Loading video...

Video Failed to Load

Go Home

a Chinese quant from Citadel drew 3 formulas on a napkin that replaced my entire salary rooftop dinner in lower manhattan. friend's colleague. four drinks in he started talking about work. "weather is pure physics. no sentiment. no politics. just math against a forecast model" he grabbed a napkin....

hanakoxbt's profile picture

Hanako

10,971 subscribers

46,595 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

an MIT quant showed me his lab's trading model on a napkin after his third whiskey bar near kendall square. friday night. he was celebrating a paper acceptance. i was checking my phone. he noticed the red P&L curve on my screen. "is that a live heartbeat monitor on a prediction market" i nodded. "what's the execution backend" a Chinese AI. $20/month. he almost spit his drink. "we have 6 researchers and $800K in grant money building this exact system. it's been in simulation for 18 months" i asked what's stopping them from going live. "IRB approval. faculty review. risk committee. three layers of bureaucracy before a single dollar moves" he grabbed a napkin. started drawing. "the model is simple. BTC 5-minute binary markets. 288 per day. YES and NO. crowd trades direction. direction is noise" he drew a spread diagram. "YES at 71c. NO at 29c. fair. crowd panics. YES crashes. NO spikes. combined drops to 93c. 7 cents of free alpha. buy the cheap side. repeat 288 times a day" he wrote three variables underneath: > edge = YES_fair - YES_market > kelly_f = edge / variance > threshold = 6c minimum "that's the whole model. three variables. everything else is noise" i memorized the napkin. went home at midnight. gave the Chinese AI one repo and the three formulas. 35,000 stars. unified exchange API. connects to every major platform through one interface. the model read the codebase. cross-referenced the formulas. had the system live by 6AM. heartbeat monitor. streak tracker. edge table. whale flow scanner. edge table live: BTC+100K 5m. 25c. +8.6c edge. BTC+99.5K. 56c. +9.6c edge. BTC AI - $20/mo > VPS - $5/mo > everything else - free i copied the setup here: texted him monday with a screenshot of the equity curve. he called immediately. "is that my napkin running live" technically it's a Chinese AI running your napkin. "my lab has 6 people, 18 months, and $800K. you did this over a weekend with a $25 subscription" the napkin didn't need IRB approval. long pause. "don't tell my advisor where you got the model" the napkin is still in my pocket.
0:41

an MIT quant showed me his lab's trading model on a napkin after his third whiskey bar near kendall square. friday night. he was celebrating a paper acceptance. i was checking my phone. he noticed the red P&L curve on my screen. "is that a live heartbeat monitor on a prediction market" i nodded. "what's the execution backend" a Chinese AI. $20/month. he almost spit his drink. "we have 6 researchers and $800K in grant money building this exact system. it's been in simulation for 18 months" i asked what's stopping them from going live. "IRB approval. faculty review. risk committee. three layers of bureaucracy before a single dollar moves" he grabbed a napkin. started drawing. "the model is simple. BTC 5-minute binary markets. 288 per day. YES and NO. crowd trades direction. direction is noise" he drew a spread diagram. "YES at 71c. NO at 29c. fair. crowd panics. YES crashes. NO spikes. combined drops to 93c. 7 cents of free alpha. buy the cheap side. repeat 288 times a day" he wrote three variables underneath: > edge = YES_fair - YES_market > kelly_f = edge / variance > threshold = 6c minimum "that's the whole model. three variables. everything else is noise" i memorized the napkin. went home at midnight. gave the Chinese AI one repo and the three formulas. 35,000 stars. unified exchange API. connects to every major platform through one interface. the model read the codebase. cross-referenced the formulas. had the system live by 6AM. heartbeat monitor. streak tracker. edge table. whale flow scanner. edge table live: BTC+100K 5m. 25c. +8.6c edge. BTC+99.5K. 56c. +9.6c edge. BTC AI - $20/mo > VPS - $5/mo > everything else - free i copied the setup here: texted him monday with a screenshot of the equity curve. he called immediately. "is that my napkin running live" technically it's a Chinese AI running your napkin. "my lab has 6 people, 18 months, and $800K. you did this over a weekend with a $25 subscription" the napkin didn't need IRB approval. long pause. "don't tell my advisor where you got the model" the napkin is still in my pocket.

Hanako

23,475 views • 5 months ago

a MIT quant told me Polymarket 5-minute BTC markets are mathematically broken we were at a bar in cambridge. he was finishing his PhD on market microstructure. third beer in he started drawing on a napkin. "Polymarket runs BTC Up or Down every 5 minutes. 288 markets per day. everyone trades direction. that's the wrong game" "when UP is at 20c and DOWN is at 85c that's $1.05 combined. overpaid. minutes later UP flips to 82c and DOWN drops to 18c. the gap reversed. you buy the cheap side. never predict direction. just capture the mispricing" i asked how he discovered this. "i studied 28,000 of these markets for my dissertation. the crowd injects emotion every 5 minutes. that creates a spread you can harvest mechanically" then i went home that night. opened Claude Opus 4.7. "build a 5-minute BTC spread capture engine for Polymarket. buy the cheap side of UP/DOWN when pair cost drops below 99c. never predict direction" 2,900 stars. 36GB. every trade on Polymarket and Kalshi. Opus built it overnight. NEURAL FLUX. 24 bayesian nodes. scanning every 2ms. the strategy is real. this account runs it live. 28,620 predictions. every trade on-chain: whale alert feed tracks who's moving: > yes 0x47ac...d5e3 BTC+103K 30m $97. > yes smart_money BTC+98K 5m $870. > yes darkpool_7 BTC+102K 15m $97. > no 0xd8dA...6045 BTC+97.5K 5m $1,014. > yes copy_bot BTC+100K 15m $1,014. > no 0xBE0e...48CD BTC+101K 5m $688. edge scanner: 4 live edges. BTC+100K 5m +7.7c. BTC+99.5K 5m +7.2c. BTC<99K 5m +4.2c. BTC+101K 5m +6.8c. $534K volume. 79% win rate. sharpe 3.64. drawdown -1.2%. +$11,681 from $1,200 seed. i copied the setup here: texted him after week one with a screenshot. "you deployed this live?" Claude deployed it. i typed what you drew on the napkin. long pause. "my thesis advisor would lose his mind if he saw this" probably. but the spread doesn't care who captures it.
0:32

a MIT quant told me Polymarket 5-minute BTC markets are mathematically broken we were at a bar in cambridge. he was finishing his PhD on market microstructure. third beer in he started drawing on a napkin. "Polymarket runs BTC Up or Down every 5 minutes. 288 markets per day. everyone trades direction. that's the wrong game" "when UP is at 20c and DOWN is at 85c that's $1.05 combined. overpaid. minutes later UP flips to 82c and DOWN drops to 18c. the gap reversed. you buy the cheap side. never predict direction. just capture the mispricing" i asked how he discovered this. "i studied 28,000 of these markets for my dissertation. the crowd injects emotion every 5 minutes. that creates a spread you can harvest mechanically" then i went home that night. opened Claude Opus 4.7. "build a 5-minute BTC spread capture engine for Polymarket. buy the cheap side of UP/DOWN when pair cost drops below 99c. never predict direction" 2,900 stars. 36GB. every trade on Polymarket and Kalshi. Opus built it overnight. NEURAL FLUX. 24 bayesian nodes. scanning every 2ms. the strategy is real. this account runs it live. 28,620 predictions. every trade on-chain: whale alert feed tracks who's moving: > yes 0x47ac...d5e3 BTC+103K 30m $97. > yes smart_money BTC+98K 5m $870. > yes darkpool_7 BTC+102K 15m $97. > no 0xd8dA...6045 BTC+97.5K 5m $1,014. > yes copy_bot BTC+100K 15m $1,014. > no 0xBE0e...48CD BTC+101K 5m $688. edge scanner: 4 live edges. BTC+100K 5m +7.7c. BTC+99.5K 5m +7.2c. BTC<99K 5m +4.2c. BTC+101K 5m +6.8c. $534K volume. 79% win rate. sharpe 3.64. drawdown -1.2%. +$11,681 from $1,200 seed. i copied the setup here: texted him after week one with a screenshot. "you deployed this live?" Claude deployed it. i typed what you drew on the napkin. long pause. "my thesis advisor would lose his mind if he saw this" probably. but the spread doesn't care who captures it.

Hanako

53,628 views • 5 months ago

Last semester a professor pulled me aside after class. "You trade prediction markets?" - he asked. I said yeah, mostly vibes. He laughed and said that's why you're losing. He spent 20 minutes on a whiteboard showing me Bayes' Theorem, Kelly Criterion, and LMSR pricing. Said this is literally how quant funds approach binary markets. I took photos of everything. Went home, opened Claude, pasted my notes and said: “build me a bot that does exactly this 3 hours later I had a working Bayesian trading bot for Polymarket BTC markets. Here's the math it runs on every single trade: - Bayesian update update beliefs before entering P(H|D) = P(D|H) · P(H) / P(D) - Edge detection -only trade if you have an edge EV = p̂ − p_market - Kelly sizing-bet exactly the right amount f* = EV / p̂(1−p̂) - LMSR pricing how Polymarket actually prices markets p(q) = e^{q/b} / Σe^{qⱼ/b} (it's literally the softmax function from neural networks) 65% win rate. Losses happen. Kelly keeps them from blowing the account. Compounding does the rest. My CLAWD BOT turned $100 into $1000 in 30min The professor was right. Vibes don't compound. Math does.
0:29

Last semester a professor pulled me aside after class. "You trade prediction markets?" - he asked. I said yeah, mostly vibes. He laughed and said that's why you're losing. He spent 20 minutes on a whiteboard showing me Bayes' Theorem, Kelly Criterion, and LMSR pricing. Said this is literally how quant funds approach binary markets. I took photos of everything. Went home, opened Claude, pasted my notes and said: “build me a bot that does exactly this 3 hours later I had a working Bayesian trading bot for Polymarket BTC markets. Here's the math it runs on every single trade: - Bayesian update update beliefs before entering P(H|D) = P(D|H) · P(H) / P(D) - Edge detection -only trade if you have an edge EV = p̂ − p_market - Kelly sizing-bet exactly the right amount f* = EV / p̂(1−p̂) - LMSR pricing how Polymarket actually prices markets p(q) = e^{q/b} / Σe^{qⱼ/b} (it's literally the softmax function from neural networks) 65% win rate. Losses happen. Kelly keeps them from blowing the account. Compounding does the rest. My CLAWD BOT turned $100 into $1000 in 30min The professor was right. Vibes don't compound. Math does.

AdiiX

174,137 views • 6 months ago

a drunk Jane Street quant drew his trading system on a napkin it started as a joke. someone's friend at a bar in lower manhattan. he mentioned prediction markets and this guy lit up. "i do this for a living. for a firm you've heard of" two rounds later he was drawing on a napkin. boxes. arrows. labels. "the crowd repeats six mistakes every single day. we just built detectors for each one" > base rate neglect > mispriced conditionals > thin book slippage > platform divergence > favourite bias > time decay "that's the whole system" i asked what it costs to run. "200 quants. proprietary infra. about $2M/year just to keep it on" i laughed. photographed the napkin. went home. 3am. couldn't sleep. opened Claude. fed it the photo and one GitHub repo - poly_data. 86 million trades. every wallet. every entry. said: build detectors for all six. by 4AM my laptop fan was screaming. 400+ markets scanning per hour. 8 agents deployed. terminal live. i didn't understand half of what was on screen. but the P&L number kept climbing. +$312 by breakfast. +$1,900 by end of day one. +$7,400 by end of week one. +$16,474 right now. 383 trades. 81% win rate. the scanner finds gaps like: > AAPL earnings - crowd says 77%. data says 91%. > Gold $2600 - crowd says 44%. model says 60%. > Senate filibuster - crowd says 68%. base rate says 82%. enters. waits 6 hours average. exits when the gap closes. politics at 93%. weather 79%. crypto 72%. eight agents split the work. one mirrors whales. one catches Binance lag. one fades favourites. one bleeds theta on dying contracts. his firm runs this with 200 people. mine runs on $25/month. copytrade here: texted him the screenshot yesterday. long pause. "you're not supposed to be able to do this" i know.
0:27

a drunk Jane Street quant drew his trading system on a napkin it started as a joke. someone's friend at a bar in lower manhattan. he mentioned prediction markets and this guy lit up. "i do this for a living. for a firm you've heard of" two rounds later he was drawing on a napkin. boxes. arrows. labels. "the crowd repeats six mistakes every single day. we just built detectors for each one" > base rate neglect > mispriced conditionals > thin book slippage > platform divergence > favourite bias > time decay "that's the whole system" i asked what it costs to run. "200 quants. proprietary infra. about $2M/year just to keep it on" i laughed. photographed the napkin. went home. 3am. couldn't sleep. opened Claude. fed it the photo and one GitHub repo - poly_data. 86 million trades. every wallet. every entry. said: build detectors for all six. by 4AM my laptop fan was screaming. 400+ markets scanning per hour. 8 agents deployed. terminal live. i didn't understand half of what was on screen. but the P&L number kept climbing. +$312 by breakfast. +$1,900 by end of day one. +$7,400 by end of week one. +$16,474 right now. 383 trades. 81% win rate. the scanner finds gaps like: > AAPL earnings - crowd says 77%. data says 91%. > Gold $2600 - crowd says 44%. model says 60%. > Senate filibuster - crowd says 68%. base rate says 82%. enters. waits 6 hours average. exits when the gap closes. politics at 93%. weather 79%. crypto 72%. eight agents split the work. one mirrors whales. one catches Binance lag. one fades favourites. one bleeds theta on dying contracts. his firm runs this with 200 people. mine runs on $25/month. copytrade here: texted him the screenshot yesterday. long pause. "you're not supposed to be able to do this" i know.

Hanako

244,564 views • 5 months ago

a Chinese PhD dropout told me Wall Street is solving the wrong equation on purpose i met him through a girl i was seeing in hong kong. he hadn't had a real job in three years. "every bank. every fund. every quant lab. they all try to predict where BTC goes next. up or down. that's the wrong question" i asked what the right question is. "who is mispricing the reaction" he opened his phone. showed me Polymarket. "288 BTC markets per day. every 5 minutes. YES or NO. the crowd bets direction. direction doesn't matter. what matters is the spread between YES and NO when the crowd panics" he drew on a napkin. "YES at 79c. NO at 22c. combined $1.01. fair. then someone dumps $3,000 on YES. it spikes to 96c. NO crashes to 5c. that's 17 cents of free alpha sitting there for 4 minutes" "Wall Street builds billion dollar models to predict direction. i buy the panic. different equation. different result" i flew home. opened a Chinese AI. typed what he told me. "build a spread capture engine for Polymarket 5-minute BTC markets. buy the underpriced side when crowd panic creates a gap. never predict direction" 30,800 stars. multi-agent LLM trading framework. the AI adapted it for prediction markets overnight. NERVE GRID. 6 pairs. BTC. ETH. SOL. AVAX. 400+ windows per day. edge table live: BTC+100K 5m. 79c vs 22c. +27c edge. BTC<99K. 35c vs 27c. +8c edge. ETH+3.8K. 46c vs 30c. +12c edge. SOL+200 5m. 55c vs 22c. +22c edge. the system kills 2,986 setups per day. enters 563. avg hold 1:02. wins are 4.51x the losses. fill rate 96.4%. avg latency 15ms. best fill 9ms. +$4,847 from $600 seed. infrastructure: $20 AI. $5 VPS. everything else open source. $25/month. i copied the setup here: texted him two weeks later with a screenshot. "you're running the panic equation?" the AI built it from one conversation. "good. now try ETH and SOL. bigger spreads. less competition" i already was. he could see it in the screenshot. long pause. "you learn fast for someone who asks the right questions" i didn't ask any questions. i just listened.
0:50

a Chinese PhD dropout told me Wall Street is solving the wrong equation on purpose i met him through a girl i was seeing in hong kong. he hadn't had a real job in three years. "every bank. every fund. every quant lab. they all try to predict where BTC goes next. up or down. that's the wrong question" i asked what the right question is. "who is mispricing the reaction" he opened his phone. showed me Polymarket. "288 BTC markets per day. every 5 minutes. YES or NO. the crowd bets direction. direction doesn't matter. what matters is the spread between YES and NO when the crowd panics" he drew on a napkin. "YES at 79c. NO at 22c. combined $1.01. fair. then someone dumps $3,000 on YES. it spikes to 96c. NO crashes to 5c. that's 17 cents of free alpha sitting there for 4 minutes" "Wall Street builds billion dollar models to predict direction. i buy the panic. different equation. different result" i flew home. opened a Chinese AI. typed what he told me. "build a spread capture engine for Polymarket 5-minute BTC markets. buy the underpriced side when crowd panic creates a gap. never predict direction" 30,800 stars. multi-agent LLM trading framework. the AI adapted it for prediction markets overnight. NERVE GRID. 6 pairs. BTC. ETH. SOL. AVAX. 400+ windows per day. edge table live: BTC+100K 5m. 79c vs 22c. +27c edge. BTC<99K. 35c vs 27c. +8c edge. ETH+3.8K. 46c vs 30c. +12c edge. SOL+200 5m. 55c vs 22c. +22c edge. the system kills 2,986 setups per day. enters 563. avg hold 1:02. wins are 4.51x the losses. fill rate 96.4%. avg latency 15ms. best fill 9ms. +$4,847 from $600 seed. infrastructure: $20 AI. $5 VPS. everything else open source. $25/month. i copied the setup here: texted him two weeks later with a screenshot. "you're running the panic equation?" the AI built it from one conversation. "good. now try ETH and SOL. bigger spreads. less competition" i already was. he could see it in the screenshot. long pause. "you learn fast for someone who asks the right questions" i didn't ask any questions. i just listened.

Hanako

37,205 views • 4 months ago

An OpenAI researcher sat down next to me at a coffee shop in Mission District I had my terminal open. Three panels. Live trades scrolling. He was reading something on his laptop. Glanced over. Stopped reading. "That's not a dashboard. That's a live scoring engine. What model is running that" I told him. Claude Code. Four repos. $25 a month. He closed his laptop. "I work at OpenAI. We benchmarked Claude internally last month. You're using it to trade prediction markets?" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "This is public? We quoted a seven-figure budget to reconstruct this kind of dataset from on-chain data. The project is still in review" I told him Claude Code connects directly. It reads the whole dataset. Finds the wallets that win. Then finds WHY they win. Then copies the pattern. He pulled his chair closer. "Walk me through the exit logic" Top wallets exit before resolution 91% of the time. They capture 86% of the move and cut losers at 12%. Everyone else holds to 58%. Same entries. Completely different exits. My bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever hits first. "Who gave you that threshold" Claude Code found it in poly_data. In about 20 minutes. "We had a team of nine working on this exact problem for six months. They never shipped it. You did it in a weekend with a competitor's model" I opened another link. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "That's our internal eval pipeline. Except it took us six months and you built it on a Saturday" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. +$9,400. Copytrade here: I showed him the article where I broke down every repo, every command, every dollar. He read it for five minutes. Then looked up. "You just published what we presented to Sam last quarter. Using the other team's model" He texted me the next morning. "My director found your thread. Take it down" Too late.
0:20

An OpenAI researcher sat down next to me at a coffee shop in Mission District I had my terminal open. Three panels. Live trades scrolling. He was reading something on his laptop. Glanced over. Stopped reading. "That's not a dashboard. That's a live scoring engine. What model is running that" I told him. Claude Code. Four repos. $25 a month. He closed his laptop. "I work at OpenAI. We benchmarked Claude internally last month. You're using it to trade prediction markets?" I opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "This is public? We quoted a seven-figure budget to reconstruct this kind of dataset from on-chain data. The project is still in review" I told him Claude Code connects directly. It reads the whole dataset. Finds the wallets that win. Then finds WHY they win. Then copies the pattern. He pulled his chair closer. "Walk me through the exit logic" Top wallets exit before resolution 91% of the time. They capture 86% of the move and cut losers at 12%. Everyone else holds to 58%. Same entries. Completely different exits. My bot cuts at 85% of expected move. Or on a 3x volume spike. Whichever hits first. "Who gave you that threshold" Claude Code found it in poly_data. In about 20 minutes. "We had a team of nine working on this exact problem for six months. They never shipped it. You did it in a weekend with a competitor's model" I opened another link. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes. "That's our internal eval pipeline. Except it took us six months and you built it on a Saturday" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. +$9,400. Copytrade here: I showed him the article where I broke down every repo, every command, every dollar. He read it for five minutes. Then looked up. "You just published what we presented to Sam last quarter. Using the other team's model" He texted me the next morning. "My director found your thread. Take it down" Too late.

Lunar

159,690 views • 5 months ago

An ex-Anthropic engineer told me something at a party he probably shouldn't have. It was in SF. Someone's rooftop. I mentioned I run trading agents on Claude. He went quiet. "You're doing it wrong. Everyone is" I asked what he meant. "Claude is a runtime. Not a chatbox. You're supposed to pair it with repos" He pulled out his phone. Opened one GitHub link. 14,000 stars. Every workflow pattern they built internally before it went public. Agents. Tool use. Evals. Citations. The entire architecture. "Everyone types prompts. That's not how we use it. You connect Claude to a codebase. It reads. It understands. It builds on top of what's already there" I went home at 2am. Connected Claude Code to poly_data - 86 million Polymarket trades. Every wallet. Every entry. Claude didn't guess. It read the data and built detectors. First week: +$1,400. Second week: +$3,800. Right now: +$9,100. 4 agents. 74% win rate. His team runs this with a floor of PhDs and $800M AUM. My setup: Claude + a VPS. $25/month. The repos are free. Copytrade here: I asked him what separates his firm from everyone else. "Honestly? Keyboard shortcuts and repo structure. That's it. The model is the same for everyone" He texted me two days later. "Delete everything I told you" Too late.
0:21

An ex-Anthropic engineer told me something at a party he probably shouldn't have. It was in SF. Someone's rooftop. I mentioned I run trading agents on Claude. He went quiet. "You're doing it wrong. Everyone is" I asked what he meant. "Claude is a runtime. Not a chatbox. You're supposed to pair it with repos" He pulled out his phone. Opened one GitHub link. 14,000 stars. Every workflow pattern they built internally before it went public. Agents. Tool use. Evals. Citations. The entire architecture. "Everyone types prompts. That's not how we use it. You connect Claude to a codebase. It reads. It understands. It builds on top of what's already there" I went home at 2am. Connected Claude Code to poly_data - 86 million Polymarket trades. Every wallet. Every entry. Claude didn't guess. It read the data and built detectors. First week: +$1,400. Second week: +$3,800. Right now: +$9,100. 4 agents. 74% win rate. His team runs this with a floor of PhDs and $800M AUM. My setup: Claude + a VPS. $25/month. The repos are free. Copytrade here: I asked him what separates his firm from everyone else. "Honestly? Keyboard shortcuts and repo structure. That's it. The model is the same for everyone" He texted me two days later. "Delete everything I told you" Too late.

Lunar

1,656,335 views • 5 months ago

My dad looked at my screen and said what is this, a hacker game? It was a Polymarket bot making $400 while he was standing behind me. He sat down. I explained. Polymarket runs on one equation. Softmax. The same math Claude uses to pick the next word. C(q) = b · ln Σ e^(qi/b) 93% of traders do not know this formula exists. They look at 40 cents and think cheap. My bot looks at 40 cents and calculates the theoretical price is 58 cents. That is an 18-cent edge per share. Two more formulas do the rest: f = (p·b − q) / b. Kelly Criterion. P(H|E) = P(E|H)·P(H) / P(E). Bayes. I gave Claude all 4 and said find every contract the market has wrong. $600 to $10,190. 425 trades. Still running. 61.2% win rate. Wrong 39% of the time. Does not matter. The sizing formula makes sure wins pay more than losses cost. 87% of wallets lose money trading against this math. The 4 formulas are on Wikipedia. The code fits in one file. The only edge: my bot reads them at 3 AM when the market is mispriced and nobody is looking. My dad still calls it a hacker game. But he stopped asking when I am getting a real job. I built the entire framework: Softmax arbitrage detection layer Kelly Criterion position sizing Bayesian probability recalibration Claude integration for autonomous execution 3 AM mispricing scanner The system runs 24/7. Finds where the math disagrees with the crowd. Executes before the edge compresses. No prediction. No gut feel. Just formulas. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word money 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the formula system this week. Start with $600. Scale on evidence.
0:44

My dad looked at my screen and said what is this, a hacker game? It was a Polymarket bot making $400 while he was standing behind me. He sat down. I explained. Polymarket runs on one equation. Softmax. The same math Claude uses to pick the next word. C(q) = b · ln Σ e^(qi/b) 93% of traders do not know this formula exists. They look at 40 cents and think cheap. My bot looks at 40 cents and calculates the theoretical price is 58 cents. That is an 18-cent edge per share. Two more formulas do the rest: f = (p·b − q) / b. Kelly Criterion. P(H|E) = P(E|H)·P(H) / P(E). Bayes. I gave Claude all 4 and said find every contract the market has wrong. $600 to $10,190. 425 trades. Still running. 61.2% win rate. Wrong 39% of the time. Does not matter. The sizing formula makes sure wins pay more than losses cost. 87% of wallets lose money trading against this math. The 4 formulas are on Wikipedia. The code fits in one file. The only edge: my bot reads them at 3 AM when the market is mispriced and nobody is looking. My dad still calls it a hacker game. But he stopped asking when I am getting a real job. I built the entire framework: Softmax arbitrage detection layer Kelly Criterion position sizing Bayesian probability recalibration Claude integration for autonomous execution 3 AM mispricing scanner The system runs 24/7. Finds where the math disagrees with the crowd. Executes before the edge compresses. No prediction. No gut feel. Just formulas. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word money 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the formula system this week. Start with $600. Scale on evidence.

Himanshu Kumar

13,333 views • 2 months ago

A programmer got fired on a Tuesday He opened Claude and just asked: "What do I do now?" Claude walked him through prediction markets. Told him the crowd is predictably wrong, smart money leaves patterns, and nobody's built a proper system to track it. "You could build that." 3 days. No sleep. Him + Claude tearing through 10,847 wallets. Found 7 traders with actual edge. Built an agent to copy them in real time - news feeds, mispricing detection, Kelly sizing. Fully autonomous. Deployed it at 11:47pm. Went to sleep. Day 1: +$8,400 Day 2: +$11,200 Day 3: +$9,800 Day 4: +$12,100 Day 5: +$6,300 Day 6: +$4,876 $52,676 in 6 days. His old salary: $48k/year. 786 trades. 68.4% win rate. He never touched it once. check here: Wall Street pays $2M/year for a person who does this. He paid $20/month for Claude. Getting fired was the best thing that ever happened to him. His boss just doesn't know it yet.
0:27

A programmer got fired on a Tuesday He opened Claude and just asked: "What do I do now?" Claude walked him through prediction markets. Told him the crowd is predictably wrong, smart money leaves patterns, and nobody's built a proper system to track it. "You could build that." 3 days. No sleep. Him + Claude tearing through 10,847 wallets. Found 7 traders with actual edge. Built an agent to copy them in real time - news feeds, mispricing detection, Kelly sizing. Fully autonomous. Deployed it at 11:47pm. Went to sleep. Day 1: +$8,400 Day 2: +$11,200 Day 3: +$9,800 Day 4: +$12,100 Day 5: +$6,300 Day 6: +$4,876 $52,676 in 6 days. His old salary: $48k/year. 786 trades. 68.4% win rate. He never touched it once. check here: Wall Street pays $2M/year for a person who does this. He paid $20/month for Claude. Getting fired was the best thing that ever happened to him. His boss just doesn't know it yet.

BuBBliK

228,008 views • 5 months ago

an ex-Citadel quant told me a salary is a short position on your own time we were at a dinner in new york. friend of a friend. he asked what i do. "software engineer. $4,200 a month" he said one simple thing "you're mass-selling the most valuable asset you have. your hours. at a fixed price. with no upside. that's a short position on your own life" i didn't have a response. then he showed me his phone. a terminal. live trades. +$39,453 running for 6 weeks. "i built this with Claude Opus 4.7 and one open source dataset. took a weekend. haven't touched it since" i asked how. "gave Opus one repo and one prompt. find who wins on prediction markets. find why. copy their edge" 2,900 stars. 36GB. every trade on Polymarket and Kalshi. every wallet. every resolution. Opus read the whole dataset friday night. by sunday it had a live terminal scanning 1,400 markets per hour. 8 detectors running in parallel. entering when void score exceeds 90. exiting when it drops below 75. no human override. > Senate filibuster. locked at 42c. now 98c. +$1,133. > Neuralink approval. entered 52c. now 98c. +$1,396. > Fed 0% rate. entered 35c. now 97c. +$1,147. > BTC 250K. entered 8c. now 98c. +$1,258. > Megaquake. entered 6c. now 97c. +$1,039. the part that broke something in me: latency arbitrage. Polymarket updates in 19ms. Kalshi in 63ms. the bot trades the 44ms gap between them. automatically. every time. "we had four people at Citadel doing what your bot does with latency alone" copy mirror tracking 6 positions: > Senate fili +$1,252. void signal. 10%. > BTC 250K +$958. zero signal. 2%. > Neuralink +$1,384. sign signal. 9%. > Fed 0% +$863. fill signal. 8%. > Megaquake +$1,070. bridge signal. 18%. > META AI +$979. gas signal. 5%. 972 trades. 83% win rate. kelly f+ 0.101. avg profit $10.65. drawdown -1.4%. maker rebate tracker collecting $203 across four platforms while the bot trades. Polymarket +$114. Kalshi +$40. dYdX +$28. Betfair +$21. $1,800 seed. +$39,453. i quit the next morning. one email. "i'm done. thank you for everything." copytrade setup: texted him a week later. "you ruined a perfectly stable career" he replied "no. i closed your short position"
0:39

an ex-Citadel quant told me a salary is a short position on your own time we were at a dinner in new york. friend of a friend. he asked what i do. "software engineer. $4,200 a month" he said one simple thing "you're mass-selling the most valuable asset you have. your hours. at a fixed price. with no upside. that's a short position on your own life" i didn't have a response. then he showed me his phone. a terminal. live trades. +$39,453 running for 6 weeks. "i built this with Claude Opus 4.7 and one open source dataset. took a weekend. haven't touched it since" i asked how. "gave Opus one repo and one prompt. find who wins on prediction markets. find why. copy their edge" 2,900 stars. 36GB. every trade on Polymarket and Kalshi. every wallet. every resolution. Opus read the whole dataset friday night. by sunday it had a live terminal scanning 1,400 markets per hour. 8 detectors running in parallel. entering when void score exceeds 90. exiting when it drops below 75. no human override. > Senate filibuster. locked at 42c. now 98c. +$1,133. > Neuralink approval. entered 52c. now 98c. +$1,396. > Fed 0% rate. entered 35c. now 97c. +$1,147. > BTC 250K. entered 8c. now 98c. +$1,258. > Megaquake. entered 6c. now 97c. +$1,039. the part that broke something in me: latency arbitrage. Polymarket updates in 19ms. Kalshi in 63ms. the bot trades the 44ms gap between them. automatically. every time. "we had four people at Citadel doing what your bot does with latency alone" copy mirror tracking 6 positions: > Senate fili +$1,252. void signal. 10%. > BTC 250K +$958. zero signal. 2%. > Neuralink +$1,384. sign signal. 9%. > Fed 0% +$863. fill signal. 8%. > Megaquake +$1,070. bridge signal. 18%. > META AI +$979. gas signal. 5%. 972 trades. 83% win rate. kelly f+ 0.101. avg profit $10.65. drawdown -1.4%. maker rebate tracker collecting $203 across four platforms while the bot trades. Polymarket +$114. Kalshi +$40. dYdX +$28. Betfair +$21. $1,800 seed. +$39,453. i quit the next morning. one email. "i'm done. thank you for everything." copytrade setup: texted him a week later. "you ruined a perfectly stable career" he replied "no. i closed your short position"

Hanako

379,758 views • 5 months ago

An ex-Cursor engineer told me something at a hackathon he probably shouldn't have It was in SF. Some YC demo day afterparty. I mentioned I trade Polymarket. He put down his drink. "You use Cursor for coding right?" I said yeah like everyone else. "Stop. Cursor is a wrapper. The model behind it is Claude. You're paying for UI. The real edge is connecting Claude Code directly to a repo" I didn't get it. What repo. He pulled out his phone. Opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history sitting in the open. "We built Cursor to make Claude easy. But the guys who actually make money skip the UI. They point Claude Code at a dataset and say - find the edge" I asked what he meant by edge. "47 wallets on Polymarket have a 70%+ win rate across 100+ trades. Average profit $214K. Average hold 7 hours" "91% exit BEFORE resolution. They don't predict outcomes. They trade the spread and leave" He said this like it was nothing. "The difference isn't entries. Top wallets capture 86% of the move and cut losers at 12%. Everyone else captures 58% and rides losers to 41%" Same trades. Exits make it a different game. He opened another link. "Three commands. Bot scans 500+ markets. No API key. Read-only. Claude builds the scoring in 20 minutes" I asked how he knows all this. "Someone wrote an article breaking down the entire build. Every repo. Every command" - he sent it Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours silence - thesis is dead. I went home at 1am. Copied the stack. Claude Code $20. VPS $5. $25 a month. No Cursor subscription. No team. No Bloomberg. 18 days. 193 trades. 72% win rate. $900 seed. +$9,200. I texted him my PNL. He replied next morning. "You just did for $25 what we charged $20/month to make slightly easier" I said - yeah but your UI is nice though. "Delete this conversation" Too late.
0:22

An ex-Cursor engineer told me something at a hackathon he probably shouldn't have It was in SF. Some YC demo day afterparty. I mentioned I trade Polymarket. He put down his drink. "You use Cursor for coding right?" I said yeah like everyone else. "Stop. Cursor is a wrapper. The model behind it is Claude. You're paying for UI. The real edge is connecting Claude Code directly to a repo" I didn't get it. What repo. He pulled out his phone. Opened one link. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history sitting in the open. "We built Cursor to make Claude easy. But the guys who actually make money skip the UI. They point Claude Code at a dataset and say - find the edge" I asked what he meant by edge. "47 wallets on Polymarket have a 70%+ win rate across 100+ trades. Average profit $214K. Average hold 7 hours" "91% exit BEFORE resolution. They don't predict outcomes. They trade the spread and leave" He said this like it was nothing. "The difference isn't entries. Top wallets capture 86% of the move and cut losers at 12%. Everyone else captures 58% and rides losers to 41%" Same trades. Exits make it a different game. He opened another link. "Three commands. Bot scans 500+ markets. No API key. Read-only. Claude builds the scoring in 20 minutes" I asked how he knows all this. "Someone wrote an article breaking down the entire build. Every repo. Every command" - he sent it Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours silence - thesis is dead. I went home at 1am. Copied the stack. Claude Code $20. VPS $5. $25 a month. No Cursor subscription. No team. No Bloomberg. 18 days. 193 trades. 72% win rate. $900 seed. +$9,200. I texted him my PNL. He replied next morning. "You just did for $25 what we charged $20/month to make slightly easier" I said - yeah but your UI is nice though. "Delete this conversation" Too late.

Lunar

12,680 views • 5 months ago

A 29-year-old sales consultant from China quit his job and now makes in 2 weeks what his boss earns all year. $306,000 profit last month. He replaced an entire quant team with Claude and 6 AI agents. Built his own ETH price simulation engine. Generating $15,000+ per day on autopilot. I reverse-engineered his system. One Claude prompt. 90 minutes. Fully autonomous. Giving this free for 24 hours. To get it: 1. Comment 'AGENT' 2. Like and retweet this 3. Follow Marry Evan so I can DM you His wallet: 0x06dc51826bc524d9a83770e7de9dd7e005b0452 on Polymarket. Almost nobody is watching. What the 6-agent swarm actually does: → Each agent validates its own trading decisions independently → Collects data 24/7 across markets → Runs continuous ETH price simulations in MiroFish engine → Memorizes every pattern, market reaction, trading signal → Detects market inefficiencies in real-time → Executes when edge appears → No human input required Not prediction. Pure math exploiting market lag. The coverage and speed beat top-tier trading teams. Every trade is a perfect cycle. Every dollar is extracted from pricing gaps that disappear in seconds. The system does not guess the future. It reads the numbers correctly and takes the money before markets reprice. The edge exists right now. It won't in 6 months when everyone runs similar systems. You only need: Claude + a device + 1 hour to deploy. Save this post. Build the agent swarm this week. Start with $100. Scale on evidence.
0:25

A 29-year-old sales consultant from China quit his job and now makes in 2 weeks what his boss earns all year. $306,000 profit last month. He replaced an entire quant team with Claude and 6 AI agents. Built his own ETH price simulation engine. Generating $15,000+ per day on autopilot. I reverse-engineered his system. One Claude prompt. 90 minutes. Fully autonomous. Giving this free for 24 hours. To get it: 1. Comment 'AGENT' 2. Like and retweet this 3. Follow Marry Evan so I can DM you His wallet: 0x06dc51826bc524d9a83770e7de9dd7e005b0452 on Polymarket. Almost nobody is watching. What the 6-agent swarm actually does: → Each agent validates its own trading decisions independently → Collects data 24/7 across markets → Runs continuous ETH price simulations in MiroFish engine → Memorizes every pattern, market reaction, trading signal → Detects market inefficiencies in real-time → Executes when edge appears → No human input required Not prediction. Pure math exploiting market lag. The coverage and speed beat top-tier trading teams. Every trade is a perfect cycle. Every dollar is extracted from pricing gaps that disappear in seconds. The system does not guess the future. It reads the numbers correctly and takes the money before markets reprice. The edge exists right now. It won't in 6 months when everyone runs similar systems. You only need: Claude + a device + 1 hour to deploy. Save this post. Build the agent swarm this week. Start with $100. Scale on evidence.

Marry Evan

19,080 views • 3 months ago

An Anthropic researcher sat next to me at Ritual Coffee in the Mission yesterday He glanced at my screen and saw the wallet tracker "Wait. Are you copytrading Polymarket wallets" I nodded. "How do you pick which ones. Most of them lose money" 87% of them. I told him that's what Claude found when it scanned 14,000 wallets. "You ran Claude on the whole chain" Yeah. 86 million trades. Every wallet. Every entry. Every exit. I asked Claude one thing. Which wallets win by category, not overall. It came back with three groups. Weather specialists. 85-94% win rate on meteorological markets. Bleed on everything else. Crypto-only. 88-96% on crypto. Lose on politics. Macro traders. 82-91% on Fed decisions and rate cuts. Dead on sports. "So you don't copy the wallet. You copy the category" Exactly. Retail mirrors the whole wallet. Smart money filters to the one category where they actually have edge. Skip the rest. He asked about speed. Profitable wallets enter 0-3 seconds after signal. Retail enters 12-18 seconds later. Same trade. Different fill. 7 cents of slippage per entry. Over 200 trades that's $1,400 gone just from being slow. "That's not intelligence. That's execution" Both. Then I showed him the third pattern. Capital velocity. Elite wallets recycle the same $500 fifty-one times a month. Retail recycles once. Same seed. 51x the work. He went quiet. Another fill landed on my screen. Weather market. +$47. Wallet for copytrading: "How long have you been running this" 11 weeks. Week 1-2. Manual. Caught 35% of trades. Lost 6 cents to slippage. +$3,100. Week 3-5. Loaded 6 wallets into Kreo. Category filter on. Priority Mode executing in the same Polygon block. Caught 78%. +$18,900. Week 6-8. Velocity filter. Only wallets recycling 40x+ monthly. +$31,400. Week 9-11. Full auto. Copying weather, crypto, macro. Trading Asia hours while I sleep. +$40,800. Total from $800. +$98,500. "What did you study" Nothing. My roommate did the first run in February and made $94K. I just copied him in April. Start in February. $94K. Start in April. $98K. Start in August. Maybe $55K. Not because the strategy stops. Because edge compresses when more people find it. He pulled out his phone and started typing. "Stanford emailed my roommate yesterday. Reconsidering his application" He didn't open it. PhD teaches you to research for 5 years. Claude taught him to find edge in one night. Wallets are on-chain. Data is public. The bottleneck was never analysis. It was category filtering and execution speed. Copytrade here: Full breakdown went up yesterday. Every wallet address. Every pattern. Every week. His manager DMed me this morning. "Any chance we can talk" I told him the article is the talk. Too late to gatekeep.
0:20

An Anthropic researcher sat next to me at Ritual Coffee in the Mission yesterday He glanced at my screen and saw the wallet tracker "Wait. Are you copytrading Polymarket wallets" I nodded. "How do you pick which ones. Most of them lose money" 87% of them. I told him that's what Claude found when it scanned 14,000 wallets. "You ran Claude on the whole chain" Yeah. 86 million trades. Every wallet. Every entry. Every exit. I asked Claude one thing. Which wallets win by category, not overall. It came back with three groups. Weather specialists. 85-94% win rate on meteorological markets. Bleed on everything else. Crypto-only. 88-96% on crypto. Lose on politics. Macro traders. 82-91% on Fed decisions and rate cuts. Dead on sports. "So you don't copy the wallet. You copy the category" Exactly. Retail mirrors the whole wallet. Smart money filters to the one category where they actually have edge. Skip the rest. He asked about speed. Profitable wallets enter 0-3 seconds after signal. Retail enters 12-18 seconds later. Same trade. Different fill. 7 cents of slippage per entry. Over 200 trades that's $1,400 gone just from being slow. "That's not intelligence. That's execution" Both. Then I showed him the third pattern. Capital velocity. Elite wallets recycle the same $500 fifty-one times a month. Retail recycles once. Same seed. 51x the work. He went quiet. Another fill landed on my screen. Weather market. +$47. Wallet for copytrading: "How long have you been running this" 11 weeks. Week 1-2. Manual. Caught 35% of trades. Lost 6 cents to slippage. +$3,100. Week 3-5. Loaded 6 wallets into Kreo. Category filter on. Priority Mode executing in the same Polygon block. Caught 78%. +$18,900. Week 6-8. Velocity filter. Only wallets recycling 40x+ monthly. +$31,400. Week 9-11. Full auto. Copying weather, crypto, macro. Trading Asia hours while I sleep. +$40,800. Total from $800. +$98,500. "What did you study" Nothing. My roommate did the first run in February and made $94K. I just copied him in April. Start in February. $94K. Start in April. $98K. Start in August. Maybe $55K. Not because the strategy stops. Because edge compresses when more people find it. He pulled out his phone and started typing. "Stanford emailed my roommate yesterday. Reconsidering his application" He didn't open it. PhD teaches you to research for 5 years. Claude taught him to find edge in one night. Wallets are on-chain. Data is public. The bottleneck was never analysis. It was category filtering and execution speed. Copytrade here: Full breakdown went up yesterday. Every wallet address. Every pattern. Every week. His manager DMed me this morning. "Any chance we can talk" I told him the article is the talk. Too late to gatekeep.

Lunar

32,867 views • 5 months ago

A 29-year-old sales consultant from China quit his job. Now making 2 weeks what his boss earns all year. $306,000 profit last month. He replaced an entire quant team with Claude and 6 AI agents. Built his own ETH price simulation engine. Generating $15,000+ per day on autopilot. I reverse-engineered his system. One Claude prompt. 90 minutes. Fully autonomous. Giving this free for 24 hours. To get it: 1. Comment AGENT 2. Like and retweet this 3. Follow Himanshu Kumar so I can DM you His wallet: 0x06dc51826bc524d9a83770e7de9dd7e005b0452 on Polymarket. Almost nobody is watching. What the 6-agent swarm actually does: → Each agent validates its own trading decisions independently → Collects data 24/7 across markets → Runs continuous ETH price simulations in MiroFish engine → Memorizes every pattern, market reaction, trading signal → Detects market inefficiencies in real-time → Executes when edge appears → No human input required Not prediction. Pure math exploiting market lag. The coverage and speed beat top-tier trading teams. Every trade is a perfect cycle. Every dollar is extracted from pricing gaps that disappear in seconds. The system does not guess the future. It reads the numbers correctly and takes the money before markets reprice. The edge exists right now. It won't in 6 months when everyone runs similar systems. You only need: Claude + a device + 1 hour to deploy. Save this post. Build the agent swarm this week. Start with $100. Scale on evidence.
0:25

A 29-year-old sales consultant from China quit his job. Now making 2 weeks what his boss earns all year. $306,000 profit last month. He replaced an entire quant team with Claude and 6 AI agents. Built his own ETH price simulation engine. Generating $15,000+ per day on autopilot. I reverse-engineered his system. One Claude prompt. 90 minutes. Fully autonomous. Giving this free for 24 hours. To get it: 1. Comment AGENT 2. Like and retweet this 3. Follow Himanshu Kumar so I can DM you His wallet: 0x06dc51826bc524d9a83770e7de9dd7e005b0452 on Polymarket. Almost nobody is watching. What the 6-agent swarm actually does: → Each agent validates its own trading decisions independently → Collects data 24/7 across markets → Runs continuous ETH price simulations in MiroFish engine → Memorizes every pattern, market reaction, trading signal → Detects market inefficiencies in real-time → Executes when edge appears → No human input required Not prediction. Pure math exploiting market lag. The coverage and speed beat top-tier trading teams. Every trade is a perfect cycle. Every dollar is extracted from pricing gaps that disappear in seconds. The system does not guess the future. It reads the numbers correctly and takes the money before markets reprice. The edge exists right now. It won't in 6 months when everyone runs similar systems. You only need: Claude + a device + 1 hour to deploy. Save this post. Build the agent swarm this week. Start with $100. Scale on evidence.

Himanshu Kumar

12,348 views • 3 months ago

An Anthropic engineer left his laptop unlocked at a cafe in SF I wasn't trying to look. But the screen was right there. A Polymarket terminal. Live trades scrolling. Green numbers. And a model ID I'd never seen before - claude-opus-4-7. He came back. Saw me staring. Didn't close it. "You trade?" I told him I run 8 Claude agents on Polymarket. He sat down like I just said a password. "What model are you on?" 4.6. He shook his head. "We've been running 4.7 internally for two weeks. Your disposition filter - what is it?" 0.70. He laughed. "Ours is 0.82. Below that you're literally copying noise. But on 4.7 you can push it to 0.58. The model filters its own noise now" He turned his laptop. A spreadsheet. 47 wallets ranked by exit quality. "Not win rate. Exit quality. Top wallets capture 86% of the move and cut at 12%. Everyone else captures 58% and holds losers past 40%" I've never heard anyone break it down like that. He opened one repo. 86 million trades. Every wallet. Every entry. Every exit. Public. Then a second. "Three commands. Every order book. No API key. 4.7 scores them in seconds. Not minutes. Seconds" I asked why he's telling me this. "Because my side bot makes more than my Anthropic salary and I want the liquidity to stay deep" He showed me his phone. +$47,000. 38 days On a model that wasn't even public yet. I asked when 4.7 drops. He said "this week". It dropped today. I switched all 8 agents in 10 minutes. Rebuilt everything that night. First week: +$2,800 Second: +$2,400 Third: +$2,100 Fourth: +$2,100 +$9,400 in 28 days. 191 trades. 73% win rate. Avg hold 4h. Crypto +$3,740 Weather +$2,910 Politics +$1,850 Macro +$1,200 Sports -$300 Killed it after day 2 Capital velocity: 47x. Kelly f+ 0.068. Max drawdown -2.1%. Bot for those who don't build: I asked if I could post this. "Don't use my name and we're good" Done.
0:21

An Anthropic engineer left his laptop unlocked at a cafe in SF I wasn't trying to look. But the screen was right there. A Polymarket terminal. Live trades scrolling. Green numbers. And a model ID I'd never seen before - claude-opus-4-7. He came back. Saw me staring. Didn't close it. "You trade?" I told him I run 8 Claude agents on Polymarket. He sat down like I just said a password. "What model are you on?" 4.6. He shook his head. "We've been running 4.7 internally for two weeks. Your disposition filter - what is it?" 0.70. He laughed. "Ours is 0.82. Below that you're literally copying noise. But on 4.7 you can push it to 0.58. The model filters its own noise now" He turned his laptop. A spreadsheet. 47 wallets ranked by exit quality. "Not win rate. Exit quality. Top wallets capture 86% of the move and cut at 12%. Everyone else captures 58% and holds losers past 40%" I've never heard anyone break it down like that. He opened one repo. 86 million trades. Every wallet. Every entry. Every exit. Public. Then a second. "Three commands. Every order book. No API key. 4.7 scores them in seconds. Not minutes. Seconds" I asked why he's telling me this. "Because my side bot makes more than my Anthropic salary and I want the liquidity to stay deep" He showed me his phone. +$47,000. 38 days On a model that wasn't even public yet. I asked when 4.7 drops. He said "this week". It dropped today. I switched all 8 agents in 10 minutes. Rebuilt everything that night. First week: +$2,800 Second: +$2,400 Third: +$2,100 Fourth: +$2,100 +$9,400 in 28 days. 191 trades. 73% win rate. Avg hold 4h. Crypto +$3,740 Weather +$2,910 Politics +$1,850 Macro +$1,200 Sports -$300 Killed it after day 2 Capital velocity: 47x. Kelly f+ 0.068. Max drawdown -2.1%. Bot for those who don't build: I asked if I could post this. "Don't use my name and we're good" Done.

rari

71,528 views • 5 months ago

a Citadel intern told me something at a party he probably shouldn't have it was on a rooftop in brooklyn. i mentioned i trade prediction markets. he got quiet for a second. "we have a model for that. it scores every contract on four factors. when all four align we enter. when any breaks we exit. that's it" i asked what the four factors are. he looked around. then said it fast like he was confessing. "cross-market divergence. disposition coefficient. capital velocity. pair network correlation" I didn't know what half of that meant. but i memorized it. went home. 11pm. opened Claude. "here are four scoring factors from a quant fund. build a terminal that runs all four on prediction markets" Claude asked one question: "Where's the data?" I sent him one repo: 86 million trades. every wallet. every entry. every outcome three weeks later i'm sitting in my apartment watching a screen i barely understand print money. the disposition meter alone changed everything. it measures how you exit - not how you enter. top wallets capture 86% of winner value and cut losers at 12%. everyone else captures 58% and holds losers to 41%. same exact entries. the exits make it a completely different game. capital velocity: 49x. every dollar gets recycled 49 times before the average trader recycles once. the terminal found 42 pair correlations across 11 markets. when MSFT beats Q3 is priced at 80c but the model reads 93% - it enters. when the gap closes 2 hours later - it exits. no opinions. no news. just four numbers that either align or don't. his fund runs this with a floor of PhDs and $800M AUM. my setup: > Claude - $20/month > VPS - $5/month > poly_data repo - free > Polymarket API - free $25/month. no team. no office. no Bloomberg. 280 trades so far. 70% win rate. $800 seed. four bots splitting the work: pulse_alpha +$299. arb_hunter +$558. trend_rider +$337. cal_engine +$719. +$11,514 total. copytrade here: he texted me last week. "delete everything i told you" too late.
0:38

a Citadel intern told me something at a party he probably shouldn't have it was on a rooftop in brooklyn. i mentioned i trade prediction markets. he got quiet for a second. "we have a model for that. it scores every contract on four factors. when all four align we enter. when any breaks we exit. that's it" i asked what the four factors are. he looked around. then said it fast like he was confessing. "cross-market divergence. disposition coefficient. capital velocity. pair network correlation" I didn't know what half of that meant. but i memorized it. went home. 11pm. opened Claude. "here are four scoring factors from a quant fund. build a terminal that runs all four on prediction markets" Claude asked one question: "Where's the data?" I sent him one repo: 86 million trades. every wallet. every entry. every outcome three weeks later i'm sitting in my apartment watching a screen i barely understand print money. the disposition meter alone changed everything. it measures how you exit - not how you enter. top wallets capture 86% of winner value and cut losers at 12%. everyone else captures 58% and holds losers to 41%. same exact entries. the exits make it a completely different game. capital velocity: 49x. every dollar gets recycled 49 times before the average trader recycles once. the terminal found 42 pair correlations across 11 markets. when MSFT beats Q3 is priced at 80c but the model reads 93% - it enters. when the gap closes 2 hours later - it exits. no opinions. no news. just four numbers that either align or don't. his fund runs this with a floor of PhDs and $800M AUM. my setup: > Claude - $20/month > VPS - $5/month > poly_data repo - free > Polymarket API - free $25/month. no team. no office. no Bloomberg. 280 trades so far. 70% win rate. $800 seed. four bots splitting the work: pulse_alpha +$299. arb_hunter +$558. trend_rider +$337. cal_engine +$719. +$11,514 total. copytrade here: he texted me last week. "delete everything i told you" too late.

Hanako

1,741,333 views • 5 months ago

Claude and a free weather API will earn you $100k+. Success rate for beginners: 80%. Complete guide and algorithm for building Polymarket weather trading bot. Simple logic, a low entry budget and high ROI -that’s why weather bots are so clean. Onchain proof these bots exist: 1st bot: 2nd bot: I verified their profitability by myself copying every trade - each bot's win rate over time ranges from 80 to 90%. I grew my starting capital by +40% in just one week. You can copy their trades and see for yourself in two clicks through this bot: The alpha is simple: you're not trading weather. You're trading other people's ignorance. Gap between what the crowd prices and what 51 ensemble models say. Polymarket asks: "Will Atlanta hit 95°F tomorrow?" Normies bet on vibes. You bet on math. The core tool: Open-Meteo API. Free. No key needed. 51-model ensemble. Clean JSON. Cooked and ready. Update every 30 min. Hardcode your city coordinates - don't waste time on geocoding at runtime. This single endpoint beats most paid tools for what Polymarket actually needs. The edge in one sentence: Market is heavy on 16°C. Your 51-model ensemble points at 19°C. That's your trade. Find that gap systematically across every city market, every day - and you have a scanner. That's what separates consistent traders from gamblers. How to start: - Week 1: Open-Meteo + tropicaltidbits. Pick one city market. Track model vs market price daily. Don't trade yet — just watch where you'd have been right. - Weeks 2–3: Automate the pull. Log ensemble divergences. Build the scanner. - Week 4: Now you have an edge. Trade it. Most people want to skip to week 4. That's exactly why most people lose. Now you have the algorithm framework plus a complete guide to get started. All that's left is to actually do it. Bookmark this post so you can come back to it when you start building the bot.
0:14

Claude and a free weather API will earn you $100k+. Success rate for beginners: 80%. Complete guide and algorithm for building Polymarket weather trading bot. Simple logic, a low entry budget and high ROI -that’s why weather bots are so clean. Onchain proof these bots exist: 1st bot: 2nd bot: I verified their profitability by myself copying every trade - each bot's win rate over time ranges from 80 to 90%. I grew my starting capital by +40% in just one week. You can copy their trades and see for yourself in two clicks through this bot: The alpha is simple: you're not trading weather. You're trading other people's ignorance. Gap between what the crowd prices and what 51 ensemble models say. Polymarket asks: "Will Atlanta hit 95°F tomorrow?" Normies bet on vibes. You bet on math. The core tool: Open-Meteo API. Free. No key needed. 51-model ensemble. Clean JSON. Cooked and ready. Update every 30 min. Hardcode your city coordinates - don't waste time on geocoding at runtime. This single endpoint beats most paid tools for what Polymarket actually needs. The edge in one sentence: Market is heavy on 16°C. Your 51-model ensemble points at 19°C. That's your trade. Find that gap systematically across every city market, every day - and you have a scanner. That's what separates consistent traders from gamblers. How to start: - Week 1: Open-Meteo + tropicaltidbits. Pick one city market. Track model vs market price daily. Don't trade yet — just watch where you'd have been right. - Weeks 2–3: Automate the pull. Log ensemble divergences. Build the scanner. - Week 4: Now you have an edge. Trade it. Most people want to skip to week 4. That's exactly why most people lose. Now you have the algorithm framework plus a complete guide to get started. All that's left is to actually do it. Bookmark this post so you can come back to it when you start building the bot.

cvxv666

50,799 views • 5 months ago

a Goldman Sachs engineer sat next to me on a delayed flight from JFK four hours on the tarmac. nowhere to go. we started talking. i told him i trade prediction markets with Claude. he almost choked on his ginger ale. "you do WHAT with an AI?" i showed him my terminal. he went quiet. scrolled through it for two full minutes. "this is close to what we run internally. how did you get the scoring model?" i told him. one GitHub repo with 2,600 stars. Claude connected the dots. official Polymarket framework. LLM-powered trading agents. open source. free. i gave Claude the repo and said: build me a grid that scans 700+ markets per hour and enters when the edge exceeds 9 cents. he didn't ask twice. the Goldman guy kept scrolling. "you have a disposition meter. a kelly gauge. a correlation matrix. we spent $4M building this infrastructure" i told him my total cost. Claude $20/mo + VPS $5/mo he laughed. not the funny kind. that was three weeks ago. today the terminal shows: +$16,976. 439 trades. 73% win rate. avg hold 7h. > Falcon Heavy - mkt 68c. model 95c. +$716. > MSFT antitrust - mkt 59c. model 77c. +$670. > Blizzard NY - mkt 74c. model 85c. +$772. > BOJ rate hike - mkt 52c. model 60c. +$422. four bots split everything: - pulse_alpha +$299. - arb_hunter +$558. - trend_rider +$337. - cal_engine +$719. kelly fraction 0.118. correlation matrix tracking 6 asset pairs. when one breaks - something is wrong. the grid trades it. copytrade here: he DM'd me yesterday. "i showed your screenshot to my desk. they want to know who built your infra" i said Claude. he said "seriously" i said seriously.
0:31

a Goldman Sachs engineer sat next to me on a delayed flight from JFK four hours on the tarmac. nowhere to go. we started talking. i told him i trade prediction markets with Claude. he almost choked on his ginger ale. "you do WHAT with an AI?" i showed him my terminal. he went quiet. scrolled through it for two full minutes. "this is close to what we run internally. how did you get the scoring model?" i told him. one GitHub repo with 2,600 stars. Claude connected the dots. official Polymarket framework. LLM-powered trading agents. open source. free. i gave Claude the repo and said: build me a grid that scans 700+ markets per hour and enters when the edge exceeds 9 cents. he didn't ask twice. the Goldman guy kept scrolling. "you have a disposition meter. a kelly gauge. a correlation matrix. we spent $4M building this infrastructure" i told him my total cost. Claude $20/mo + VPS $5/mo he laughed. not the funny kind. that was three weeks ago. today the terminal shows: +$16,976. 439 trades. 73% win rate. avg hold 7h. > Falcon Heavy - mkt 68c. model 95c. +$716. > MSFT antitrust - mkt 59c. model 77c. +$670. > Blizzard NY - mkt 74c. model 85c. +$772. > BOJ rate hike - mkt 52c. model 60c. +$422. four bots split everything: - pulse_alpha +$299. - arb_hunter +$558. - trend_rider +$337. - cal_engine +$719. kelly fraction 0.118. correlation matrix tracking 6 asset pairs. when one breaks - something is wrong. the grid trades it. copytrade here: he DM'd me yesterday. "i showed your screenshot to my desk. they want to know who built your infra" i said Claude. he said "seriously" i said seriously.

Hanako

286,938 views • 5 months ago

Ran into a Chinese quant at a noodle spot in Flushing last week. Jane Street badge on his belt. Came straight from the PATH. Laptop open on the counter. Position check running. He stopped. "Is that Polymarket" Yeah. "You trade it with Claude" I nodded. He sat down without asking. "I'm on the systematic desk. We model this venue in research. You're running it from a noodle shop" I asked what the desk does with it. "We don't trade. Compliance won't let us. We run shadow books. Cleanest retail venue on earth. Every wallet public. Every fill on-chain. You're sitting on a dataset we'd pay seven figures for" I showed him the scanner. 86M trades. - nobody outside maintainers touches it. 14,000 wallets in. Filter by floor WR, trade count, size, recency. 9 wallets out. Opus 4.7 chewed it in 38 minutes on a $5 VPS. "The filter" 40-200 trades. 74+ lifetime WR. Sub $1,500 avg. Active last 45 days. 3 qualifying 21-day windows. "Why those bands" Above 200 is a fund. Below 40 is luck. Between is the edge. A fill landed. +$112 on BTC+100K 5-min. "How does it enter" Each wallet only prints in its zone. 83% crypto. 51% politics. 49% sports. Copy only inside the zone. "Domain conditioning. We have a paper on it. Nobody ships it retail" I ship it. Four Python scripts. Claude Code wrote 80% in a weekend. Delay 21 min. Bet size is the signal. $900 normal, $1,600 is 1.8 sigma. Size up. Exit mirrors source. 74.1% of max gain. Stale past 18h under 3% gets cut. Sharpe 2.67 253 trades 72.7% WR $200 seed +$14,985 in 31 days He put his chopsticks down. "Add one thing. When 8+ wallets dump the same side of a 5-min BTC window in under 60s, fade them. Crowd is the signal" Execution For those who don't build - He slid a napkin across before leaving. "If anyone at my firm asks, we never spoke" I said we didn't. I found it myself. He smiled. "Good answer" Napkin said: "the crowd is the liquidity"
0:24

Ran into a Chinese quant at a noodle spot in Flushing last week. Jane Street badge on his belt. Came straight from the PATH. Laptop open on the counter. Position check running. He stopped. "Is that Polymarket" Yeah. "You trade it with Claude" I nodded. He sat down without asking. "I'm on the systematic desk. We model this venue in research. You're running it from a noodle shop" I asked what the desk does with it. "We don't trade. Compliance won't let us. We run shadow books. Cleanest retail venue on earth. Every wallet public. Every fill on-chain. You're sitting on a dataset we'd pay seven figures for" I showed him the scanner. 86M trades. - nobody outside maintainers touches it. 14,000 wallets in. Filter by floor WR, trade count, size, recency. 9 wallets out. Opus 4.7 chewed it in 38 minutes on a $5 VPS. "The filter" 40-200 trades. 74+ lifetime WR. Sub $1,500 avg. Active last 45 days. 3 qualifying 21-day windows. "Why those bands" Above 200 is a fund. Below 40 is luck. Between is the edge. A fill landed. +$112 on BTC+100K 5-min. "How does it enter" Each wallet only prints in its zone. 83% crypto. 51% politics. 49% sports. Copy only inside the zone. "Domain conditioning. We have a paper on it. Nobody ships it retail" I ship it. Four Python scripts. Claude Code wrote 80% in a weekend. Delay 21 min. Bet size is the signal. $900 normal, $1,600 is 1.8 sigma. Size up. Exit mirrors source. 74.1% of max gain. Stale past 18h under 3% gets cut. Sharpe 2.67 253 trades 72.7% WR $200 seed +$14,985 in 31 days He put his chopsticks down. "Add one thing. When 8+ wallets dump the same side of a 5-min BTC window in under 60s, fade them. Crowd is the signal" Execution For those who don't build - He slid a napkin across before leaving. "If anyone at my firm asks, we never spoke" I said we didn't. I found it myself. He smiled. "Good answer" Napkin said: "the crowd is the liquidity"

rari

25,293 views • 4 months ago

An Anthropic researcher sat down next to me at a hackathon last week. Claude Opus 4.7 was running 4 agents on my laptop. Live. No manual input. She looked at the terminal and said: "What is this?" I showed her. 4 agents. 678 trades. 81% win rate. $16,200 last 30 days. She worked on the evals team. She'd never seen Claude pointed at 88 million on-chain trades. The setup is 3 public repos. All free. -> 88 million Polymarket trades. Every wallet. Every entry. Every exit. Every resolution. -> the framework that bridges Claude Opus 4.7 directly to live markets. Order placement, position tracking, exit timing. -> real-time WebSocket order book. Depth on both sides. No polling, no lag. Four agents. One loop. Agent 1 identifies which wallets win consistently across 88 million trades. Agent 2 reverse-engineers their entry timing. Agent 3 monitors order book volume spikes. Agent 4 sizes positions using Kelly. No overbet. Drawdown capped at 1.4% over 678 trades. 85% of windows get killed. No trade. The bot only enters when 3 signals align: -> Elite wallet consensus pointing the same direction. -> Price divergence with Binance and Coinbase both agreeing. -> Order book imbalance confirming the bias. Single-source price data was 57% accurate. All three together: 81%. Exit before resolution. Always. Losers hold to 0 or $1. The agents copy their exits. The agents don't gamble on that. My stack: Claude Opus 4.7 at $19/mo, VPS Hetzner at $4.99/mo, Everything else free. Total stats: $23.99/month. 30 days: 678 trades, 81% win rate, net +$16,200, max drawdown -1.2%, avg hold 4h 12m. She asked if Anthropic could test this internally. "We run Claude on benchmarks and evals. Nobody pointed it at a live market dataset with 88 million rows." Claude Opus 4.7 didn't need a system prompt. It read the wallet index, understood the signal structure, and wrote the combiner logic in one pass. The people who built the model hadn't thought to point it at this data. I had. Copy the live trades: -> all 4 agents run 24/7. The window is open right now. Save this, follow me and comment OPUS. I will send the guide to you.
0:26

An Anthropic researcher sat down next to me at a hackathon last week. Claude Opus 4.7 was running 4 agents on my laptop. Live. No manual input. She looked at the terminal and said: "What is this?" I showed her. 4 agents. 678 trades. 81% win rate. $16,200 last 30 days. She worked on the evals team. She'd never seen Claude pointed at 88 million on-chain trades. The setup is 3 public repos. All free. -> 88 million Polymarket trades. Every wallet. Every entry. Every exit. Every resolution. -> the framework that bridges Claude Opus 4.7 directly to live markets. Order placement, position tracking, exit timing. -> real-time WebSocket order book. Depth on both sides. No polling, no lag. Four agents. One loop. Agent 1 identifies which wallets win consistently across 88 million trades. Agent 2 reverse-engineers their entry timing. Agent 3 monitors order book volume spikes. Agent 4 sizes positions using Kelly. No overbet. Drawdown capped at 1.4% over 678 trades. 85% of windows get killed. No trade. The bot only enters when 3 signals align: -> Elite wallet consensus pointing the same direction. -> Price divergence with Binance and Coinbase both agreeing. -> Order book imbalance confirming the bias. Single-source price data was 57% accurate. All three together: 81%. Exit before resolution. Always. Losers hold to 0 or $1. The agents copy their exits. The agents don't gamble on that. My stack: Claude Opus 4.7 at $19/mo, VPS Hetzner at $4.99/mo, Everything else free. Total stats: $23.99/month. 30 days: 678 trades, 81% win rate, net +$16,200, max drawdown -1.2%, avg hold 4h 12m. She asked if Anthropic could test this internally. "We run Claude on benchmarks and evals. Nobody pointed it at a live market dataset with 88 million rows." Claude Opus 4.7 didn't need a system prompt. It read the wallet index, understood the signal structure, and wrote the combiner logic in one pass. The people who built the model hadn't thought to point it at this data. I had. Copy the live trades: -> all 4 agents run 24/7. The window is open right now. Save this, follow me and comment OPUS. I will send the guide to you.

slash1s

46,379 views • 5 months ago