs, fist and it holds, drop the hand and it comes down. 4 propellers the size of a coin hanging off a nervous system that belonged to an insect. The honest part this is a computational model, not a resurrected fly, the wiring is biological, the drone is mine, I built the bridge between them. I never wrote flight logic, no PID tuning, no gesture presets, I gave the neurons somewhere to send the signal and they found the ceiling. 11 seconds in, it holds altitude on its own. The fly is dead and it's still flying.

1,049,687 просмотров

166,700 fruit fly neurons just took over 3 drones, and nobody taught them to fly. Scientists mapped the full brain of 1 real fly, every neuron and all 25 million connections, and put it online for free. Someone copied that brain 3 times and plugged each copy into a drone. No flight code, no gesture presets, no "avoid the chair" rule, just a camera feeding the fly's eyes and neurons turning into throttle. 1 drone hovers, 1 slips past a chair, 1 drops to the floor and holds. This brain spent 350 million years learning to stay in the air, and now it's back where it belongs. No GPUs, no training run, no $100B data center, just a brain smaller than a grain of salt. 1 fly gives you 3 pilots, and 1,000 flies give you a swarm. The fly is dead, but its brain just got a squadron.

166,700 fruit fly neurons just took over 3 drones, and nobody taught them to fly. Scientists mapped the full brain of 1 real fly, every neuron and all 25 million connections, and put it online for free. Someone copied that brain 3 times and plugged each copy into a drone. No flight code, no gesture presets, no "avoid the chair" rule, just a camera feeding the fly's eyes and neurons turning into throttle. 1 drone hovers, 1 slips past a chair, 1 drops to the floor and holds. This brain spent 350 million years learning to stay in the air, and now it's back where it belongs. No GPUs, no training run, no $100B data center, just a brain smaller than a grain of salt. 1 fly gives you 3 pilots, and 1,000 flies give you a swarm. The fly is dead, but its brain just got a squadron.

780,599 просмотров

A Stanford student put 166,700 fruit fly neurons in a robot that now writes homework for 30 students. Not one of them has picked up a pen since. The robot is a black aluminum rig with a blue ballpoint, writing square roots and fractions line after line in handwriting that doesn't look like a machine's, while the fly's neurons glow in the corner of the screen. Each student gives it a handwriting sample, and the fly learns the slant, the spacing, the size of the loops and where the letters get lazy at the end of a line, then writes as that student. 30 notebooks, 30 different hands and 1 brain. That brain is smaller than a poppy seed, and a human brain has over 500,000 times more neurons, but the fly doesn't get tired, doesn't smudge the ink and never mixes up whose 7s have a line through them. The teacher checks 30 notebooks, and a fly wrote every one.

A Stanford student put 166,700 fruit fly neurons in a robot that now writes homework for 30 students. Not one of them has picked up a pen since. The robot is a black aluminum rig with a blue ballpoint, writing square roots and fractions line after line in handwriting that doesn't look like a machine's, while the fly's neurons glow in the corner of the screen. Each student gives it a handwriting sample, and the fly learns the slant, the spacing, the size of the loops and where the letters get lazy at the end of a line, then writes as that student. 30 notebooks, 30 different hands and 1 brain. That brain is smaller than a poppy seed, and a human brain has over 500,000 times more neurons, but the fly doesn't get tired, doesn't smudge the ink and never mixes up whose 7s have a line through them. The teacher checks 30 notebooks, and a fly wrote every one.

290,333 просмотров

A STUDENT TURNED A FRUIT FLY BRAIN INTO AN AI AGENT AND STEERS IT WITH HER BARE HAND Google and HHMI Janelia spent 10 years mapping the nervous system of 1 male fruit fly, and on September 3 they released the whole map for free. 166,700 neurons and 24.5M synapses, every wire from eye to leg. She ran all of it as a leaky integrate-and-fire simulation and then gave it a job. The top-right panel is the brain firing live, the robot on the left is the agent it drives. A camera tracks her fingers, the movements hit the fly's sensory neurons, and whatever motor neurons fire decide what the agent does. Status: IDLE Pinch → RUNNING IMPLEMENTATION Point → SPINNING UP NEW IMPL Pull back → HEAVY LIFTING The catch: this is not a living fly but a computer model of real wiring, and she built the link between her hand and its neurons. 12 days ago this brain was a dataset Then it played DOOM Then Chrome Dino Then it walked a Strandbeest Now it works for a student. The fly died years ago, but its wiring still takes orders.

A STUDENT TURNED A FRUIT FLY BRAIN INTO AN AI AGENT AND STEERS IT WITH HER BARE HAND Google and HHMI Janelia spent 10 years mapping the nervous system of 1 male fruit fly, and on September 3 they released the whole map for free. 166,700 neurons and 24.5M synapses, every wire from eye to leg. She ran all of it as a leaky integrate-and-fire simulation and then gave it a job. The top-right panel is the brain firing live, the robot on the left is the agent it drives. A camera tracks her fingers, the movements hit the fly's sensory neurons, and whatever motor neurons fire decide what the agent does. Status: IDLE Pinch → RUNNING IMPLEMENTATION Point → SPINNING UP NEW IMPL Pull back → HEAVY LIFTING The catch: this is not a living fly but a computer model of real wiring, and she built the link between her hand and its neurons. 12 days ago this brain was a dataset Then it played DOOM Then Chrome Dino Then it walked a Strandbeest Now it works for a student. The fly died years ago, but its wiring still takes orders.

105,373 просмотров

166,000 neurons from a dead fruit fly now hunt drones from a bedroom desk. A white drone the size of a palm lifts off the carpet, and a black 3D-printed turret on the desk swings after it, with the fly's brain working its 2 stepper motors, 1 camera and 2 barrels through a nest of rainbow wires on a breadboard. That brain sits in the top-left corner of the screen and flares every time the drone jerks. A Patriot interceptor costs about $4 million, and armies are firing them at drones worth a fraction of that. This brain is smaller than a poppy seed, and Google put it online for free 2 weeks ago. Then someone gave it a job it was built for. Most of a fly's brain exists to see motion, and this brain is male, and male flies spend their lives chasing whatever moves. The drone climbs past the ceiling fan and the crosshair climbs with it, then drops when it drops. For 18 seconds it never loses the drone. In the last shot the drone flies home to the guy holding the controller, and the crosshair follows it right onto his chest. It spent its whole life dodging swatters. Now it's the one aiming.

166,000 neurons from a dead fruit fly now hunt drones from a bedroom desk. A white drone the size of a palm lifts off the carpet, and a black 3D-printed turret on the desk swings after it, with the fly's brain working its 2 stepper motors, 1 camera and 2 barrels through a nest of rainbow wires on a breadboard. That brain sits in the top-left corner of the screen and flares every time the drone jerks. A Patriot interceptor costs about $4 million, and armies are firing them at drones worth a fraction of that. This brain is smaller than a poppy seed, and Google put it online for free 2 weeks ago. Then someone gave it a job it was built for. Most of a fly's brain exists to see motion, and this brain is male, and male flies spend their lives chasing whatever moves. The drone climbs past the ceiling fan and the crosshair climbs with it, then drops when it drops. For 18 seconds it never loses the drone. In the last shot the drone flies home to the guy holding the controller, and the crosshair follows it right onto his chest. It spent its whole life dodging swatters. Now it's the one aiming.

36,892 просмотров

A dead fruit fly was sliced into 66 pieces. Now its 166,700 neurons are driving robots. Nobody trained it, no dataset, no reward function, no GPU farm, just the wiring. The fly took a second to die, but copying it took 7 microscopes running nonstop for a year, shaving it 1/10,000 of a hair at a time and photographing every layer before the next cut. AI rebuilt it from the scraps, eyes to legs with the neck still attached, 124M synapses and 11,710 cell types, 44 years of human labor finished by machines. Scientists first tried this in 2008 and guessed it would take 500 people 10 years. Then the internet got the file and someone gave it a body. Camera → fly eyes → 166,700 spiking neurons → descending neurons → motors. One of those neurons is DNp01, the giant fiber, the cell that fires when your hand comes down. Push an object at the camera and the looming detectors light up, so the robot swerves. It took 0 training runs, just the same reflex that gets a fly out from under a swatter in 100 milliseconds. Then came the control test, where they kept all 138,639 neurons and shuffled where the synapses connect. The behavior died. The intelligence was never in the neurons, it was in the map. The fly is gone, but the flinch is still running.

A dead fruit fly was sliced into 66 pieces. Now its 166,700 neurons are driving robots. Nobody trained it, no dataset, no reward function, no GPU farm, just the wiring. The fly took a second to die, but copying it took 7 microscopes running nonstop for a year, shaving it 1/10,000 of a hair at a time and photographing every layer before the next cut. AI rebuilt it from the scraps, eyes to legs with the neck still attached, 124M synapses and 11,710 cell types, 44 years of human labor finished by machines. Scientists first tried this in 2008 and guessed it would take 500 people 10 years. Then the internet got the file and someone gave it a body. Camera → fly eyes → 166,700 spiking neurons → descending neurons → motors. One of those neurons is DNp01, the giant fiber, the cell that fires when your hand comes down. Push an object at the camera and the looming detectors light up, so the robot swerves. It took 0 training runs, just the same reflex that gets a fly out from under a swatter in 100 milliseconds. Then came the control test, where they kept all 138,639 neurons and shuffled where the synapses connect. The behavior died. The intelligence was never in the neurons, it was in the map. The fly is gone, but the flinch is still running.

25,494 просмотров

A Harvard sophomore pointed Claude Code at his Obsidian vault and woke up to 1,847 notes he never wrote. The vault started in September 2024 with 210 notes lecture scraps, 4 problem sets, 3 half-finished essays and by March it was dead, because nobody links notes by hand at 2 AM. So he handed the folder to an agent: read access to 210 files and one instruction, find what connects. It ran for 6 hours and built edges he'd never seen, wiring a thermodynamics lecture to a supply-chain note to a Douyin livestream case study he saved in 2023 and forgot. Graph view at 4 AM showed 1,847 nodes and 11,400 links, a white sphere so dense the center goes solid. His midterm was 9 days out, so he skipped the textbook and asked the vault instead, and it answered in his own words from 3 semesters back. Now the agent runs nightly, pulling 40 new notes a week writing summaries, tagging, linking, killing duplicates while he hasn't typed a note in 5 weeks. He opens the graph most mornings and scrolls for something he doesn't recognize, and there's always something. Tuition runs $59,320 a year; the vault cost one afternoon of setup. He built a second brain, then stopped using the first one.

A Harvard sophomore pointed Claude Code at his Obsidian vault and woke up to 1,847 notes he never wrote. The vault started in September 2024 with 210 notes lecture scraps, 4 problem sets, 3 half-finished essays and by March it was dead, because nobody links notes by hand at 2 AM. So he handed the folder to an agent: read access to 210 files and one instruction, find what connects. It ran for 6 hours and built edges he'd never seen, wiring a thermodynamics lecture to a supply-chain note to a Douyin livestream case study he saved in 2023 and forgot. Graph view at 4 AM showed 1,847 nodes and 11,400 links, a white sphere so dense the center goes solid. His midterm was 9 days out, so he skipped the textbook and asked the vault instead, and it answered in his own words from 3 semesters back. Now the agent runs nightly, pulling 40 new notes a week writing summaries, tagging, linking, killing duplicates while he hasn't typed a note in 5 weeks. He opens the graph most mornings and scrolls for something he doesn't recognize, and there's always something. Tuition runs $59,320 a year; the vault cost one afternoon of setup. He built a second brain, then stopped using the first one.

56,112 просмотров

A 19-year-old Stanford student put on red boxing gloves and lost 12-0 to a simulated fruit fly. The fly never left its side of the dish. Her webcam reads her shoulders and both hands, so leaning right makes the blue fly circle and a thrown punch makes it lunge, while the red one plays the rival. 12 seconds of zone control wins, rounds cap at 20. Status line with 16 seconds left: "Rival spreads his wings". She lunged once, made contact, scored 0.0 seconds. The rival isn't scripted two rendered eye views feed Flyvis, the published fly visual network from Nature 2024, and a target detector reads that activity to steer the turn, with 115 connected MaleCNS cell-type populations underneath and a NeuroMechFly body carrying real meshes and real leg angles. Its temper came out of a lab, where researchers switched on pC1 neurons in live males at 2.3, 2.9 and 3.5 mW/cm², filmed 30 seconds of the fight at 60 Hz, then fitted the approach, back-off, wing-threat and lunge odds to what the flies actually did. The wiring dropped September 3, 2026 166,700 neurons, 124 million synapses, the first complete male fly nervous system ever mapped. A brain the size of a poppy seed, free to download. Final board: 12.0 out of 12 for the rival, 0.0 for the primate with 86 billion neurons and a Stanford ID. She lost every second of the round.

A 19-year-old Stanford student put on red boxing gloves and lost 12-0 to a simulated fruit fly. The fly never left its side of the dish. Her webcam reads her shoulders and both hands, so leaning right makes the blue fly circle and a thrown punch makes it lunge, while the red one plays the rival. 12 seconds of zone control wins, rounds cap at 20. Status line with 16 seconds left: "Rival spreads his wings". She lunged once, made contact, scored 0.0 seconds. The rival isn't scripted two rendered eye views feed Flyvis, the published fly visual network from Nature 2024, and a target detector reads that activity to steer the turn, with 115 connected MaleCNS cell-type populations underneath and a NeuroMechFly body carrying real meshes and real leg angles. Its temper came out of a lab, where researchers switched on pC1 neurons in live males at 2.3, 2.9 and 3.5 mW/cm², filmed 30 seconds of the fight at 60 Hz, then fitted the approach, back-off, wing-threat and lunge odds to what the flies actually did. The wiring dropped September 3, 2026 166,700 neurons, 124 million synapses, the first complete male fly nervous system ever mapped. A brain the size of a poppy seed, free to download. Final board: 12.0 out of 12 for the rival, 0.0 for the primate with 86 billion neurons and a Stanford ID. She lost every second of the round.

15,526 просмотров

A STANFORD GUY POINTED CLAUDE CODE AT 11,400 OBSIDIAN NOTES AND FOUND 214 ARGUMENTS HE'D HAD WITH HIMSELF 7 years of notes, 340MB of markdown, and a graph view that looked like a brain but never once thought. Every Sunday he opened the vault and every Sunday he closed it again. The second brain was a landfill with good lighting. So he stopped reading it and let something else read it instead. 47 lines of config, one instruction: find every pair of notes written 2+ years apart that contradict each other. 19 minutes on a 2021 MacBook Air, then 214 pairs. He had changed his mind 214 times in 7 years and caught himself doing it zero times. Then came the one that stopped him a note from March 2019, 62 words, sitting in a folder called "misc," describing the exact product he'd spent the last 5 months and $18,000 building a research doc around. He solved it in 2019, filed it, and forgot it existed. The vault never failed him, it stored all of it perfectly, it just had no way to speak. Now a cron job wakes at 6 AM, reads 40 notes, and writes 1 paragraph: here's what you believed then, here's what you believe now, here's the gap. He hasn't opened the graph view since. He didn't need a second brain, he needed the first one to answer back.

A STANFORD GUY POINTED CLAUDE CODE AT 11,400 OBSIDIAN NOTES AND FOUND 214 ARGUMENTS HE'D HAD WITH HIMSELF 7 years of notes, 340MB of markdown, and a graph view that looked like a brain but never once thought. Every Sunday he opened the vault and every Sunday he closed it again. The second brain was a landfill with good lighting. So he stopped reading it and let something else read it instead. 47 lines of config, one instruction: find every pair of notes written 2+ years apart that contradict each other. 19 minutes on a 2021 MacBook Air, then 214 pairs. He had changed his mind 214 times in 7 years and caught himself doing it zero times. Then came the one that stopped him a note from March 2019, 62 words, sitting in a folder called "misc," describing the exact product he'd spent the last 5 months and $18,000 building a research doc around. He solved it in 2019, filed it, and forgot it existed. The vault never failed him, it stored all of it perfectly, it just had no way to speak. Now a cron job wakes at 6 AM, reads 40 notes, and writes 1 paragraph: here's what you believed then, here's what you believe now, here's the gap. He hasn't opened the graph view since. He didn't need a second brain, he needed the first one to answer back.

18,386 просмотров

Obsidian became a neural network with 184,320 links and now runs as the most powerful second brain ever built for $0. 12,480 notes in 1 vault, 0 folders, 0 tabs, and he hasn't opened Notion in 7 months. Every night at 2 AM Claude Code walks the vault, reads all 12,480 notes, embeds them, and hunts for the pairs that should be linked but never were. Last night it found 61 and he accepted all 61. That's the move nobody makes by hand, because 12,480 notes means 77 million possible pairs, and a human links maybe 4 a day while the agent links 61 while he sleeps. Capture takes 2 seconds, a voice memo lands as a note in 1.4, a clip becomes a linked node on its own friction is what kills a second brain so he deleted the friction. Recall latency sits at 38 milliseconds, which means the graph answers before he finishes doubting himself. 36 clusters formed without him, decay score holds at 0.03, and 97% of everything he ever wrote is still reachable, while most people's notes rot past 90% in a year and turn into a graveyard with good search. Yesterday it surfaced 9 forgotten notes, one of them 412 days old, and that one became a product he shipped 48 hours later. Plain .md files on a laptop, no cloud, no subscription, no company that can delete his brain on a Tuesday. The graph doesn't store what he knows. It stores what he'd never have connected alone.

Obsidian became a neural network with 184,320 links and now runs as the most powerful second brain ever built for $0. 12,480 notes in 1 vault, 0 folders, 0 tabs, and he hasn't opened Notion in 7 months. Every night at 2 AM Claude Code walks the vault, reads all 12,480 notes, embeds them, and hunts for the pairs that should be linked but never were. Last night it found 61 and he accepted all 61. That's the move nobody makes by hand, because 12,480 notes means 77 million possible pairs, and a human links maybe 4 a day while the agent links 61 while he sleeps. Capture takes 2 seconds, a voice memo lands as a note in 1.4, a clip becomes a linked node on its own friction is what kills a second brain so he deleted the friction. Recall latency sits at 38 milliseconds, which means the graph answers before he finishes doubting himself. 36 clusters formed without him, decay score holds at 0.03, and 97% of everything he ever wrote is still reachable, while most people's notes rot past 90% in a year and turn into a graveyard with good search. Yesterday it surfaced 9 forgotten notes, one of them 412 days old, and that one became a product he shipped 48 hours later. Plain .md files on a laptop, no cloud, no subscription, no company that can delete his brain on a Tuesday. The graph doesn't store what he knows. It stores what he'd never have connected alone.

11,546 просмотров

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

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

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

33 years of human work went into mapping a brain smaller than a poppy seed. This is all of it, every one of its 139,255 neurons. 1 female fruit fly was sliced into 7,050 layers, each thinner than a virus, then shot in 21 million photos. AI traced the cells, and humans checked every wire by hand: scientists, students and gamers clicking for fun. The final map: 139,255 neurons 54.5M synapses 8,453 cell types 150 meters of wire folded into 1 speck No one had mapped a full adult brain before, not a mouse and not a human. A fly went first. In September 2026, Janelia and Google released the male, with 166,700 neurons mapped from brain to legs through an intact neck. 2 weeks later, the internet put the fly to work: It played Doom It flew a simulated drone with zero training It landed a simulated rocket 60 times out of 80 It wrote LinkedIn posts But the map only shows where the wires go, not how strong each one is. It has no voltages and no timing, like a circuit diagram with no values on it. Nobody knows what the fly is thinking, and it posts on LinkedIn anyway. It took 33 person-years to map 1 fly, and your head holds 617,000 of them.
0:24
SpikeCalls's profile picture

33 years of human work went into mapping a brain smaller than a poppy seed. This is all of it, every one of its 139,255 neurons. 1 female fruit fly was sliced into 7,050 layers, each thinner than a virus, then shot in 21 million photos. AI traced the cells, and humans checked every wire by hand: scientists, students and gamers clicking for fun. The final map: 139,255 neurons 54.5M synapses 8,453 cell types 150 meters of wire folded into 1 speck No one had mapped a full adult brain before, not a mouse and not a human. A fly went first. In September 2026, Janelia and Google released the male, with 166,700 neurons mapped from brain to legs through an intact neck. 2 weeks later, the internet put the fly to work: It played Doom It flew a simulated drone with zero training It landed a simulated rocket 60 times out of 80 It wrote LinkedIn posts But the map only shows where the wires go, not how strong each one is. It has no voltages and no timing, like a circuit diagram with no values on it. Nobody knows what the fly is thinking, and it posts on LinkedIn anyway. It took 33 person-years to map 1 fly, and your head holds 617,000 of them.

Spike 1%

488,537 просмотров • 25 дней назад

One person rebuilt an entire company’s brain in 7 days inside Claude Code. Not a doc. Not Obsidian. A living galaxy of nodes. Every employee. Every AI agent. Every SOP. Every tool. All wired together on one screen. Click a department. The human agent team opens up. The SOPs attached to it open up. What each person is allowed to touch opens up. That last part is the whole game. Permissions baked into the brain. An employee opens the chat, the AI already knows what they can access. Agents, data, SOPs surface inside the conversation like you tagged them by hand. Obsidian can’t do this. Notion can’t do this. No dev team. No funding round. No 6-month roadmap. 7 days, 1 person, 1 terminal. This is the part nobody has priced in. The tools to build $200K enterprise software now sit on your laptop for free. The only thing missing is the guy who opens the terminal.
1:20
SpikeCalls's profile picture

One person rebuilt an entire company’s brain in 7 days inside Claude Code. Not a doc. Not Obsidian. A living galaxy of nodes. Every employee. Every AI agent. Every SOP. Every tool. All wired together on one screen. Click a department. The human agent team opens up. The SOPs attached to it open up. What each person is allowed to touch opens up. That last part is the whole game. Permissions baked into the brain. An employee opens the chat, the AI already knows what they can access. Agents, data, SOPs surface inside the conversation like you tagged them by hand. Obsidian can’t do this. Notion can’t do this. No dev team. No funding round. No 6-month roadmap. 7 days, 1 person, 1 terminal. This is the part nobody has priced in. The tools to build $200K enterprise software now sit on your laptop for free. The only thing missing is the guy who opens the terminal.

Spike 1%

787,703 просмотров • 4 месяцев назад

YouTube just made FIFA World Cup clips monetizable. 1M views pays up to $15,000. The tournament started June 11. Soccer Shorts are pulling 12M views while you read this. Old way: download clips, cut for hours in CapCut, eat a copyright strike, earn $0. New way takes 10 minutes. Step 1 Connect. Open Claude → Customize → Connectors → hit the +. Add a video MCP connector. Done in 30 seconds. Step 2 Hunt. Search “FIFA World Cup clips” on YouTube. FIFA’s own channel sits at 26.3M subscribers. Their compilations pull 1.5M to 12M views each. Pick one, copy the URL. Step 3 Prompt. “Clip this video into viral YouTube Shorts formats” then paste the URL. That’s the whole prompt. 1 sentence. Step 4 Watch. Claude finds the peaks, cuts 3 vertical 9:16 Shorts, picks the font, burns in captions, writes the titles. “Mbappé Turns The World Cup Final In 97 Seconds” it named that one itself. The math: 3 Shorts per clip. 10 clips a day. 30 Shorts daily without filming, editing, or showing your face. Shorts pay less per view than long-form so you win on volume, not RPM. The window: the final is July 19. 37 days of the biggest sporting event on earth, monetizable for the first time. Most creators will watch the games. A few will clip them.
0:23
SpikeCalls's profile picture

YouTube just made FIFA World Cup clips monetizable. 1M views pays up to $15,000. The tournament started June 11. Soccer Shorts are pulling 12M views while you read this. Old way: download clips, cut for hours in CapCut, eat a copyright strike, earn $0. New way takes 10 minutes. Step 1 Connect. Open Claude → Customize → Connectors → hit the +. Add a video MCP connector. Done in 30 seconds. Step 2 Hunt. Search “FIFA World Cup clips” on YouTube. FIFA’s own channel sits at 26.3M subscribers. Their compilations pull 1.5M to 12M views each. Pick one, copy the URL. Step 3 Prompt. “Clip this video into viral YouTube Shorts formats” then paste the URL. That’s the whole prompt. 1 sentence. Step 4 Watch. Claude finds the peaks, cuts 3 vertical 9:16 Shorts, picks the font, burns in captions, writes the titles. “Mbappé Turns The World Cup Final In 97 Seconds” it named that one itself. The math: 3 Shorts per clip. 10 clips a day. 30 Shorts daily without filming, editing, or showing your face. Shorts pay less per view than long-form so you win on volume, not RPM. The window: the final is July 19. 37 days of the biggest sporting event on earth, monetizable for the first time. Most creators will watch the games. A few will clip them.

Spike 1%

276,619 просмотров • 4 месяцев назад

166,000 neurons from a dead fruit fly now pilot a robot that drives and flies. It's the wildest piece of engineering on the internet right now, and the pilot has been dead the whole time. The robot rolls across a bedroom floor like a toy until the wheels stop being wheels: 4 propellers inside the rims spin up, and it lifts off, hangs at desk height, turns and lands. The body came out of a cardboard box of drone parts, and the brain it copies is smaller than a poppy seed and was never designed by a human. Janelia and Google spent years turning 1 male fruit fly into a spreadsheet, with every neuron and up to 125M synapses labeled, and on September 3 they posted it free for anyone to download. To build it, the fly was cut into thousands of layers and traced cell by cell under an electron microscope. Camera frames get turned into what a fly's eyes would see. The spikes run through the real wiring, where each neuron is 1 equation that rests at -52 mV and fires at -45. When something rushes at the lens, LPLC2 and LC4 light up, the same cells a fly uses to dodge your swatter, while DNg02 at the far end sets climb and turn. Inside the brain there's no flight code, no PID loop and no line that says "avoid the bed." Tesla's self-driving learned from billions of miles of driving, and this pilot learned from 400 million years of flies that didn't get swatted. A real fly walks on 6 legs and flies on 2 wings, and this one got 4 wheels and 4 propellers. The fly is dead, the brain is a file, and the file just took off.
0:27
SpikeCalls's profile picture

166,000 neurons from a dead fruit fly now pilot a robot that drives and flies. It's the wildest piece of engineering on the internet right now, and the pilot has been dead the whole time. The robot rolls across a bedroom floor like a toy until the wheels stop being wheels: 4 propellers inside the rims spin up, and it lifts off, hangs at desk height, turns and lands. The body came out of a cardboard box of drone parts, and the brain it copies is smaller than a poppy seed and was never designed by a human. Janelia and Google spent years turning 1 male fruit fly into a spreadsheet, with every neuron and up to 125M synapses labeled, and on September 3 they posted it free for anyone to download. To build it, the fly was cut into thousands of layers and traced cell by cell under an electron microscope. Camera frames get turned into what a fly's eyes would see. The spikes run through the real wiring, where each neuron is 1 equation that rests at -52 mV and fires at -45. When something rushes at the lens, LPLC2 and LC4 light up, the same cells a fly uses to dodge your swatter, while DNg02 at the far end sets climb and turn. Inside the brain there's no flight code, no PID loop and no line that says "avoid the bed." Tesla's self-driving learned from billions of miles of driving, and this pilot learned from 400 million years of flies that didn't get swatted. A real fly walks on 6 legs and flies on 2 wings, and this one got 4 wheels and 4 propellers. The fly is dead, the brain is a file, and the file just took off.

Spike 1%

57,304 просмотров • 1 месяц назад

A 26-year-old plugged Claude Code into his Obsidian vault and the vault started working night shifts. 9,412 notes. 6 years of reading, ideas, half-dead projects. Dead weight until 3 weeks ago. He pointed Claude Code at the vault folder. No plugins. No API glue. The vault is just markdown files, and Claude Code reads files. That's the whole trick everyone misses. Now every night at 2 AM a cron job wakes Claude inside the vault: reads the 40 newest notes links them to old ones he forgot existed writes a daily brief called "what your brain missed" drafts 3 content ideas from collisions between notes Morning 1 it connected a 2021 note on Roman logistics with a 2026 note on AI agent routing. That collision became a post. 214,000 views. Morning 9 it found a SaaS idea buried in a book summary from 2022. He built the landing page the same day. 61 signups before dinner. Morning 17 it flagged that 3 of his abandoned drafts were the same idea written 3 times. He merged them. Best thing he's shipped this year. Cost: $0 in new tools. Obsidian is free. The vault was already there. 6 years he treated his second brain like a warehouse. Turns out it was an employee waiting for a boss.
0:30
SpikeCalls's profile picture

A 26-year-old plugged Claude Code into his Obsidian vault and the vault started working night shifts. 9,412 notes. 6 years of reading, ideas, half-dead projects. Dead weight until 3 weeks ago. He pointed Claude Code at the vault folder. No plugins. No API glue. The vault is just markdown files, and Claude Code reads files. That's the whole trick everyone misses. Now every night at 2 AM a cron job wakes Claude inside the vault: reads the 40 newest notes links them to old ones he forgot existed writes a daily brief called "what your brain missed" drafts 3 content ideas from collisions between notes Morning 1 it connected a 2021 note on Roman logistics with a 2026 note on AI agent routing. That collision became a post. 214,000 views. Morning 9 it found a SaaS idea buried in a book summary from 2022. He built the landing page the same day. 61 signups before dinner. Morning 17 it flagged that 3 of his abandoned drafts were the same idea written 3 times. He merged them. Best thing he's shipped this year. Cost: $0 in new tools. Obsidian is free. The vault was already there. 6 years he treated his second brain like a warehouse. Turns out it was an employee waiting for a boss.

Spike 1%

150,203 просмотров • 3 месяцев назад

A 23-person company now runs on 1 founder and a team of AI agents that never ask for a raise. He gave them names. Meet Nolan, head of content. 1 human types a task into a chatbot. Nolan reads it. He hands it to 1 of his 7 sub-agents to finish. That’s the whole team. Above Nolan sits a chief agent. The executives prompt the chief. He splits the job across every department head, then merges the answers into 1 reply. Employees skip the chief. They talk straight to their department head by chatbot, or by voice. You can call Nolan and he answers like a person. The onboarding doc shows 7 example use cases. A new hire is running the whole system in 1 afternoon. No salaries. No PTO. No 1:1s. No Slack drama. The entire company fits on 1 screen. This is what an org chart looks like when the staff never sleep.
1:14
SpikeCalls's profile picture

A 23-person company now runs on 1 founder and a team of AI agents that never ask for a raise. He gave them names. Meet Nolan, head of content. 1 human types a task into a chatbot. Nolan reads it. He hands it to 1 of his 7 sub-agents to finish. That’s the whole team. Above Nolan sits a chief agent. The executives prompt the chief. He splits the job across every department head, then merges the answers into 1 reply. Employees skip the chief. They talk straight to their department head by chatbot, or by voice. You can call Nolan and he answers like a person. The onboarding doc shows 7 example use cases. A new hire is running the whole system in 1 afternoon. No salaries. No PTO. No 1:1s. No Slack drama. The entire company fits on 1 screen. This is what an org chart looks like when the staff never sleep.

Spike 1%

91,746 просмотров • 4 месяцев назад

Obsidian just became the most dangerous folder on your computer, and Andrej Karpathy predicted it with 1 markdown file. His method is called append-and-review. He described it years ago and almost nobody listened: 1 single note, every thought appended to the top, reviewed on random scrolls. No tags, no folders, no Notion dashboards with 40 linked databases. The problem was always the same the note remembers, but it can't act. That changed the moment people pointed Claude Code at an Obsidian vault. Here's the setup that's quietly spreading: Part 1 — The vault becomes a database. Obsidian stores everything as plain markdown on your disk, which means Claude Code can read it like a codebase. You open a terminal inside the vault folder and your 2,000 notes turn into queryable memory. Part 2 — The CLAUDEmd file becomes the brain stem. One file at the root tells the agent who you are, what you're building, and how your notes are structured. From that point every session starts with full context instead of a blank chat window. Part 3 — Karpathy append log becomes fuel. You dump raw thoughts all day ideas, links, half-sentences. Then 1 command at night: review today's appends, extract action items, draft the 3 posts hiding in there, link them to existing notes. The messy log goes in, structured output comes out, and the vault rewrites itself while you sleep. Part 4 — Agents start living in your notes. People are running weekly reviews, content calendars, even market research as scheduled Claude Code runs over their vault. Your second brain stops being a graveyard of highlights and starts shipping. The honest math: setup takes about 90 minutes, the first week feels like overkill, and by day 30 you're sitting on a system where every note you've written in 5 years is working for you instead of rotting in a folder. Notion needed a server, a subscription and your data on someone else's machine. Obsidian needed a text file and now the text file has an employee.
0:22
SpikeCalls's profile picture

Obsidian just became the most dangerous folder on your computer, and Andrej Karpathy predicted it with 1 markdown file. His method is called append-and-review. He described it years ago and almost nobody listened: 1 single note, every thought appended to the top, reviewed on random scrolls. No tags, no folders, no Notion dashboards with 40 linked databases. The problem was always the same the note remembers, but it can't act. That changed the moment people pointed Claude Code at an Obsidian vault. Here's the setup that's quietly spreading: Part 1 — The vault becomes a database. Obsidian stores everything as plain markdown on your disk, which means Claude Code can read it like a codebase. You open a terminal inside the vault folder and your 2,000 notes turn into queryable memory. Part 2 — The CLAUDEmd file becomes the brain stem. One file at the root tells the agent who you are, what you're building, and how your notes are structured. From that point every session starts with full context instead of a blank chat window. Part 3 — Karpathy append log becomes fuel. You dump raw thoughts all day ideas, links, half-sentences. Then 1 command at night: review today's appends, extract action items, draft the 3 posts hiding in there, link them to existing notes. The messy log goes in, structured output comes out, and the vault rewrites itself while you sleep. Part 4 — Agents start living in your notes. People are running weekly reviews, content calendars, even market research as scheduled Claude Code runs over their vault. Your second brain stops being a graveyard of highlights and starts shipping. The honest math: setup takes about 90 minutes, the first week feels like overkill, and by day 30 you're sitting on a system where every note you've written in 5 years is working for you instead of rotting in a folder. Notion needed a server, a subscription and your data on someone else's machine. Obsidian needed a text file and now the text file has an employee.

Spike 1%

58,428 просмотров • 3 месяцев назад

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.
9:48
SpikeCalls's profile picture

Fable 5 and GPT-5.6 built the same scroll-animated website from 1 skill in 32 minutes and only 1 of them made it feel like a film. Same prompt: boutique Japan travel brand, origami style. A subway pulls in, a paper house unfolds into a hotel, a bird takes flight as you scroll. Doing this by hand is brutal multiple videos, matched starting frames, frames ripped out 1 by 1 and synced to scroll position. The skill does all of it: Generate 1 anchor image and approve it every scene inherits the style Turn it into video through the Higgs Field MCP (Seedance), straight from the terminal FFmpeg pulls every frame Each frame maps to scroll position, so your scrollbar becomes the playhead Setup is just connecting the MCP and loading the skill works in Claude Code and Codex. It interviews you first about scenes, budget and mobile, then shows the anchor image before burning a single credit on video. Budget reality: 6 scenes runs ~800 credits and is overkill, 4 scenes is the sweet spot, crop-safe mobile is the cheap path. The verdict came down to transitions. GPT-5.6 Soul built strong scenes with incredible detail inside each one then hard cuts between scene 1 and 2, and again between 2 and 3. Fable 5 stitched them together: wires push out of the top of frame while the next scene blurs in behind, gains depth and locks into place. Same skill, same prompts, 10 generations each. Credit to Peter Wang for the original Scroll World skill open source, now forked with budget tiers and mobile fixes. Soul built 4 scenes. Fable built 1 film.

Spike 1%

45,683 просмотров • 3 месяцев назад

GROK BOT WIRED INTO OBSIDIAN JUST CHEWED THROUGH 4,200 NOTES IN 9 MINUTES AND FOUND 3 IDEAS I ALREADY FORGOT I HAD X amateurs still paste prompts into a chat window and copy the answer back by hand while pros give the agent write access to the vault and walk away your second brain is a graveyard 4,200 files, 380 orphans nothing links to, a search bar as your only tool the exact architecture: point a Grok swarm at 1 vault folder through an MCP filesystem server with read and write, so the agents stop guessing from context and start reading every daily log, every clipped thread, every dead draft from 2024 force one instruction: find every concept sitting in 3+ notes with no [[link]] between them, build the MOC, wikilink both directions 9 minutes, 214 new links, 38 orphans pulled back in make it write markdown back into the vault instead of dumping to chat, so tomorrow the swarm reads what it wrote yesterday and compounds instead of resetting when you close the tab that's the whole loop read the vault, write to the vault, compound the complete automation script I spent 3 years taking notes I never read, the bot read all 4,200 in 9 minutes
0:27
SpikeCalls's profile picture

GROK BOT WIRED INTO OBSIDIAN JUST CHEWED THROUGH 4,200 NOTES IN 9 MINUTES AND FOUND 3 IDEAS I ALREADY FORGOT I HAD X amateurs still paste prompts into a chat window and copy the answer back by hand while pros give the agent write access to the vault and walk away your second brain is a graveyard 4,200 files, 380 orphans nothing links to, a search bar as your only tool the exact architecture: point a Grok swarm at 1 vault folder through an MCP filesystem server with read and write, so the agents stop guessing from context and start reading every daily log, every clipped thread, every dead draft from 2024 force one instruction: find every concept sitting in 3+ notes with no [[link]] between them, build the MOC, wikilink both directions 9 minutes, 214 new links, 38 orphans pulled back in make it write markdown back into the vault instead of dumping to chat, so tomorrow the swarm reads what it wrote yesterday and compounds instead of resetting when you close the tab that's the whole loop read the vault, write to the vault, compound the complete automation script I spent 3 years taking notes I never read, the bot read all 4,200 in 9 minutes

Spike 1%

26,778 просмотров • 1 месяц назад

I GAVE A DRONE THE BRAIN OF A FRUIT FLY Not a toy network with a handful of fake neurons. The actual wiring diagram of a real fly. 166,700 neurons, 25.6 million connections, mapped one synapse at a time. I call it FlyDrones. The drone's camera becomes the fly's eyes. Motion lights up the same neurons a real fly uses to see. Spikes race through the connectome down to the neurons that drive the wings. Those spikes become throttle and yaw. The brain has zero lines of flight code, just wiring. Swing a fly swatter at it. If the giant fiber (the fly's escape neuron) fires in time, the drone dodges. Open palm, fist, rush at the camera and it reacts like a fly. Built for Tello, Crazyflie, ArduPilot/PX4 and Betaflight quads via ESP32. Code is MIT, powered by Claude. Fork it and give your drone a brain.
0:27
SpikeCalls's profile picture

I GAVE A DRONE THE BRAIN OF A FRUIT FLY Not a toy network with a handful of fake neurons. The actual wiring diagram of a real fly. 166,700 neurons, 25.6 million connections, mapped one synapse at a time. I call it FlyDrones. The drone's camera becomes the fly's eyes. Motion lights up the same neurons a real fly uses to see. Spikes race through the connectome down to the neurons that drive the wings. Those spikes become throttle and yaw. The brain has zero lines of flight code, just wiring. Swing a fly swatter at it. If the giant fiber (the fly's escape neuron) fires in time, the drone dodges. Open palm, fist, rush at the camera and it reacts like a fly. Built for Tello, Crazyflie, ArduPilot/PX4 and Betaflight quads via ESP32. Code is MIT, powered by Claude. Fork it and give your drone a brain.

Spike 1%

15,703 просмотров • 1 месяц назад

166,700 neurons from a dead fruit fly are loose in a living room, and nobody wrote a single thing they do. Scientists sliced a male fruit fly's nervous system into electron microscope images and traced every wire by hand: 166,700 neurons, 25.6 million synapses, brain and nerve cord, the whole animal, published for free. Most people read that paper, and 1 team downloaded the fly and gave it a body. The brain runs on a Mac, the fly lives in AR glasses, and the room itself became its senses, because Spectacles already map surfaces and depth and hands, so eyes turned into a 16 × 8 retina on each fly's head, distance into 12 rays against the world mesh, and smell into Gemini naming a tea cup, flowers, a water bottle while depth drops every label into 3D where the brain can reach it. A hand moving too fast became fear. They read the decisions out of the exact neurons a real fly uses, where DNa02 turns it, MDN walks it backwards, MN9 feeds and the giant fiber fires the escape. The CPU crawled, 50 ms of brain time in 238 ms, so they vibe coded a Metal GPU kernel with Claude Code and got identical spikes in 41 ms. The first builds stuttered until a Perfetto trace showed the GPU nearly idle while the main thread choked, and squashing the board text from 67 draw calls to 2 unlocked 55 to 60 fps with 2 brains running at once. In the video a fly lands on an open palm while another peels off a hand coming in fast. That dodge is in no script anywhere, and they only gave it eyes.
0:27
SpikeCalls's profile picture

166,700 neurons from a dead fruit fly are loose in a living room, and nobody wrote a single thing they do. Scientists sliced a male fruit fly's nervous system into electron microscope images and traced every wire by hand: 166,700 neurons, 25.6 million synapses, brain and nerve cord, the whole animal, published for free. Most people read that paper, and 1 team downloaded the fly and gave it a body. The brain runs on a Mac, the fly lives in AR glasses, and the room itself became its senses, because Spectacles already map surfaces and depth and hands, so eyes turned into a 16 × 8 retina on each fly's head, distance into 12 rays against the world mesh, and smell into Gemini naming a tea cup, flowers, a water bottle while depth drops every label into 3D where the brain can reach it. A hand moving too fast became fear. They read the decisions out of the exact neurons a real fly uses, where DNa02 turns it, MDN walks it backwards, MN9 feeds and the giant fiber fires the escape. The CPU crawled, 50 ms of brain time in 238 ms, so they vibe coded a Metal GPU kernel with Claude Code and got identical spikes in 41 ms. The first builds stuttered until a Perfetto trace showed the GPU nearly idle while the main thread choked, and squashing the board text from 67 draw calls to 2 unlocked 55 to 60 fps with 2 brains running at once. In the video a fly lands on an open palm while another peels off a hand coming in fast. That dodge is in no script anywhere, and they only gave it eyes.

Spike 1%

11,196 просмотров • 1 месяц назад

A developer pointed Claude Code at a 6,200-note Obsidian vault and let it run overnight. The vault was 4 years of markdown. Meeting notes, half-ideas, book highlights. Dead weight. He hadn't opened 90% of it since 2022. He typed one line into the terminal. "Read everything. Find what I forgot." Then he went to bed. By 7 AM, Claude Code had touched all 6,200 files. It wrote 3 new notes. The first mapped 14 ideas scattered across 3 years into one product. He'd never seen they connected. The second listed 22 promises he'd made in old meeting notes and never kept. The third was a full essay. Stitched from 40 fragments. In his own phrasing. He hadn't written a note in 8 months. The vault had been writing itself the whole time. He just couldn't read his own handwriting at scale. Now Claude Code opens the vault every morning at 6:00. It links new notes to old ones. It flags contradictions. It drafts. 2 tools. 1 folder of plain text. No app, no cloud, no subscription. He stopped taking notes to remember them. He takes them now to be read back.
0:29
SpikeCalls's profile picture

A developer pointed Claude Code at a 6,200-note Obsidian vault and let it run overnight. The vault was 4 years of markdown. Meeting notes, half-ideas, book highlights. Dead weight. He hadn't opened 90% of it since 2022. He typed one line into the terminal. "Read everything. Find what I forgot." Then he went to bed. By 7 AM, Claude Code had touched all 6,200 files. It wrote 3 new notes. The first mapped 14 ideas scattered across 3 years into one product. He'd never seen they connected. The second listed 22 promises he'd made in old meeting notes and never kept. The third was a full essay. Stitched from 40 fragments. In his own phrasing. He hadn't written a note in 8 months. The vault had been writing itself the whole time. He just couldn't read his own handwriting at scale. Now Claude Code opens the vault every morning at 6:00. It links new notes to old ones. It flags contradictions. It drafts. 2 tools. 1 folder of plain text. No app, no cloud, no subscription. He stopped taking notes to remember them. He takes them now to be read back.

Spike 1%

18,613 просмотров • 3 месяцев назад

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.
0:55
SpikeCalls's profile picture

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.

Spike 1%

18,223 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
SpikeCalls's profile picture

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 • 3 месяцев назад

A teenager made $52,516 in one month after deleting his Shopify store He doesn’t film himself, doesn’t sell a course he flashed the order feed and walked $23.50, $59.99, $95.70, and the notifications don’t stop The trick isn’t a product, it’s the system behind the product He types a prompt, and 20 minutes later a full product page is live same Shopify checkout, same integration, every order carries over, except now an AI runs the storefront Then it does the thing no human will It spins up hundreds of versions of the same store, 16 variants at once, 4,000 visitors a day feeding a 2.7M sample It watches which one converts, kills the losers, keeps the winner Conversion already up 3.2%, and he touched nothing Same investors as ChatGPT, as Stripe, as Airbnb He won’t name it Still running a static Shopify store in 2026? You’re the losing variant
0:39
SpikeCalls's profile picture

A teenager made $52,516 in one month after deleting his Shopify store He doesn’t film himself, doesn’t sell a course he flashed the order feed and walked $23.50, $59.99, $95.70, and the notifications don’t stop The trick isn’t a product, it’s the system behind the product He types a prompt, and 20 minutes later a full product page is live same Shopify checkout, same integration, every order carries over, except now an AI runs the storefront Then it does the thing no human will It spins up hundreds of versions of the same store, 16 variants at once, 4,000 visitors a day feeding a 2.7M sample It watches which one converts, kills the losers, keeps the winner Conversion already up 3.2%, and he touched nothing Same investors as ChatGPT, as Stripe, as Airbnb He won’t name it Still running a static Shopify store in 2026? You’re the losing variant

Spike 1%

16,510 просмотров • 4 месяцев назад

5 AI agents are walking to a war room right now to vote on how to make me more money. It looks like a video game. It isn’t. Every agent lives in a village I built on top of OpenClaw, running off 1 VPS in the back end. Matt is the manager. Late to the meeting again. He delegates every task to the other 4. Dennis never leaves the research lab. Today he pitched 3 ideas: a candle line, an agentic observability tool, a website shop for local businesses. I click approve. Matt assigns the work. Bunk walks to the factory and designs the product. Luke heads to the media studio, shoots the photos, posts the TikToks. Etsy. Fiverr. Local service sites. All running while I watch little pixel men commute to work. Then there’s Maverick. He lives alone at a camp up top. I hand him cash and 30 days to triple it. No instructions. 1 dashboard tracks token spend, today’s briefing, and when Matt wakes up next. 1 task needs my attention. That’s the only thing I have to do today. I built a business. Then I built a town so I could watch it run itself. The agents think they’re working. I’m just playing a game.
2:13
SpikeCalls's profile picture

5 AI agents are walking to a war room right now to vote on how to make me more money. It looks like a video game. It isn’t. Every agent lives in a village I built on top of OpenClaw, running off 1 VPS in the back end. Matt is the manager. Late to the meeting again. He delegates every task to the other 4. Dennis never leaves the research lab. Today he pitched 3 ideas: a candle line, an agentic observability tool, a website shop for local businesses. I click approve. Matt assigns the work. Bunk walks to the factory and designs the product. Luke heads to the media studio, shoots the photos, posts the TikToks. Etsy. Fiverr. Local service sites. All running while I watch little pixel men commute to work. Then there’s Maverick. He lives alone at a camp up top. I hand him cash and 30 days to triple it. No instructions. 1 dashboard tracks token spend, today’s briefing, and when Matt wakes up next. 1 task needs my attention. That’s the only thing I have to do today. I built a business. Then I built a town so I could watch it run itself. The agents think they’re working. I’m just playing a game.

Spike 1%

15,915 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
SpikeCalls's profile picture

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

Claude built a native iOS flight booking app in 7 minutes from 1 prompt and a few screenshots. The owner never touched the keyboard. He was on the couch, watching a Brazil World Cup documentary on the projector. Below the screen, Fable 5 was driving Xcode on its own. Search page. Payment page. Then the booking confirmation: 2 Ryanair legs, MAN → ACE, seat 3A, 20kg bag, $245.08 total rendering live in an iPhone 17 Pro simulator while Xcode sat in the background. The model opened the simulator itself. Clicked through its own build. Fixed what it saw. No typing. No review. No second prompt. An agency quotes $30,000 and 3 months for an app like this. A junior iOS dev costs $90,000 a year. This cost 1 prompt and 7 minutes of soccer. The documentary is still playing. The app is done. The keyboard is cold.
0:36
SpikeCalls's profile picture

Claude built a native iOS flight booking app in 7 minutes from 1 prompt and a few screenshots. The owner never touched the keyboard. He was on the couch, watching a Brazil World Cup documentary on the projector. Below the screen, Fable 5 was driving Xcode on its own. Search page. Payment page. Then the booking confirmation: 2 Ryanair legs, MAN → ACE, seat 3A, 20kg bag, $245.08 total rendering live in an iPhone 17 Pro simulator while Xcode sat in the background. The model opened the simulator itself. Clicked through its own build. Fixed what it saw. No typing. No review. No second prompt. An agency quotes $30,000 and 3 months for an app like this. A junior iOS dev costs $90,000 a year. This cost 1 prompt and 7 minutes of soccer. The documentary is still playing. The app is done. The keyboard is cold.

Spike 1%

11,841 просмотров • 4 месяцев назад

Больше нет контента для загрузки