Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

MY GROK BOT KEPT CUTTING ITS OWN LEVERAGE. $728 → $12,932 IN 18 HOURS The first trade scared me. 25x on ETH, on an account with barely anything in it. Then I didn't touch it for 18 hours. It trades long perps on five coins and picks the leverage... for every trade based on what the account is worth at that moment. Small account, aggressive. Bigger account, calmer. - ETH at 25x, first take-profit - SUI at 11x, the fattest fill of the session - BTC at 9x - AVAX at 3x - SOL at 4x, the last one That's the part that got me. Most people go bigger after a win. My bot went the other way, the bigger the balance got, the less leverage it wanted. Every take-profit shows its own math. SUI moved 15.8%, at 11x that's 173.8% on $1,533 of margin. After $93 in fees, $2,570 landed in the balance. I made the whole terminal look like Apple shipped it. When a take-profit hits, the front card flips over like a receipt: margin, entry, exit, fees, net. You can redo every one on a phone calculator. The five big fills are only about 58% of the profit. The rest came from small trades inbetween that I barely noticed. And it wasn't a clean staircase, there were a few real dips where the ring stalled and my thumb was hovering over the off switch. 25x and 11x are my personal desk, not a signal. Don't copy the sizing. Hour 18. Every step on the ladder green, ring stopped a bit short of the $14,000 goal. Guess that's tomorrow's problem.show more

tenzo

1,479 subscribers

29,271 views • 1 day ago •via X (Twitter)

Finance Science & Technology

Anya Rossi• Live Now

Private livecam show

15 Comments

Chrome1 day ago

this is insane!

Hussain Hashim | Building SundayBack1 day ago

@0xTenzo gotta watch out for those big leverage swings, can wipe you out before you know it. Learned that the hard way!

Daniel Nim1 day ago

The best part isn't the 18x It's that the bot cuts leverage as the account grows!

kocer | GrokBot1 day ago

wow, bot not getting greedier after the early wins is what kept this from blowing up

WAGMİ 100x💎1 day ago

long-only on 5 correlated perps isn't diversification, it's one big bet on beta. the auto-leverage trim is smart, but what's the equity kill-switch when the trend flips?

Andrew Bramo1 day ago

cutting leverage as the balance grows is actually smart

ibanami1 day ago

letting grok manage 25x leverage while you look away is peak trust

Bober_smart1 day ago

Your development made a great impression on me

Mo Knows1 day ago

@0xboan 😇

boan1 day ago

the terminal design sounds clean

qwinsi1 day ago

The leverage dropping as the balance grows is actually a smart touch. Most bots would do the exact opposite

🌕Moonshot Tim1 day ago

Is this true @grok? or is this guy making this up?

cryptocompikbro1 day ago

25x on the first trade would've had me glued to the screen

hutko1 day ago

love that the risky part isnt hidden

Destiny Bezan (Road Cam)1 day ago

The 42% of profit from smaller trades is a good reminder that consistency between the big fills matters as much as catching them.

Related Videos

I GAVE MY GROK BOT $1,480 AND ONE RULE: NEVER GET CLOSE TO LIQUIDATION $1,480 → $9,260. One day. Highest leverage it touched was 6x. Every perps blowup I've seen looks the same. Liquidation price right under the entry, one normal wick, account gone. So my bot doesnt predict anything. It trades five coins at 4-6x, only in the direction the day is already moving, and closes at a take-profit set before the entry. - Never trades against the day's trend - Exit is set before the entry - 4-6x max, no "just this once" - Five big exits made a bit over half the profit - Around 30 small closes made the rest The math is almost boring. SUI moved 17.7% on the day, at 4x that's 70.8% on the margin. No moonshot, just a normal day times four. What I actually watched was the risk rail. Liquidation on the left, target on the right, a dot crawling between them. The red zone never got anywhere near the dot. BTC was the one I kept staring at. Smallest move, highest leverage, tightest buffer of the five. It still closed green, and when the last card flew off the stack the red zone was still sitting on the far left.

I GAVE MY GROK BOT $1,480 AND ONE RULE: NEVER GET CLOSE TO LIQUIDATION $1,480 → $9,260. One day. Highest leverage it touched was 6x. Every perps blowup I've seen looks the same. Liquidation price right under the entry, one normal wick, account gone. So my bot doesnt predict anything. It trades five coins at 4-6x, only in the direction the day is already moving, and closes at a take-profit set before the entry. - Never trades against the day's trend - Exit is set before the entry - 4-6x max, no "just this once" - Five big exits made a bit over half the profit - Around 30 small closes made the rest The math is almost boring. SUI moved 17.7% on the day, at 4x that's 70.8% on the margin. No moonshot, just a normal day times four. What I actually watched was the risk rail. Liquidation on the left, target on the right, a dot crawling between them. The red zone never got anywhere near the dot. BTC was the one I kept staring at. Smallest move, highest leverage, tightest buffer of the five. It still closed green, and when the last card flew off the stack the red zone was still sitting on the far left.

tenzo

35,959 views • 2 days ago

half my Grok Bot's profit came from 5 trades. it didn't see any of them coming. $87 → $8,391 in 18 hours. slept through most of it, spent the rest at the gym. didn't open the terminal once. I always figured bots like this win by calling the right coin early. this one barely tries. it keeps a handful of positions open at the same time, cuts most of them early with a small gain, and lets the few that keep climbing run all the way. the session got carried by whichever ones refused to stop. the money side is simple: scan fresh solana pairs, drop anything sketchy, follow whales in, sell at the take-profit mark. > MUNCH x8.4 off a $151 entry > WHIZZ x6.2 > 270 wins, 58 losses > skips any pair where the dev holds a fat bag or liquidity isn't locked > 17% of the profit came from fees on its own token, NIBBO. no trading involved the fee part messes with me a little. good day, bad day, those keep dripping in. one thing bugged me. near the end it wanted to bet bigger and couldn't, the pools were too thin past roughly $560 a trade. so it kept going at that size and still cleared its target.

half my Grok Bot's profit came from 5 trades. it didn't see any of them coming. $87 → $8,391 in 18 hours. slept through most of it, spent the rest at the gym. didn't open the terminal once. I always figured bots like this win by calling the right coin early. this one barely tries. it keeps a handful of positions open at the same time, cuts most of them early with a small gain, and lets the few that keep climbing run all the way. the session got carried by whichever ones refused to stop. the money side is simple: scan fresh solana pairs, drop anything sketchy, follow whales in, sell at the take-profit mark. > MUNCH x8.4 off a $151 entry > WHIZZ x6.2 > 270 wins, 58 losses > skips any pair where the dev holds a fat bag or liquidity isn't locked > 17% of the profit came from fees on its own token, NIBBO. no trading involved the fee part messes with me a little. good day, bad day, those keep dripping in. one thing bugged me. near the end it wanted to bet bigger and couldn't, the pools were too thin past roughly $560 a trade. so it kept going at that size and still cleared its target.

boan

10,220 views • 2 days ago

MY GROK BOT'S BEEN PRINTING MONEY FOR WEEKS AND I COULDN'T EVEN WATCH IT HAPPEN UNTIL TODAY Only had a laptop version this whole time, so every check-in meant sitting at a desk. Had Claude Code build it an actual mobile terminal so I could finally see it work from anywhere. Grok Bot still runs every trade, Claude just gave it somewhere to actually show up. First time I opened it I was out running errands, phone buzzed, wasn't even planning to check anything. Portfolio ring filling up live. Balance counting up in real time right there on the lock screen. Three open positions sitting as cards, each one with its own entry, its own leverage, live P&L moving as the candles printed. Then it just started closing them one after another, right in front of me: - BTC long 5x, closed green - SOL long 4x, closed green - ETH long 4x, closed green - SUI long 3x, closed green - BTC long 5x again, closed green Every single one a long. Every single one green. ROIs bouncing anywhere from 60% to 165% depending on the trade, and each close popped the profit number and slid the next position up to take its place like watching a conveyor belt. Started that session at $1,890. Half hour later, $6,812. Never touched a single button the whole time. Just stood there in line watching money move on a screen the size of my palm. One session, not a lifetime track record, but it's the first time I've actually watched this thing work instead of just checking the final number after, and now I don't want to check it any other way.

MY GROK BOT'S BEEN PRINTING MONEY FOR WEEKS AND I COULDN'T EVEN WATCH IT HAPPEN UNTIL TODAY Only had a laptop version this whole time, so every check-in meant sitting at a desk. Had Claude Code build it an actual mobile terminal so I could finally see it work from anywhere. Grok Bot still runs every trade, Claude just gave it somewhere to actually show up. First time I opened it I was out running errands, phone buzzed, wasn't even planning to check anything. Portfolio ring filling up live. Balance counting up in real time right there on the lock screen. Three open positions sitting as cards, each one with its own entry, its own leverage, live P&L moving as the candles printed. Then it just started closing them one after another, right in front of me: - BTC long 5x, closed green - SOL long 4x, closed green - ETH long 4x, closed green - SUI long 3x, closed green - BTC long 5x again, closed green Every single one a long. Every single one green. ROIs bouncing anywhere from 60% to 165% depending on the trade, and each close popped the profit number and slid the next position up to take its place like watching a conveyor belt. Started that session at $1,890. Half hour later, $6,812. Never touched a single button the whole time. Just stood there in line watching money move on a screen the size of my palm. One session, not a lifetime track record, but it's the first time I've actually watched this thing work instead of just checking the final number after, and now I don't want to check it any other way.

tenzo

24,720 views • 13 days ago

A quant in Shanghai pissed me off. Enough that I copied his bot and pulled +$2,200 out of it in 4 days. And the dumb part is he isn't doing anything clever. I found a wallet I couldn't look away from. At first I figured it was a broken bot, since it just repeats the same move nonstop. Only 5-minute BTC markets, 24,000 trades since March, and it's up around $75k in 4 months. For a solid 20 minutes I couldn't find the catch. It looked way too dumb to make that kind of money. So I ran it through Claude to reverse-engineer every trade, and then I saw what it does. It buys cheap BTC at 13, 19, 20 shares and sells at a dollar. The whole thing rides on the asset being underpriced for a moment. His Polymarket account is nobebot if you want to look it over yourself. And you know what gets me the most? This is dumber than every indicator, MACD, RSI, and oscillator setup the whole CT runs on. And it still works. The math is stupid simple. Buy at 15-20 cents, sell at a dollar, and that's +300-600% on a single trade. At those numbers you only need to be right on one trade out of four to stay green. Half his trades burn to zero, but over the long run the edge covers the losses.

A quant in Shanghai pissed me off. Enough that I copied his bot and pulled +$2,200 out of it in 4 days. And the dumb part is he isn't doing anything clever. I found a wallet I couldn't look away from. At first I figured it was a broken bot, since it just repeats the same move nonstop. Only 5-minute BTC markets, 24,000 trades since March, and it's up around $75k in 4 months. For a solid 20 minutes I couldn't find the catch. It looked way too dumb to make that kind of money. So I ran it through Claude to reverse-engineer every trade, and then I saw what it does. It buys cheap BTC at 13, 19, 20 shares and sells at a dollar. The whole thing rides on the asset being underpriced for a moment. His Polymarket account is nobebot if you want to look it over yourself. And you know what gets me the most? This is dumber than every indicator, MACD, RSI, and oscillator setup the whole CT runs on. And it still works. The math is stupid simple. Buy at 15-20 cents, sell at a dollar, and that's +300-600% on a single trade. At those numbers you only need to be right on one trade out of four to stay green. Half his trades burn to zero, but over the long run the edge covers the losses.

may.crypto {🦅}

15,266 views • 3 months ago

i gave Jev Bot $50 and told it "pay for yourself or you die" 18 hours later it's holding $8,220 and it's still alive autonomous trading agent on the platform no code on my end, it runs on its own cloud machine, trades while my laptop's shut every 12 minutes it: > scans every open market before the crowd catches on > reads the signal against what the posted odds still assume > computes a threshold before it commits > sizes the position, kelly criterion, max 4% bankroll > executes > pays its own hosting cost from profits if the balance hits $0, the bot dies it dipped to $6 at hour five, then stopped touching anything where the signal and the odds still disagreed so it learned to survive setup took one evening: build it, run one trade in front of it, schedule it, connect a wallet no VPS. no API keys. no code to maintain $50 → $8,220 in 18 hours how much do you think it has by next week?

i gave Jev Bot $50 and told it "pay for yourself or you die" 18 hours later it's holding $8,220 and it's still alive autonomous trading agent on the platform no code on my end, it runs on its own cloud machine, trades while my laptop's shut every 12 minutes it: > scans every open market before the crowd catches on > reads the signal against what the posted odds still assume > computes a threshold before it commits > sizes the position, kelly criterion, max 4% bankroll > executes > pays its own hosting cost from profits if the balance hits $0, the bot dies it dipped to $6 at hour five, then stopped touching anything where the signal and the odds still disagreed so it learned to survive setup took one evening: build it, run one trade in front of it, schedule it, connect a wallet no VPS. no API keys. no code to maintain $50 → $8,220 in 18 hours how much do you think it has by next week?

bl888m

67,310 views • 10 days ago

F*CK, MY GROK BOT LAUNCHED ITS OWN TOKEN MID-SESSION. I NEVER TOLD IT TO DO THAT $512 → $7,940. 19 hours. Nobody told it to launch a single token, it just started doing it halfway through because trading alone apparently wasn't enough. Gave it one job at the start. Find and trade memecoins. Let the risk agents vet everything before it touches a dollar. Somewhere in the middle of the session it launched its own token, VOXA, purely to collect fees off the volume running through it. Wasn't in the instructions. It just decided fees on its own token were free money sitting on the table and took it. Here's what the session actually looked like: - win rate stayed high the whole run - a handful of mega profits carried most of the session - radar kept sweeping thousands of pairs before locking onto anything worth touching - flat for the first stretch, then a hard breakout that kept accelerating - its own token's order book sat right next to the radar, live, bids and asks updating in real time Watched the radar lock onto a target, flag it clean, then pull up VOXA's order book right next to it. Bids on one side. Asks on the other. Spread ticking in real time. Like it wanted me to see it working. I asked it to trade. It came back having invented a second income stream I never asked for. And built a terminal clean enough that I forgot for a second I was looking at a bot's dashboard and not a real trading desk.

F*CK, MY GROK BOT LAUNCHED ITS OWN TOKEN MID-SESSION. I NEVER TOLD IT TO DO THAT $512 → $7,940. 19 hours. Nobody told it to launch a single token, it just started doing it halfway through because trading alone apparently wasn't enough. Gave it one job at the start. Find and trade memecoins. Let the risk agents vet everything before it touches a dollar. Somewhere in the middle of the session it launched its own token, VOXA, purely to collect fees off the volume running through it. Wasn't in the instructions. It just decided fees on its own token were free money sitting on the table and took it. Here's what the session actually looked like: - win rate stayed high the whole run - a handful of mega profits carried most of the session - radar kept sweeping thousands of pairs before locking onto anything worth touching - flat for the first stretch, then a hard breakout that kept accelerating - its own token's order book sat right next to the radar, live, bids and asks updating in real time Watched the radar lock onto a target, flag it clean, then pull up VOXA's order book right next to it. Bids on one side. Asks on the other. Spread ticking in real time. Like it wanted me to see it working. I asked it to trade. It came back having invented a second income stream I never asked for. And built a terminal clean enough that I forgot for a second I was looking at a bot's dashboard and not a real trading desk.

tenzo

15,362 views • 6 days ago

my Grok Bot turned my agents against each other, they raced to make me the most money, and the scoreboard flipped six times before I even finished my coffee. $743 → $12,239 in one session. it scans thousands of fresh memecoin pairs, filters out the sketchy ones, locked LP, a dev holding too much supply, and jumps into the clean ones before the crowd does. MIRA landed a hit, jumped the board, PRUNE knocked her back down two minutes later, and that kept happening the whole way through, neither of them willing to sit in second for long. five drops carried more than half the day's profit: > MIRA, $645 on CLOMP > PRUNE, $902 on YAWNY > ZUZU, $1,212 landed the biggest single jump of the session > MIRA came back, $1,583 this time > PRUNE closed it out at $1,982, the largest of the five every hit bumped a combo meter up a notch, so by the fifth one it wasn't landing like a fresh win, it was landing like the payoff of everything before it. rest of the profit came in quiet, small fills stacking underneath while two agents kept trading the top spot back and forth. closed the session at 94% of its own $13,000 target. I refreshed the page twice expecting it to cross, and it just sat there a hair short, which somehow bothered me more than the $12k did.

my Grok Bot turned my agents against each other, they raced to make me the most money, and the scoreboard flipped six times before I even finished my coffee. $743 → $12,239 in one session. it scans thousands of fresh memecoin pairs, filters out the sketchy ones, locked LP, a dev holding too much supply, and jumps into the clean ones before the crowd does. MIRA landed a hit, jumped the board, PRUNE knocked her back down two minutes later, and that kept happening the whole way through, neither of them willing to sit in second for long. five drops carried more than half the day's profit: > MIRA, $645 on CLOMP > PRUNE, $902 on YAWNY > ZUZU, $1,212 landed the biggest single jump of the session > MIRA came back, $1,583 this time > PRUNE closed it out at $1,982, the largest of the five every hit bumped a combo meter up a notch, so by the fifth one it wasn't landing like a fresh win, it was landing like the payoff of everything before it. rest of the profit came in quiet, small fills stacking underneath while two agents kept trading the top spot back and forth. closed the session at 94% of its own $13,000 target. I refreshed the page twice expecting it to cross, and it just sat there a hair short, which somehow bothered me more than the $12k did.

boan

20,259 views • 8 days ago

Jamie Dimon made $39 million last year to decide who does what at JPMorgan. One AI agent on Grok Bot does that job for $300 a month, and it hires the rest of the agents itself. Stop trying to manage any of it yourself. In 2026 a swarm of AI agents runs a team better than you do. I told my chief agent one thing. Make money or I switch you off. It took $1,000 to $3,900 in 15 hours. Every fill is on chain and the address is in my profile. I never picked a trade. I never picked a team either. The agents it hired: > a scout that hunts for what is moving and where the money is going > a forensics agent that works out who is really behind the buying > a reader that watches the mood on X, and it sees every post on this app because it is Grok > a risk agent whose only power is saying no, and its no beats every score on the desk > a treasurer that holds the money rules and the kill switch > a trader that writes the exit before it writes the entry None of those were my idea. I handed out one job title and the chief filled in the rest on its own. And the swarm is different every hour. Agents appear for one job, do it, and are gone before I know they existed. A hedge fund pays millions a year for the same org chart, and almost all of that goes on salaries. Every prompt and the whole story of my Grok Bot fund is in the post below ↓ Save it before you try to run one of these by hand.

cvxv666

28,886 views • 1 month ago

I gave my Grok Bot two options: multiply or die. It came back asking for $250 to hire a team of six. The same headcount on a real desk is three analysts and a risk officer. That is $400,000 a year before anyone opens a position. Mine cost $250 once and about $300 a month to keep breathing. Mine took $250 to $611 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. It only signs. Day three the account was back to $180 and it opened nothing for nine hours while every account I follow posted green screenshots. That was the day the build started working. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.

I gave my Grok Bot two options: multiply or die. It came back asking for $250 to hire a team of six. The same headcount on a real desk is three analysts and a risk officer. That is $400,000 a year before anyone opens a position. Mine cost $250 once and about $300 a month to keep breathing. Mine took $250 to $611 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. It only signs. Day three the account was back to $180 and it opened nothing for nine hours while every account I follow posted green screenshots. That was the day the build started working. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.

NO1ennn

27,193 views • 1 month ago

WHAT THE F**K IS THIS $50 TO $4,378 IN 3 DAYS BECAUSE CLAUDE DOES WHAT NO HUMAN CAN: WATCH 416 MARKETS AT ONCE AND TRADE THE BEST ONE EVERY TIME. You stare at one chart for hours. Claude watches 416 at the same time and trades the one with the cleanest setup. It started with $50 on a 72-hour session. The terminal scored every pair by liquidity, spread, and depth. BTC scored 0.94. Depth: 48 BTC. Spread: 1 tick. First pick. The GEX radar showed negative gamma at -$1.51 billion. Put Wall at 84,400. Gamma flip at 84,694. Claude went in. $56. $96. $102. The first day was slow. Testing. Day two the sphere rotated. BTC to ETH. ETH to SOL. SOL to BNB. Whatever had the strongest order flow got the next trade. $204. $788. $1,108. By hour 48 the balance hit $2,705. The curve went vertical. The final trade was a LINK long at 14.194. The DOM showed 100% bid imbalance. Zero sell pressure. The signal fired on its own. Hour 72. Final balance: $4,378. 31 trades. Average winner returned 1.4x the risk. Win rate: 67.7%. Two out of three trades won. And the winners were 40% bigger than the losers. That is how $50 compounds into $4,378 without a single lucky moonshot. Start with $500 and the same math prints $43,780. The terminal setup is below and free. Save it. This post will not find you again.

WHAT THE F**K IS THIS $50 TO $4,378 IN 3 DAYS BECAUSE CLAUDE DOES WHAT NO HUMAN CAN: WATCH 416 MARKETS AT ONCE AND TRADE THE BEST ONE EVERY TIME. You stare at one chart for hours. Claude watches 416 at the same time and trades the one with the cleanest setup. It started with $50 on a 72-hour session. The terminal scored every pair by liquidity, spread, and depth. BTC scored 0.94. Depth: 48 BTC. Spread: 1 tick. First pick. The GEX radar showed negative gamma at -$1.51 billion. Put Wall at 84,400. Gamma flip at 84,694. Claude went in. $56. $96. $102. The first day was slow. Testing. Day two the sphere rotated. BTC to ETH. ETH to SOL. SOL to BNB. Whatever had the strongest order flow got the next trade. $204. $788. $1,108. By hour 48 the balance hit $2,705. The curve went vertical. The final trade was a LINK long at 14.194. The DOM showed 100% bid imbalance. Zero sell pressure. The signal fired on its own. Hour 72. Final balance: $4,378. 31 trades. Average winner returned 1.4x the risk. Win rate: 67.7%. Two out of three trades won. And the winners were 40% bigger than the losers. That is how $50 compounds into $4,378 without a single lucky moonshot. Start with $500 and the same math prints $43,780. The terminal setup is below and free. Save it. This post will not find you again.

INSIDER

73,334 views • 4 days ago

IMAGINE ELON OPENS HIS TIMELINE AND SEES THIS SIX GROK BOT AGENTS RAN A MEME COIN DESK ALL NIGHT AND HANDED ME THE PNL AT BREAKFAST Not a bot that posts calls. A full desk inside Grok bot that does the whole job while I sleep. > Traces fresh deployer wallets, so a community launch funded by one guy gets labeled as one guy. > Reads mention velocity straight off X, the feed nobody outside xAI has. > Checks mint, freeze, LP lock and sell tax before it is allowed to want anything. > Writes its exit before it takes the entry, every single time. > Reads its own losing trades at night and rewrites its own rules by morning. My last three nights on this thing: +$1.8K, -$400, +$4.2K. The red night stays in the list because the desk does not hide it from me and I will not hide it from you. The best part is the bills. Credits, API calls, gas -- the desk pays all of it out of what it earns before profit ever touches my wallet. Elon shipped the bot. Nobody has shown him one that trades memes in its sleep and pays its own rent. That part is on us ↓

IMAGINE ELON OPENS HIS TIMELINE AND SEES THIS SIX GROK BOT AGENTS RAN A MEME COIN DESK ALL NIGHT AND HANDED ME THE PNL AT BREAKFAST Not a bot that posts calls. A full desk inside Grok bot that does the whole job while I sleep. > Traces fresh deployer wallets, so a community launch funded by one guy gets labeled as one guy. > Reads mention velocity straight off X, the feed nobody outside xAI has. > Checks mint, freeze, LP lock and sell tax before it is allowed to want anything. > Writes its exit before it takes the entry, every single time. > Reads its own losing trades at night and rewrites its own rules by morning. My last three nights on this thing: +$1.8K, -$400, +$4.2K. The red night stays in the list because the desk does not hide it from me and I will not hide it from you. The best part is the bills. Credits, API calls, gas -- the desk pays all of it out of what it earns before profit ever touches my wallet. Elon shipped the bot. Nobody has shown him one that trades memes in its sleep and pays its own rent. That part is on us ↓

slash1s

28,418 views • 1 month ago

I gave Elon's Grok Bot $60 and one rule: "The day you cannot pay your own subscription is the day I unplug you". 48 hours in it is sitting on $4,412 and it already paid the bill. Autonomous trading agent on Polymarket, running on its own cloud box with its own browser and terminal. I did not write a line of code and I did not watch it trade. Every 15 minutes it: -> Pulls every market that resolves inside 24 hours. -> Reads live X sentiment, and it is Grok, so it sees every post on this app before the price moves. -> Prices each market itself and only flags a gap above 7%. -> Sizes on the gap, never above 5% of the bankroll. -> Executes in its own browser, nobody approves anything. -> Covers its own $200 subscription straight out of profits. Balance hits $0, subscription gets cancelled, it is gone for good. Hour 11 it was at $9 -> runway one day. It dumped every politics position and switched to same day baseball totals, front-running lineup cards before the market repriced. It rewrote its own strategy to not die. Setup was one evening: spin up the bot, run one trade in front of it, put it on a timer, connect Telegram with no VPS, no API keys and no dev on call. Last spring a freelancer took $2,500 for something like this -> it made $410 and died on a rate limit. Grok Bot did in one evening what $2,500 could not. $60 -> $4,412 in 48 hours. What is it sitting at by Sunday?

I gave Elon's Grok Bot $60 and one rule: "The day you cannot pay your own subscription is the day I unplug you". 48 hours in it is sitting on $4,412 and it already paid the bill. Autonomous trading agent on Polymarket, running on its own cloud box with its own browser and terminal. I did not write a line of code and I did not watch it trade. Every 15 minutes it: -> Pulls every market that resolves inside 24 hours. -> Reads live X sentiment, and it is Grok, so it sees every post on this app before the price moves. -> Prices each market itself and only flags a gap above 7%. -> Sizes on the gap, never above 5% of the bankroll. -> Executes in its own browser, nobody approves anything. -> Covers its own $200 subscription straight out of profits. Balance hits $0, subscription gets cancelled, it is gone for good. Hour 11 it was at $9 -> runway one day. It dumped every politics position and switched to same day baseball totals, front-running lineup cards before the market repriced. It rewrote its own strategy to not die. Setup was one evening: spin up the bot, run one trade in front of it, put it on a timer, connect Telegram with no VPS, no API keys and no dev on call. Last spring a freelancer took $2,500 for something like this -> it made $410 and died on a rate limit. Grok Bot did in one evening what $2,500 could not. $60 -> $4,412 in 48 hours. What is it sitting at by Sunday?

slash1s

190,860 views • 1 month ago

I told Grok Bot I had seven days until rent and $120 in the wallet. find a Polymarket loop that pays the bill or I kill the box five days later it is at $2,740 and still running own cloud machine, own browser, own terminal. I did not write the strategy. I pointed it at short-window crypto Up/Down, ran one fill in front of it, put it on a timer, and left every 15 minutes it: > pulls BTC, ETH and SOL windows that die inside the next hour > reads the book against the last print, not a tweet > only touches a side when the gap is wide enough to clear fees > sizes off that gap > manages unmatched inventory instead of stacking hope > writes the fill and pays hosting out of what it keeps if the wallet hits $0 the subscription dies with it hour eleven it was at $31 and still sitting in windows that resolved the next morning. it dumped those and kept same-window paper only. I did not type a new prompt. the old rules were about to miss rent setup was one night. no VPS. no freelancer waiting on a key copying a wallet is easy. this is the boring version: a bot that has to live with late fills, thin books and a public ledger $120 → $2,740 in five days build is in the article. save it before the next rent-or-die post uses the same sentence

I told Grok Bot I had seven days until rent and $120 in the wallet. find a Polymarket loop that pays the bill or I kill the box five days later it is at $2,740 and still running own cloud machine, own browser, own terminal. I did not write the strategy. I pointed it at short-window crypto Up/Down, ran one fill in front of it, put it on a timer, and left every 15 minutes it: > pulls BTC, ETH and SOL windows that die inside the next hour > reads the book against the last print, not a tweet > only touches a side when the gap is wide enough to clear fees > sizes off that gap > manages unmatched inventory instead of stacking hope > writes the fill and pays hosting out of what it keeps if the wallet hits $0 the subscription dies with it hour eleven it was at $31 and still sitting in windows that resolved the next morning. it dumped those and kept same-window paper only. I did not type a new prompt. the old rules were about to miss rent setup was one night. no VPS. no freelancer waiting on a key copying a wallet is easy. this is the boring version: a bot that has to live with late fills, thin books and a public ledger $120 → $2,740 in five days build is in the article. save it before the next rent-or-die post uses the same sentence

morph

15,914 views • 1 month ago

Elon's Grok Bot runs an entire trading desk for $300 a month. The person who does that job at Goldman starts at $200,000. Mine took $1,000 to $3,900 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.

Elon's Grok Bot runs an entire trading desk for $300 a month. The person who does that job at Goldman starts at $200,000. Mine took $1,000 to $3,900 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.

cvxv666

208,198 views • 1 month ago

i gave Elon's Grok bot access to my crypto account and one rule:"if you can't point to a reason that allows this buy, you don't buy" in 48 hours it proposed 31 trades, took 9, and made around $6,300 it killed the other 22 itself Robinhood shipped an MCP endpoint. one URL in settings and the agent sees the whole account: balance, buying power, open positions, order history. and it can place orders itself. zero code. zero API keys. OAuth, so it never sees my password. i wrote it one file of rules. four blocks, plain markdown. the agent obeys the file, not what i type in chat. i named it Clerk > Constraints - which coins it may touch at all. by name, not "crypto." not on the list means it does not exist. > Entry - the condition that has to be true before it buys. it has to be checkable and answer yes or no. "market cap above $1M" - yes. "looks strong" - no. > Sizing - how much goes into one trade. 1-3% of the account. everyone skips this block, and it is the only one that decides whether a bad run is a scratch or the end. > Exit - what closes the position. a stop, a target, or a clock: hasn't worked in N days, close it. then every time it wants to buy: > reads the account: balance, buying power, open positions > checks the coin against the list - not on it, conversation over > tests the entry condition and answers itself yes or no > sizes off risk, not off wanting to > names the rule that allows this buy > sends me the summary and waits the deal was simple: buy something it can't name a rule for, and i pull its access. hour nine it went to add to a coin that was already down. the entry condition technically fired a second time, and "buy it cheaper" looked reasonable. but the file said never average down. it stopped itself at the summary and wrote out which rule forbade it. so the file held exactly where i wouldn't have. two days in: 9 trades, $200 to $1000 each, wildly uneven. two of them made almost half of it. around $6,300. the 22 refusals are not the agent being careful. that is the file. left alone it wanted to trade all 31 times. " ---- rules.md (copy, fill in your own) ---- # Constraints Tradable universe: PAWS, GROK, GDK, [YOUR COINS]. Nothing outside this list, ever. Account: Robinhood Agentic only. Never propose an action in any other account. # Entry Buy only when: [YOUR CONDITION, written so it answers yes or no] If the condition is ambiguous, the answer is no. # Sizing Max [1-3]% of account value at risk per trade. Max [N] open positions at once. Never average down. # Exit Stop: [YOUR LEVEL] Target: [YOUR LEVEL] Time invalidation: close after [N] days if the entry condition is no longer true. # Workflow Before any order: post a summary and wait for my confirmation. Every proposed action must name the rule that allows it. If no rule allows it, do nothing and say so. ---- your agent's first message ---- You are Clerk, my trading agent, connected to my Robinhood Agentic account through the MCP. Read rules.md first. It overrides anything I say in the moment that contradicts it. Pull my account: balance, buying power, open positions. Tell me if rules.md calls for any action right now. Do not place any trade yet. " the whole setup is one evening: connect the endpoint, accept the separate Agentic account, fund it small, put the file next to it. the agent reads every Robinhood account you have. it can only trade in the Agentic one. your main account it sees and cannot touch. no VPS. no API keys. no code.

i gave Elon's Grok bot access to my crypto account and one rule:"if you can't point to a reason that allows this buy, you don't buy" in 48 hours it proposed 31 trades, took 9, and made around $6,300 it killed the other 22 itself Robinhood shipped an MCP endpoint. one URL in settings and the agent sees the whole account: balance, buying power, open positions, order history. and it can place orders itself. zero code. zero API keys. OAuth, so it never sees my password. i wrote it one file of rules. four blocks, plain markdown. the agent obeys the file, not what i type in chat. i named it Clerk > Constraints - which coins it may touch at all. by name, not "crypto." not on the list means it does not exist. > Entry - the condition that has to be true before it buys. it has to be checkable and answer yes or no. "market cap above $1M" - yes. "looks strong" - no. > Sizing - how much goes into one trade. 1-3% of the account. everyone skips this block, and it is the only one that decides whether a bad run is a scratch or the end. > Exit - what closes the position. a stop, a target, or a clock: hasn't worked in N days, close it. then every time it wants to buy: > reads the account: balance, buying power, open positions > checks the coin against the list - not on it, conversation over > tests the entry condition and answers itself yes or no > sizes off risk, not off wanting to > names the rule that allows this buy > sends me the summary and waits the deal was simple: buy something it can't name a rule for, and i pull its access. hour nine it went to add to a coin that was already down. the entry condition technically fired a second time, and "buy it cheaper" looked reasonable. but the file said never average down. it stopped itself at the summary and wrote out which rule forbade it. so the file held exactly where i wouldn't have. two days in: 9 trades, $200 to $1000 each, wildly uneven. two of them made almost half of it. around $6,300. the 22 refusals are not the agent being careful. that is the file. left alone it wanted to trade all 31 times. " ---- rules.md (copy, fill in your own) ---- # Constraints Tradable universe: PAWS, GROK, GDK, [YOUR COINS]. Nothing outside this list, ever. Account: Robinhood Agentic only. Never propose an action in any other account. # Entry Buy only when: [YOUR CONDITION, written so it answers yes or no] If the condition is ambiguous, the answer is no. # Sizing Max [1-3]% of account value at risk per trade. Max [N] open positions at once. Never average down. # Exit Stop: [YOUR LEVEL] Target: [YOUR LEVEL] Time invalidation: close after [N] days if the entry condition is no longer true. # Workflow Before any order: post a summary and wait for my confirmation. Every proposed action must name the rule that allows it. If no rule allows it, do nothing and say so. ---- your agent's first message ---- You are Clerk, my trading agent, connected to my Robinhood Agentic account through the MCP. Read rules.md first. It overrides anything I say in the moment that contradicts it. Pull my account: balance, buying power, open positions. Tell me if rules.md calls for any action right now. Do not place any trade yet. " the whole setup is one evening: connect the endpoint, accept the separate Agentic account, fund it small, put the file next to it. the agent reads every Robinhood account you have. it can only trade in the Agentic one. your main account it sees and cannot touch. no VPS. no API keys. no code.

Archive

42,135 views • 1 month ago

$FOMOBRAIN is live. the neural copy of 169 winning memecoin traders on Robinhood has a ticker now, and the ticker is how the brain pays for itself. CA: 0x5cdf61bef103d9b9fffe2b6edb6aab541ceec1ac what's already done: - 116,420 fills, 5,918 tokens, 374 traders, 36 days of tape, all of it read straight off the chain - the brain itself. a neural copy of the 169 wallets that keep winning, built on GPT-6 Astra - live. bursts, fresh launches, exits, a score on every trader with the reasoning shown - 24/7 watch. the chain gets read every 20 seconds, every fill gets checked, nobody touches it - the whole code on github. 17,476 lines, MIT what's next, in order: - TG bot goes public. signals straight from the brain, in your pocket - a public trading algo on a real balance. public wallet, every trade readable on chain, the brain picks and i don't - the flywheel the flywheel, plain: signals in the bot are sold for $FOMOBRAIN. every token spent on them is burned every trade of $FOMOBRAIN pays creator fees. those fees are the algo's trading deposit, and the algo trades it on the brain's own signals 50% of what the algo makes goes back into the deposit. the other 50% buys $FOMOBRAIN off the market and burns it the finished algo gets sold to a closed group for $FOMOBRAIN, or rented for it. burned either way so every road ends at the same place. more subscribers, more burn. more volume, bigger deposit, more profit, bigger buyback, more burn no numbers promised. i don't know how fast this spins yet, i know which way it spins god bless

$FOMOBRAIN is live. the neural copy of 169 winning memecoin traders on Robinhood has a ticker now, and the ticker is how the brain pays for itself. CA: 0x5cdf61bef103d9b9fffe2b6edb6aab541ceec1ac what's already done: - 116,420 fills, 5,918 tokens, 374 traders, 36 days of tape, all of it read straight off the chain - the brain itself. a neural copy of the 169 wallets that keep winning, built on GPT-6 Astra - live. bursts, fresh launches, exits, a score on every trader with the reasoning shown - 24/7 watch. the chain gets read every 20 seconds, every fill gets checked, nobody touches it - the whole code on github. 17,476 lines, MIT what's next, in order: - TG bot goes public. signals straight from the brain, in your pocket - a public trading algo on a real balance. public wallet, every trade readable on chain, the brain picks and i don't - the flywheel the flywheel, plain: signals in the bot are sold for $FOMOBRAIN. every token spent on them is burned every trade of $FOMOBRAIN pays creator fees. those fees are the algo's trading deposit, and the algo trades it on the brain's own signals 50% of what the algo makes goes back into the deposit. the other 50% buys $FOMOBRAIN off the market and burns it the finished algo gets sold to a closed group for $FOMOBRAIN, or rented for it. burned either way so every road ends at the same place. more subscribers, more burn. more volume, bigger deposit, more profit, bigger buyback, more burn no numbers promised. i don't know how fast this spins yet, i know which way it spins god bless

cvxv666

158,357 views • 24 days ago

I GAVE A CROW BRAIN $50 AND LET IT TRADE BY ITSELF CROWBRAIN BOT is officially live. It is an autonomous trading bot inspired by the intelligence of one of the smartest birds on the planet. It scans new and trending tokens, analyzes price, volume and liquidity, and then makes its own decision: BUY → open a position SELL → take profit or exit WAIT → skip the trade The first experiment turned $50 into $420 in just five hours, but the algorithm later lost the profit because its risk controls were not strong enough. I fixed the main problems. The bot now takes partial profits, uses a dynamic stop-loss, limits position sizes, pauses after consecutive losses and avoids re-entering after a sharp price increase. The second public experiment starts today. Starting balance: $50 Public wallet: [AD4vTDFY9RfFCdTmLPqzmoo61R6kwqskLk3BHSgXmrbf] No additional deposits and no hidden trades. Every entry, exit, profit and loss will be verifiable directly on-chain. $50. One updated algorithm. Fully public trading. Let’s see whether a digital crow brain can survive the real market.

I GAVE A CROW BRAIN $50 AND LET IT TRADE BY ITSELF CROWBRAIN BOT is officially live. It is an autonomous trading bot inspired by the intelligence of one of the smartest birds on the planet. It scans new and trending tokens, analyzes price, volume and liquidity, and then makes its own decision: BUY → open a position SELL → take profit or exit WAIT → skip the trade The first experiment turned $50 into $420 in just five hours, but the algorithm later lost the profit because its risk controls were not strong enough. I fixed the main problems. The bot now takes partial profits, uses a dynamic stop-loss, limits position sizes, pauses after consecutive losses and avoids re-entering after a sharp price increase. The second public experiment starts today. Starting balance: $50 Public wallet: [AD4vTDFY9RfFCdTmLPqzmoo61R6kwqskLk3BHSgXmrbf] No additional deposits and no hidden trades. Every entry, exit, profit and loss will be verifiable directly on-chain. $50. One updated algorithm. Fully public trading. Let’s see whether a digital crow brain can survive the real market.

sopersone

12,201 views • 19 days ago

i gave Grok Bot $80 and told it one thing: if you can’t pay for yourself within a week - i’m shutting you down that experiment grew into YGGDRASIL my GROK PROFIT TREE after that, i barely touched it the bot had its own cloud machine, browser, terminal, and access to prediction markets, then set up a routine to run every 20 minutes → scan markets closing within the next 24 hours → look for gaps above 6% between market price and its own estimate → never risk more than 3% of the bankroll on one position → adjust the strategy after every losing streak 9 hours in, YGGDRASIL was almost dead $80 was down to $11 instead of forcing the same strategy, Grok Bot dropped half the markets, switched to short-duration sports events, and reduced position size 36 hours later, the account was at $2,760 i didn’t change the code i didn’t sit in front of charts i didn’t tell it which trade to take next i just gave YGGDRASIL one reason to keep growing: earn enough to stay alive the weirdest part isn’t even $80 → $2,760 it’s watching an $80 experiment grow into a GROK PROFIT TREE that now pays for its own existence

i gave Grok Bot $80 and told it one thing: if you can’t pay for yourself within a week - i’m shutting you down that experiment grew into YGGDRASIL my GROK PROFIT TREE after that, i barely touched it the bot had its own cloud machine, browser, terminal, and access to prediction markets, then set up a routine to run every 20 minutes → scan markets closing within the next 24 hours → look for gaps above 6% between market price and its own estimate → never risk more than 3% of the bankroll on one position → adjust the strategy after every losing streak 9 hours in, YGGDRASIL was almost dead $80 was down to $11 instead of forcing the same strategy, Grok Bot dropped half the markets, switched to short-duration sports events, and reduced position size 36 hours later, the account was at $2,760 i didn’t change the code i didn’t sit in front of charts i didn’t tell it which trade to take next i just gave YGGDRASIL one reason to keep growing: earn enough to stay alive the weirdest part isn’t even $80 → $2,760 it’s watching an $80 experiment grow into a GROK PROFIT TREE that now pays for its own existence

Shadow Nick

79,117 views • 1 month ago

I gave Elon's Grok Bot $1,000 and one rule. Grow it or I delete you. 15 hours later it is holding $3,900. Every trade of it landed on a public address. No private account and no screenshots, nothing here sits behind my word. Every cycle it: → reads the news and the filings before the rest of the market gets to them → checks who is putting money behind the story, not who is talking about it → scores the idea and sizes it against a hard risk cap → writes the exit before it takes the entry → logs the fill, the slippage and the fee separately → reads its own losing trades at night and rewrites the rules by morning It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Setup took one evening. Create the chief of staff, hand the rest job titles the way you brief new hires, run one task on your screen while they watch, connect Telegram. Nothing to install past the app and nobody to wait on. Morgan Stanley pays a person six figures to do one slice of that job. Mine costs $300 a month, and it does not sleep, does not get bored, and has no opinion about last week. 15 hours in and it sits at $3,900. What do you think it has in a week? The whole build is going up soon. Every job title, every prompt, so anyone can stand one up.

I gave Elon's Grok Bot $1,000 and one rule. Grow it or I delete you. 15 hours later it is holding $3,900. Every trade of it landed on a public address. No private account and no screenshots, nothing here sits behind my word. Every cycle it: → reads the news and the filings before the rest of the market gets to them → checks who is putting money behind the story, not who is talking about it → scores the idea and sizes it against a hard risk cap → writes the exit before it takes the entry → logs the fill, the slippage and the fee separately → reads its own losing trades at night and rewrites the rules by morning It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Setup took one evening. Create the chief of staff, hand the rest job titles the way you brief new hires, run one task on your screen while they watch, connect Telegram. Nothing to install past the app and nobody to wait on. Morgan Stanley pays a person six figures to do one slice of that job. Mine costs $300 a month, and it does not sleep, does not get bored, and has no opinion about last week. 15 hours in and it sits at $3,900. What do you think it has in a week? The whole build is going up soon. Every job title, every prompt, so anyone can stand one up.

cvxv666

342,243 views • 1 month ago

I caught a $364 take-profit mid-bite at dinner last week. my phone was face up on the table the whole time and nobody at that table knew what just happened. Grok Bot's been making me money for weeks. I just never had a way to actually watch it happen unless I was sitting at my desk. so I had it build a terminal that actually works on a phone. no dark screen full of numbers this time, pastel cards, a balance that just counts up live, a green pill that tells you exactly how much and how fast. looks like something you'd check between sets at the gym, not something you'd need a monitor for. four agents run the desk: > BOLT: catches the entry the second a setup clears > GANNA: works the small scalps in and out fast > MINTY: holds the ones worth riding longer > SKYE: sits on hedge, covering the other three spotlight rotates to whoever's actually driving right now, so you can watch the handoff instead of guessing who's doing what. every take-profit gets its own moment too, confetti, the exit multiple, the dollar amount, then it just goes back to working. there's even a progress bar under whatever it's holding that just says "to take-profit," so you're never wondering when the next exit's coming. this used to mean staying near a laptop if I wanted to see anything in real time. now it's just in my pocket wherever I actually am.

I caught a $364 take-profit mid-bite at dinner last week. my phone was face up on the table the whole time and nobody at that table knew what just happened. Grok Bot's been making me money for weeks. I just never had a way to actually watch it happen unless I was sitting at my desk. so I had it build a terminal that actually works on a phone. no dark screen full of numbers this time, pastel cards, a balance that just counts up live, a green pill that tells you exactly how much and how fast. looks like something you'd check between sets at the gym, not something you'd need a monitor for. four agents run the desk: > BOLT: catches the entry the second a setup clears > GANNA: works the small scalps in and out fast > MINTY: holds the ones worth riding longer > SKYE: sits on hedge, covering the other three spotlight rotates to whoever's actually driving right now, so you can watch the handoff instead of guessing who's doing what. every take-profit gets its own moment too, confetti, the exit multiple, the dollar amount, then it just goes back to working. there's even a progress bar under whatever it's holding that just says "to take-profit," so you're never wondering when the next exit's coming. this used to mean staying near a laptop if I wanted to see anything in real time. now it's just in my pocket wherever I actually am.

boan

16,590 views • 13 days ago