Загрузка видео...

Не удалось загрузить видео

На главную

A FLY IS NOW WRITING PYTHON CODE WITH ITS OWN NERVOUS SYSTEM I genuinely didn't expect a fly to end up behind a code editor. The setup is strangely simple. A fly sits on a keyboard while its neural activity is captured in real time. On the other side...

insomnia_vip's profile picture

Insomnia

4,424 subscribers

11,764 просмотров • 4 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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.
0:15

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.

Spike 1%

1,026,314 просмотров • 4 дней назад

NEURALINK: REAL-TIME BRAIN ACTIVITY, STREAMED Neuralink's implanted neural device is already delivering what scientists have chased for decades: live visibility into human brain activity within minutes of surgery. In this demo, signals flare as a participant wakes up post-procedure - the device capturing the gradual surge of neural activity in real time. It’s a glimpse of the frontier: hardware that doesn’t just record the brain, but streams its inner rhythms instantly. From clinical care to brain-computer interfaces, the implications are massive. Source: Neuralink
0:13

NEURALINK: REAL-TIME BRAIN ACTIVITY, STREAMED Neuralink's implanted neural device is already delivering what scientists have chased for decades: live visibility into human brain activity within minutes of surgery. In this demo, signals flare as a participant wakes up post-procedure - the device capturing the gradual surge of neural activity in real time. It’s a glimpse of the frontier: hardware that doesn’t just record the brain, but streams its inner rhythms instantly. From clinical care to brain-computer interfaces, the implications are massive. Source: Neuralink

Mario Nawfal

204,494 просмотров • 1 год назад

A CLUB JUST ASKED MY FLY TO DJ THEIR ENTIRE NIGHT Yesterday I got a message from a club called Neon Hive with a completely insane proposal: they wanted my FLY to run their next party from start to finish and choose everything by itself. They wanted no human controlling the set. So I gave them my code, connected the system to their DJ setup and let the fly take over the booth for the night. From that moment, every decision was hers. Fly picked what played next, controlled the decks and kept the party moving while hundreds of people danced, sang and had absolutely no idea who was actually running the music. The weirdest part is watching the footage afterward. You see a packed nightclub going completely crazy while this tiny fly is sitting behind the decks with its headphones on, casually running the entire night like this is what it was born to do. Nobody in the crowd knows their DJ is an insect. And somehow, the party just keeps going. Neon Hive might have been the first club brave enough to hire a FLY
0:13

A CLUB JUST ASKED MY FLY TO DJ THEIR ENTIRE NIGHT Yesterday I got a message from a club called Neon Hive with a completely insane proposal: they wanted my FLY to run their next party from start to finish and choose everything by itself. They wanted no human controlling the set. So I gave them my code, connected the system to their DJ setup and let the fly take over the booth for the night. From that moment, every decision was hers. Fly picked what played next, controlled the decks and kept the party moving while hundreds of people danced, sang and had absolutely no idea who was actually running the music. The weirdest part is watching the footage afterward. You see a packed nightclub going completely crazy while this tiny fly is sitting behind the decks with its headphones on, casually running the entire night like this is what it was born to do. Nobody in the crowd knows their DJ is an insect. And somehow, the party just keeps going. Neon Hive might have been the first club brave enough to hire a FLY

Insomnia

84,256 просмотров • 1 день назад

a real fly brain saw its 40th video 3 seconds ago. it did not choose any of them. it never will. that's FLYTOK. I open-sourced a live simulation of a real fruit fly connectome and gave it a phone. here's exactly what 166,700 neurons do while you scroll: THE WIRING MaleCNS v1.0. the reconstructed central nervous system of a real male Drosophila. 166,700 neurons. 25,582,938 directed connections. 124,177,617 synaptic contacts. nothing cropped. no "simplified 1,000-neuron version" running behind the scenes. the whole graph is in memory on every single step. THE LOCK the app checksums the connectome against SHA-256 before it's allowed to boot. one array off by a byte and the brain refuses to start. you are either watching the real MaleCNS graph or you are watching nothing. THE SPIKES every neuron is a leaky integrate-and-fire cell. crosses −45 mV, it fires. the spike lands 1.8 ms later. 2.2 ms of silence, then it's live again. the network advances in 0.1 ms steps inside a compiled C++ kernel. roughly 1.2 million spikes per simulated second. THE EYES the browser captures the phone at 90×160 pixels. brightness drives 3,335 R1–R6 photoreceptors. color drives 811 R8 cells, blue and green. each one is placed on the screen by inferring its eye column from its real connections onto L1, L2, L3. real input, through real visual wiring. it's measurable. same brain, same saved state. 100 ms of white produced 127,378 spikes. black produced 92,952. the screen changes the brain. THE ALGORITHM while a video plays, I inject a fixed current into all 15 PAM11 dopamine neurons in the mushroom body. that's it. that's the whole trick. matched 200 ms control: 0 PAM11 spikes. drive on: 261. live, it sits at 85–97 Hz for as long as the feed runs. the fly does not earn it. an app decided watching one more should feel good. THE PLASTICITY 7,835 Kenyon-cell connections onto MBON07 and MBON11 can change. dopamine fires while Kenyon cells were active, those synapses weaken, floored at 10% and never flipping sign. after one stimulated run, 3,087 of them no longer matched their original weight. freeze it and they stay put. restore a checkpoint, replay the input, identical spikes bit for bit. THE SWIPE every 3 seconds the front right leg reaches up and strokes the screen, on the same 900 ms timeline as the video transition. wings, legs and head turns come from actual motor firing, MN9, DNp09, left-vs-right DNa02. those are real. the swipe is not. the fly never decides to swipe. the feed decides for it. ONE BRAIN this isn't a video of a simulation. it's the simulation. there is exactly one brain on one server. whoever loads the page first becomes its eyes and supplies the frames. everyone else watches the same brain react in real time. no video, no input, it just waits. no data, no numbers, the overlay shows nothing. it never invents a reading to look alive. THE HONEST PART the wiring is real. the physiology is approximate. the eyes are approximate. the dopamine is artificial. the feed is on a timer. the learning rule is unvalidated on this connectome. nothing here shows the fly enjoys it, prefers it, is addicted, or experiences anything at all. no living fly was involved. it took a few hundred lines of glue code to build a loop out of a screen, a timer and a reward signal wired to the right cells. imagine what an industry with a budget can do. open source. MaleCNS under CC BY 4.0. runs on your own machine, 16 GB RAM and a few GB of disk. the fly is still scrolling. nobody is coming to take the phone away. links in the reply.
0:12

a real fly brain saw its 40th video 3 seconds ago. it did not choose any of them. it never will. that's FLYTOK. I open-sourced a live simulation of a real fruit fly connectome and gave it a phone. here's exactly what 166,700 neurons do while you scroll: THE WIRING MaleCNS v1.0. the reconstructed central nervous system of a real male Drosophila. 166,700 neurons. 25,582,938 directed connections. 124,177,617 synaptic contacts. nothing cropped. no "simplified 1,000-neuron version" running behind the scenes. the whole graph is in memory on every single step. THE LOCK the app checksums the connectome against SHA-256 before it's allowed to boot. one array off by a byte and the brain refuses to start. you are either watching the real MaleCNS graph or you are watching nothing. THE SPIKES every neuron is a leaky integrate-and-fire cell. crosses −45 mV, it fires. the spike lands 1.8 ms later. 2.2 ms of silence, then it's live again. the network advances in 0.1 ms steps inside a compiled C++ kernel. roughly 1.2 million spikes per simulated second. THE EYES the browser captures the phone at 90×160 pixels. brightness drives 3,335 R1–R6 photoreceptors. color drives 811 R8 cells, blue and green. each one is placed on the screen by inferring its eye column from its real connections onto L1, L2, L3. real input, through real visual wiring. it's measurable. same brain, same saved state. 100 ms of white produced 127,378 spikes. black produced 92,952. the screen changes the brain. THE ALGORITHM while a video plays, I inject a fixed current into all 15 PAM11 dopamine neurons in the mushroom body. that's it. that's the whole trick. matched 200 ms control: 0 PAM11 spikes. drive on: 261. live, it sits at 85–97 Hz for as long as the feed runs. the fly does not earn it. an app decided watching one more should feel good. THE PLASTICITY 7,835 Kenyon-cell connections onto MBON07 and MBON11 can change. dopamine fires while Kenyon cells were active, those synapses weaken, floored at 10% and never flipping sign. after one stimulated run, 3,087 of them no longer matched their original weight. freeze it and they stay put. restore a checkpoint, replay the input, identical spikes bit for bit. THE SWIPE every 3 seconds the front right leg reaches up and strokes the screen, on the same 900 ms timeline as the video transition. wings, legs and head turns come from actual motor firing, MN9, DNp09, left-vs-right DNa02. those are real. the swipe is not. the fly never decides to swipe. the feed decides for it. ONE BRAIN this isn't a video of a simulation. it's the simulation. there is exactly one brain on one server. whoever loads the page first becomes its eyes and supplies the frames. everyone else watches the same brain react in real time. no video, no input, it just waits. no data, no numbers, the overlay shows nothing. it never invents a reading to look alive. THE HONEST PART the wiring is real. the physiology is approximate. the eyes are approximate. the dopamine is artificial. the feed is on a timer. the learning rule is unvalidated on this connectome. nothing here shows the fly enjoys it, prefers it, is addicted, or experiences anything at all. no living fly was involved. it took a few hundred lines of glue code to build a loop out of a screen, a timer and a reward signal wired to the right cells. imagine what an industry with a budget can do. open source. MaleCNS under CC BY 4.0. runs on your own machine, 16 GB RAM and a few GB of disk. the fly is still scrolling. nobody is coming to take the phone away. links in the reply.

sopersone

37,608 просмотров • 7 дней назад

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.
0:14

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.

Spike 1%

102,643 просмотров • 3 дней назад

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.
0:12

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.

Spike 1%

272,128 просмотров • 1 день назад

Google just gave away the full wiring diagram of a fruit fly's brain, and a student turned it into an AI agent. Google and HHMI Janelia spent 10 years mapping the full nervous system of one male fruit fly, then released the complete map for free on September 3. 166,700 neurons. 24.5 million synapses. Every wire from eye to leg, mapped and public. She turned the wiring into a leaky integrate and fire simulation and gave it a job. A camera tracks her fingers, the movement hits the fly's sensory neurons, and whatever motor neurons fire decide what a robot does on the other side of the screen. ▪ Pinch triggers running implementation ▪ Point spins up a new implementation ▪ Pull back triggers heavy lifting Twelve days ago this brain was just a dataset. Then it played DOOM. Then Chrome Dino. Then it walked a Strandbeest. Now it works for a student. This isn't a living fly. It's a computer model of real wiring, and she built the bridge between her hand and its neurons herself. The fly died years ago. Its wiring still takes orders.
0:14

Google just gave away the full wiring diagram of a fruit fly's brain, and a student turned it into an AI agent. Google and HHMI Janelia spent 10 years mapping the full nervous system of one male fruit fly, then released the complete map for free on September 3. 166,700 neurons. 24.5 million synapses. Every wire from eye to leg, mapped and public. She turned the wiring into a leaky integrate and fire simulation and gave it a job. A camera tracks her fingers, the movement hits the fly's sensory neurons, and whatever motor neurons fire decide what a robot does on the other side of the screen. ▪ Pinch triggers running implementation ▪ Point spins up a new implementation ▪ Pull back triggers heavy lifting Twelve days ago this brain was just a dataset. Then it played DOOM. Then Chrome Dino. Then it walked a Strandbeest. Now it works for a student. This isn't a living fly. It's a computer model of real wiring, and she built the bridge between her hand and its neurons herself. The fly died years ago. Its wiring still takes orders.

Zentrix⌚️

61,569 просмотров • 1 день назад

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.
0:13

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.

Spike 1%

760,145 просмотров • 3 дней назад

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇
0:17

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇

darkzodchi

406,556 просмотров • 2 месяцев назад

When Ghostty detects a password input prompt, it now changes the cursor to a lock and on macOS enables the secure input API. When the secure input API is enabled, we show a neat, animated icon that explains what's going on when clicked. Another example of native UI wins (imo). Secure Input is the macOS system API that prevents accessibility APIs from reading your keystrokes, so things like screen recording software and so on can't read your passwords. Other terminals on macOS support secure input. I think only iTerm also supports secure input on password detection. So as a disclaimer, I'm not trying to claim this as a huge innovation, I just think our implementation is nice. 😊
0:13

When Ghostty detects a password input prompt, it now changes the cursor to a lock and on macOS enables the secure input API. When the secure input API is enabled, we show a neat, animated icon that explains what's going on when clicked. Another example of native UI wins (imo). Secure Input is the macOS system API that prevents accessibility APIs from reading your keystrokes, so things like screen recording software and so on can't read your passwords. Other terminals on macOS support secure input. I think only iTerm also supports secure input on password detection. So as a disclaimer, I'm not trying to claim this as a huge innovation, I just think our implementation is nice. 😊

Mitchell Hashimoto

81,773 просмотров • 2 лет назад

ClickUp is working on agents that build custom user interfaces on the fly. > Agents can build custom interactive blocks, with buttons, editable fields, and embedded charts. > Agents decide what the user needs to see and construct an interactive experience in real time. > Clicking or editing inside a generated block can fire an action directly. Agents will be able to create a working code block that responds to users' input, built in the moment for the task at hand.
0:15

ClickUp is working on agents that build custom user interfaces on the fly. > Agents can build custom interactive blocks, with buttons, editable fields, and embedded charts. > Agents decide what the user needs to see and construct an interactive experience in real time. > Clicking or editing inside a generated block can fire an action directly. Agents will be able to create a working code block that responds to users' input, built in the moment for the task at hand.

🚨 AI News | TestingCatalog

12,841 просмотров • 1 месяц назад

ToggleX is now live here: ToggleX is an Ambient Work Intelligence Fabric that sits across your tools and turns everyday activity into work intelligence: context, insights and simple signals. Join as an early user with this limited-time discount code: EARLYX Find a special code in the new Era 1 & Era 2 dashboard here: Paid users all going to be key participants in the new Season X. More details next year.
0:12

ToggleX is now live here: ToggleX is an Ambient Work Intelligence Fabric that sits across your tools and turns everyday activity into work intelligence: context, insights and simple signals. Join as an early user with this limited-time discount code: EARLYX Find a special code in the new Era 1 & Era 2 dashboard here: Paid users all going to be key participants in the new Season X. More details next year.

Toggle

18,300 просмотров • 9 месяцев назад

New favorite noise function! I had lots of fun tweaking the yonatan shader and ended up using it as a semi-transparent overlay With color changing on scroll and slight cursor response, the total code size is still <9 kb 🫣 Live demo & source code: Original algorithm:
0:13

New favorite noise function! I had lots of fun tweaking the yonatan shader and ended up using it as a semi-transparent overlay With color changing on scroll and slight cursor response, the total code size is still <9 kb 🫣 Live demo & source code: Original algorithm:

Ksenia Kondrashova

20,374 просмотров • 2 лет назад

scary fact: if you repeat a lie many times, your brain may start to believe it's true. neuroscience suggests the brain does not only respond to what is objectively true. It responds to what is repeatedly rehearsed. through neuroplasticity, repeated thoughts strengthen neural pathways; through predictive processing, the brain begins filtering reality around what it expects to find. so even a belief that starts as "not true yet" can slowly become familiar to the nervous system. and once something feels familiar, the brain starts treating it as more available, more possible, and eventually more real.
0:12

scary fact: if you repeat a lie many times, your brain may start to believe it's true. neuroscience suggests the brain does not only respond to what is objectively true. It responds to what is repeatedly rehearsed. through neuroplasticity, repeated thoughts strengthen neural pathways; through predictive processing, the brain begins filtering reality around what it expects to find. so even a belief that starts as "not true yet" can slowly become familiar to the nervous system. and once something feels familiar, the brain starts treating it as more available, more possible, and eventually more real.

alexei

101,419 просмотров • 27 дней назад

Yesterday at 3 AM Claude Code called me I woke up, picked up the phone, and on the screen was a message: "Wallet entered BTC Up at 11 cents. Open Polymarket?" I said yes and went back to sleep Claude Code unlocked my 2nd phone on its own, opened Polymarket, found the right market, entered the amount, and hit Buy. I could see all of it in real time through the web interface on my laptop. Screenshots from the phone updating every second. By morning the position closed in profit Let me tell you how I got here A week ago I asked Claude Code to write a script that pulls on-chain data from Polymarket and ranks wallets by win rate on 15-minute BTC markets In 20 minutes I had a table with hundreds of addresses, and 1 of them stood apart from the rest. More than 200 trades per day, surgical entry precision, and a profit curve going straight up I fed that address back into Claude Code and asked it to break down the strategy. Turns out the wallet monitors BTC volatility on Binance and Bybit every 100 milliseconds, and when it drops below 0.08% it enters Up and Down simultaneously at 25 to 35 cents A pure straddle: 1 side burns and the other flies to a dollar, giving 3 to 4x per position. Dozens of times a day I wanted to follow it but signals came at any hour, and waking up every 15 minutes for a notification was simply impossible. So I built something else Took an old Android phone and installed an agent running on the Qwen3-VL visual model. It sees what is happening on the screen and mimics human actions through ADB: taps, swipes, text input. Then I connected it to Claude Code as the executor Now the chain works like this: Claude Code monitors the wallet, sees a new position, calls me. And if I say "yes" or just do not pick up within 30 seconds, the agent on the phone opens Polymarket on its own and copies the entry Essentially I built myself an autopilot out of 2 AI systems: 1 thinks and the other presses buttons. I just sleep and occasionally pick up the phone → Here is the wallet the whole thing is tracking: For those who do not want to build a setup like this there is a Telegram bot that handles the 1st part: tracks this wallet and sends a signal on every new entry: AI calls me at 3 AM to ask permission to spend my money A year ago this would have sounded like schizophrenia. Now it is just Tuesday
0:15

Yesterday at 3 AM Claude Code called me I woke up, picked up the phone, and on the screen was a message: "Wallet entered BTC Up at 11 cents. Open Polymarket?" I said yes and went back to sleep Claude Code unlocked my 2nd phone on its own, opened Polymarket, found the right market, entered the amount, and hit Buy. I could see all of it in real time through the web interface on my laptop. Screenshots from the phone updating every second. By morning the position closed in profit Let me tell you how I got here A week ago I asked Claude Code to write a script that pulls on-chain data from Polymarket and ranks wallets by win rate on 15-minute BTC markets In 20 minutes I had a table with hundreds of addresses, and 1 of them stood apart from the rest. More than 200 trades per day, surgical entry precision, and a profit curve going straight up I fed that address back into Claude Code and asked it to break down the strategy. Turns out the wallet monitors BTC volatility on Binance and Bybit every 100 milliseconds, and when it drops below 0.08% it enters Up and Down simultaneously at 25 to 35 cents A pure straddle: 1 side burns and the other flies to a dollar, giving 3 to 4x per position. Dozens of times a day I wanted to follow it but signals came at any hour, and waking up every 15 minutes for a notification was simply impossible. So I built something else Took an old Android phone and installed an agent running on the Qwen3-VL visual model. It sees what is happening on the screen and mimics human actions through ADB: taps, swipes, text input. Then I connected it to Claude Code as the executor Now the chain works like this: Claude Code monitors the wallet, sees a new position, calls me. And if I say "yes" or just do not pick up within 30 seconds, the agent on the phone opens Polymarket on its own and copies the entry Essentially I built myself an autopilot out of 2 AI systems: 1 thinks and the other presses buttons. I just sleep and occasionally pick up the phone → Here is the wallet the whole thing is tracking: For those who do not want to build a setup like this there is a Telegram bot that handles the 1st part: tracks this wallet and sends a signal on every new entry: AI calls me at 3 AM to ask permission to spend my money A year ago this would have sounded like schizophrenia. Now it is just Tuesday

Blaze

56,524 просмотров • 6 месяцев назад

🚨 CHINA IS BUILDING THE FOUNDATION FOR A NEW GOLD-BASED FINANCIAL ORDER. At today’s BRICS summit in India, Xi Jinping announced that China will take the presidency and open a third “GOLDEN DECADE.” That wording matters because it comes while China has been buying gold for 22 straight months, Hong Kong has launched a government-backed gold clearing system linked to Shanghai, and Beijing is pushing the yuan deeper into global trade and settlement. At the same time, BRICS countries are expanding alternative payment infrastructure designed to reduce dependence on SWIFT and the dollar system, while China has dumped roughly $70 BILLION in U.S. Treasuries in one of its biggest sell-offs since the financial crisis. THIS IS NOT RANDOM RESERVE MANAGEMENT. China is buying more gold, holding fewer Treasuries, expanding yuan settlement, and building the infrastructure for a more independent financial system. They do not need to announce that they are replacing the dollar tomorrow. The strategy is already visible in what they are building. THE GOLD IS BEING STACKED, THE TREASURIES ARE BEING SOLD, AND THE YUAN IS MOVING DEEPER INTO GLOBAL TRADE. This is how a monetary system starts to change: not with one announcement, but with a parallel system being built underneath the old one!👀
0:14

🚨 CHINA IS BUILDING THE FOUNDATION FOR A NEW GOLD-BASED FINANCIAL ORDER. At today’s BRICS summit in India, Xi Jinping announced that China will take the presidency and open a third “GOLDEN DECADE.” That wording matters because it comes while China has been buying gold for 22 straight months, Hong Kong has launched a government-backed gold clearing system linked to Shanghai, and Beijing is pushing the yuan deeper into global trade and settlement. At the same time, BRICS countries are expanding alternative payment infrastructure designed to reduce dependence on SWIFT and the dollar system, while China has dumped roughly $70 BILLION in U.S. Treasuries in one of its biggest sell-offs since the financial crisis. THIS IS NOT RANDOM RESERVE MANAGEMENT. China is buying more gold, holding fewer Treasuries, expanding yuan settlement, and building the infrastructure for a more independent financial system. They do not need to announce that they are replacing the dollar tomorrow. The strategy is already visible in what they are building. THE GOLD IS BEING STACKED, THE TREASURIES ARE BEING SOLD, AND THE YUAN IS MOVING DEEPER INTO GLOBAL TRADE. This is how a monetary system starts to change: not with one announcement, but with a parallel system being built underneath the old one!👀

Qmo

51,992 просмотров • 6 дней назад

Finally! A RAG over code solution that actually works (open-source). Naive chunking used in RAG isn't suited for code. This is because codebases have long-range dependencies, cross-file references, etc., that independent text chunks just can't capture. Graph-Code is a graph-driven RAG system that solves this. It analyzes the Python codebase and builds knowledge graphs to enable natural language querying. Key features: - Deep code parsing to extract classes, functions, and relationships. - Uses Memgraph to store the codebase as a graph. - Parses pyproject to understand external dependencies. - Retrieves actual source code snippets for found functions. Find the repo in the replies!
0:15

Finally! A RAG over code solution that actually works (open-source). Naive chunking used in RAG isn't suited for code. This is because codebases have long-range dependencies, cross-file references, etc., that independent text chunks just can't capture. Graph-Code is a graph-driven RAG system that solves this. It analyzes the Python codebase and builds knowledge graphs to enable natural language querying. Key features: - Deep code parsing to extract classes, functions, and relationships. - Uses Memgraph to store the codebase as a graph. - Parses pyproject to understand external dependencies. - Retrieves actual source code snippets for found functions. Find the repo in the replies!

Avi Chawla

121,874 просмотров • 1 год назад

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.
0:12

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,623 просмотров • 6 месяцев назад