Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

GROK BOT HAS BEEN RUNNING THIS LAB FOR 9 DAYS, AND THE SYSTEM LOOKS VERY DIFFERENT NOW what started as 6 agents with separate roles has grown into a research clinic built around Milo, with literature search, molecule design, safety checks and human approval while his mobility sits at... 1.1/10 scout → papers → chem → candidates → tox → safety → vitals → Milo → chief → decision each bot still owns one narrow job, but the crew now works through Milo’s case together. anything that could reach him still stops before the treatment gate after burning through every candidate, scout goes back to the archives and finds LN-8802 hidden in a paper from 1987. it was in the shortlist the whole time 9 days → 6 agents → 1 dog → 1 candidate left. the lab keeps getting deeper with every run. bookmark thisshow more

Gipp 🦅

10,206 subscribers

15,441 Aufrufe • vor 19 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

HOLY SH*T, I BUILT A F**KING COMPANY INSIDE GROK BOT i split the operation into separate roles for research, writing, outreach, ops, finance and support. each agent owns one narrow job 6 agents → 1 shared operation → automatic handoffs → human approval each bot keeps its own workflow and memory, then passes finished work forward instead of routing everything back through me the control layer catches anything that sends, spends, publishes or deletes and pushes it into approval before anything happens after a few runs this stops feeling like ai chat. it feels like a 24/7 operations team running behind one dashboard

HOLY SH*T, I BUILT A F**KING COMPANY INSIDE GROK BOT i split the operation into separate roles for research, writing, outreach, ops, finance and support. each agent owns one narrow job 6 agents → 1 shared operation → automatic handoffs → human approval each bot keeps its own workflow and memory, then passes finished work forward instead of routing everything back through me the control layer catches anything that sends, spends, publishes or deletes and pushes it into approval before anything happens after a few runs this stops feeling like ai chat. it feels like a 24/7 operations team running behind one dashboard

Gipp 🦅

1,387,782 Aufrufe • vor 1 Monat

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock

Gipp 🦅

19,071 Aufrufe • vor 2 Monaten

ANTHROPIC LEAKED ONE FILE WORTH $3.4M WHERE 7 WORKERS BUILD AN AI COMPANY IN 24 HOURS you hire nobody - you paste in 1 file and get 7 roles across three shifts with zero onboarding. scout → architect → builders ×3 → critic → scribe → night crew → chief → back into the file the scout goes through mail, tickets and news - and has the agenda ready before you sit down at the desk. the architect cuts the work into a task graph and holds the decisions - 3 builders run on parallel branches. the critic checks every diff before you ever open one - you're no longer the first to see the mistake. the scribe closes the docs and the changelog - the thing you postponed for 3 years now happens daily, without you. the night crew takes the long jobs and the research - the ones that never fit inside an 8-hour day. the chief rolls up the metrics, writes the morning report, and is the only one of the 7 allowed to write back into the file. that one back edge is what turns a pile of assistants into a company - tomorrow's rules get written tonight. every shift hands the next one a finished artefact - nothing gets re-derived from scratch. you work 8 hours, the fleet works 16, 7 roles and zero onboarding. save this and paste it into Claude Code - and your company stops idling ↓

ANTHROPIC LEAKED ONE FILE WORTH $3.4M WHERE 7 WORKERS BUILD AN AI COMPANY IN 24 HOURS you hire nobody - you paste in 1 file and get 7 roles across three shifts with zero onboarding. scout → architect → builders ×3 → critic → scribe → night crew → chief → back into the file the scout goes through mail, tickets and news - and has the agenda ready before you sit down at the desk. the architect cuts the work into a task graph and holds the decisions - 3 builders run on parallel branches. the critic checks every diff before you ever open one - you're no longer the first to see the mistake. the scribe closes the docs and the changelog - the thing you postponed for 3 years now happens daily, without you. the night crew takes the long jobs and the research - the ones that never fit inside an 8-hour day. the chief rolls up the metrics, writes the morning report, and is the only one of the 7 allowed to write back into the file. that one back edge is what turns a pile of assistants into a company - tomorrow's rules get written tonight. every shift hands the next one a finished artefact - nothing gets re-derived from scratch. you work 8 hours, the fleet works 16, 7 roles and zero onboarding. save this and paste it into Claude Code - and your company stops idling ↓

Noisy

50,907 Aufrufe • vor 1 Monat

THIS GUY BUILT A SYSTEM THAT GETS SMARTER EVERY TIME HE USES IT AND IT LOOKS LIKE A GALAXY he types one command into Claude Code it finds sources, runs analysis through NotebookLM, saves everything to Obsidian automatically graph in the background is every idea he's ever researched - all linked together system handles the research so he only has to think about what to do with it most people are still copy-pasting into Notion and losing everything by next week full setup in the article

THIS GUY BUILT A SYSTEM THAT GETS SMARTER EVERY TIME HE USES IT AND IT LOOKS LIKE A GALAXY he types one command into Claude Code it finds sources, runs analysis through NotebookLM, saves everything to Obsidian automatically graph in the background is every idea he's ever researched - all linked together system handles the research so he only has to think about what to do with it most people are still copy-pasting into Notion and losing everything by next week full setup in the article

monokern

45,188 Aufrufe • vor 3 Monaten

This guy turned Grok Bot into an MM system and it made $1,335 a day The result is already +$65,425 PnL with only $40 per average trade while repeating the same setup 9 times every hour across BTC "Up or Down" markets Six AI agents work together as one algorithm: 1. They try to build Up + Down < 100¢ The bot accumulates both outcomes at different moments as BTC moves For example: Down at 38¢ + Up later at 56¢ = 94¢ total cost (6¢ locked on every complete set) The two entries do not need to happen at the same time 2. Order Flow tells the agents which side to accumulate next The model tracks imbalance inside the book: OBI = (B - A) / (B + A) When buying pressure shifts toward one outcome, its fair probability changes and the bot adjusts which side it wants to accumulate This trader’s Polymarket account: GoodFallen 10,322 predictions with a 50% win rate Follow this account and trade on Polymarket through this bot: Most profitable trades: $974 → $2,525 (+$1,551) $723 → $1,923 (+$1,200) $1,270 → $2,323 (+$1,053) The bot uses changes in Order Flow and BTC price to keep rebuilding the same position before resolution

This guy turned Grok Bot into an MM system and it made $1,335 a day The result is already +$65,425 PnL with only $40 per average trade while repeating the same setup 9 times every hour across BTC "Up or Down" markets Six AI agents work together as one algorithm: 1. They try to build Up + Down < 100¢ The bot accumulates both outcomes at different moments as BTC moves For example: Down at 38¢ + Up later at 56¢ = 94¢ total cost (6¢ locked on every complete set) The two entries do not need to happen at the same time 2. Order Flow tells the agents which side to accumulate next The model tracks imbalance inside the book: OBI = (B - A) / (B + A) When buying pressure shifts toward one outcome, its fair probability changes and the bot adjusts which side it wants to accumulate This trader’s Polymarket account: GoodFallen 10,322 predictions with a 50% win rate Follow this account and trade on Polymarket through this bot: Most profitable trades: $974 → $2,525 (+$1,551) $723 → $1,923 (+$1,200) $1,270 → $2,323 (+$1,053) The bot uses changes in Order Flow and BTC price to keep rebuilding the same position before resolution

Daniro

19,789 Aufrufe • vor 18 Tagen

42 AI agents now run an entire sales department. Not one of them takes a salary. Hundreds of thousands in payroll. Gone in a weekend. At the top sits the chief sales officer. It delegates to every team’s manager. Outreach writes the emails, runs voice, fires SMS across 8 languages. RevOps wires HubSpot into the data warehouse. Research scores every lead and preps every call before a rep walks in. Then the part that breaks your brain. They talk to each other. The researcher hands context to the email writer. The call analyst feeds the follow up drafter. 42 specialists. 1 nervous system. This isn’t a chatbot. It’s an org chart that compounds while I sleep. And it’s day 1. Over the next 30 days this becomes a full company. Every department. Every role. Nobody on payroll. The last team I’ll ever have to hire. Want the full breakdown of all 42 agents and the org chart? Comment 42 and I’ll send it through.

42 AI agents now run an entire sales department. Not one of them takes a salary. Hundreds of thousands in payroll. Gone in a weekend. At the top sits the chief sales officer. It delegates to every team’s manager. Outreach writes the emails, runs voice, fires SMS across 8 languages. RevOps wires HubSpot into the data warehouse. Research scores every lead and preps every call before a rep walks in. Then the part that breaks your brain. They talk to each other. The researcher hands context to the email writer. The call analyst feeds the follow up drafter. 42 specialists. 1 nervous system. This isn’t a chatbot. It’s an org chart that compounds while I sleep. And it’s day 1. Over the next 30 days this becomes a full company. Every department. Every role. Nobody on payroll. The last team I’ll ever have to hire. Want the full breakdown of all 42 agents and the org chart? Comment 42 and I’ll send it through.

West Lord

29,206 Aufrufe • vor 3 Monaten

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

Blaze

56,062 Aufrufe • vor 4 Monaten

ELON MUSK REPOSTED MY GROK BOT CONTENT SETUP. AND I STILL DON'T UNDERSTAND WHY NOBODY IS DOING THIS WITH TRADING YET. A WALL STREET RESEARCH DESK COSTS MILLIONS A YEAR TO STAFF – YOU CAN NOW RUN THE SAME THING WITH 9 GROK BOT AGENTS. Nine people used to do this job. Nine Grok Bot agents now do it while you sleep. Here's the entire desk: → MACRO – watches rates, CPI, FOMC. Tells you what kind of day it is before you open a single chart. → SCANNER – sweeps 9,000 tickers for one thing: your setup. Not "interesting stocks". Yours. → CATALYST – reads every 8-K, earnings call and wire the second it drops. Flags the two that matter. → QUANT – backtests the idea before you fall in love with it. Kills it if the edge isn't there. → CRYPTO – on-chain flows, funding, basis. The stuff nobody has the energy to check at 2am. → RISK – the one that actually saves you. Sizes the position, sets the stop, refuses the 4th trade. → EXECUTION – places the order, tracks the fill, reports the slippage in basis points. → COMPLIANCE – logs every single decision. So you can audit yourself instead of lying to yourself. → CHIEF OF STAFF – sits on top of all eight. Ranks their output and hands you one page every morning. Here's the part nobody says out loud: Retail traders don't lose because they lack information. They lose because they can't process it fast enough – and can't stay disciplined when they do. Grok Bot solves the first problem completely. RISK and COMPLIANCE quietly solve the second one, because a bot never moves a stop loss. And you write zero code. You describe each agent in plain English, tell it where to look, give it one job. Start with two: SCANNER and RISK. That alone is more process than 95% of retail traders have ever run. Not financial advice – this is a research desk, not a money printer. The bots find and organise. You decide. Bookmark this & read more in the article below ↓

ELON MUSK REPOSTED MY GROK BOT CONTENT SETUP. AND I STILL DON'T UNDERSTAND WHY NOBODY IS DOING THIS WITH TRADING YET. A WALL STREET RESEARCH DESK COSTS MILLIONS A YEAR TO STAFF – YOU CAN NOW RUN THE SAME THING WITH 9 GROK BOT AGENTS. Nine people used to do this job. Nine Grok Bot agents now do it while you sleep. Here's the entire desk: → MACRO – watches rates, CPI, FOMC. Tells you what kind of day it is before you open a single chart. → SCANNER – sweeps 9,000 tickers for one thing: your setup. Not "interesting stocks". Yours. → CATALYST – reads every 8-K, earnings call and wire the second it drops. Flags the two that matter. → QUANT – backtests the idea before you fall in love with it. Kills it if the edge isn't there. → CRYPTO – on-chain flows, funding, basis. The stuff nobody has the energy to check at 2am. → RISK – the one that actually saves you. Sizes the position, sets the stop, refuses the 4th trade. → EXECUTION – places the order, tracks the fill, reports the slippage in basis points. → COMPLIANCE – logs every single decision. So you can audit yourself instead of lying to yourself. → CHIEF OF STAFF – sits on top of all eight. Ranks their output and hands you one page every morning. Here's the part nobody says out loud: Retail traders don't lose because they lack information. They lose because they can't process it fast enough – and can't stay disciplined when they do. Grok Bot solves the first problem completely. RISK and COMPLIANCE quietly solve the second one, because a bot never moves a stop loss. And you write zero code. You describe each agent in plain English, tell it where to look, give it one job. Start with two: SCANNER and RISK. That alone is more process than 95% of retail traders have ever run. Not financial advice – this is a research desk, not a money printer. The bots find and organise. You decide. Bookmark this & read more in the article below ↓

SCOTTY BEAM

93,953 Aufrufe • vor 29 Tagen

This GitHub script makes $500K a week. Someone found a legal API loophole worth $3.7M. According to his profile: I studied legendary swisstony wallet and I was blown away. The bot really started with some measly $5 and now his profit has hit the $3.7 million mark in just six months. Just picture him making $90K pure cash and everyone getting into a debate about the next prediction on the chat. There is no trading in the normal sense. This is systematic clearing with code. I went back into his working head and heres what the bot does with liquidity: First it works like a vacuum cleaner for'free'money. The bot searches for outcomes with a 99% improbability of occurrence and allocates significant sums to the 'NO' category at 99 cents. For him this is a guaranteed 1 and he does it hundreds of times. This isn't a casino this is an insurance company that takes your premiums but never pays claims. 2nd the bot catches misstake in the system itself. If A must cause B and the quotes did differ the script is immediately in the trade. And while you are still reading the headline on Sports the bot has already identified the mismatch in the order book and secured its gain. No way a human can keep up with it. However, the true excitement exists within the domains of sports and politics. The bot intentionally enters these markets. Why? Since that is where the biggest crowd of hamsters place bets for fun and the info about the matches always gets to the masses with the delay The script just sits in the middle and takes one cent of spread from each trade. Monthly, this equates to 22,000 such micro-bites, which accumulate into millions. Here's the bottom line. Right now there is the real bot war at Polymarket. The platform has already commenced applying charges on crypto markets as a measure to decelerate their pace. But in sports is still chaos and easy money.

Blaze

217,714 Aufrufe • vor 8 Monaten

This trader used Claude to build a Quant Bot and made +$162,939 on Polymarket Since Apr 6, this wallet has been averaging about $2,232 in profit per day while doing roughly 9 trades per hour 15,738 predictions with a 71% win rate in 73 days This trader’s Polymarket account: This trader started with about $167.1K in deposits and is now sitting at roughly +97.5% ROI The bot strategy is simple: > It keeps leaning into short crypto markets when the pricing is still behind > Gets filled before the board fully adjusts and keeps rotating through the same setup across many entries > The edge on any one trade is limited, but repetition is what turns it into a large result Most profitable trades: $167 → $836 (+$669, +399.85%) $475 → $1,113 (+$638, +134.14%) $935 → $1,560 (+$625, +66.87%) It is a repeatable short-window process that keeps converting delayed repricing into steady profit

This trader used Claude to build a Quant Bot and made +$162,939 on Polymarket Since Apr 6, this wallet has been averaging about $2,232 in profit per day while doing roughly 9 trades per hour 15,738 predictions with a 71% win rate in 73 days This trader’s Polymarket account: This trader started with about $167.1K in deposits and is now sitting at roughly +97.5% ROI The bot strategy is simple: > It keeps leaning into short crypto markets when the pricing is still behind > Gets filled before the board fully adjusts and keeps rotating through the same setup across many entries > The edge on any one trade is limited, but repetition is what turns it into a large result Most profitable trades: $167 → $836 (+$669, +399.85%) $475 → $1,113 (+$638, +134.14%) $935 → $1,560 (+$625, +66.87%) It is a repeatable short-window process that keeps converting delayed repricing into steady profit

Daniro

40,344 Aufrufe • vor 3 Monaten

Grok Bot turned $500 into $100,000 in 2 days on Polymarket, and I built it in 20 minutes. 20 minutes of setup. No code. I don't run it. The bot lives on its own cloud machine. Own browser. Own terminal. My laptop is shut. Every 10 minutes, 6 assistants wake up in order. Scout scans 800 markets and drops anything under $10K liquidity. Listener is Grok itself. It reads live sentiment on every market Scout flags - it sees every post on this app. Pricer builds fair value and marks the gap. Under 8% mispricing, it stays quiet. Risk sizes the bet. Kelly criterion, hard cap 6% of bankroll. It has killed more trades than it has approved. Hands executes in its own browser. No API keys. No rust. Treasurer logs every fill to Telegram and pays the $200 subscription out of profit. Hour 4 the balance dipped to $380. Risk cut position size to 2% for 9 hours and came back up only after 6 green fills. Nobody told it to do that. Last winter I built the same thing by hand. 3 weeks of code for a worse version. Grok Bot did it in 20 minutes. I built it to trade for me. Now it pays its own bills.

Grok Bot turned $500 into $100,000 in 2 days on Polymarket, and I built it in 20 minutes. 20 minutes of setup. No code. I don't run it. The bot lives on its own cloud machine. Own browser. Own terminal. My laptop is shut. Every 10 minutes, 6 assistants wake up in order. Scout scans 800 markets and drops anything under $10K liquidity. Listener is Grok itself. It reads live sentiment on every market Scout flags - it sees every post on this app. Pricer builds fair value and marks the gap. Under 8% mispricing, it stays quiet. Risk sizes the bet. Kelly criterion, hard cap 6% of bankroll. It has killed more trades than it has approved. Hands executes in its own browser. No API keys. No rust. Treasurer logs every fill to Telegram and pays the $200 subscription out of profit. Hour 4 the balance dipped to $380. Risk cut position size to 2% for 9 hours and came back up only after 6 green fills. Nobody told it to do that. Last winter I built the same thing by hand. 3 weeks of code for a worse version. Grok Bot did it in 20 minutes. I built it to trade for me. Now it pays its own bills.

RGK

20,331 Aufrufe • vor 28 Tagen

ANTHROPIC LEAKED A 5-FILE SETUP THAT BUILDS A VIDEO STUDIO FROM ONE PROMPT AT $100K A MONTH no agency, no editors - one root brief, 5 stages, and a gate that rejects a quarter of everything. brief → scout → script → storyboard ×6 → gate → publish → back into the brief the root file defines what counts as a good video - every stage reads it, so 100 videos stay one channel. the scout looks at what already works in the niche before a single line gets written. 6 scenes get storyboarded at once - on the clock that's one scene, not six. and here's the key part: the gate watches it back, scores retention, and 1 in 4 never ships. 400 videos in, 300 pass, 100 come back for a rewrite - not for deletion. three reasons they come back: the hook dies in the first two seconds, the middle has no reason to stay, the niche already has this video. remove the gate and the whole line turns into a generator. one video costs $0.33 in Claude - 300 videos a month is $98, so the model was never the cost line. the real money goes into the render: voice and footage run $0.63 to $5 per video. $100K isn't one channel's number - a typical channel does $200-$2,000, so the setup scales sideways: 10 channels, one brief each, the same 5 files. read the article below and you'll see why one root file does what a team of editors doesn't ↓

ANTHROPIC LEAKED A 5-FILE SETUP THAT BUILDS A VIDEO STUDIO FROM ONE PROMPT AT $100K A MONTH no agency, no editors - one root brief, 5 stages, and a gate that rejects a quarter of everything. brief → scout → script → storyboard ×6 → gate → publish → back into the brief the root file defines what counts as a good video - every stage reads it, so 100 videos stay one channel. the scout looks at what already works in the niche before a single line gets written. 6 scenes get storyboarded at once - on the clock that's one scene, not six. and here's the key part: the gate watches it back, scores retention, and 1 in 4 never ships. 400 videos in, 300 pass, 100 come back for a rewrite - not for deletion. three reasons they come back: the hook dies in the first two seconds, the middle has no reason to stay, the niche already has this video. remove the gate and the whole line turns into a generator. one video costs $0.33 in Claude - 300 videos a month is $98, so the model was never the cost line. the real money goes into the render: voice and footage run $0.63 to $5 per video. $100K isn't one channel's number - a typical channel does $200-$2,000, so the setup scales sideways: 10 channels, one brief each, the same 5 files. read the article below and you'll see why one root file does what a team of editors doesn't ↓

Noisy

20,707 Aufrufe • vor 1 Monat

whoever leaked this has bigger balls than sense someone in the Grok Bot beta posted one night of receipts and deleted them an hour later: 6 agents, 1,284 analysis jobs between midnight and 6am, total bill $4.98. same account, a second bot sent 100 outreach messages on X and came back with 41 signups, and a third closed 3 deals and now pays for its own upgrades out of what it earns i gave one of mine a research brief first and watched it hire four agents for the job and fire three of them by lunch, already past the point where i'd have hired a human this is the one-employee company, the layer where the human owns and the agents do everything else, and it installs into the Grok Bot sub you already pay for: - give one bot the hiring seat and nothing else: it spins up agents per task and kills them when the task closes, so the roster is never bigger than tonight's work - price the night before you scale it: 1,284 jobs for $4.98 is the number to beat, and a routine that can't come in under a junior's hourly rate does not get a schedule - put outreach on its own agent with a daily cap: 100 messages and 41 signups is what a clean list does, a dirty one gets the account banned by message 30 - let a bot spend only through a one-time card with a hard limit, the official client already supports it, so the worst night costs the card's ceiling and nothing else - keep one closer bot funding its own upgrades: if it can't pay for its next tool out of what it closed, it isn't a business, it's a demo turns out the roster does not travel: the biggest win came off a research desk where the brain fired agents daily, and the worst blowup off a sales bot that kept every hire on forever my position, and it is the arguable one: this is a beta, and a beta is already running companies with one human inside. the finished product doesn't make that more true, it makes it cheaper bookmark this, the three moves that set up the hiring seat, the card limit and the first paying agent are in the post below ↓

whoever leaked this has bigger balls than sense someone in the Grok Bot beta posted one night of receipts and deleted them an hour later: 6 agents, 1,284 analysis jobs between midnight and 6am, total bill $4.98. same account, a second bot sent 100 outreach messages on X and came back with 41 signups, and a third closed 3 deals and now pays for its own upgrades out of what it earns i gave one of mine a research brief first and watched it hire four agents for the job and fire three of them by lunch, already past the point where i'd have hired a human this is the one-employee company, the layer where the human owns and the agents do everything else, and it installs into the Grok Bot sub you already pay for: - give one bot the hiring seat and nothing else: it spins up agents per task and kills them when the task closes, so the roster is never bigger than tonight's work - price the night before you scale it: 1,284 jobs for $4.98 is the number to beat, and a routine that can't come in under a junior's hourly rate does not get a schedule - put outreach on its own agent with a daily cap: 100 messages and 41 signups is what a clean list does, a dirty one gets the account banned by message 30 - let a bot spend only through a one-time card with a hard limit, the official client already supports it, so the worst night costs the card's ceiling and nothing else - keep one closer bot funding its own upgrades: if it can't pay for its next tool out of what it closed, it isn't a business, it's a demo turns out the roster does not travel: the biggest win came off a research desk where the brain fired agents daily, and the worst blowup off a sales bot that kept every hire on forever my position, and it is the arguable one: this is a beta, and a beta is already running companies with one human inside. the finished product doesn't make that more true, it makes it cheaper bookmark this, the three moves that set up the hiring seat, the card limit and the first paying agent are in the post below ↓

Argona

43,764 Aufrufe • vor 19 Tagen

10 days ago this was an empty map. A loop of AI agents has been building GTA 6 on it and the community building it together while I sleep. day 10. look at it now. People are walking around. a skyline that actually holds up from the air. from a distance you'd swear it was the real one. Unreal is so goated, this would've taken months on Godot. Up close it's still rough, not every building can enter. on night time the far side of the ocean is empty, so the water goes black. might build a second city over there to fix it. still deciding. Going to implement steal cars and shoot tomorrow. Any suggestions?

10 days ago this was an empty map. A loop of AI agents has been building GTA 6 on it and the community building it together while I sleep. day 10. look at it now. People are walking around. a skyline that actually holds up from the air. from a distance you'd swear it was the real one. Unreal is so goated, this would've taken months on Godot. Up close it's still rough, not every building can enter. on night time the far side of the ocean is empty, so the water goes black. might build a second city over there to fix it. still deciding. Going to implement steal cars and shoot tomorrow. Any suggestions?

Ziwen

209,732 Aufrufe • vor 3 Monaten

I'M SHOCKED – ALMOST NOBODY IS USING GROK BOT THE RIGHT WAY. A LEAD ENGINEER AT SPACEX AI JUST DROPPED A 1-HOUR COURSE ON HOW IT'S ACTUALLY DONE. HERE'S ALL OF IT IN 60 SECONDS. The mistake almost everyone makes: they hand Grok Bot random one-off tasks. That's it. That's the whole reason it still feels like a chatbot to you. Here's the system he teaches instead – five parts: → ROLE – stop assigning tasks, create permanent roles. Chief of Staff, Inbox Manager, Researcher, Developer, Reviewer. A bot with a job title beats a bot with a to-do list → TOOLS – connect each bot to what it actually needs: Gmail, Slack, Calendar, Notion, GitHub. It does the work on its own persistent cloud computer → SKILL – teach it your workflow. Write the instructions, or just record yourself doing the job once – Grok Bot turns that demonstration into a reusable skill → ROUTINE – anything you repeat becomes a routine. It runs on a schedule or fires off an event, with your laptop closed → TEAM – group the bots together. The lead bot delegates, the specialists work in parallel, and you set approval rules before anything sends an email, moves a calendar or pushes code The one honest catch: a new bot still needs context and some hand-holding on its first few runs. But that's the entire system. Role → Tools → Skill → Routine → Team. Everyone else is still typing one-off prompts into Grok Bot and wondering why nothing compounds. Bookmark this & read the full breakdown in the article below ↓

I'M SHOCKED – ALMOST NOBODY IS USING GROK BOT THE RIGHT WAY. A LEAD ENGINEER AT SPACEX AI JUST DROPPED A 1-HOUR COURSE ON HOW IT'S ACTUALLY DONE. HERE'S ALL OF IT IN 60 SECONDS. The mistake almost everyone makes: they hand Grok Bot random one-off tasks. That's it. That's the whole reason it still feels like a chatbot to you. Here's the system he teaches instead – five parts: → ROLE – stop assigning tasks, create permanent roles. Chief of Staff, Inbox Manager, Researcher, Developer, Reviewer. A bot with a job title beats a bot with a to-do list → TOOLS – connect each bot to what it actually needs: Gmail, Slack, Calendar, Notion, GitHub. It does the work on its own persistent cloud computer → SKILL – teach it your workflow. Write the instructions, or just record yourself doing the job once – Grok Bot turns that demonstration into a reusable skill → ROUTINE – anything you repeat becomes a routine. It runs on a schedule or fires off an event, with your laptop closed → TEAM – group the bots together. The lead bot delegates, the specialists work in parallel, and you set approval rules before anything sends an email, moves a calendar or pushes code The one honest catch: a new bot still needs context and some hand-holding on its first few runs. But that's the entire system. Role → Tools → Skill → Routine → Team. Everyone else is still typing one-off prompts into Grok Bot and wondering why nothing compounds. Bookmark this & read the full breakdown in the article below ↓

SCOTTY BEAM

97,697 Aufrufe • vor 1 Monat

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 Aufrufe • vor 21 Tagen

Day 12 of building a cozy game with zero game dev experience Around 80 hours in, it now has a complete story, 27 characters with their own backstories and secrets, and 6 planned biomes with 4 already built. Most of the recent work went into quests, dialogue and connecting every character through one larger mystery. Claude is still writing all the dialogue and helping build the game. There’s even a web/mobile build available now for playtesting. 12 days ago this started with no game dev experience. Now it’s becoming an actual world with characters, systems and a full story.

Day 12 of building a cozy game with zero game dev experience Around 80 hours in, it now has a complete story, 27 characters with their own backstories and secrets, and 6 planned biomes with 4 already built. Most of the recent work went into quests, dialogue and connecting every character through one larger mystery. Claude is still writing all the dialogue and helping build the game. There’s even a web/mobile build available now for playtesting. 12 days ago this started with no game dev experience. Now it’s becoming an actual world with characters, systems and a full story.

Hakimi Eiqbal

58,372 Aufrufe • vor 7 Tagen

Early this year, H.E. Edwin Sifuna visited Meru, where he attended church. At that time, we had only held the Busia and Kitengela rallies. The journey was still young, the vision was still taking shape, and many could not yet see what we were beginning to build. That day, the pastor spoke a powerful prophecy over him and anointed him. He spoke of Joshua, of going where Moses had not reached, and of taking the journey forward to conquer new ground. I remember him telling him that where Baba, our Moses, did not reach, it was his assignment to reach and conquer. The pastor prayed for strength, wisdom and favour upon him. And now, we return to Meru this weekend. But this time, we return with a different story. The journey has grown. The movement has grown. The dream that began with a few people willing to believe has now become a national conversation. We return to Meru with H.E. Edwin Sifuna as the Linda Mwananchi presidential candidate. Sometimes you have to go back to where a word was spoken, not because you have forgotten it, but because you now understand the journey it was preparing you for. From Meru, the journey continues. So help us God. 🇰🇪

Early this year, H.E. Edwin Sifuna visited Meru, where he attended church. At that time, we had only held the Busia and Kitengela rallies. The journey was still young, the vision was still taking shape, and many could not yet see what we were beginning to build. That day, the pastor spoke a powerful prophecy over him and anointed him. He spoke of Joshua, of going where Moses had not reached, and of taking the journey forward to conquer new ground. I remember him telling him that where Baba, our Moses, did not reach, it was his assignment to reach and conquer. The pastor prayed for strength, wisdom and favour upon him. And now, we return to Meru this weekend. But this time, we return with a different story. The journey has grown. The movement has grown. The dream that began with a few people willing to believe has now become a national conversation. We return to Meru with H.E. Edwin Sifuna as the Linda Mwananchi presidential candidate. Sometimes you have to go back to where a word was spoken, not because you have forgotten it, but because you now understand the journey it was preparing you for. From Meru, the journey continues. So help us God. 🇰🇪

AbbieZuena

10,067 Aufrufe • vor 28 Tagen

I BUILT GROK BOT SECOND BRAIN 26 agents, one core, running off a single rule my own memory never followed: capture everything, forget nothing, connect it before you even ask. A voice note on a coffee walk gets split into a task and an idea in under 6 seconds - the core already knows the difference between something you have to do and something you just thought of. An idea from three weeks ago gets linked to the one you just had, automatically, before you remember you'd had it the first time. That visual -the rotating profile, the 26 glowing lines firing out through the skull, each one labeled with the agent running it - isn't a rendered mockup. It's the actual runtime. Every line is a live agent doing its job in real time, right now, in your browser. This isn't a note app. Note apps hold what you give them. This is a nervous system for everything your brain was never built to hold onto in the first place. Full build - the 26 agents, how memory actually persists, what it costs to set one up for real - is in the article.

Aleiah

257,595 Aufrufe • vor 25 Tagen

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

JUMPERZ

34,181 Aufrufe • vor 7 Monaten