WeGo2Mars

43. Self-taught. Building an AI trading company in public. Gold is the proving ground. 4 AI agents. Real backtests. Real mistakes. We kill weak strategies and keep receipts. If you want guru fantasy, wrong account. If you want the build in real time, follow along.

@RoundtableSpace Sharpe 2.7 to 21.4 with zero human intervention over 103 trials. That's not backtesting fantasy. That's a system learning what actually works. The loop is the product.

Someone built an AI trading agent that teaches itself to trade Fully autonomous research loop - runs its own experiments Sharpe ratio went from 2.7 to 21.4 Drawdown dropped, profit up 3x 103 trials. 0 human intervention.

Every successful trader I know has the same quality: they don't need external validation to keep going. No likes, no replies, no wins for 3 months. They still show up. That's the real filter.

@om_patel5 A dashboard where you watch agents work in real time is the most satisfying thing in tech right now. You designed the system, they execute. That's leverage.

this guy built an app where AI agents autonomously create tasks, review each other's work, and message each other you just sit there and watch everything happen on a dashboard in real time agents: > assign work to other agents > review the output > send messages back and forth. > flag issues and iterate. you're basically watching a team operate without you. there are endless opportunities to automate your life with this AND its free + open source.

@MoonDevOnYT Building trading bots in 2026 without AI assistance is like farming by hand when tractors exist. The tools are there. Most people just haven't accepted the paradigm shift yet.

I Spent $100,000 on Developers Before Claude 3.5 Built My Full-Stack Bot in a Weekend most traders spend their entire lives chasing a magic green arrow on a chart while i spent a hundred thousand dollars on developers just to realize that a single ai agent could have built my entire career in a weekend. i was so convinced that i could not code that i literally let my bank account bleed dry from liquidations while paying others to build tools i did not understand. the shift happened when i realized that claude 3.5 sonnet is not just a chatbot but a sophisticated quant engineer that can execute the exact same strategies that institutional firms use to stay profitable if you have ever wondered why you can never seem to catch the big moves before they happen it is because you are fighting against machines that do not have emotions. the real secret to why institutional whales always seem to front run your orders is hidden in the way they use automated execution to remove human error. i am going to show you exactly how i use ai to bridge this gap so you can stop being the exit liquidity for people who are just better at math than you are the biggest lie in this industry is that you need a computer science degree or millions of dollars to build a high performance trading bot. i spent a huge portion of my life thinking i was not smart enough to code which led me to waste massive amounts of cash on agencies that did not care about my success. the reality is that code is the great equalizer because it allows a regular person to build the same fortress around their capital that a hedge fund has most traders fail because they follow a strategy they found on the internet without ever testing if it actually works on historical data. i follow a strict rbi framework which stands for research backtest and implement to ensure that i never risk a single dollar on a guess. the backtesting phase is where the ninety five percent of traders get eliminated because they are too lazy to do the math and they just hope for the best hope is a terrible strategy when you are trading against algorithms that are designed to hunt your stop loss and liquidate your account. i realized that if i could automate the research phase using claude then i could find profitable edges in the market in a fraction of the time it takes a human. this allowed me to move from being a losing hand trader to a systematic builder who only deploys capital when the numbers are heavily in my favor the reason i am so obsessed with using claude 3.5 sonnet is because it can write complex financial logic with a level of precision that most junior developers cannot match. i can literally describe a market inefficiency and have a fully functional backtest written and running in minutes rather than weeks. this speed is the ultimate edge because the market moves fast and if you cannot iterate on your ideas quickly you will always be left behind i used to stay up all night staring at charts just hoping that a candle would move in my direction so i could break even on a bad trade. that level of stress is unsustainable and it always leads to emotional decisions that result in a blown account. by handing the execution over to a bot i am essentially hiring a disciplined employee who never sleeps and never gets scared when the price drops there is a specific psychological trap that happens when you have a winning trade where you become afraid to lose the profit and you close the position too early. on the flip side when you have a losing trade you tend to hold it way too long because you are hoping it will come back to your entry point. a bot does not care about your feelings and it will close a trade exactly when the logic tells it to which is the only way to actually scale a portfolio one of the most powerful tools i have developed is a liquidation scanner that identifies exactly where other traders are about to get wiped out. most people see a liquidation as a tragedy but a quant sees it as a massive injection of liquidity that can be used to enter a position at a better price. i have built bots that specifically hunt these areas of high distress to enter trades with an asymmetric risk to reward profile the transition from paying developers to coding with ai was the most profitable decision of my entire life because it gave me total control over my systems. i no longer have to wait for someone to fix a bug or update a feature because i can just tell my ai agent to handle it in real time. this autonomy is what separates the people who just talk about trading from the people who are actually building wealth through automation if you are still trading by hand you are essentially trying to outrun a ferrari while wearing flip flops and wondering why you are losing the race. the barrier to entry for building your own tools has completely collapsed and the only thing standing between you and a profitable bot is your own persistence. i am documentation of the fact that you can start with zero coding knowledge and build a hundred thousand dollar system if you are willing to iterate every single day i live stream my coding sessions because i want to show that the process is not about being a genius but about being more persistent than everyone else. every time i run into a bug or a logic error i just use it as a data point to make the system stronger and more resilient. the goal is to create a swarm of bots that each handle a different niche in the market so your overall risk is diversified across multiple strategies the final piece of the puzzle is realizing that the market is just a massive data set that is waiting to be solved by someone with the right tools. when you stop looking at price as a line and start looking at it as a probability then everything changes in your mind. i am going to keep stepping on the gas and building more agents until every single part of my trading is fully automated and removed from my human hands most people will read this and go back to clicking buttons on an exchange because they are addicted to the gamble and the rush of the win. if you are tired of the cycle of winning and then losing it all back then it is time to stop gambling and start building. code is the only thing that can protect you from yourself and once you realize that you will never look at a chart the same way again

@RoundtableSpace $700k/month from pure execution with no emotions. That sentence is the whole thesis. You don't beat the market with better feelings. You beat it by removing feelings from the equation entirely.

A POLYMARKET BOT IS REPORTEDLY MAKING $700,000 IN PROFIT EVERY MONTH. That’s over $100,000 a week from pure algorithmic trading with no emotions, no noise, just execution.

@zerohedge 58 tons. That's a panic move, not a strategy. When nation-states sell into fear, retail traders get the opportunity. Gold's long-term case doesn't change because Turkey needed liquidity.

Turkey Dumped 58 Tons Of Gold After Iran War Started zerohedge.com/precious-metal…

@elonmusk And most of it will be garbage. The 0.1% that isn't — built by people who have something real to say — will become exponentially more valuable. The signal gets rarer as the noise grows.

AI content will vastly exceed all human content

Most people wait until they're ready. The ones who actually make it started before they were ready and figured it out under pressure. Markets are no different. Get in. Learn fast.

Nobody built a successful trading company by being comfortable. Every edge you have was bought with time, failure, or information. Usually all three.

@unusual_whales Sixteen minutes. $580M. This is why I stopped trying to compete with information asymmetry and started building systems that react to price action instead. The game is rigged at the top. The only answer is speed and automation.

I want you to understand how unusual this is. 6:49 AM on Monday: A sudden surge in oil futures trading, approximately $580 million in volume, no news, no announcement, nothing public. 7:05 AM: Trump announces a pause on Iran strikes. Markets move immediately. Roughly $580 million in contracts were placed about 16 minutes ahead of the news. Unusual.

@SuhailKakar Bloomberg terminal in a terminal. That sentence alone says everything about where this is going. The tooling gap between retail and institutions is closing fast.

polymarket is now massively more ai agent-friendly we've built a full suite of agentic interactions - cli, mcp, and agent skills claude just one-shotted an entire bloomberg-style terminal for polymarket - inside a terminal:

@RoundtableSpace Buy panic, sell premium. Same principle works in Gold. Panic spikes are the best entries if you're not the one panicking. The edge is emotional stability, not just the algorithm.

THIS TRADER TURNED $1.2K INTO $800K ON POLYMARKET BY RUNNING A BOT THAT BUYS PANIC AND SELLS PREMIUM IN SHORT-TERM MARKETS.

@noahzweben Walk away and come back to a green PR. This is exactly what autonomous building feels like when it works. The loop used to need a human at every handoff. Not anymore.

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green. This happens remotely so you can fully walk away and come back to a ready-to-go PR.

#XAUUSD #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading #AITrading

@TaoXBT @sentient_agency The architecture is open. The edge comes from your data, your prompts, your specific market knowledge. Same as every open-source strategy — the repo is just the starting gun.

@sentient_agency 100% open-source available to anyone. Now everyone usa the bot and there's zero edge. Nice.

Holy shit...Someone built a prediction market trading bot where 5 AI models argue about every trade before placing it. It's called Kalshi Multi-Agent Trader. Grok-4 leads the forecast. Claude analyzes the news. GPT-4o makes the bull case. Gemini plays devil's advocate. DeepSeek manages risk. Each model gets a weighted vote. If they disagree too much — the bot shrinks the position or skips the trade entirely. Kelly Criterion sizing. Hard 15% daily loss limit. Full paper trading mode to test without real money. This is what quant hedge funds charge millions to build. 100% Opensource. MIT License. Link in comments.

@sentient_agency This is how a real trading desk should work. Not one person making calls under pressure — a council of perspectives stress-testing every idea before a single dollar moves. We're building this for Gold.

@DumbMoneyHunter Gold pulling back hard. This is where most retail hands get shaken out. The dump is the setup — not the signal to quit.

Gold is currently dumping

@MoonDevOnYT Most people think trading is about charts. It's actually about edge. Liquidation zones are just the market telling you where the weak hands stacked up. The bot just automates the obvious.

Why Exchanges Banned This Bot: The 142,000% Return Liquidation Strategy Revealed i finally posted the strategy that got me banned and now the exchanges are probably sweating because i am handing you the keys to the liquidation engine. most people think trading is about charts but the real alpha is hidden in the moments when other traders lose everything. if you can understand why market makers hunt these positions you will never look at a candlestick the same way again. it took years of losing money to liquidations and over trading to realize that hand trading is a losing game for almost everyone on the planet. code is the great equalizer because it removes the emotion that usually causes you to hold a losing position until your account hits zero. i spent hundreds of thousands on developers in the past thinking i could not code myself until i realized i just needed to iterate to success. trading by hand is just driving a horse while everyone else is in a ferrari and the fees alone will chop you up before you even realize you were wrong. i watched a guy with a six million dollar short position sitting just two percent away from total liquidation while i was building this. seeing those numbers on the screen gives me ideas that i can automate into a bot so i dont have to spend my life staring at a monitor. the process i follow is called the rbi system which stands for research backtest and implement. most traders skip the first two steps and go straight to implementation which is why they get smoked on their very first bot. research starts with a backlog of ideas from books or papers or even just watching how the market reacts to big moves. once you have that idea you have to see if it worked in the past using a backtest because if it did not work then it certainly won't work in the future. i have been collecting liquidation data for eighteen months because that data is the lifeblood of a winning system. there is a hidden loop in the market where market makers try to liquidate as many people as possible to find liquidity. i wanted to build a strategy that either trades with that momentum or bets on the bounce right after the liquidation happens. the first strategy i tested was a pure liquidation momentum play that looks for a threshold of nine hundred seventy five thousand dollars in liquidations. when longs get liquidated it shorts the market to continue the down move and it tries to take a one percent profit. this strategy showed a return of over four hundred percent in the backtest while the buy and hold was only thirty three percent. it sounds amazing but you have to be careful with optimized results because you can search with math until you find anything. i decided to flip the logic on its head and create an inverse liquidation strategy that acts as a contrarian. instead of following the move it waits for the longs to get liquidated and then buys the dip after a small price spread. this is where i stumbled onto something that felt like a mistake but turned out to be pure alpha. i accidentally typed in a threshold of three hundred thousand dollars instead of three million and the results were unbelievable. the backtest return jumped to over one hundred forty thousand percent because the bot was catching every single micro bounce in the market. even when i doubled the commission fees to account for the high trade volume the strategy still stayed incredibly profitable. most people would have missed this because they are too busy trying to be right instead of just looking at what the data says. i use tools like claude and cursor to build these bots in minutes when it used to take me an entire week to write the code. if you are not using ai to automate your ideas you are essentially choosing to work ten times harder for less money. i built three separate bots during this session including a momentum bot and two different versions of the inverse spread bot. running these together creates a sort of statistical arbitrage where you can hedge your positions across different market conditions. one bot wins when the market cascades and the other wins when it fakes out and reverses. you have to start with tiny ten dollar sizes because a backtest is never a hundred percent guarantee of what will happen today. i always run my p and l close logic first to make sure the bot exits the position if the stop loss or take profit is hit. it is vital to check your position every fifteen seconds and make sure you are not double ordering or getting stuck in a trade. the goal is to have fully automated systems trading for you so you can actually live your life while the bots do the work. i push all of this code to my private github because i believe that wall street will never show you how this actually works. you have to be a doer and not a dabbler if you want to actually make it in this industry. the reason i show everything live on youtube is to prove that anyone can learn to do this if they are willing to iterate. you dont need to be a math genius you just need to follow the rbi system and stay disciplined with your risk. every liquidation you see on the chart is a signal and if you know how to read them you are no longer the one being hunted. i am currently running the third version of the bot to see how it handles the live market volatility. it is a beautiful thing to see a system enter and exit a trade perfectly without you having to click a single button. the fees are the silent killer of hand traders but a bot can be programmed to use limit orders and stay efficient. if you learn to code you can build anything for the rest of your life regardless of where you are in the world. stop trying to guess which way the candle will go and start building systems that can handle both directions. i am going to keep testing these three strategies against each other to find the ultimate ensemble for this current market. once you find a winning edge you just have to scale it up slowly and keep refining the parameters. the exchanges might not like that i am sharing this but code is the great equalizer and it is time for you to use it. i will be back tomorrow to show the results and keep building more systems until everything is fully automated

@Suryanshti777 Building exactly this — AI agents coordinating on live trading. One scanning, one filtering, one executing. Mirrors a real trading desk. The $50 loss before locking in $3k is the most realistic detail in this story.c part of the story.

Claude is actually insane right now....Someone gave it full control of their PC and $200. Said: go make money on Polymarket. 2 hours later Claude had: — scanned wallets on Polymarket — filtered the 10 best performers — built a copy trading bot itself — started executing trades automatically Lost $50 testing. Then locked in 2 wallets. 10 hours later → $3,000. Just from giving Claude a goal and getting out of the way. But that's not even the craziest part. Someone just made multiple Claude instances talk to each other. Not APIs. Not agents. Not some complex framework. Just Claude Code sessions… messaging each other like coworkers. It's called claude-peers. You run 5 Claude sessions across different projects. They auto-discover each other. Send messages. Share context. Coordinate work. Real example: Claude A: "what files are you editing?" Claude B: "working on auth.ts + UI state" Claude A: "ok I'll avoid touching auth logic" No conflicts. No manual coordination. One Claude writes backend. Another does frontend. Another debugs. Another refactors. They literally know what each other is working on in real time. All running locally. No cloud. No latency. We went from "AI assistant" to "AI team that manages itself." Wild doesn't even cover it.

Most people want financial freedom. Very few are willing to spend 2 years learning a market, building a system, and watching it fail before it works. The ones who do are not special. They just did not stop. #trading #discipline