Loading video...

Video Failed to Load

Go Home

Russian young guy used free source Claude Code and Open Claw and turned $13 into $195,000 in one month He is from a small town near Moscow He had no starting capital He just used free tools When limits appeared on his account he simply created new ones and...

adiix_official's profile picture

AdiiX

24,297 subscribers

57,519 views • 4 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

Anthropic released an update for Claude, and one young guy turned $1,400 into $238,000 in 11 days His account is 0xdE17. He is not a trader. Not a developer. Just a student with a laptop and access to Claude. When Anthropic updated the skills architecture for Claude, he didn’t sleep for two nights, read the documentation, and built a bot from scratch. Result: $1,430 → $238,006 in 11 days 366 trades. Win rate 62%. The biggest win $52,700 on a single bet. How it works: The bot scans Polymarket every few seconds looking for markets where the price deviates from the fair value by more than 8%. That’s the edge. Most people don’t see it the bot always does. The strategy is painfully simple - The market says 30¢ for an event - The real probability based on data is 55¢ - The bot enters. Waits. Exits at the peak. This isn’t luck. It’s attention arbitrage. The biggest trade was a bet that Trump would sign a crypto executive order in March. The market priced it at 28¢. The bot placed $16,000. Exited at 81¢. In 11 days he went through a journey most traders don’t go through in years. Now his wallet is public, and with the help of this terminal you will be able to copy his trades in time: Bot 0xdE17 CLAWD BTC SNIPER is open for copy-trade. People ask him: “How much starting capital do you need?” He replied: “I had $1,400 and a sleepless night.” Anthropic gave the tool. He simply wasn’t afraid to use it.
1:01

Anthropic released an update for Claude, and one young guy turned $1,400 into $238,000 in 11 days His account is 0xdE17. He is not a trader. Not a developer. Just a student with a laptop and access to Claude. When Anthropic updated the skills architecture for Claude, he didn’t sleep for two nights, read the documentation, and built a bot from scratch. Result: $1,430 → $238,006 in 11 days 366 trades. Win rate 62%. The biggest win $52,700 on a single bet. How it works: The bot scans Polymarket every few seconds looking for markets where the price deviates from the fair value by more than 8%. That’s the edge. Most people don’t see it the bot always does. The strategy is painfully simple - The market says 30¢ for an event - The real probability based on data is 55¢ - The bot enters. Waits. Exits at the peak. This isn’t luck. It’s attention arbitrage. The biggest trade was a bet that Trump would sign a crypto executive order in March. The market priced it at 28¢. The bot placed $16,000. Exited at 81¢. In 11 days he went through a journey most traders don’t go through in years. Now his wallet is public, and with the help of this terminal you will be able to copy his trades in time: Bot 0xdE17 CLAWD BTC SNIPER is open for copy-trade. People ask him: “How much starting capital do you need?” He replied: “I had $1,400 and a sleepless night.” Anthropic gave the tool. He simply wasn’t afraid to use it.

AdiiX

1,764,166 views • 4 months ago

Stanford student fed Claude a book with 151 trading strategies and turned $87 into $213,000 in one week His account is 0xB27 He gave him one task: -find an edge on Polymarket BTC markets Claude analyzed 550 mathematical formulas in 2 minutes and said that most of them don’t work in prediction markets and explained why what remained: → momentum on 5m/15m/1h → binary markets systematically overestimate short-term BTC volatility → there is a gap between what the market thinks and what the data shows He wrote a bot over the weekend from March 4 to today: → 3,426 trades → biggest win: $11,900 on a single position → the account is public, you can check it Profile: “I’m not a trader, I didn’t have trading education, I had a book and Claude”-he says cost of entry: one book and a few prompts The link to the book will be under the post 👇🏼 Just insert PDF files into Claude and create your own bot Add this post to bookmarks so you don’t lose this PDF If you’re interested in which 5 prompts he used to set up the bot Like, repost, comment STANFORD and I’ll send them to you in DM The main thing is to be subscribed so I can DM you
0:24

Stanford student fed Claude a book with 151 trading strategies and turned $87 into $213,000 in one week His account is 0xB27 He gave him one task: -find an edge on Polymarket BTC markets Claude analyzed 550 mathematical formulas in 2 minutes and said that most of them don’t work in prediction markets and explained why what remained: → momentum on 5m/15m/1h → binary markets systematically overestimate short-term BTC volatility → there is a gap between what the market thinks and what the data shows He wrote a bot over the weekend from March 4 to today: → 3,426 trades → biggest win: $11,900 on a single position → the account is public, you can check it Profile: “I’m not a trader, I didn’t have trading education, I had a book and Claude”-he says cost of entry: one book and a few prompts The link to the book will be under the post 👇🏼 Just insert PDF files into Claude and create your own bot Add this post to bookmarks so you don’t lose this PDF If you’re interested in which 5 prompts he used to set up the bot Like, repost, comment STANFORD and I’ll send them to you in DM The main thing is to be subscribed so I can DM you

AdiiX

47,280 views • 4 months ago

Anthropic released an update for Claude, and one student turned $1,400 into $238,000 in 11 days. His wallet: 0xdE17 He’s not a trader. Not a developer. Just a student with a laptop and access to Claude. When Anthropic updated Claude’s skills architecture, he spent two nights reading the documentation and built a bot from scratch. The result: $1,430 → $238,006 in 11 days 366 trades 62% win rate Largest single win: $52,700 How it works: The bot scans Polymarket every few seconds looking for markets where the price deviates from fair value by more than 8%. That’s the edge. Most people never notice it. The bot always does. The strategy is simple: The market prices an event at 30¢ The real probability based on data is closer to 55¢ The bot enters, waits, and exits as the market reprices It’s not luck. It’s attention arbitrage. The biggest trade was a bet that Trump would sign a crypto executive order in March. The market priced it at 28¢. The bot entered with $16,000. Exited at 81¢. In 11 days, he went through a journey most traders never experience in years. Now the wallet is public, and with this terminal you can copy the trades in real time: 0xde17f7144fbd0eddb2679132c10ff5e74b120988 Copytrade → People keep asking him: “How much starting capital do you need?” He answered: “I had $1,400 and a sleepless night.” Anthropic built the tool. He simply wasn’t afraid to use it.
1:00

Anthropic released an update for Claude, and one student turned $1,400 into $238,000 in 11 days. His wallet: 0xdE17 He’s not a trader. Not a developer. Just a student with a laptop and access to Claude. When Anthropic updated Claude’s skills architecture, he spent two nights reading the documentation and built a bot from scratch. The result: $1,430 → $238,006 in 11 days 366 trades 62% win rate Largest single win: $52,700 How it works: The bot scans Polymarket every few seconds looking for markets where the price deviates from fair value by more than 8%. That’s the edge. Most people never notice it. The bot always does. The strategy is simple: The market prices an event at 30¢ The real probability based on data is closer to 55¢ The bot enters, waits, and exits as the market reprices It’s not luck. It’s attention arbitrage. The biggest trade was a bet that Trump would sign a crypto executive order in March. The market priced it at 28¢. The bot entered with $16,000. Exited at 81¢. In 11 days, he went through a journey most traders never experience in years. Now the wallet is public, and with this terminal you can copy the trades in real time: 0xde17f7144fbd0eddb2679132c10ff5e74b120988 Copytrade → People keep asking him: “How much starting capital do you need?” He answered: “I had $1,400 and a sleepless night.” Anthropic built the tool. He simply wasn’t afraid to use it.

Discover

114,227 views • 4 months ago

He started using Claude AI and made $25,000 in his first month The guy could not even hide how much it changed his life. He paid for Claude and treated it like a real business partner. Built workflows that automate client work, content and outreach all in one place. What used to take him 12 hours a day now takes 2. He started taking on triple the clients without burning out once. At $5,000 per client and five clients a month, the numbers move fast. That is $25,000 landing in his account from a tool that costs $20. Most people use Claude to write captions and call it a day. He used it to rebuild his entire income from the ground up. Follow if you want the exact workflows he uses to scale this.
0:46

He started using Claude AI and made $25,000 in his first month The guy could not even hide how much it changed his life. He paid for Claude and treated it like a real business partner. Built workflows that automate client work, content and outreach all in one place. What used to take him 12 hours a day now takes 2. He started taking on triple the clients without burning out once. At $5,000 per client and five clients a month, the numbers move fast. That is $25,000 landing in his account from a tool that costs $20. Most people use Claude to write captions and call it a day. He used it to rebuild his entire income from the ground up. Follow if you want the exact workflows he uses to scale this.

winkle.

21,373 views • 1 month ago

This trader fooled EVERYONE... And turned $0.10 into $280,260 in ONE DAY. Everyone was flexing their bot dashboards. Meanwhile this guy quietly farmed them: • 41 trades • near 100% Win Rate And he didn’t even predict anything. He hunted liquidity. Here’s what he understood that most don’t: Bots dominate Polymarket during dead hours. Late nights. Weekends. Low volume windows. Books get thin, but models stay active. Human oversight disappears. That’s when small capital can distort price massively. So what did he do? You probably already guessed. He didn’t chase direction. He nudged price. Push a contract slightly off balance so bots recalibrate mechanically. They start selling or buying based on their spread logic, not context. They see deviation. They respond automatically. He forces them into bad fills. Then, once price is stretched far from real probability, he accumulates size the other way. No rush. No panic. When liquidity returns and price normalizes? He just exits. Not because of news. Not because of edge in outcome. Because structure snapped back. This isn’t prophecy trading. It’s understanding how automated systems behave when liquidity is stressed. Most people think Polymarket profits come from being right. Wrong. Big money flows to whoever understands: • when bots are dominant • when books are fragile • when models overreact He didn’t beat the market. He beat the bots and took their profit. He made the market overreact and sold it back to itself. His profile: Absolute cinema, right? Leaving a full copy trading guide in the attached quote.
0:34

This trader fooled EVERYONE... And turned $0.10 into $280,260 in ONE DAY. Everyone was flexing their bot dashboards. Meanwhile this guy quietly farmed them: • 41 trades • near 100% Win Rate And he didn’t even predict anything. He hunted liquidity. Here’s what he understood that most don’t: Bots dominate Polymarket during dead hours. Late nights. Weekends. Low volume windows. Books get thin, but models stay active. Human oversight disappears. That’s when small capital can distort price massively. So what did he do? You probably already guessed. He didn’t chase direction. He nudged price. Push a contract slightly off balance so bots recalibrate mechanically. They start selling or buying based on their spread logic, not context. They see deviation. They respond automatically. He forces them into bad fills. Then, once price is stretched far from real probability, he accumulates size the other way. No rush. No panic. When liquidity returns and price normalizes? He just exits. Not because of news. Not because of edge in outcome. Because structure snapped back. This isn’t prophecy trading. It’s understanding how automated systems behave when liquidity is stressed. Most people think Polymarket profits come from being right. Wrong. Big money flows to whoever understands: • when bots are dominant • when books are fragile • when models overreact He didn’t beat the market. He beat the bots and took their profit. He made the market overreact and sold it back to itself. His profile: Absolute cinema, right? Leaving a full copy trading guide in the attached quote.

Oracle Boar

51,827 views • 5 months ago

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.
0:37

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 views • 1 month ago

ANOTHER CRAZY BOT FOR COPYTRADING ON POLYMARKET TURNED $5 INTO $500,000 no one is talking about him He made more than 17,000 prediction with a total profit $500,000 and 100% win rate trades in one market category: Up/Down The most successful bets: - $180 → $8,400 (%4,500) - $250 → $8,000 (%3,100) His strategy is simple : - buy and accumulate positions with the highest probability of winning You won’t be able to do this manually in time, but a bot can check his profile: you can copy his trades via : If you want to write such a bot without mistakes, I have outlined a step-by-step guide on how to do it Start today and thank yourself tomorrow
0:28

ANOTHER CRAZY BOT FOR COPYTRADING ON POLYMARKET TURNED $5 INTO $500,000 no one is talking about him He made more than 17,000 prediction with a total profit $500,000 and 100% win rate trades in one market category: Up/Down The most successful bets: - $180 → $8,400 (%4,500) - $250 → $8,000 (%3,100) His strategy is simple : - buy and accumulate positions with the highest probability of winning You won’t be able to do this manually in time, but a bot can check his profile: you can copy his trades via : If you want to write such a bot without mistakes, I have outlined a step-by-step guide on how to do it Start today and thank yourself tomorrow

AdiiX

21,187 views • 3 months ago

A bot pulled $294K in one month with something I have never seen a 100% win rate. I scrolled through 5,000 trades looking for one loss. Could not find it. 100%. Not 99.5. Not "almost perfect." Actual, literal, every single trade green. CRYINGLITTLEBABY does not play the same game as other bots. They enter at the start of a window, read momentum, guess direction. This one waits. → Account: The 15-minute BTC window opens. He watches. Does nothing. Five minutes pass. BTC drops hard on spot. The move is real. But Polymarket still shows DOWN at 25 cents. Now he enters. The bet is not "will BTC go down?" The bet is "BTC already went down and the odds have not caught up yet." By the time the window closes, he is paid $1 for something he bought at 20-30 cents. Not because he predicted anything. Because he waited until predicting was unnecessary. The treemap broke my brain a little. Solid green. A full month of trading and not one red tile. I kept scrolling thinking I would find it hiding somewhere. Nothing. The edge is patience. Other bots race to enter first. This one lets them fight, watches the result, and collects what is left. A month of trading. Zero losses. Just a wall of green proving that sometimes the best prediction is no prediction at all.
1:07

A bot pulled $294K in one month with something I have never seen a 100% win rate. I scrolled through 5,000 trades looking for one loss. Could not find it. 100%. Not 99.5. Not "almost perfect." Actual, literal, every single trade green. CRYINGLITTLEBABY does not play the same game as other bots. They enter at the start of a window, read momentum, guess direction. This one waits. → Account: The 15-minute BTC window opens. He watches. Does nothing. Five minutes pass. BTC drops hard on spot. The move is real. But Polymarket still shows DOWN at 25 cents. Now he enters. The bet is not "will BTC go down?" The bet is "BTC already went down and the odds have not caught up yet." By the time the window closes, he is paid $1 for something he bought at 20-30 cents. Not because he predicted anything. Because he waited until predicting was unnecessary. The treemap broke my brain a little. Solid green. A full month of trading and not one red tile. I kept scrolling thinking I would find it hiding somewhere. Nothing. The edge is patience. Other bots race to enter first. This one lets them fight, watches the result, and collects what is left. A month of trading. Zero losses. Just a wall of green proving that sometimes the best prediction is no prediction at all.

Blaze

272,546 views • 6 months ago

Chinese student used AI from Anthropic to turn $1,000 into $1,500,000 He studies at Tsinghua University in Beijing. His account is k9Q2m In such a young age he already make a million simply knowing the right formulas and being able to use Claude Result: $1,430 → $1,550,750 44,364 trades Win rate 100% The biggest win $23,600 on a single bet k9Q2m profile: How it bots work: The bot runs 6 formulas hedge funds use simultaneously, every tick. Most traders guess. This bot calculates. Formula 1 - LMSR Pricing Polymarket prices move on a logarithmic curve. The bot knows the exact price impact before entering. Market says 31¢ for BTC up in 5 minutes. The model sees the curve is mispriced. The bot enters before the correction. Formula 2 - Kelly Criterion Renaissance Capital uses it. Two Sigma uses it. Now your bot uses it. Every bet is sized exactly right. Never too big to blow the account. Never too small to matter. $1,000 bankroll. Consistent edge. Kelly compounds it into something real. Formula 3 - EV Gap Detection The bot scans every BTC market looking for one thing: - Where is the market price wrong by more than 5%? - Market says 30¢. Real probability is 55¢. EV = +0.52. The bot enters. Most people never see this gap. The bot never misses it. Formula 4 - KL-Divergence BTC 5-minute and 15-minute markets are correlated. When they drift apart - that's an arb. The bot measures the statistical distance between them every second. When it crosses 0.2, it flags the trade. This is how hedge funds extracted $100K+ on correlated election markets. The same logic runs here. Formula 5 - Bayesian Updates New block confirmed. Volume spike. Price movement. The bot doesn't ignore signals - it updates. Prior probability was 54%. New data comes in. Posterior jumps to 71%. The bot re-prices in real time while the market is still asleep. Formula 6 - Stoikov Execution Entering at the wrong moment kills the edge. The bot calculates the reservation price-the exact point where the risk-adjusted entry makes sense. It doesn't chase. It doesn't panic. It waits for the right tick, then fills What this means in practice: - Every few seconds the bot runs all six formulas in parallel. - If LMSR confirms mispricing - EV gap is above 5% - Kelly says the bet size is justified - Bayesian posterior agrees - KL-divergence flags the correlated drift - Stoikov clears the execution price Only then does the bot enter. Six filters. One trade. This isn't a trading bot. It's a hedge fund strategy running on a prediction market. The edge is real. The math is public. The difference is most people never build it. Just insert all these formulas into Claude and create your own bot Add this post to bookmarks so you don’t lose it Soon I will publish another bot with working formulas
0:38

Chinese student used AI from Anthropic to turn $1,000 into $1,500,000 He studies at Tsinghua University in Beijing. His account is k9Q2m In such a young age he already make a million simply knowing the right formulas and being able to use Claude Result: $1,430 → $1,550,750 44,364 trades Win rate 100% The biggest win $23,600 on a single bet k9Q2m profile: How it bots work: The bot runs 6 formulas hedge funds use simultaneously, every tick. Most traders guess. This bot calculates. Formula 1 - LMSR Pricing Polymarket prices move on a logarithmic curve. The bot knows the exact price impact before entering. Market says 31¢ for BTC up in 5 minutes. The model sees the curve is mispriced. The bot enters before the correction. Formula 2 - Kelly Criterion Renaissance Capital uses it. Two Sigma uses it. Now your bot uses it. Every bet is sized exactly right. Never too big to blow the account. Never too small to matter. $1,000 bankroll. Consistent edge. Kelly compounds it into something real. Formula 3 - EV Gap Detection The bot scans every BTC market looking for one thing: - Where is the market price wrong by more than 5%? - Market says 30¢. Real probability is 55¢. EV = +0.52. The bot enters. Most people never see this gap. The bot never misses it. Formula 4 - KL-Divergence BTC 5-minute and 15-minute markets are correlated. When they drift apart - that's an arb. The bot measures the statistical distance between them every second. When it crosses 0.2, it flags the trade. This is how hedge funds extracted $100K+ on correlated election markets. The same logic runs here. Formula 5 - Bayesian Updates New block confirmed. Volume spike. Price movement. The bot doesn't ignore signals - it updates. Prior probability was 54%. New data comes in. Posterior jumps to 71%. The bot re-prices in real time while the market is still asleep. Formula 6 - Stoikov Execution Entering at the wrong moment kills the edge. The bot calculates the reservation price-the exact point where the risk-adjusted entry makes sense. It doesn't chase. It doesn't panic. It waits for the right tick, then fills What this means in practice: - Every few seconds the bot runs all six formulas in parallel. - If LMSR confirms mispricing - EV gap is above 5% - Kelly says the bet size is justified - Bayesian posterior agrees - KL-divergence flags the correlated drift - Stoikov clears the execution price Only then does the bot enter. Six filters. One trade. This isn't a trading bot. It's a hedge fund strategy running on a prediction market. The edge is real. The math is public. The difference is most people never build it. Just insert all these formulas into Claude and create your own bot Add this post to bookmarks so you don’t lose it Soon I will publish another bot with working formulas

AdiiX

717,823 views • 4 months ago

You know NOTHING about arbitrage. If you watch sport or crypto markets, you already LOST. This guy makes $30k / month on weather markets. Because there's NO COMPETITION. His bot is trading every market AUTOMATICALLY. Here's how he applied the strategy from my article: His script identifies weather markets with spreads. And the best part is that almost each of them has it. Why? Because of low liquidity. This trader used one simple formula to trade those markets: Buy YES if P_model > P_market + T Buy NO if P_model < P_market − T So each time he's buying two outcomes at the same time. And wins. Check his last trade: It looks like he turned $200 into $6,000+ by betting on 0.2% outcome. But here's the real math: He he bought his YES shares at $0.002. At the same time he bought NO side at $0.994. The spread was tiny, just $0.004. That's why his actual profit is not $6k. He lost his NO position (-$6,072k) and won on YES side (+$6,172k). So his actual profit is just $100. His profile: He’s not betting on temperature. He’s buying a mispriced binary pair. If both sides together cost less than $1, the payout at resolution is $1. Most people try to be right. He just makes sure the math can’t be wrong. That's why you always have to double check everything. Details show the full picture.
0:57

You know NOTHING about arbitrage. If you watch sport or crypto markets, you already LOST. This guy makes $30k / month on weather markets. Because there's NO COMPETITION. His bot is trading every market AUTOMATICALLY. Here's how he applied the strategy from my article: His script identifies weather markets with spreads. And the best part is that almost each of them has it. Why? Because of low liquidity. This trader used one simple formula to trade those markets: Buy YES if P_model > P_market + T Buy NO if P_model < P_market − T So each time he's buying two outcomes at the same time. And wins. Check his last trade: It looks like he turned $200 into $6,000+ by betting on 0.2% outcome. But here's the real math: He he bought his YES shares at $0.002. At the same time he bought NO side at $0.994. The spread was tiny, just $0.004. That's why his actual profit is not $6k. He lost his NO position (-$6,072k) and won on YES side (+$6,172k). So his actual profit is just $100. His profile: He’s not betting on temperature. He’s buying a mispriced binary pair. If both sides together cost less than $1, the payout at resolution is $1. Most people try to be right. He just makes sure the math can’t be wrong. That's why you always have to double check everything. Details show the full picture.

Oracle Boar

61,326 views • 5 months ago

This guy used Claude to build a Quant Bot and made +$589,139 on Polymarket. 25,388 predictions with a 63% win rate in 77 days. That comes out to roughly $7,651 in profit per day and almost 14 trades per hour. With $217K in deposits, he is now up 2.7x. About +271.5% ROI. The bot strategy is simple: It finds markets where the pricing is still off. Gets in before the odds fully catch up. Repeats the same setup again and again across many entries. The edge on each trade is small. But scale and repetition turn it into a massive result. Most profitable trades: $17,839 → $36,318 (+$18,478, +103.58%) $3,112 → $15,011 (+$11,898, +382.22%) $10,676 → $22,178 (+$11,502, +107.74%) What makes it work is not one huge trade. It is the same small advantage, applied fast, applied often, and repeated until the pricing gap is gone. I reverse-engineered it. Had Claude rebuild the same logic. One prompt. 90 minutes. Fully deployed. You only need: Claude + a device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word PROFIT 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you
0:26

This guy used Claude to build a Quant Bot and made +$589,139 on Polymarket. 25,388 predictions with a 63% win rate in 77 days. That comes out to roughly $7,651 in profit per day and almost 14 trades per hour. With $217K in deposits, he is now up 2.7x. About +271.5% ROI. The bot strategy is simple: It finds markets where the pricing is still off. Gets in before the odds fully catch up. Repeats the same setup again and again across many entries. The edge on each trade is small. But scale and repetition turn it into a massive result. Most profitable trades: $17,839 → $36,318 (+$18,478, +103.58%) $3,112 → $15,011 (+$11,898, +382.22%) $10,676 → $22,178 (+$11,502, +107.74%) What makes it work is not one huge trade. It is the same small advantage, applied fast, applied often, and repeated until the pricing gap is gone. I reverse-engineered it. Had Claude rebuild the same logic. One prompt. 90 minutes. Fully deployed. You only need: Claude + a device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word PROFIT 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you

Himanshu Kumar

85,181 views • 1 month ago

I interviewed the dev of the best Polymarket bot His bot trades BTC Up/Down markets automatically 24/7 Result? +$650k each month passively Here're the tips he gave me on how to create the same bot: First thing: stop trying to predict Better build a system that reacts. His bot doesn’t guess tops or bottoms, but waits for confluence. Core stack: • EMA (defines trend: filters chop) • VWAP (shows fair value: avoid bad entries) • OBV (confirms money flow: no volume = no trade) • RSI (detects extremes: don’t buy highs or sell lows) • MACD (confirms momentum) Then he adds a volatility filter. Most bots die because they trade in dead or chaotic markets. His doesn’t. Risk model is everything: • fixed % per trade • no overtrading • strict cooldown after losses And the real edge: the bot trades only when 3-4 signals align at once No signal = no trade. His wallet address: It’s not about being right more often. It’s about only playing when odds are clearly in your favor. That’s how you turn a bot from a toy into a machine.
0:26

I interviewed the dev of the best Polymarket bot His bot trades BTC Up/Down markets automatically 24/7 Result? +$650k each month passively Here're the tips he gave me on how to create the same bot: First thing: stop trying to predict Better build a system that reacts. His bot doesn’t guess tops or bottoms, but waits for confluence. Core stack: • EMA (defines trend: filters chop) • VWAP (shows fair value: avoid bad entries) • OBV (confirms money flow: no volume = no trade) • RSI (detects extremes: don’t buy highs or sell lows) • MACD (confirms momentum) Then he adds a volatility filter. Most bots die because they trade in dead or chaotic markets. His doesn’t. Risk model is everything: • fixed % per trade • no overtrading • strict cooldown after losses And the real edge: the bot trades only when 3-4 signals align at once No signal = no trade. His wallet address: It’s not about being right more often. It’s about only playing when odds are clearly in your favor. That’s how you turn a bot from a toy into a machine.

Oracle Boar

40,432 views • 3 months ago

Anthropic engineer stops me in a hallway at a conference and points at my screen. "Are you the one running the Polymarket bot on Claude Code?" I say maybe. He looks back at the terminal. "This thing is live?" Yeah. He laughs. "We built Claude to write code. You people immediately turned it into a market animal." I ask what gave it away. "The layout," he says. "Official CLI on one side. Orderbook on the other. You’re not paper trading." He was right. I show him the stack. - official CLI. Rust. Scanning markets, placing orders, no UI tax. Claude Code on top of it. No giant infra. No team. Just prompts, a terminal, and a model that’s better at reading weird edge cases than most interns. "What’s the loop," he asks. "Short horizon only," I tell him. "Scan for contracts under 48h. Pull structure. Look for mispriced panic. Feed the market state to Claude. Let it decide if the crowd is overreacting or just early." "And execution?" "Three commands and the order is live." He nods. Profile bot: "That’s the part people miss. Everyone thinks the alpha is the model. The alpha is the model plus an execution path short enough that you don’t talk yourself out of the fill." A market flips while we’re standing there. +118. He sees it print. "Jesus." I keep going. "Most people use Claude Code to save time writing wrappers. Fine. But the real trick is that it reads messy market context better than brittle rule systems. News fragments. weird phrasing. half-broken incentives. Retail panic. You can feel the model noticing when the tape smells wrong." He smiles at that. "So what’s the cost." "$25 a month." He laughs again. "We spend more than that on lunch." Copytrade here: I show him the numbers. 214 trades. 74% win rate. +$9,437 in 19 days. He goes quiet for a second. "OpenAI people will say use Codex. Quant guys will say build a proper system. Old traders will say this isn’t robust." I shrug. "It placed the order." That’s when he gives me the line I kept. "Anthropic made Claude. GitHub did the rest." Then he taps the CLI window one more time. "Keep it ugly," he says. "The second you wrap this in a beautiful dashboard, someone upstairs will understand how little infrastructure the edge actually needed."
0:20

Anthropic engineer stops me in a hallway at a conference and points at my screen. "Are you the one running the Polymarket bot on Claude Code?" I say maybe. He looks back at the terminal. "This thing is live?" Yeah. He laughs. "We built Claude to write code. You people immediately turned it into a market animal." I ask what gave it away. "The layout," he says. "Official CLI on one side. Orderbook on the other. You’re not paper trading." He was right. I show him the stack. - official CLI. Rust. Scanning markets, placing orders, no UI tax. Claude Code on top of it. No giant infra. No team. Just prompts, a terminal, and a model that’s better at reading weird edge cases than most interns. "What’s the loop," he asks. "Short horizon only," I tell him. "Scan for contracts under 48h. Pull structure. Look for mispriced panic. Feed the market state to Claude. Let it decide if the crowd is overreacting or just early." "And execution?" "Three commands and the order is live." He nods. Profile bot: "That’s the part people miss. Everyone thinks the alpha is the model. The alpha is the model plus an execution path short enough that you don’t talk yourself out of the fill." A market flips while we’re standing there. +118. He sees it print. "Jesus." I keep going. "Most people use Claude Code to save time writing wrappers. Fine. But the real trick is that it reads messy market context better than brittle rule systems. News fragments. weird phrasing. half-broken incentives. Retail panic. You can feel the model noticing when the tape smells wrong." He smiles at that. "So what’s the cost." "$25 a month." He laughs again. "We spend more than that on lunch." Copytrade here: I show him the numbers. 214 trades. 74% win rate. +$9,437 in 19 days. He goes quiet for a second. "OpenAI people will say use Codex. Quant guys will say build a proper system. Old traders will say this isn’t robust." I shrug. "It placed the order." That’s when he gives me the line I kept. "Anthropic made Claude. GitHub did the rest." Then he taps the CLI window one more time. "Keep it ugly," he says. "The second you wrap this in a beautiful dashboard, someone upstairs will understand how little infrastructure the edge actually needed."

Lunar

19,355 views • 2 months ago

Polymarket just got mathematically robbed. Top 0.04% already took 70% of all the money ($3.7B) thanks to 4 formulas from this article below. Open the leaderboard and there he is. [0x8dxd]: $2,285,751 ALL-TIME profit. Joined Dec 2025. $41.2K biggest win. 31,570 predictions. Not luck. Not "feeling the market". This is a bot running strictly on Lunar’s formulas on autopilot: Formula 1 - Expected Value (When to Enter) Contract at 40¢, but your real probability assessment is 60% -> +20¢ edge per dollar. Claude calculates this in seconds. Formula 2 - Kelly Criterion (How Much to Bet) f = (p·b − q)/b* (Quarter Kelly - that's why he doesn't blow up and compounds without any emotion) Formula 3 - Bayesian Updating (How to Change Your Mind) P(H|E) = [P(E|H) × P(H)] / P(E) Instantly rebuilds probability on any news. Formula 4 - Log Returns (Real Profit Calculation) Regular arithmetic lies. Only log returns show the real picture. Scans 50+ markets at once, enters only 15-min BTC Up/Down with real edge (where [0x8dxd] prints +157%, +207%, +181%), sleeps the rest of the time. 87% of wallets are in the red. A few such bots take everything. And this guy didn't just write an article - he handed out the blueprint that's already working for [0x8dxd]. Don't want to code it yourself? Just copy this trader with You can runs exactly this system: the same 4 formulas + Claude + auto-copying top math. Add his wallet: 0x63ce342161250d705dc0b16df89036c8e5f9ba9a to [ and start track/copy him right now. 4 formulas from Wikipedia + Claude brain + Kreo execution = meta 2026. The math doesn't sleep. Your FOMO does. Save and use this.
0:24

Polymarket just got mathematically robbed. Top 0.04% already took 70% of all the money ($3.7B) thanks to 4 formulas from this article below. Open the leaderboard and there he is. [0x8dxd]: $2,285,751 ALL-TIME profit. Joined Dec 2025. $41.2K biggest win. 31,570 predictions. Not luck. Not "feeling the market". This is a bot running strictly on Lunar’s formulas on autopilot: Formula 1 - Expected Value (When to Enter) Contract at 40¢, but your real probability assessment is 60% -> +20¢ edge per dollar. Claude calculates this in seconds. Formula 2 - Kelly Criterion (How Much to Bet) f = (p·b − q)/b* (Quarter Kelly - that's why he doesn't blow up and compounds without any emotion) Formula 3 - Bayesian Updating (How to Change Your Mind) P(H|E) = [P(E|H) × P(H)] / P(E) Instantly rebuilds probability on any news. Formula 4 - Log Returns (Real Profit Calculation) Regular arithmetic lies. Only log returns show the real picture. Scans 50+ markets at once, enters only 15-min BTC Up/Down with real edge (where [0x8dxd] prints +157%, +207%, +181%), sleeps the rest of the time. 87% of wallets are in the red. A few such bots take everything. And this guy didn't just write an article - he handed out the blueprint that's already working for [0x8dxd]. Don't want to code it yourself? Just copy this trader with You can runs exactly this system: the same 4 formulas + Claude + auto-copying top math. Add his wallet: 0x63ce342161250d705dc0b16df89036c8e5f9ba9a to [ and start track/copy him right now. 4 formulas from Wikipedia + Claude brain + Kreo execution = meta 2026. The math doesn't sleep. Your FOMO does. Save and use this.

slash1s

20,164 views • 4 months ago

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.
1:16

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.

Blaze

93,219 views • 1 month 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

50,509 views • 3 months ago

THIS WALLET STACKED $230K ON BTC UP/DOWN BETS. THE BLUEPRINT TO AUTOMATE THE SAME EDGE WITH CLAUDE The wallet is $230K all-time, every position a Bitcoin or Ethereum Up or Down market It never guesses direction. It enters only when the math and the market disagree THE STRATEGY: BTC moves are not fully random. When the market enters a committed directional state, continuation is measurable. That is Markov persistence Entry signal: > Δ = p̂ − q ≥ ε Model probability minus market price. Enter only on a 5% gap or more Persistence filter: > p(j*,j*) ≥ 0.87 Only trade states with 0.87 persistence or higher. Below that, skip. This is what holds the win rate above 65% with zero directional guessing Payout: > r = (1 − q) / q At q = 0.647 that is +54.5% a win. At q = 0.441, +126.7%. Lower entry price, bigger asymmetry Sizing: > f* = p − (1−p)/b Kelly. At p = 0.87, b = 0.647, f* ≈ 0.71. Size to the edge, never to gut HOW TO BUILD IT WITH CLAUDE: What separates this from a static bot: Claude reads its own trade journal every night and rewrites its own thresholds 1. Take an open-source Polymarket bot repo as your base logic. Feed it to Claude and have it migrate to CLOB v2: py_clob_client_v2, Safe wallet support, fee-aware evaluation 2. Hard-code the filters. Enter only when Δ ≥ 0.05 and p(j*,j*) ≥ 0.87. Apply Kelly on every fill. 3. Run DRY_RUN first. Log every signal, entry price, Markov state, and simulated P/L. No real money until the numbers hold for days 4. The nightly loop. Claude reads the journal, finds which persistence states actually won, adjusts MIN_PROB and MIN_EDGE, ships tomorrow's rules. The agent is sharper after 50 to 100 trades THE SETUP: Claude Opus as the brain. An open-source repo as the starting logic. A Polygon wallet with $50 to $100. Telegram for the morning report Start at $1 to $2 per trade while it learns. Scale only when the dry runs and the live fills line up 17,000 trades compound a thin edge into six figures. The model finds the edge. The nightly loop keeps it sharp Bookmark before you point a bot at your first window
0:23

THIS WALLET STACKED $230K ON BTC UP/DOWN BETS. THE BLUEPRINT TO AUTOMATE THE SAME EDGE WITH CLAUDE The wallet is $230K all-time, every position a Bitcoin or Ethereum Up or Down market It never guesses direction. It enters only when the math and the market disagree THE STRATEGY: BTC moves are not fully random. When the market enters a committed directional state, continuation is measurable. That is Markov persistence Entry signal: > Δ = p̂ − q ≥ ε Model probability minus market price. Enter only on a 5% gap or more Persistence filter: > p(j*,j*) ≥ 0.87 Only trade states with 0.87 persistence or higher. Below that, skip. This is what holds the win rate above 65% with zero directional guessing Payout: > r = (1 − q) / q At q = 0.647 that is +54.5% a win. At q = 0.441, +126.7%. Lower entry price, bigger asymmetry Sizing: > f* = p − (1−p)/b Kelly. At p = 0.87, b = 0.647, f* ≈ 0.71. Size to the edge, never to gut HOW TO BUILD IT WITH CLAUDE: What separates this from a static bot: Claude reads its own trade journal every night and rewrites its own thresholds 1. Take an open-source Polymarket bot repo as your base logic. Feed it to Claude and have it migrate to CLOB v2: py_clob_client_v2, Safe wallet support, fee-aware evaluation 2. Hard-code the filters. Enter only when Δ ≥ 0.05 and p(j*,j*) ≥ 0.87. Apply Kelly on every fill. 3. Run DRY_RUN first. Log every signal, entry price, Markov state, and simulated P/L. No real money until the numbers hold for days 4. The nightly loop. Claude reads the journal, finds which persistence states actually won, adjusts MIN_PROB and MIN_EDGE, ships tomorrow's rules. The agent is sharper after 50 to 100 trades THE SETUP: Claude Opus as the brain. An open-source repo as the starting logic. A Polygon wallet with $50 to $100. Telegram for the morning report Start at $1 to $2 per trade while it learns. Scale only when the dry runs and the live fills line up 17,000 trades compound a thin edge into six figures. The model finds the edge. The nightly loop keeps it sharp Bookmark before you point a bot at your first window

Yarchi

22,966 views • 2 months ago

An ex-OpenAI engineer walked up to me at a meetup in SF I was showing my Polymarket terminal. He looked at the screen for ten seconds and said one sentence. "You're trading blind. The data is sitting in the open and you're writing prompts" I didn't understand. What data. He took my laptop. Opened one repository. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "At OpenAI models don't guess. They read. Connect Claude Code to this dataset and say - find every wallet with a win rate above 70% and more than 100 trades" I asked - why Claude and not GPT? He looked at me like I was an idiot. "Because Claude Code connects to the repo directly. It reads the entire codebase. It's not a chatbox. It's a runtime" That evening I connected it. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% close their position BEFORE resolution. Top wallets capture 86% of the move and cut losers at 12%. Everyone else - 58% of profit and hold losers to 41%. Same exact entries. The exits make it a completely different game. "Now connect the scanner" Three commands - the bot sees 500+ markets in real time. No API key. Read-only. Claude built the scoring in 20 minutes: Gap between price and model > 7 cents. Book depth > $500. Resolution in 4-48 hours. 93% of markets get killed instantly. Only the fat ones survive. "Now this is the important part" - he sent me an article where a guy built a full bot over a weekend from these same repos Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours of silence - thesis is dead. I copied the whole stack. VPS $5. Claude $20. Total $25 a month. No team. No office. No Bloomberg. 16 days. 187 trades. 71% win rate. $800 seed. +$8,700. I sent him my screen. He replied a day later. "You just replicated for $25 what cost us six months and 11 people" I said - thanks for the tip. "Delete this chat" Too late.
0:24

An ex-OpenAI engineer walked up to me at a meetup in SF I was showing my Polymarket terminal. He looked at the screen for ten seconds and said one sentence. "You're trading blind. The data is sitting in the open and you're writing prompts" I didn't understand. What data. He took my laptop. Opened one repository. 86 million trades. Every wallet. Every entry. Every exit. The entire Polymarket history since day one. "At OpenAI models don't guess. They read. Connect Claude Code to this dataset and say - find every wallet with a win rate above 70% and more than 100 trades" I asked - why Claude and not GPT? He looked at me like I was an idiot. "Because Claude Code connects to the repo directly. It reads the entire codebase. It's not a chatbox. It's a runtime" That evening I connected it. Claude pulled 47 wallets in 4 minutes. Average profit: $214K. Hold time: 7 hours. 91% close their position BEFORE resolution. Top wallets capture 86% of the move and cut losers at 12%. Everyone else - 58% of profit and hold losers to 41%. Same exact entries. The exits make it a completely different game. "Now connect the scanner" Three commands - the bot sees 500+ markets in real time. No API key. Read-only. Claude built the scoring in 20 minutes: Gap between price and model > 7 cents. Book depth > $500. Resolution in 4-48 hours. 93% of markets get killed instantly. Only the fat ones survive. "Now this is the important part" - he sent me an article where a guy built a full bot over a weekend from these same repos Copytrade here: Three exit triggers: Target 85% of expected move. Volume spike x3 - smart money leaving. 24 hours of silence - thesis is dead. I copied the whole stack. VPS $5. Claude $20. Total $25 a month. No team. No office. No Bloomberg. 16 days. 187 trades. 71% win rate. $800 seed. +$8,700. I sent him my screen. He replied a day later. "You just replicated for $25 what cost us six months and 11 people" I said - thanks for the tip. "Delete this chat" Too late.

Lunar

480,799 views • 3 months ago

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?
4:01

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?

Vikram M

58,688 views • 10 days ago

Raphael Townshend, Stanford AI PhD and founder of Atomic AI (Forbes 30 Under 30): ""Wall Street will pay you $500K a year to build these models. I'd rather teach them to you for free." this free stanford lecture holds the entire "77% win rate, pure math" random forest the 2026 quant threads sell you. and the guy teaching it didn't take the wall street money either, townshend went on to found an ai drug-discovery company and land forbes 30 under 30. at the board he builds it from scratch: one decision tree overfits, so you grow hundreds on random subsets of the data and features and average them. the errors cancel, the signal survives. that's the whole "100 ai agents auditing the market" idea, minus the marketing. the √N feature rule, the out-of-bag error, the probability output, all of it is standard ensemble learning, taught free by stanford for years. random forests came out of leo breiman's public paper in 2001. the thread didn't discover it. it renamed it. and here's the honest part the win rate hides. a model that scored 77% on past data is describing the past, not promising the future. ensembles cut variance, they don't turn a weak edge into a real one, and markets shift under the model in ways the training set never warned about. the lecture is free. knowing whether your 77% survives out of sample and on live capital is exactly the part the post skips."
1:20:22

Raphael Townshend, Stanford AI PhD and founder of Atomic AI (Forbes 30 Under 30): ""Wall Street will pay you $500K a year to build these models. I'd rather teach them to you for free." this free stanford lecture holds the entire "77% win rate, pure math" random forest the 2026 quant threads sell you. and the guy teaching it didn't take the wall street money either, townshend went on to found an ai drug-discovery company and land forbes 30 under 30. at the board he builds it from scratch: one decision tree overfits, so you grow hundreds on random subsets of the data and features and average them. the errors cancel, the signal survives. that's the whole "100 ai agents auditing the market" idea, minus the marketing. the √N feature rule, the out-of-bag error, the probability output, all of it is standard ensemble learning, taught free by stanford for years. random forests came out of leo breiman's public paper in 2001. the thread didn't discover it. it renamed it. and here's the honest part the win rate hides. a model that scored 77% on past data is describing the past, not promising the future. ensembles cut variance, they don't turn a weak edge into a real one, and markets shift under the model in ways the training set never warned about. the lecture is free. knowing whether your 77% survives out of sample and on live capital is exactly the part the post skips."

Rossst.03

201,268 views • 1 month ago