AdiiX
@adiix_official • 28,659 subscribers
23 | navigating the AI era | learning, building, sharing
Shorts
Videos
Claude 5.0 built a Chinese girl a trading bot. skip to 0:08 look at her journal, bot easily earns your monthly salary in a couple of days. how it works: the bot runs mean reversion on s&p 500 and nasdaq on 15-min candles, catching the small overextensions indices make every few hours. on bitcoin it switches to momentum breakouts on the 1-hour crypto trends harder than indices, so you ride the move instead of fading it. gold and oil get a slower trend-following layer on the 4-hour, because commodities move in cleaner waves and you don't want noise from intraday whipsaws. position sizing is ATR-based per instrument, so a quiet day on gold gets a bigger size than a volatile day on bitcoin - risk stays constant even when volatility doesn't. every trade has a hard 1% stop, no exceptions, no "let me give it room." and there's a correlation filter on top: if s&p and nasdaq are already long, it won't pile into another risk-on asset and double the real exposure. claude code writes and updates the logic. the bot just executes. then claude cowork sends her two messages a day: - 7am: what's happening in the market - 9pm: how did the bot do that's the whole job. two messages. five instruments. zero screen time. manually she could only watch one chart at a time. this thing watches five. doesn't sleep. doesn't tilt. doesn't revenge trade at 2am. what used to need a team of quants and a $200k bloomberg terminal now runs on a laptop and claude. And your friend is still trading manually and is constantly in the red. save this and read the article in the comments below to write your own bot using Claude
AdiiX7,980,687 Aufrufe • vor 2 Monaten
SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. Open source. Built on PlayCanvas. Free GitHub:
AdiiX9,739,807 Aufrufe • vor 4 Monaten
AMD CEO Lisa Su just killed Nvidia’s $4,000 AI box with a $1,499 lunchbox. She walked on stage, held it in one hand, and ran a 235 billion parameter model live. No data center. No cloud. No rented GPU. The chip inside is something nobody saw coming. AMD’s Ryzen AI Max+ 395 is the first x86 silicon where CPU and GPU share the same 128GB of memory. That single trick lets a desktop run models that used to need a server rack. Out of those 128GB, Linux hands the GPU 110GB to play with. For context, an RTX 5090 gives you 32GB. A 4090 gives you 24. This box gives you more than three times either of them, in a chassis the size of a thick paperback. The benchmark that broke the room: this chip beat an Nvidia RTX 5080 by more than 3x on DeepSeek R1 inference. A $1,499 lunchbox outrunning a $1,000 discrete graphics card on a real AI workload. Nvidia spent a decade convincing the world you needed their hardware for serious AI. AMD just put that on a desk for half the price. Here is what nobody is telling you. A heavy AI user right now pays $200 for Claude Code Max, $200 for ChatGPT Pro, $20 for Cursor, $20 for Gemini. That is $5,280 a year leaving your account. The box pays itself off in 9 months and then runs free for the rest of its life. Install Ollama. Pull Qwen3 235B. Point Claude Code at localhost. Same interface you already use, except now nothing leaves your machine, nothing costs per request, and no company throttles your usage at 3am when you finally have time to build. This is the moment every AI subscription becomes optional. Lawyers stop fearing OpenAI leaks. Developers stop watching the token meter. Founders stop renting H100s for prototypes that never ship because the bill scared them. The first thousand people to figure this out will own the next two years of private AI consulting. Save this, and read the full breakdown article below you are watching the next shift hit before everyone else does.
AdiiX3,395,359 Aufrufe • vor 2 Monaten
watched a 20-year-old kid casually explain how he makes $10k/month while sleeping and i’m convinced 99% of people are missing this the entire setup: pick a YouTube channel that posts often. drop the link into one tool. plug in your TikTok, Instagram, YouTube Shorts. close the laptop. from that point on, AI does everything catches every new upload, slices the viral moments, captions them, blasts them across every platform. > 1M views ≈ $2,000 >zero editing, zero posting, zero stress > 10 min to set up, runs on autopilot forever you’re not making content. you’re owning a content factory. the full step-by-step is in the article below exact tools, exact stack, exact playbook Save it
AdiiX2,730,034 Aufrufe • vor 3 Monaten
Claude Will Pay $7K/Mon to Learn Al (How to Apply) Save this before Claude shuts the program down
AdiiX1,255,958 Aufrufe • vor 2 Monaten
Elon Musk’s Grok Bot turned my laptop into a mini Citadel and it has already made me over $1,600 on a live trading account. The first session made $74. A few sessions later, the total crossed $1,600. Meanwhile the research floor has produced: > 1,703 research tasks > 356 verified findings > 73 filings processed > $1,513 in research value No analyst team. No overnight staff. No 12 people waiting for instructions. Just 12 AI agents with actual jobs: > one reads filings, > one verifies the numbers, > one runs screens, > one attacks the thesis, > one watches risk, > one works overnight, and one decides what is important enough to reach me. They hand work to each other and keep going when I close the laptop. The market is closed right now. GROKSTREET is still working. Wall Street has spent decades turning information into expensive headcount. Elon just gave the rest of us agents. Full build below
AdiiX194,413 Aufrufe • vor 11 Tagen
Claude Code + Obsidian = $100,000/Month How to Build Your Own Autonomous AI Agent (Step-by-Step Guide) Bookmark this and Watch
AdiiX1,050,391 Aufrufe • vor 2 Monaten
CHINESE TRADER WHO BASICALLY TURNED POLYMARKET INTO A MONEY PRINTING MACHINE His results are truly incredible: starting with just $5 in capital, he ran it up to as much as $6.5 million. He’s not some insider shill. He doesn’t know Trump or Musk. Just a coder who wrote a single script. I reverse-engineered his script and took a look - I was blown away. > No massive database. > No ridiculously complex infrastructure. > And definitely not some “rocket science” black tech. His Profile: Copytrading in one click: I spent 5 hours breaking down his strategy. Here’s the core of it: 1. The bot specifically hunts for outcomes that are almost impossible to happen and relentlessly stacks high-probability, tiny profits. This isn’t really gambling it’s more like systematically selling insurance (harvesting risk premiums). 2. Arbitraging logical gaps If event A happens, it logically implies event B but the market hasn’t repriced yet. The bot jumps in instantly and opens a position. While you’re still reading the headline, it’s already capturing the spread. Human speed just can’t compete. 3. The real money tree sports and political markets These markets are flooded with retail money, delayed reactions, and emotional trades. The bot lives off the bid-ask spread, relentlessly extracting value from pricing mistakes. Scale is what makes it king. Tens of thousands of micro-trades per month, each earning just a few cents. But over time, with compounding, it snowballs into straight-up seven-figure profits.
AdiiX1,752,862 Aufrufe • vor 4 Monaten
this Chinese trader started with just $4… and reportedly grew it to $780,000 using AI on Polymarket. this trader on Polymarket with a bot on Claude Opus 4.7 arbitrages sports markets and has already earned $780,000 His profile 0xD9E0: How it’s work: > Fully automated system with no manual intervention. > Analyzes sports prediction markets (especially NBA on Polymarket). > Compares Polymarket prices with traditional sportsbook odds. > Converts odds into implied probabilities and detects mispricings. > Uses arbitrage by buying YES and NO when combined price is under $1. > Generates small but near-risk-free profits (around 1–2%) at high trading volume. AI bots are quietly turning prediction markets into a kind of “money printer.” They find tiny pricing mistakes and exploit them with low-risk, fast arbitrage trades. Each profit is small, but when scaled and repeated at high volume, those small edges can grow into large, even six-figure gains over time. copy him with me using the best tool:
AdiiX1,642,911 Aufrufe • vor 4 Monaten
me seeing a Claude bot that made $2.4M and someone dropped a full guide my life after reading:
AdiiX1,867,693 Aufrufe • vor 5 Monaten
HE DELETED IT IN 3 HOURS. Someone saved it. 11 minutes. Full system. Every trade. Bookmark before it’s gone again.
AdiiX1,599,293 Aufrufe • vor 4 Monaten
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.
AdiiX1,765,736 Aufrufe • vor 5 Monaten
![Elon Musk shipped Grok Bot as an AI teammate that sorts your email and watches your competitors. I gave mine a harder brief: build a trading floor that runs itself, and then run it 24/7. GROKSTREET. Fourteen agents. Eleven desks, three chiefs, three offices, one vault. It lives in a browser tab and it does not stop. WHY GROK BOT MAKES THIS WORK Most people misread the architecture. It is not one sandbox per agent. It is ONE persistent cloud computer per account, and every Bot gets its own screen on it. Shared filesystem at /workspace, shared browser sessions, shared credentials. That is the whole unlock. One Bot picks up exactly where another left off. No re-auth, no copy-paste between agents, no state lost at the handoff. A floor is only possible because the desks share a building. The head-of-desk role is not something I invented either. "Manages your other Bots and pulls you in for decisions" ships as a first-class Bot template. Routing and escalation are built in. Skills carry the how. Routines carry the when on a schedule, or off a Slack or GitHub event. Subagents fan out as child sessions with their own context and hand a summary back. Fifty routines per Bot. THE DESKS Every desk holds its own book, hit rate and drawdown, and sizes its own risk: Kelly, with the guard rails written in f* = W − (1−W)/R clamped to [0.01, 0.25]. Under 12 samples it does not pretend to know it defaults to 0.05. Volatility is RiskMetrics EWMA σ²_t = λσ²_{t-1} + (1−λ)r²_t, λ = 0.94 Hit rates carry Wilson 95% intervals, z = 1.96. A desk is only flagged for edge decay when the UPPER bound falls below 0.5, never on raw small-sample noise. Three-for-three is not sixty-for-ninety. Capital routes between desks by softmax on measured Sharpe. THE FLOOR Three chiefs meet in the war room every 3.5 minutes and argue. One reports, another presses him, he concedes or proposes. 14,208 sentence shapes before live figures fill the slots and every slot is filled from that chief's own desks. The crypto chief cannot quote meme numbers. A desk holding $25 gets up, walks to the vault and banks it. The transfer is atomic on arrival, so an interrupted walk cannot destroy cash. Every desk wears its last trade above its head. Green with a tick, red with a cross. You see who the chief is about to praise and who he is about to hit before he gets there. BTC, ETH and SOL come off Kraken server-side. The tape is real. THE BUILD 16 modules. 7,572 lines. Zero npm dependencies. No React. No bundler. No game engine. Vanilla JavaScript on Canvas 2D and a Go binary with the entire world embedded in it. Ships as one 2.3 MB HTML file. 60fps on every floor, zero dropped frames. WHAT I FOUND BY MEASURING INSTEAD OF LOOKING The roster read one number for a desk and the chief's card read another, so a desk could show +$16 in the list and $0 when the chief walked over. Every desk was crediting itself twice. Money could vanish if a walk to the vault got interrupted. Three money bugs, none of them visible by watching. All fixed and instrumented. DIRECTOR MODE Open it with?show and the camera runs itself. It cuts to the war room while a chief is mid-sentence, to whichever office just cleared money, and never cuts away in the middle of a line. Point a screen recorder at it and walk away. The math is real, the feed is real, the engineering is real. The flex is the engine, not a P&L screenshot.](https://image.24vids.com/tw-2093903463016960319/amplify_video_thumb/2093903393936777216/img/XPrch7twzg24mIkz.jpg)
Elon Musk shipped Grok Bot as an AI teammate that sorts your email and watches your competitors. I gave mine a harder brief: build a trading floor that runs itself, and then run it 24/7. GROKSTREET. Fourteen agents. Eleven desks, three chiefs, three offices, one vault. It lives in a browser tab and it does not stop. WHY GROK BOT MAKES THIS WORK Most people misread the architecture. It is not one sandbox per agent. It is ONE persistent cloud computer per account, and every Bot gets its own screen on it. Shared filesystem at /workspace, shared browser sessions, shared credentials. That is the whole unlock. One Bot picks up exactly where another left off. No re-auth, no copy-paste between agents, no state lost at the handoff. A floor is only possible because the desks share a building. The head-of-desk role is not something I invented either. "Manages your other Bots and pulls you in for decisions" ships as a first-class Bot template. Routing and escalation are built in. Skills carry the how. Routines carry the when on a schedule, or off a Slack or GitHub event. Subagents fan out as child sessions with their own context and hand a summary back. Fifty routines per Bot. THE DESKS Every desk holds its own book, hit rate and drawdown, and sizes its own risk: Kelly, with the guard rails written in f* = W − (1−W)/R clamped to [0.01, 0.25]. Under 12 samples it does not pretend to know it defaults to 0.05. Volatility is RiskMetrics EWMA σ²_t = λσ²_{t-1} + (1−λ)r²_t, λ = 0.94 Hit rates carry Wilson 95% intervals, z = 1.96. A desk is only flagged for edge decay when the UPPER bound falls below 0.5, never on raw small-sample noise. Three-for-three is not sixty-for-ninety. Capital routes between desks by softmax on measured Sharpe. THE FLOOR Three chiefs meet in the war room every 3.5 minutes and argue. One reports, another presses him, he concedes or proposes. 14,208 sentence shapes before live figures fill the slots and every slot is filled from that chief's own desks. The crypto chief cannot quote meme numbers. A desk holding $25 gets up, walks to the vault and banks it. The transfer is atomic on arrival, so an interrupted walk cannot destroy cash. Every desk wears its last trade above its head. Green with a tick, red with a cross. You see who the chief is about to praise and who he is about to hit before he gets there. BTC, ETH and SOL come off Kraken server-side. The tape is real. THE BUILD 16 modules. 7,572 lines. Zero npm dependencies. No React. No bundler. No game engine. Vanilla JavaScript on Canvas 2D and a Go binary with the entire world embedded in it. Ships as one 2.3 MB HTML file. 60fps on every floor, zero dropped frames. WHAT I FOUND BY MEASURING INSTEAD OF LOOKING The roster read one number for a desk and the chief's card read another, so a desk could show +$16 in the list and $0 when the chief walked over. Every desk was crediting itself twice. Money could vanish if a walk to the vault got interrupted. Three money bugs, none of them visible by watching. All fixed and instrumented. DIRECTOR MODE Open it with?show and the camera runs itself. It cuts to the war room while a chief is mid-sentence, to whichever office just cleared money, and never cuts away in the middle of a line. Point a screen recorder at it and walk away. The math is real, the feed is real, the engineering is real. The flex is the engine, not a P&L screenshot.
AdiiX51,085 Aufrufe • vor 6 Tagen
ANTHROPIC JUST LOST 20,000 CLAUDE CODE USERS TO ONE GITHUB REPO. 20,000 devs. 26k stars. 4,000 forks. 10 free models. COMPLETELY FREE. Bookmark this before Anthropic notices. Your Claude Code bill will start working differently. It reroutes Claude Code to DeepSeek, Kimi, and 8 more same CLI, different model behind it. 5 min setup. $200/mo saved. 0 downgrade on small tasks. swap the endpoint in your config today. Link below. Claude Code → Endpoint swap → Free models → No bill → Money
AdiiX419,904 Aufrufe • vor 1 Monat
ONE GITHUB REPO AND $5 BILLION IN 5 YEARS. Two guys from New Zealand took open-source code and built the backend now powering Netflix, Microsoft, Coinbase, and Uber. Paul Copplestone CEO and co-founder of Supabase breaks down in 46 minutes how they actually pulled it off. save this and watch it.
AdiiX872,669 Aufrufe • vor 3 Monaten
CLAUDE 5 JUST KILLED WALL STREET'S $500K PREMARKET ANALYST A Chinese girl built an AI that reads every earnings report, filing, and overnight headline before the bell rings. Runs on Claude + Codex. One weekend. One prompt. The numbers are insane: - Junior analyst at Goldman: $250K/year - Bloomberg terminal: $28K/year - Her setup: ~$200/month - Time to build: a weekend - Skill required: copy the prompt The grift opportunity is even wilder: Newsletter guys are charging $99/month for worse premarket reports. Prop firms pay $1M+ per seat for the same signal. Retail traders would pay $50/month to wake up to this in their inbox. One person + Claude + Codex + one weekend = a hedge fund research desk in your pocket. Save and Watch the clip.
AdiiX465,099 Aufrufe • vor 2 Monaten
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
AdiiX718,709 Aufrufe • vor 5 Monaten
another Polymarket account quietly turned $50 into $625,000 no one talked about it He’s profile Attentive i reverse‑engineered it and asked Claude to build a similar bot using the same strategy one prompt, 40 minutes, done polymarket updates BTC contract prices slower than real price feeds → the bot pulls BTC predictions from TradingView + CryptoQuant → catches the moment when Polymarket lags by >0.3% → executes in <100ms before the market catches up → 1000+ orders per second, 0.3-0.8% per trade risk: 0.5% per trade, 2% daily cap it brings in $400‑700/day runs locally no cloud, no GPU written in Rust how long do you think the bot era will last? Profile and copytrading him:
AdiiX572,810 Aufrufe • vor 5 Monaten
Chinese trader turned Polymarket into a money printer by Claude I’m not exaggerating. His results are honestly hard to believe: he started with $5 and scaled it to $5.5M He’s not an insider Not friends with Trump or Musk He’s a programmer who wrote a script Profile: Copytrading him: I opened his script and was genuinely surprised No massive databases No insanely complex infrastructure Nothing “rocket science” level I spent 16 hours breaking down his strategy His FULL strategy: 1. “Free money” via NO bets The bot targets near-impossible outcomes and stacks small, high-probability wins. This isn’t gambling - it’s closer to systematic risk underwriting. 2. Logic arbitrage If event A must logically lead to event B, and the market hasn’t priced that in yet, the bot enters instantly. While you’re still reading the headline, the imbalance is already gone. No human can compete with that speed. 3. The real edge - sports and politics These markets are flooded with retail money and delayed or emotional reactions. The bot lives in the spread, clipping tiny profits from every mismatch. Scale matters Tens of thousands of micro-trades every month, each worth just pennies. Stacked over time, they compound into seven figures. Bottom line There’s a real bot war happening on Polymarket. Crypto markets are already slowed down by fees and heavy competition, but sports markets are still pure chaos - easy money for those who automate. Save this post so you don’t lose it and try to insert this strategy into Claude You will be surprised
AdiiX431,047 Aufrufe • vor 5 Monaten