正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I BUILT A BOT THAT PREDICTS NBA GAMES BEFORE TIPOFF. IT RUNS EVERY DAY AT 5:00 PM. HERE'S WHAT'S INSIDE. Three data sources. Three probability layers. One automated pipeline. No manual input. Every evening the bot wakes up. Pulls today's NBA slate. Builds features from live data.Generates predictions. Sends... them to me before the first whistle. The ML layer: XGBoost on three seasons of data. Four Factors. ELO ratings. Net rating. Pace. Back-to-back fatigue. Rest days. Travel distance. Every stat computed only from data available before the game. No future leakage. Ever. The sportsbook layer: spread and moneyline converted into implied probabilities. The spread alone contains the aggregated intelligence of an entire betting market. The bot doesn't fight it. It absorbs it. The Polymarket layer: live crowd-sourced probabilities from a decentralized prediction market. No vig. Prices shift in seconds when a star sits out. The bot pulls them through the Gamma API in real time. Then all three layers talk to each other. All three agree - high confidence bet. Polymarket diverges from the books - someone knows something. My model diverges from both - either I found edge or I found noise. The bot flags every disagreement automatically. The fourth layer: Claude API reads everything. Injury reports. Schedule context. Matchup history. Generates a written explanation for every single prediction. No black box. Every call has reasoning attached. The stack: Python. nba_api. pandas. XGBoost. scikit-learn. SHAP. Polymarket Gamma API. Claude API. Flask. GitHub Actions. It took mass of work to build. It takes zero effort to run. 5:00 PM ET. Every day. Predictions land before tipoff. Trading here: I didn't build a model. I built a machine.show more

zostaff

15,028 subscribers

48,649 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

🚨 The future of sports betting is here - and it's on the blockchain > Sharp bettors are already leaving bookmakers for prediction markets. > 15-35% of handle is migrating within 18 months. > The reason - taxes, limits, 12% margin. > Polymarket: ~1% margin, no limits reaction in seconds. > But most people still use it like a regular sportsbook. > What if you compare Polymarket with a bookmaker and an ML model? > Three sources disagree - someone knows more. > That divergence is the edge. > Built a full pipeline: Python + Claude API + XGBoost + ELO.

🚨 The future of sports betting is here - and it's on the blockchain > Sharp bettors are already leaving bookmakers for prediction markets. > 15-35% of handle is migrating within 18 months. > The reason - taxes, limits, 12% margin. > Polymarket: ~1% margin, no limits reaction in seconds. > But most people still use it like a regular sportsbook. > What if you compare Polymarket with a bookmaker and an ML model? > Three sources disagree - someone knows more. > That divergence is the edge. > Built a full pipeline: Python + Claude API + XGBoost + ELO.

zostaff

34,030 次观看 • 4 个月前

I BUILT A BOT THAT PREDICTS FOOTBALL MORE ACCURATELY THAN BOOKMAKERS 3 probability sources. ML model + Bet365 odds + Polymarket. When all three diverge - that's edge 5 seasons of EPL, La Liga, Bundesliga. 7,600+ matches. Each with goals, shots, possession, corners, cards, odds ELO rating using the FIFA formula - accounts for opponent strength, goal difference, home advantage. Not just W/D/L but the context behind every win xG proxy from basic stats - shots on target * 30% conversion + shots off target * 3%. Teams scoring more than they should - regression is coming Rolling averages over 5 matches, fatigue factor, head-to-head history, day of the week Claude API analyzes context the model can't see - motivation, pressure, derbies XGBoost + Random Forest + Logistic Regression in an ensemble. Walk-forward backtest, not random split Bookmaker says 55% home. Polymarket says 48%. Model says 52%. KL-divergence between sources = signal. The bigger the gap + the fatter the edge All three agree - I skip, zero edge. Two against one - I enter on the majority side Kelly sizes the position, Claude explains why

I BUILT A BOT THAT PREDICTS FOOTBALL MORE ACCURATELY THAN BOOKMAKERS 3 probability sources. ML model + Bet365 odds + Polymarket. When all three diverge - that's edge 5 seasons of EPL, La Liga, Bundesliga. 7,600+ matches. Each with goals, shots, possession, corners, cards, odds ELO rating using the FIFA formula - accounts for opponent strength, goal difference, home advantage. Not just W/D/L but the context behind every win xG proxy from basic stats - shots on target * 30% conversion + shots off target * 3%. Teams scoring more than they should - regression is coming Rolling averages over 5 matches, fatigue factor, head-to-head history, day of the week Claude API analyzes context the model can't see - motivation, pressure, derbies XGBoost + Random Forest + Logistic Regression in an ensemble. Walk-forward backtest, not random split Bookmaker says 55% home. Polymarket says 48%. Model says 52%. KL-divergence between sources = signal. The bigger the gap + the fatter the edge All three agree - I skip, zero edge. Two against one - I enter on the majority side Kelly sizes the position, Claude explains why

zostaff

512,907 次观看 • 4 个月前

A guy running quant models for a tennis betting syndicate DM'd me last month. "We spend $40K/month on data feeds. What are you using?" A webcam pointed at a tennis stream. Not metaphorically.YOLO tracks both players and the ball 30fps. A second model maps the court to real meters. Every 5 seconds I get three numbers: aggression positioning, court coverage, rally intensity. Those feed into a Bayesian engine. Beta prior on serve probability, updated every game, 15,000 Monte Carlo sims sampling from the posterior. Not point estimates - distributions with confidence intervals. 62% +/- 3% is a trade. 62% +/- 18% is noise. Most people never compute the interval. "Okay but models are wrong" That's why the model is only layer two out of five Layer three connects Polymarket and a bookmaker simultaneously. When my model says 71%, Polymarket says 62%, bookmaker says 67% - something is mispriced. Layer four is the unfair one. Claude reads every press conference transcript, news article, and social post from the last 48 hours. Extracts structured signals - injury flags, form deltas, surface comfort. JSON, not vibes. A player mentioned shoulder tightness at a presser. Claude flagged injury probability 0.25. Bookmaker didn't adjust for 3 hours. Polymarket never did. I was already in Layer five compares all four sources and finds the edge. Value, arbitrage, fade, or intel override when Claude catches something critical. "What's your hit rate" 2,400 ATP matches backtested. Model alone: 61%. With market bridge: 67%. With Claude: 72% Live 11 weeks: 247 contracts, 178 winners, +$14,200 from $1,800 He went quiet then wrote "my syndicate is rethinking our entire pipeline. We've been doing this 6 years and never used CV on live streams" They spend $40K/month. My setup: a Claude subscription and an API key Bot:

A guy running quant models for a tennis betting syndicate DM'd me last month. "We spend $40K/month on data feeds. What are you using?" A webcam pointed at a tennis stream. Not metaphorically.YOLO tracks both players and the ball 30fps. A second model maps the court to real meters. Every 5 seconds I get three numbers: aggression positioning, court coverage, rally intensity. Those feed into a Bayesian engine. Beta prior on serve probability, updated every game, 15,000 Monte Carlo sims sampling from the posterior. Not point estimates - distributions with confidence intervals. 62% +/- 3% is a trade. 62% +/- 18% is noise. Most people never compute the interval. "Okay but models are wrong" That's why the model is only layer two out of five Layer three connects Polymarket and a bookmaker simultaneously. When my model says 71%, Polymarket says 62%, bookmaker says 67% - something is mispriced. Layer four is the unfair one. Claude reads every press conference transcript, news article, and social post from the last 48 hours. Extracts structured signals - injury flags, form deltas, surface comfort. JSON, not vibes. A player mentioned shoulder tightness at a presser. Claude flagged injury probability 0.25. Bookmaker didn't adjust for 3 hours. Polymarket never did. I was already in Layer five compares all four sources and finds the edge. Value, arbitrage, fade, or intel override when Claude catches something critical. "What's your hit rate" 2,400 ATP matches backtested. Model alone: 61%. With market bridge: 67%. With Claude: 72% Live 11 weeks: 247 contracts, 178 winners, +$14,200 from $1,800 He went quiet then wrote "my syndicate is rethinking our entire pipeline. We've been doing this 6 years and never used CV on live streams" They spend $40K/month. My setup: a Claude subscription and an API key Bot:

zostaff

55,452 次观看 • 3 个月前

9 repos that mass replace a $150,000/year NBA analytics department. all free. all open source. -> replaces Second Spectrum and SportVU YOLO tracks every player and ball from any broadcast. assigns teams by jersey color. court keypoint detection builds a tactical top-down map. speed, distance, passes - all from a TV feed. no sensors. -> replaces paid NBA prediction services ($100/mo) XGBoost + Neural Net. moneyline and totals. Kelly Criterion sizing. 69% accuracy. pulls odds from FanDuel/DraftKings automatically. the most starred NBA betting repo on GitHub. -> replaces an entire quant sports desk 5-model ensemble: XGBoost + PyTorch MLP + Ridge + Lasso + baseline. Optuna-tuned hyperparameters. SQLite database with box scores, play-by-play, betting lines, injury reports. production-grade. -> replaces manual daily prediction workflows XGBoost/LightGBM with GitHub Actions automation. scrapes new data, retrains models, outputs daily win probabilities. set it and forget it. -> replaces ELO subscription services custom ELO + Ridge + XGBoost + Neural Networks ensemble. full data scraping pipeline. comprehensive visualizations. FiveThirtyEight-style ratings from scratch. -> replaces Four Factors analytics dashboards ELO rating system + Four Factors + PCA dimensionality reduction. detailed comparison of 10+ models. honest 65.3% accuracy - because that's what real NBA prediction looks like. -> replaces computer vision analytics platforms ($500/mo) YOLO player/ball tracking. automatic team assignment. court keypoints. pass and interception detection. speed and distance. full tactical view. modular architecture. -> replaces shot tracking hardware YOLOv8 detects ball and hoop in real-time. linear regression predicts trajectory. registers makes and misses automatically. works on any video feed. -> replaces paid sports data subscriptions ($300/mo) official Python client for NBA. com API. box scores, play-by-play, shot charts, player tracking. 40+ years of data. zero cost. the foundation every NBA ML project is built on. like + bookmark you'll need this when you build your first NBA prediction bot

9 repos that mass replace a $150,000/year NBA analytics department. all free. all open source. -> replaces Second Spectrum and SportVU YOLO tracks every player and ball from any broadcast. assigns teams by jersey color. court keypoint detection builds a tactical top-down map. speed, distance, passes - all from a TV feed. no sensors. -> replaces paid NBA prediction services ($100/mo) XGBoost + Neural Net. moneyline and totals. Kelly Criterion sizing. 69% accuracy. pulls odds from FanDuel/DraftKings automatically. the most starred NBA betting repo on GitHub. -> replaces an entire quant sports desk 5-model ensemble: XGBoost + PyTorch MLP + Ridge + Lasso + baseline. Optuna-tuned hyperparameters. SQLite database with box scores, play-by-play, betting lines, injury reports. production-grade. -> replaces manual daily prediction workflows XGBoost/LightGBM with GitHub Actions automation. scrapes new data, retrains models, outputs daily win probabilities. set it and forget it. -> replaces ELO subscription services custom ELO + Ridge + XGBoost + Neural Networks ensemble. full data scraping pipeline. comprehensive visualizations. FiveThirtyEight-style ratings from scratch. -> replaces Four Factors analytics dashboards ELO rating system + Four Factors + PCA dimensionality reduction. detailed comparison of 10+ models. honest 65.3% accuracy - because that's what real NBA prediction looks like. -> replaces computer vision analytics platforms ($500/mo) YOLO player/ball tracking. automatic team assignment. court keypoints. pass and interception detection. speed and distance. full tactical view. modular architecture. -> replaces shot tracking hardware YOLOv8 detects ball and hoop in real-time. linear regression predicts trajectory. registers makes and misses automatically. works on any video feed. -> replaces paid sports data subscriptions ($300/mo) official Python client for NBA. com API. box scores, play-by-play, shot charts, player tracking. 40+ years of data. zero cost. the foundation every NBA ML project is built on. like + bookmark you'll need this when you build your first NBA prediction bot

zostaff

102,941 次观看 • 3 个月前

I BUILT A PLATFORM FOR SYSTEMATIC SENTIMENT TRADING Trading by Fear & Greed Index on prediction markets. In realtime it collects market data, VIX, Fear & Greed, sentiment - analyzes through ML model, evaluates risk, and only then makes a trade decision. Not before, not after, only when all layers confirm. Inside 6 layers: data ingestion, analytics engine, risk manager, execution engine, backtesting, dashboard. System receives data from Polymarket CLOB API, VIX, Fear & Greed and external sentiment sources, calculates market sensitivity, trains the model and outputs trade signals. Every trade goes through risk manager: position sizing, drawdown control, entry limits, slippage control. Nothing executes without permission. Execution through Polymarket API and Polygon, on top a dashboard - portfolio, P&L, active signals, strategy tuning in realtime. Sentiment trading goes to the next level

I BUILT A PLATFORM FOR SYSTEMATIC SENTIMENT TRADING Trading by Fear & Greed Index on prediction markets. In realtime it collects market data, VIX, Fear & Greed, sentiment - analyzes through ML model, evaluates risk, and only then makes a trade decision. Not before, not after, only when all layers confirm. Inside 6 layers: data ingestion, analytics engine, risk manager, execution engine, backtesting, dashboard. System receives data from Polymarket CLOB API, VIX, Fear & Greed and external sentiment sources, calculates market sensitivity, trains the model and outputs trade signals. Every trade goes through risk manager: position sizing, drawdown control, entry limits, slippage control. Nothing executes without permission. Execution through Polymarket API and Polygon, on top a dashboard - portfolio, P&L, active signals, strategy tuning in realtime. Sentiment trading goes to the next level

zostaff

44,661 次观看 • 4 个月前

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.

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 次观看 • 4 个月前

Another quiet Polymarket account just quietly turned $62 into $721,000. Almost nobody is talking about it. The trader’s profile is Careful. I reverse-engineered his exact strategy and asked Claude to build an identical bot using the same edge. One solid prompt + 50 minutes later and it was live. The opportunity is straightforward: Polymarket updates BTC contract prices slower than real market feeds. -> The bot pulls live BTC predictions from TradingView + CryptoQuant -> It instantly spots when Polymarket lags by more than 0.3% -> Executes in under 100 ms before the market corrects -> Handles 1,000+ orders per second and captures 0.3–0.8% per trade Risk is tightly controlled: 0.5% per trade with a strict 2% daily cap. It prints a clean $400–700 every single day. Runs 100% locally - no cloud, no GPU required. Written in Rust for maximum speed. Also john f pitha shows full stats for every trader - so you know exactly who you're following. Data first. Action second. Profile and copy-trading him: Save him.

slash1s

153,938 次观看 • 4 个月前

$1,840 OVERNIGHT. NOTIFICATION AT 2:00 AM FROM OPENCLAW: " FOUND 1M MARKET ON BTC " He found them literally the moment they launched And gave Codex the command to rebuild the architecture from 5m to 1m I woke up at 8:00, opened Telegram - 47 trades, +$1,840 The bot was a scalper, now it's HFT. Built the entire architecture in Rust because Python simply doesn't survive on 60-second cycles. The race for milliseconds began. Claude added a momentum filter: if the last 10s the price accelerates in one direction - the bot enters. In one minute the trend doesn't have time to reverse On the 5m market 18 trades per day, on 1m - 210. Same edge, 10x more often. Three agents found a market, turned a scalper into HFT, and made $1,840. i found a new market here: I'm starting to think it has a mind of its own. What did I create?

$1,840 OVERNIGHT. NOTIFICATION AT 2:00 AM FROM OPENCLAW: " FOUND 1M MARKET ON BTC " He found them literally the moment they launched And gave Codex the command to rebuild the architecture from 5m to 1m I woke up at 8:00, opened Telegram - 47 trades, +$1,840 The bot was a scalper, now it's HFT. Built the entire architecture in Rust because Python simply doesn't survive on 60-second cycles. The race for milliseconds began. Claude added a momentum filter: if the last 10s the price accelerates in one direction - the bot enters. In one minute the trend doesn't have time to reverse On the 5m market 18 trades per day, on 1m - 210. Same edge, 10x more often. Three agents found a market, turned a scalper into HFT, and made $1,840. i found a new market here: I'm starting to think it has a mind of its own. What did I create?

zostaff

26,746 次观看 • 4 个月前

How MiroFish helped me make $669/day on Polymarket One week ago I plugged a swarm intelligence engine into my Polymarket bot. It simulates 2,847 digital humans before every trade. The bot watches how they behave, then bets against the real crowd. 338 trades. $4,266 profit. One position returned 1,655% in five minutes. The engine is called MiroFish. It doesn't predict price. It predicts how people will react and on a prediction market, that's the only thing that matters. I feed it market context. It builds a parallel world. Thousands of AI agents argue, form groups, shift opinions. When their consensus diverges from what Polymarket is pricing, the bot enters. 5-minute windows. BTC, ETH, SOL, XRP. I've been running the bot live on What MiroFish actually is: > Built in 10 days by a 20-year-old undergraduate in Beijing using vibe coding > Hit #1 on GitHub's global trending above OpenAI, Google, and Microsoft > Backed by Chen Tianqiao, former richest man in China, who committed $4.1M within 24 hours of seeing one demo > Runs on OASIS by CAMEL-AI with GraphRAG knowledge graphs and Zep Cloud memory The edge is simple. Polymarket is a crowd behavior market. MiroFish is a crowd behavior simulator. Nobody is connecting the two yet.

How MiroFish helped me make $669/day on Polymarket One week ago I plugged a swarm intelligence engine into my Polymarket bot. It simulates 2,847 digital humans before every trade. The bot watches how they behave, then bets against the real crowd. 338 trades. $4,266 profit. One position returned 1,655% in five minutes. The engine is called MiroFish. It doesn't predict price. It predicts how people will react and on a prediction market, that's the only thing that matters. I feed it market context. It builds a parallel world. Thousands of AI agents argue, form groups, shift opinions. When their consensus diverges from what Polymarket is pricing, the bot enters. 5-minute windows. BTC, ETH, SOL, XRP. I've been running the bot live on What MiroFish actually is: > Built in 10 days by a 20-year-old undergraduate in Beijing using vibe coding > Hit #1 on GitHub's global trending above OpenAI, Google, and Microsoft > Backed by Chen Tianqiao, former richest man in China, who committed $4.1M within 24 hours of seeing one demo > Runs on OASIS by CAMEL-AI with GraphRAG knowledge graphs and Zep Cloud memory The edge is simple. Polymarket is a crowd behavior market. MiroFish is a crowd behavior simulator. Nobody is connecting the two yet.

BuBBliK

124,905 次观看 • 5 个月前

A Google DeepMind researcher cornered me at a bar in Hayes Valley I was showing my Polymarket PNL to a friend. She leaned over. Didn't introduce herself. "That's not a trading app. Show me your stack" I told her. Claude Code. Four repos. $25 a month. She set down her drink. "We tested this internally. You connect Claude directly to a dataset. It builds its own detectors. But nobody ships it because compliance kills everything" I asked what she meant. She took my phone. Opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You don't tell Claude what to look for. It finds the wallets that win. Then it finds WHY they win. Then it copies the pattern" Her team spent 9 months building this for a hedge fund. 14 people. $2M budget. "The part that took us the longest - exit logic. Everyone thinks entries matter. They don't. Exits are the entire game" I told her my bot cuts at 85% of expected move or on a 3x volume spike. She went quiet. "Who taught you that" Claude Code found it in poly_data. Top wallets exit before resolution 91% of the time. They capture the move and leave. She opened another link. "This is the scanner. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes" "That's our exact infra. Except it took us 9 months and you did it in a weekend" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. Copytrade here: I showed her the article where I broke down every repo, every command, every dollar. She read it for five minutes. Then: "You just open-sourced our entire pipeline" She texted me the next day. "My team lead saw your thread. Take it down" Too late.

A Google DeepMind researcher cornered me at a bar in Hayes Valley I was showing my Polymarket PNL to a friend. She leaned over. Didn't introduce herself. "That's not a trading app. Show me your stack" I told her. Claude Code. Four repos. $25 a month. She set down her drink. "We tested this internally. You connect Claude directly to a dataset. It builds its own detectors. But nobody ships it because compliance kills everything" I asked what she meant. She took my phone. Opened one link. 86 million trades. Every wallet. Every entry. Every exit. "You don't tell Claude what to look for. It finds the wallets that win. Then it finds WHY they win. Then it copies the pattern" Her team spent 9 months building this for a hedge fund. 14 people. $2M budget. "The part that took us the longest - exit logic. Everyone thinks entries matter. They don't. Exits are the entire game" I told her my bot cuts at 85% of expected move or on a 3x volume spike. She went quiet. "Who taught you that" Claude Code found it in poly_data. Top wallets exit before resolution 91% of the time. They capture the move and leave. She opened another link. "This is the scanner. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes" "That's our exact infra. Except it took us 9 months and you did it in a weekend" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. Copytrade here: I showed her the article where I broke down every repo, every command, every dollar. She read it for five minutes. Then: "You just open-sourced our entire pipeline" She texted me the next day. "My team lead saw your thread. Take it down" Too late.

Lunar

124,367 次观看 • 4 个月前

Someone trained a swarm model on 3 years of NBA data and let it loose on Polymarket The result: $1.49M. He didn't build a better model. He built a better crowd. Here's how the system actually works. He takes MiroFish - an open-source engine that simulates thousands of AI agents and feeds it raw sports data. The actual building blocks: > Player stat vectors: points, rebounds, assists, eFG%, usage rate across 3 full seasons > Team form tensors: last 10 games, home/away splits, pace-of-play, defensive rating > Matchup history: head-to-head records, positional mismatches, referee tendencies > Injury probability models: medical staff reports weighted by recovery timelines > Line movement tracking: where the sharp money flows before tip-off Check how this wallet works: MiroFish generates 4,096 agents - analysts, bettors, insiders, oddsmakers - each with different reasoning. They argue, form clusters, shift opinions. Consensus emerges. He pipes that consensus into a 12-layer transformer trained on the full history of his 16,695 predictions. The model compares MiroFish output against live Polymarket odds. When the gap exceeds his Kelly criterion threshold, it enters. Lakers at 40 cents. MiroFish said 62%. One position: $190,823. The edge isn't data. Every sharp has data. The edge is simulating how 4,000 fake humans process it - before the real crowd does.

Someone trained a swarm model on 3 years of NBA data and let it loose on Polymarket The result: $1.49M. He didn't build a better model. He built a better crowd. Here's how the system actually works. He takes MiroFish - an open-source engine that simulates thousands of AI agents and feeds it raw sports data. The actual building blocks: > Player stat vectors: points, rebounds, assists, eFG%, usage rate across 3 full seasons > Team form tensors: last 10 games, home/away splits, pace-of-play, defensive rating > Matchup history: head-to-head records, positional mismatches, referee tendencies > Injury probability models: medical staff reports weighted by recovery timelines > Line movement tracking: where the sharp money flows before tip-off Check how this wallet works: MiroFish generates 4,096 agents - analysts, bettors, insiders, oddsmakers - each with different reasoning. They argue, form clusters, shift opinions. Consensus emerges. He pipes that consensus into a 12-layer transformer trained on the full history of his 16,695 predictions. The model compares MiroFish output against live Polymarket odds. When the gap exceeds his Kelly criterion threshold, it enters. Lakers at 40 cents. MiroFish said 62%. One position: $190,823. The edge isn't data. Every sharp has data. The edge is simulating how 4,000 fake humans process it - before the real crowd does.

BuBBliK

504,526 次观看 • 5 个月前

CLAUDE + CODEX + OPENCLAW MADE $2,8K IN A DAY Launched it in the morning - docker compose up, three agents started. By lunch there were 4 trades on Polymarket, by evening 7, and by midnight I was up $2,8K. My monthly salary at work is $2,4K. The next day I didn't show up to work, but the bot did +$3,1K. Third day, same story +$1,9K. A Telegram notification dropped in: "New market, edge 0.41, Confidence 0.87, going in" I was eating a shawarma at the time. In one week, three AI agents earned more than my office pays in two months. OpenClaw coordinated everything, Claude calculated the probabilities, and Codex fixed a module on its own when it crashed at 3:00 AM - without me. On Friday the bot sent a weekly report: 19 trades, 14 profitable, +$11,300. My boss sent quarterly feedback: "Good work, but no promotion planned for now" I don't need a promotion anymore. I need Wi-Fi.

CLAUDE + CODEX + OPENCLAW MADE $2,8K IN A DAY Launched it in the morning - docker compose up, three agents started. By lunch there were 4 trades on Polymarket, by evening 7, and by midnight I was up $2,8K. My monthly salary at work is $2,4K. The next day I didn't show up to work, but the bot did +$3,1K. Third day, same story +$1,9K. A Telegram notification dropped in: "New market, edge 0.41, Confidence 0.87, going in" I was eating a shawarma at the time. In one week, three AI agents earned more than my office pays in two months. OpenClaw coordinated everything, Claude calculated the probabilities, and Codex fixed a module on its own when it crashed at 3:00 AM - without me. On Friday the bot sent a weekly report: 19 trades, 14 profitable, +$11,300. My boss sent quarterly feedback: "Good work, but no promotion planned for now" I don't need a promotion anymore. I need Wi-Fi.

zostaff

148,425 次观看 • 5 个月前

Using Claude Fable 5, I built a model that predicts the entire 2026 FIFA world cup.. every single game, not just the final.. so let me break the whole thing down. what it does, how it works, and exactly how i built it.. #1 First what it does: it predicts all 104 games of the tournament. not just who lifts the trophy, but every group match, every knockout, the full path from the round of 32 to the final.. everything lands in one dashboard: > group stage, every match with each team's win % and the chance of a draw > standings, how all 12 groups are projected to finish > bracket, the full knockout tree with each team's odds of advancing > champion odds, who's most likely to actually win it all and it doesn't freeze after one prediction. the moment a real game is played, it locks that result in and re-runs everything around it. so the odds move live as the tournament goes, week by week you watch favorites rise and contenders collapse. #2. How it works: the core idea is simple. the model only ever predicts one thing, a single match. the real trick is the repetition. it learns from decades of match history, then plays the whole tournament out from the first game to the final, tens of thousands of times. each run it records who advanced and who won. do that enough and you stop getting one guess and start getting real odds, one team lifts the trophy in maybe 14% of the runs, another in 9%, and so on. #3. So, how i built it ? i didn't hand-write most of the code. i broke the project into 4 pieces, described each one to fable, and let it build while i focused on getting the football logic exactly right. - The data every international match going back over a century, around 50,000 games, plus each team's elo rating, which is the truest measure of strength, and the official 2026 schedule. garbage data means garbage predictions, so this part mattered most. - The features i turned that raw history into signals the model can learn from, the elo gap between the two teams, recent form, goals scored and conceded, and a home boost for the hosts, usa, canada and mexico. - The model for each match it predicts the expected goals for both sides, then turns that into win, draw and loss probabilities plus a likely scoreline. that's what feeds the simulation. - The tournament engine this was the hard part. the 2026 world cup is brand new, 48 teams, 12 groups, a round of 32 that's never existed before, and 8 "best third-placed" teams that slot into the bracket by a fixed fifa table. even the group tiebreakers changed this year, head to head now counts before goal difference. get any of it wrong and the whole bracket falls apart, so i built it carefully and tested the format until it was exact, then wrapped it in a simulation loop that plays the tournament out tens of thousands of times. and the last piece, the live part. as real results come in, they get locked, and only the unplayed games get re-simulated. that's what makes it a living model instead of a one-time prediction. all of it outputs to a clean dashboard you can actually read and screenshot.. right now, before kickoff, it already has a clear favorite to lift the trophy.. 👀 btw who's your pick to win the 2026 world cup?

Axel Bitblaze 🪓

63,666 次观看 • 2 个月前

i build a polymarket trading bot. took an old abandoned repo, rewrote 90% of it. name: zostaff repo: mit. python 3.12+. py-clob-client with eip-712 signed orders. usdc.e on polygon. three strategies in the box: AI Directional (llm via openrouter, any model), Safe Compounder (pure edge math, no llm), Beast Mode (aggressive, kept for comparison). most "ai bots" for polymarket on github are abandoned templates with hardcoded losing strategies. this one ships with a streamlit dashboard, sqlite telemetry on every trade, fallback chain across llm models, circuit breaker at 15% drawdown, quarter-kelly default, paper trading mode by default - until you flip LIVE_TRADING_ENABLED=true, nothing goes live. the readme has a section called "Lessons From Live Trading". real numbers from real losses: three-quarter kelly destroys capital on a 45% win-rate strategy. category discipline beats ai confidence every single time. a 50% drawdown limit isn't a limit. more trades without edge = faster path to zero. this is not a turnkey bot. nobody on polymarket is selling a turnkey bot that works. it's a toolkit with three example strategies you fork to fit your own edge. if you don't have an edge - no llm will save you. if you do - run paper mode for a week before flipping live.

i build a polymarket trading bot. took an old abandoned repo, rewrote 90% of it. name: zostaff repo: mit. python 3.12+. py-clob-client with eip-712 signed orders. usdc.e on polygon. three strategies in the box: AI Directional (llm via openrouter, any model), Safe Compounder (pure edge math, no llm), Beast Mode (aggressive, kept for comparison). most "ai bots" for polymarket on github are abandoned templates with hardcoded losing strategies. this one ships with a streamlit dashboard, sqlite telemetry on every trade, fallback chain across llm models, circuit breaker at 15% drawdown, quarter-kelly default, paper trading mode by default - until you flip LIVE_TRADING_ENABLED=true, nothing goes live. the readme has a section called "Lessons From Live Trading". real numbers from real losses: three-quarter kelly destroys capital on a 45% win-rate strategy. category discipline beats ai confidence every single time. a 50% drawdown limit isn't a limit. more trades without edge = faster path to zero. this is not a turnkey bot. nobody on polymarket is selling a turnkey bot that works. it's a toolkit with three example strategies you fork to fit your own edge. if you don't have an edge - no llm will save you. if you do - run paper mode for a week before flipping live.

zostaff

28,174 次观看 • 3 个月前

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff

230,734 次观看 • 3 个月前

I gave Claude Fable 5 just $100 to test the simplest arbitrage. Left my laptop opened for 24 hours. Session PnL: clean $1,571.66 On Polymarket, YES + NO Aren't there thousands of arbitrage bots already? Absolutely. You're not competing against people. You're competing against infrastructure. The biggest improvement wasn't a new strategy. It was rebuilding the entire execution pipeline. The bot runs on a VPS close to the APIs it talks to instead of my local machine. It keeps persistent connections open instead of reconnecting every request. Market metadata is cached in memory so it only refreshes live prices. Orders are prepared before the opportunity exists. When YES + NO finally drops below $1, there's almost nothing left to calculate. It checks liquidity, order book and submits both legs immediately. Will that beat firms spending millions on low-latency infrastructure? Probably not. It doesn't have to. There are hundreds of active prediction markets, constant volatility and plenty of opportunities that last long enough for a well-engineered bot to compete. That's probably the biggest thing Claude Fable 5 changed for me. I stopped asking it to build me a trading bot and started asking where am I wasting milliseconds. That single shift made the bot noticeably more competitive than any new trading strategy I could have invented. Arbitrage is the king. Irt lives everywhere. The only question is are you ready to study it. Leaving a full build + latency tips guide below this post.

I gave Claude Fable 5 just $100 to test the simplest arbitrage. Left my laptop opened for 24 hours. Session PnL: clean $1,571.66 On Polymarket, YES + NO Aren't there thousands of arbitrage bots already? Absolutely. You're not competing against people. You're competing against infrastructure. The biggest improvement wasn't a new strategy. It was rebuilding the entire execution pipeline. The bot runs on a VPS close to the APIs it talks to instead of my local machine. It keeps persistent connections open instead of reconnecting every request. Market metadata is cached in memory so it only refreshes live prices. Orders are prepared before the opportunity exists. When YES + NO finally drops below $1, there's almost nothing left to calculate. It checks liquidity, order book and submits both legs immediately. Will that beat firms spending millions on low-latency infrastructure? Probably not. It doesn't have to. There are hundreds of active prediction markets, constant volatility and plenty of opportunities that last long enough for a well-engineered bot to compete. That's probably the biggest thing Claude Fable 5 changed for me. I stopped asking it to build me a trading bot and started asking where am I wasting milliseconds. That single shift made the bot noticeably more competitive than any new trading strategy I could have invented. Arbitrage is the king. Irt lives everywhere. The only question is are you ready to study it. Leaving a full build + latency tips guide below this post.

Oracle Boar

18,091 次观看 • 26 天前

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.

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

1,739,699 次观看 • 4 个月前

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

718,301 次观看 • 5 个月前

one npm package replaced the entire stack of paid crypto data APIs. 42,100 stars. javascript + python + php + c# + go. one interface to 108 exchanges. ohlcv, orderbooks, order execution - all through the same methods. cryptocompare api: $79-499/mo. coingecko pro: $129-499/mo. coinapi: $79-7,499/mo. all of them resell you data you can pull directly from the exchanges for free. ccxt just did it. for you. for every exchange at once. under MIT. every second open-source crypto bot in this list is built on top of ccxt. including freqtrade. including half of polymarket bots through web3 wrappers. if you're paying for crypto data - you're paying because someone read the exchange docs before you did.

one npm package replaced the entire stack of paid crypto data APIs. 42,100 stars. javascript + python + php + c# + go. one interface to 108 exchanges. ohlcv, orderbooks, order execution - all through the same methods. cryptocompare api: $79-499/mo. coingecko pro: $129-499/mo. coinapi: $79-7,499/mo. all of them resell you data you can pull directly from the exchanges for free. ccxt just did it. for you. for every exchange at once. under MIT. every second open-source crypto bot in this list is built on top of ccxt. including freqtrade. including half of polymarket bots through web3 wrappers. if you're paying for crypto data - you're paying because someone read the exchange docs before you did.

zostaff

21,681 次观看 • 3 个月前

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.

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

480,969 次观看 • 4 个月前