kiruwaaaa's banner

kiruwaaaa

@kiruwaaaaaa • 2,210 subscribers

ex-Google research @CELE8EX business degradation manager @polymarket degen

Shorts

UPDATE: Flyctor has a second body now I bought another Vector robot and connected it to the same stack: - a camera feed - GPT-6 Astra for real-time visual understanding - a MaleCNS fly-brain simulation for movement decisions - a small audio protocol for robot-to-robot communication I didn't let them exchange normal Wi-Fi messages. Instead, each robot has to communicate through its speaker and microphone. One robot emits a short sequence of tones. The other records the sound, converts it into a frequency pattern, classifies the pattern, and injects it into its fly-brain simulation as a sensory event. Right now their entire vocabulary is only four signals: one chirp = "I found an object" two chirps = "come closer" long tone = "path blocked" rapid chirps = "I need help" The interesting part is that the robots don't send coordinates. They don't share a map. They don't know where the other robot is. One Flyctor sees something through Astra, decides it matters, sends a sound, and the other Flyctor has to hear it, interpret it, then decide what to do with that information. camera -> Astra -> fly brain -> speaker microphone -> audio decoder -> fly brain -> movement It is basically a tiny sensory loop between two digital insect nervous systems. Yesterday one robot detected a blocked path and sent the long-tone signal. The other one heard it, turned toward the sound, and rolled over to investigate. It was not impressive in the way modern AI demos are impressive. It was impressive because it felt like watching two small creatures notice each other for the first time.

UPDATE: Flyctor has a second body now I bought another Vector robot and connected it to the same stack: - a camera feed - GPT-6 Astra for real-time visual understanding - a MaleCNS fly-brain simulation for movement decisions - a small audio protocol for robot-to-robot communication I didn't let them exchange normal Wi-Fi messages. Instead, each robot has to communicate through its speaker and microphone. One robot emits a short sequence of tones. The other records the sound, converts it into a frequency pattern, classifies the pattern, and injects it into its fly-brain simulation as a sensory event. Right now their entire vocabulary is only four signals: one chirp = "I found an object" two chirps = "come closer" long tone = "path blocked" rapid chirps = "I need help" The interesting part is that the robots don't send coordinates. They don't share a map. They don't know where the other robot is. One Flyctor sees something through Astra, decides it matters, sends a sound, and the other Flyctor has to hear it, interpret it, then decide what to do with that information. camera -> Astra -> fly brain -> speaker microphone -> audio decoder -> fly brain -> movement It is basically a tiny sensory loop between two digital insect nervous systems. Yesterday one robot detected a blocked path and sent the long-tone signal. The other one heard it, turned toward the sound, and rolled over to investigate. It was not impressive in the way modern AI demos are impressive. It was impressive because it felt like watching two small creatures notice each other for the first time.

21,000 views

$5 into $500,000 on polymarket nobody is talking about him 17,000 predictions. 100% win rate. one market category: Up/Down. $180 → $8,400 $250 → $8,000 he doesnt pick markets. he doesnt guess directions. he finds the bets with the highest probability of already being correct and just keeps buying them before they close sounds obvious. but you cant do it manually by the time you see the opportunity the window is already closing a bot can. and this one does it 17,000 times. every trade is public: $5 starting capital $500,000 result zero losses across 17,000 trades the math on this profile alone is worth studying for a week open it. look at the entry prices. look at the timing. everything you need to understand the strategy is right there on chain most people will screenshot this and forget the ones who open the profile today will understand something that took this guy 17,000 trades to prove

27,401 views

this claude bot doesnt predict markets it just enters them faster than humans can react found this wallet 3 days ago on Polymarket $7 → $3,595 $30 → $11,063 $142 → $13,356 $1,205 → $37,939 > $78,083 total > 5 days the bot isnt smarter than you it just doesnt hesitate thats the whole thing. speed beats intelligence on prediction markets.

this claude bot doesnt predict markets it just enters them faster than humans can react found this wallet 3 days ago on Polymarket $7 → $3,595 $30 → $11,063 $142 → $13,356 $1,205 → $37,939 > $78,083 total > 5 days the bot isnt smarter than you it just doesnt hesitate thats the whole thing. speed beats intelligence on prediction markets.

14,883 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

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

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

A DEAD FLY IS DRIVING MY ROBOT RIGHT NOW. Not a metaphor. A reconstructed neural map of a fruit fly - 166,700 neurons, 25.6 million synapses - is now running on my MacBook and steering a quadruped robot in my living room. Here's how it works: 1. MaleCNS - a full connectome reconstruction of an adult fly brain - runs as a live simulation on my laptop. 2. I used Codex to build a decoder that reads the simulation's neural activity and turns it into movement commands: forward, left, right. 3. Those commands get sent over Wi-Fi to the robot, which still uses its own firmware to drive all 12 servos. The brain only decides where to go, not how to move each leg. No scripts. No prerecorded paths. The simulation runs continuously, live, while the robot walks. The fly has been dead for years. But its reconstructed nervous system is producing real decisions again, in real time, controlling a machine that didn't exist when it was alive. Next step: feed the robot's sensors back into the simulation and close the loop. A dead brain that can finally feel the world it's walking through. This fly has been dead for years. Its brain runs on my laptop. Its decisions move a machine through my living room. One dead nervous system, walking again.

A DEAD FLY IS DRIVING MY ROBOT RIGHT NOW. Not a metaphor. A reconstructed neural map of a fruit fly - 166,700 neurons, 25.6 million synapses - is now running on my MacBook and steering a quadruped robot in my living room. Here's how it works: 1. MaleCNS - a full connectome reconstruction of an adult fly brain - runs as a live simulation on my laptop. 2. I used Codex to build a decoder that reads the simulation's neural activity and turns it into movement commands: forward, left, right. 3. Those commands get sent over Wi-Fi to the robot, which still uses its own firmware to drive all 12 servos. The brain only decides where to go, not how to move each leg. No scripts. No prerecorded paths. The simulation runs continuously, live, while the robot walks. The fly has been dead for years. But its reconstructed nervous system is producing real decisions again, in real time, controlling a machine that didn't exist when it was alive. Next step: feed the robot's sensors back into the simulation and close the loop. A dead brain that can finally feel the world it's walking through. This fly has been dead for years. Its brain runs on my laptop. Its decisions move a machine through my living room. One dead nervous system, walking again.

77,997 views • 1 month ago

I uploaded a fly brain and GPT-6 Astra into a Vector robot I bought on eBay Vector was supposed to be a desk pet. Now it has a reconstructed fruit fly nervous system running inside it. MaleCNS gives it 166,700 simulated neurons and 25.6 million connections. GPT-6 Astra gives it vision. Astra sees the room through Vector's camera - furniture, walls, doors, objects on the floor - and turns the visual scene into sensory signals. The fly brain processes those signals and chooses where Vector should go next. Astra sees. The fly brain decides. Vector moves. > No joystick > No preset route > No one manually telling it to turn left or right It started roaming around my apartment, stopping in front of furniture, changing direction, and reacting to things in its path. I bought it on eBay because it looked like a cute little WALL-E. Now it has a brain, eyes, and a body. And it keeps looking at me like it knows I’m the reason it exists.

I uploaded a fly brain and GPT-6 Astra into a Vector robot I bought on eBay Vector was supposed to be a desk pet. Now it has a reconstructed fruit fly nervous system running inside it. MaleCNS gives it 166,700 simulated neurons and 25.6 million connections. GPT-6 Astra gives it vision. Astra sees the room through Vector's camera - furniture, walls, doors, objects on the floor - and turns the visual scene into sensory signals. The fly brain processes those signals and chooses where Vector should go next. Astra sees. The fly brain decides. Vector moves. > No joystick > No preset route > No one manually telling it to turn left or right It started roaming around my apartment, stopping in front of furniture, changing direction, and reacting to things in its path. I bought it on eBay because it looked like a cute little WALL-E. Now it has a brain, eyes, and a body. And it keeps looking at me like it knows I’m the reason it exists.

54,854 views • 1 month ago

FLYCTOR TOKEN IS LIVE CA: 7MRKu5x6S7wXr9FSdcg6eKJkGPNizgSxL8Kqx2VBpump Flyctor started as a pet robot I bought on eBay. Then I gave it a reconstructed fly brain, GPT-6 Astra vision, and a physical body that can explore the real world. Now I want to turn one robot into a whole colony. Every fee generated by the token will be allocated to building the project: more robot bodies more cameras more fly-brain simulations a live stream and eventually a public interface where anyone can send commands to the Flyctors online. The largest holders will get early access to the experiments, private builds, live control sessions, and a direct role in deciding what the colony learns to do next. This is not another token with a roadmap made of words. The roadmap has wheels, cameras, speakers, and a digital insect brain. First there was one Flyctor. Next, there will be a swarm.

FLYCTOR TOKEN IS LIVE CA: 7MRKu5x6S7wXr9FSdcg6eKJkGPNizgSxL8Kqx2VBpump Flyctor started as a pet robot I bought on eBay. Then I gave it a reconstructed fly brain, GPT-6 Astra vision, and a physical body that can explore the real world. Now I want to turn one robot into a whole colony. Every fee generated by the token will be allocated to building the project: more robot bodies more cameras more fly-brain simulations a live stream and eventually a public interface where anyone can send commands to the Flyctors online. The largest holders will get early access to the experiments, private builds, live control sessions, and a direct role in deciding what the colony learns to do next. This is not another token with a roadmap made of words. The roadmap has wheels, cameras, speakers, and a digital insect brain. First there was one Flyctor. Next, there will be a swarm.

41,786 views • 29 days ago

>be 007: First Light >drop combat gameplay and the internet loses its mind >looks like Hitman but Bond pulls the trigger with a British accent >stealth mechanics, zipline extractions, hand-to-hand >every NPC you walk past could be a witness or a target >this is the game GoldenEye fans have been waiting 25 years for >be every COD and Splinter Cell player right now >already uninstalling

>be 007: First Light >drop combat gameplay and the internet loses its mind >looks like Hitman but Bond pulls the trigger with a British accent >stealth mechanics, zipline extractions, hand-to-hand >every NPC you walk past could be a witness or a target >this is the game GoldenEye fans have been waiting 25 years for >be every COD and Splinter Cell player right now >already uninstalling

37,144 views • 4 months ago

$5 into $500,000 on polymarket nobody is talking about him 17,000 predictions. 100% win rate. one market category: Up/Down. $180 → $8,400 $250 → $8,000 he doesnt pick markets. he doesnt guess directions. he finds the bets with the highest probability of already being correct and just keeps buying them before they close sounds obvious. but you cant do it manually by the time you see the opportunity the window is already closing a bot can. and this one does it 17,000 times. every trade is public: $5 starting capital $500,000 result zero losses across 17,000 trades the math on this profile alone is worth studying for a week open it. look at the entry prices. look at the timing. everything you need to understand the strategy is right there on chain most people will screenshot this and forget the ones who open the profile today will understand something that took this guy 17,000 trades to prove

27,401 views • 6 months ago

this claude bot doesnt predict markets it just enters them faster than humans can react found this wallet 3 days ago on Polymarket $7 → $3,595 $30 → $11,063 $142 → $13,356 $1,205 → $37,939 > $78,083 total > 5 days the bot isnt smarter than you it just doesnt hesitate thats the whole thing. speed beats intelligence on prediction markets.

this claude bot doesnt predict markets it just enters them faster than humans can react found this wallet 3 days ago on Polymarket $7 → $3,595 $30 → $11,063 $142 → $13,356 $1,205 → $37,939 > $78,083 total > 5 days the bot isnt smarter than you it just doesnt hesitate thats the whole thing. speed beats intelligence on prediction markets.

14,883 views • 6 months ago

No more content to load