正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

The loop has a name. And it runs in five steps. 1.Something feels heavy. 2. You reach for your poison. 3. You get the hit. 4. The relief dissipates, and you're lower than square one. 5. You start over. That circle, on repeat, is the loop. And notice: I... show more

Command Within | Build Self-Command

108,552 subscribers

19,326 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

GREG ISENBERG

436,752 次观看 • 5 个月前

For the guy who’s scared this part of him is the problem. It isn’t. The fear makes sense, and it’s common, especially in our community. But the thing draining you was never the kink. It’s the loop underneath it. And the second you see it clearly, you get to turn it around. If you want a simple way to start, the Exit Kit is in my bio. Much love. Save this for the night the loop comes knocking. #selfmastery #dopaminedetox #screenaddiction #reclaimyourenergy

For the guy who’s scared this part of him is the problem. It isn’t. The fear makes sense, and it’s common, especially in our community. But the thing draining you was never the kink. It’s the loop underneath it. And the second you see it clearly, you get to turn it around. If you want a simple way to start, the Exit Kit is in my bio. Much love. Save this for the night the loop comes knocking. #selfmastery #dopaminedetox #screenaddiction #reclaimyourenergy

Command Within | Build Self-Command

36,542 次观看 • 1 个月前

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 次观看 • 2 个月前

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

82,714 次观看 • 1 个月前

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

The Startup Ideas Podcast (SIP) 🧃

14,202 次观看 • 4 个月前

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anatoli Kopadze

28,042 次观看 • 2 个月前

Introducing Loop The autonomous business manager that runs your outreach, your follow-ups, and your pipeline,while you focus on the work only you can do. Loop doesn't live in your inbox. Your inbox lives in Loop. Reads every lead like a teammate who's been on your team for years Writes the reply, makes the call, chases the deal when email goes cold Pauses the moment a human actually needs to show up Replaces the patchwork of CRMs, outreach tools, and follow-up apps with one system that does the work Stop managing tools. Start running your loop. comment "loop" and we'll send you in. loop

Introducing Loop The autonomous business manager that runs your outreach, your follow-ups, and your pipeline,while you focus on the work only you can do. Loop doesn't live in your inbox. Your inbox lives in Loop. Reads every lead like a teammate who's been on your team for years Writes the reply, makes the call, chases the deal when email goes cold Pauses the moment a human actually needs to show up Replaces the patchwork of CRMs, outreach tools, and follow-up apps with one system that does the work Stop managing tools. Start running your loop. comment "loop" and we'll send you in. loop

Anushka Singh

12,881 次观看 • 2 个月前

A finance professor manages $200M with AI agents, and he told everyone why: "Large language models are at the level of a fourth-year PhD student in every field" Alejandro Lopez-Lira's AI fund, Autopilot, returned 56% last year. The S&P did 16%. There are 52,000 people with money in it, and most of them just watch the machine work. What he automated is the same six-step loop every fund on earth runs: find an idea, code it, backtest it, deploy it, read the autopsy, learn from it. A quant at Two Sigma runs that loop once a month, and the salary time alone costs around $50,000 per hypothesis. All steps from this loop now fit in AI trading text box. Plain English in, executable strategy out, five-year backtest in 12 seconds, live on a broker 90 seconds after you typed the sentence. He runs $200M with AI. You can run same AI fund in two clicks, free to try: Step 6 on this loop is where everyone is stuck. Your agent has no memory. Every strategy it kills goes into a log nobody reads, and the next one starts from zero. Nobody keeps negative results. Not Citadel, not Man Group, not a single repo on GitHub. Fix that and the agent remembers every hypothesis it killed and the regime it died in. It stops burning cycles on your old mistakes. Jane Street pays 3,500 people to run this cycle and made $39.6 billion doing it. Five sixths of it is now free. Bookmark & read full map of this loop in the article below. Most people still think AI trading is out of reach for them - it isn't. Don't want to spend a dollar for testing this? Kalshi just opened a perps exchange and gives US users $25 free to start ->

A finance professor manages $200M with AI agents, and he told everyone why: "Large language models are at the level of a fourth-year PhD student in every field" Alejandro Lopez-Lira's AI fund, Autopilot, returned 56% last year. The S&P did 16%. There are 52,000 people with money in it, and most of them just watch the machine work. What he automated is the same six-step loop every fund on earth runs: find an idea, code it, backtest it, deploy it, read the autopsy, learn from it. A quant at Two Sigma runs that loop once a month, and the salary time alone costs around $50,000 per hypothesis. All steps from this loop now fit in AI trading text box. Plain English in, executable strategy out, five-year backtest in 12 seconds, live on a broker 90 seconds after you typed the sentence. He runs $200M with AI. You can run same AI fund in two clicks, free to try: Step 6 on this loop is where everyone is stuck. Your agent has no memory. Every strategy it kills goes into a log nobody reads, and the next one starts from zero. Nobody keeps negative results. Not Citadel, not Man Group, not a single repo on GitHub. Fix that and the agent remembers every hypothesis it killed and the regime it died in. It stops burning cycles on your old mistakes. Jane Street pays 3,500 people to run this cycle and made $39.6 billion doing it. Five sixths of it is now free. Bookmark & read full map of this loop in the article below. Most people still think AI trading is out of reach for them - it isn't. Don't want to spend a dollar for testing this? Kalshi just opened a perps exchange and gives US users $25 free to start ->

cvxv666

81,854 次观看 • 15 天前

How do you get out of a negative thought loop? The first step to regulation is awareness. When you become aware of the loop, you can shift your attention to your heart and your breathing … and soon, as your body responds, so does your mind.

How do you get out of a negative thought loop? The first step to regulation is awareness. When you become aware of the loop, you can shift your attention to your heart and your breathing … and soon, as your body responds, so does your mind.

Dr Joe Dispenza

48,821 次观看 • 2 天前

Step 1. Get naked Step 2. Put your headphones on Step 3. Click play and stare into the center Step 4. Loop at least 5 times Step 5. Become a mindless slave Step 6. SEND! Repeat daily 🔁

Step 1. Get naked Step 2. Put your headphones on Step 3. Click play and stare into the center Step 4. Loop at least 5 times Step 5. Become a mindless slave Step 6. SEND! Repeat daily 🔁

LD

95,793 次观看 • 17 天前

These words from GSP mean more to me than anyone will ever know. 🙏 "I have to say, Ariel, your job is to deliver the news and you're one of the guys that I really look up to in a way that... Everyone was afraid of the UFC and everybody was always doing what they were being told and you didn't follow that. You stuck to your values and you report the news the way it is, no matter if it was brutal or if it could impact your career. You always stood up for your ideology and I respect that."

These words from GSP mean more to me than anyone will ever know. 🙏 "I have to say, Ariel, your job is to deliver the news and you're one of the guys that I really look up to in a way that... Everyone was afraid of the UFC and everybody was always doing what they were being told and you didn't follow that. You stuck to your values and you report the news the way it is, no matter if it was brutal or if it could impact your career. You always stood up for your ideology and I respect that."

Ariel Helwani

173,607 次观看 • 1 年前

Trading strategy making you money right now is already dying. You just can't feel it yet. Two finance professors tracked 97 published strategies. One year after they went public, the average edge was down 58%. Every edge has a half-life. Nobody hands you the expiration date. So three red weeks hit, and you panic-quit a strategy that was still alive. Or you marry a dead one and bleed for six months defending it. You can't tell the two apart by feel. That's the entire problem. There's now AI tool that draws the line for you. Horizon backtests 5 years in seconds and runs thousands of simulated paths, so before you go live you already know how deep and how long a normal drawdown runs. Drawdown is weather. Decay is information. One you ride out. One you cut. Then it runs the strategy automated -> the exit gets decided by the math you set when you were calm, not the mood you're in at the bottom. The same loop a quant desk pays $25,000 a year for. Yours for $0 while the beta open. Save this -> re-read it the next time you're three red weeks deep and about to fold a strategy that's still alive. Full framework in the article above. Free access while the beta's open:

Trading strategy making you money right now is already dying. You just can't feel it yet. Two finance professors tracked 97 published strategies. One year after they went public, the average edge was down 58%. Every edge has a half-life. Nobody hands you the expiration date. So three red weeks hit, and you panic-quit a strategy that was still alive. Or you marry a dead one and bleed for six months defending it. You can't tell the two apart by feel. That's the entire problem. There's now AI tool that draws the line for you. Horizon backtests 5 years in seconds and runs thousands of simulated paths, so before you go live you already know how deep and how long a normal drawdown runs. Drawdown is weather. Decay is information. One you ride out. One you cut. Then it runs the strategy automated -> the exit gets decided by the math you set when you were calm, not the mood you're in at the bottom. The same loop a quant desk pays $25,000 a year for. Yours for $0 while the beta open. Save this -> re-read it the next time you're three red weeks deep and about to fold a strategy that's still alive. Full framework in the article above. Free access while the beta's open:

cvxv666

71,962 次观看 • 2 个月前

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

cvxv666

53,163 次观看 • 2 个月前

Anthropic engineer: «You're not supposed to sit and re-prompt Claude all day. You build one loop, and it does the work while you sleep.» • 00:00 - Build your first agent that runs on its own • 05:02 - The loop that fixes its own mistakes • 16:43 - Why Claude forgets you between chats, and the fix You can learn it in one afternoon. 30 minutes here replace what most people spend a year figuring out. Watch it today, then read the guide on building loops below.

Anthropic engineer: «You're not supposed to sit and re-prompt Claude all day. You build one loop, and it does the work while you sleep.» • 00:00 - Build your first agent that runs on its own • 05:02 - The loop that fixes its own mistakes • 16:43 - Why Claude forgets you between chats, and the fix You can learn it in one afternoon. 30 minutes here replace what most people spend a year figuring out. Watch it today, then read the guide on building loops below.

Raytar

28,046 次观看 • 1 个月前

ChatGPT told your trading strategy was profitable. You went live. Two weeks later your account was bleeding out. That's not his fault. It handed you a guess and called it an edge. You're missing the one skill that separates quants from the retail they feed on: loop engineering. Horizon is the first tool that hands it to you - absolutely free: Here's the actual problem. ChatGPT can generate a thousand trading strategies in a minute. It cannot tell you which one actually works. 999 are noise. The one real edge is buried in there, and from the outside it looks exactly like the junk. So you trade the junk, lose, and call it a skill issue. Loop engineering does the opposite. It tests all thousand instead of trusting one - generate, score, kill, refine, repeat - and keeps only what survives data it never saw. That's the entire gap between you and a quant desk. Not brains. Not capital. The loop. It's why they print billions and 89% of retail funded them last year. Horizon runs that exact loop end to end: > a 5-year backtest in 12 seconds > thousands of simulated paths > out-of-sample gate before a dollar goes live The machine that cost a $25,000 terminal and a row of PhDs - now a sentence and a login. Save this - it's full framework below. Fewer than 1,300 seats left before launch locks the list. Link at the top - don't be the one who read all this and skip.

ChatGPT told your trading strategy was profitable. You went live. Two weeks later your account was bleeding out. That's not his fault. It handed you a guess and called it an edge. You're missing the one skill that separates quants from the retail they feed on: loop engineering. Horizon is the first tool that hands it to you - absolutely free: Here's the actual problem. ChatGPT can generate a thousand trading strategies in a minute. It cannot tell you which one actually works. 999 are noise. The one real edge is buried in there, and from the outside it looks exactly like the junk. So you trade the junk, lose, and call it a skill issue. Loop engineering does the opposite. It tests all thousand instead of trusting one - generate, score, kill, refine, repeat - and keeps only what survives data it never saw. That's the entire gap between you and a quant desk. Not brains. Not capital. The loop. It's why they print billions and 89% of retail funded them last year. Horizon runs that exact loop end to end: > a 5-year backtest in 12 seconds > thousands of simulated paths > out-of-sample gate before a dollar goes live The machine that cost a $25,000 terminal and a row of PhDs - now a sentence and a login. Save this - it's full framework below. Fewer than 1,300 seats left before launch locks the list. Link at the top - don't be the one who read all this and skip.

cvxv666

18,985 次观看 • 1 个月前

PROPHETIC DECLARATIONS I pray for you, in the name of Jesus Christ, the grace to pray and pray consistently, I release that grace upon you! I declare that the quickening of the spirit that sponsors discipline to stay in the place of prayer, until you are transformed and changed, and you can discern, receive it now in Jesus Christ's name! I pray for you, the benefits that come from prayer, may it be evident in your life! The help that prayer brings, may you experience it in your life! The wisdom that prayer brings, may you experience it in your life! The direction that is obtained in the place of prayer, may you experience it in your life, in the name of Jesus Christ! Every attack on your prayer life, I decree that the attack gives way now! Everything you've seen in the place of prayer, according to the will of God, may your hands handle it speedily, in Jesus Christ name! I declare that you're blessed in Jesus name! Your week beginning is blessed! The hand of The Lord is strong upon you. His grace is multiplied upon your life! The wisdom of The Spirit is producing results in your life, in Jesus Christ's name! I declare that your week is full of favour! Your week is full of help! Your week is full of victory, in the name of Jesus Christ! By next Sunday, you will be eager to come and testify. Indeed, you will say, “See what The Lord has done”! I declare that every crying stops as you step into this week! Shame and reproach come to an end as you step into this week! For your shame, you shall receive double, in the name of Jesus Christ! #PropheticDeclarations #ApostleJoshuaSelman #WhenWePray #TheWondersOfConsistentPrayer #KoinoniaAbuja #KoinoniaZaria #KoinoniaGlobal

PROPHETIC DECLARATIONS I pray for you, in the name of Jesus Christ, the grace to pray and pray consistently, I release that grace upon you! I declare that the quickening of the spirit that sponsors discipline to stay in the place of prayer, until you are transformed and changed, and you can discern, receive it now in Jesus Christ's name! I pray for you, the benefits that come from prayer, may it be evident in your life! The help that prayer brings, may you experience it in your life! The wisdom that prayer brings, may you experience it in your life! The direction that is obtained in the place of prayer, may you experience it in your life, in the name of Jesus Christ! Every attack on your prayer life, I decree that the attack gives way now! Everything you've seen in the place of prayer, according to the will of God, may your hands handle it speedily, in Jesus Christ name! I declare that you're blessed in Jesus name! Your week beginning is blessed! The hand of The Lord is strong upon you. His grace is multiplied upon your life! The wisdom of The Spirit is producing results in your life, in Jesus Christ's name! I declare that your week is full of favour! Your week is full of help! Your week is full of victory, in the name of Jesus Christ! By next Sunday, you will be eager to come and testify. Indeed, you will say, “See what The Lord has done”! I declare that every crying stops as you step into this week! Shame and reproach come to an end as you step into this week! For your shame, you shall receive double, in the name of Jesus Christ! #PropheticDeclarations #ApostleJoshuaSelman #WhenWePray #TheWondersOfConsistentPrayer #KoinoniaAbuja #KoinoniaZaria #KoinoniaGlobal

Koinonia Global

31,103 次观看 • 1 年前

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

codila

290,979 次观看 • 22 天前

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight

Sprytix

37,904 次观看 • 24 天前

Jordan Peterson on what to do when you don't know what you want from life: 1. Don't start with the big goal. you won't find it by staring at the horizon. look around you instead, at your direct sphere of influence, and fix the things that are obviously in need of repair. they're usually small. 2. clean your room. i know it turned into a joke online. it's harder than people think, and more useful too. the point isn't the tidy room. the point is you learn to tell chaos from order, and to act in a way that produces order. 3. ask yourself, don't tell yourself. instead of "do this," ask "what could i do today that i'd actually do, that makes tomorrow a little better than today?" it's usually some small thing, because you're not that disciplined. that's fine. 4. it'll be the toad. the thing you keep avoiding. the task that feels like a snake. that's the one. do it anyway. 5. then it compounds. you fix one thing, you get a bit stronger, the next day you take on something slightly bigger. compound interest. and at some point you stop just patching what's broken, and you catch a glimmer of something positive you could build. that's your vision. it shows up at the end, not the start.

Jordan Peterson on what to do when you don't know what you want from life: 1. Don't start with the big goal. you won't find it by staring at the horizon. look around you instead, at your direct sphere of influence, and fix the things that are obviously in need of repair. they're usually small. 2. clean your room. i know it turned into a joke online. it's harder than people think, and more useful too. the point isn't the tidy room. the point is you learn to tell chaos from order, and to act in a way that produces order. 3. ask yourself, don't tell yourself. instead of "do this," ask "what could i do today that i'd actually do, that makes tomorrow a little better than today?" it's usually some small thing, because you're not that disciplined. that's fine. 4. it'll be the toad. the thing you keep avoiding. the task that feels like a snake. that's the one. do it anyway. 5. then it compounds. you fix one thing, you get a bit stronger, the next day you take on something slightly bigger. compound interest. and at some point you stop just patching what's broken, and you catch a glimmer of something positive you could build. that's your vision. it shows up at the end, not the start.

Naruto

44,050 次观看 • 1 个月前