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.

Been using Loopit since it opened Friday. Honest Day 3 notes. Day 1: novelty. Cool outputs, shared a couple, moved on. Day 2: started actually experimenting with the physics prompts. Something clicked - the prompts that work aren't the obvious ones. Weirdly specific, almost wrong descriptions generate better mechanics... show more

Khusboo Tayal

64,731 subscribers

29,966 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture it's the clearest explanation I've seen of how ChatGPT and Claude actually work useful whether you've never touched AI in your life or have been using it every day for the past year i took the key ideas and turned them into a practical guide on how to actually get 100% out of AI you can find it below with ready-to-copy prompts and solutions

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture it's the clearest explanation I've seen of how ChatGPT and Claude actually work useful whether you've never touched AI in your life or have been using it every day for the past year i took the key ideas and turned them into a practical guide on how to actually get 100% out of AI you can find it below with ready-to-copy prompts and solutions

Anatoli Kopadze

2,768,887 views • 11 days ago

Tung Tung Tung Sahur is here!! Day 14 of building GTA 6 with a loop of AI agents. Today's progress: - Reloads in. mag drops, new one goes in, old one on the ground. - Shot effects landed. - Full of Tung Tung Tung Sahur walking around the city now We have to actually learn Unreal. if we don't, our prompts stay vague and the agents give vague results. The second we need them to generate blueprints, animation blueprints, any of that, you have to know what to ask for. The more specific i get, the better the output. Tomorrow: aiming + all the full animations on the character.

Tung Tung Tung Sahur is here!! Day 14 of building GTA 6 with a loop of AI agents. Today's progress: - Reloads in. mag drops, new one goes in, old one on the ground. - Shot effects landed. - Full of Tung Tung Tung Sahur walking around the city now We have to actually learn Unreal. if we don't, our prompts stay vague and the agents give vague results. The second we need them to generate blueprints, animation blueprints, any of that, you have to know what to ask for. The more specific i get, the better the output. Tomorrow: aiming + all the full animations on the character.

Ziwen

53,240 views • 1 month ago

Most people trying to fix AI slop keep rewriting their prompts. The actual fix looks more like onboarding a new hire. One operator described handing Claude some data for a root cause analysis. Before he'd finished reviewing it, Claude had already raced ahead and drafted a full pricing strategy doc nobody asked for. Not because the model is bad. Because it's built to please, fast, on partial information. Sound familiar? It's the exact failure mode of a sharp junior employee who hears one instruction and sprints to look impressive instead of asking what you actually need. Most people respond to this by tweaking the prompt. That's treating the symptom. The operators actually getting clean output do something different. They write the equivalent of a "how to work with me" doc, upfront, once. Ask clarifying questions before executing. Don't assume the first read of the task is the real task. Wait for the go-ahead before building anything. That single rule, stated once, does more than a hundred clever prompts. It changes what the model believes its job is: not "finish fast," but "understand first." The gap between AI users right now isn't who has better prompts. It's who's actually managing the thing instead of just talking to it. Manage it.

Most people trying to fix AI slop keep rewriting their prompts. The actual fix looks more like onboarding a new hire. One operator described handing Claude some data for a root cause analysis. Before he'd finished reviewing it, Claude had already raced ahead and drafted a full pricing strategy doc nobody asked for. Not because the model is bad. Because it's built to please, fast, on partial information. Sound familiar? It's the exact failure mode of a sharp junior employee who hears one instruction and sprints to look impressive instead of asking what you actually need. Most people respond to this by tweaking the prompt. That's treating the symptom. The operators actually getting clean output do something different. They write the equivalent of a "how to work with me" doc, upfront, once. Ask clarifying questions before executing. Don't assume the first read of the task is the real task. Wait for the go-ahead before building anything. That single rule, stated once, does more than a hundred clever prompts. It changes what the model believes its job is: not "finish fast," but "understand first." The gap between AI users right now isn't who has better prompts. It's who's actually managing the thing instead of just talking to it. Manage it.

Aakash Gupta

10,813 views • 1 month ago

This is crazy 🤯 I built an app in 10 minutes I built the distribution in 5 minutes Literally created a beautiful APP w functional navigation in 2-3 prompts And then Cooked up and AI reel to promote my new app in literally 5 minutes, Using Arcads I used to think AI UGC was cooked but.. The quality of these AI reels is insane. You can literally mass produce the reel format and post 30-60 reels/mo (then if any video gets above 5k views organically , throw it on ads) and you are on the money. im 100% serious Me and Mau have an app doing $1,000/day with just 4 winning UGC videos running on spark ads But now you can save time and money by having your UGC generated with AI We are living in the ERA of prompts a few prompts, can change your life

This is crazy 🤯 I built an app in 10 minutes I built the distribution in 5 minutes Literally created a beautiful APP w functional navigation in 2-3 prompts And then Cooked up and AI reel to promote my new app in literally 5 minutes, Using Arcads I used to think AI UGC was cooked but.. The quality of these AI reels is insane. You can literally mass produce the reel format and post 30-60 reels/mo (then if any video gets above 5k views organically , throw it on ads) and you are on the money. im 100% serious Me and Mau have an app doing $1,000/day with just 4 winning UGC videos running on spark ads But now you can save time and money by having your UGC generated with AI We are living in the ERA of prompts a few prompts, can change your life

Ernesto Lopez

50,060 views • 7 months ago

And one day, it wasn’t. It wasn’t me, and it wasn’t you. It wasn’t us against the world. It wasn’t two souls colliding, wasn’t some story meant to unfold like those Hallmark movies. We just were. Like the day before we met, strangers again, holding faint echoes of something that once tasted like hope. Like iridescent tinfoil, shiny enough to believe in, but never better than the day before we met. Do I regret it? Not even close. You were a moment that collided with mine. A moment we needed. But we never needed each other. We just thought we did. We twisted ourselves into shapes that almost fit, breaking off pieces until we couldn’t recognize our own reflections. I’m sorry for the part I played. And thank you for the good days. The ones where nothing mattered but our breathing, in sync. Thank you for holding me when no one else could hear me breaking. I love you. But only the version of you that didn’t resent me. Because one day, you won’t. One day, it will just be. #progress #gettingsoberverysoon #ilovedthisjourney #tweaker

And one day, it wasn’t. It wasn’t me, and it wasn’t you. It wasn’t us against the world. It wasn’t two souls colliding, wasn’t some story meant to unfold like those Hallmark movies. We just were. Like the day before we met, strangers again, holding faint echoes of something that once tasted like hope. Like iridescent tinfoil, shiny enough to believe in, but never better than the day before we met. Do I regret it? Not even close. You were a moment that collided with mine. A moment we needed. But we never needed each other. We just thought we did. We twisted ourselves into shapes that almost fit, breaking off pieces until we couldn’t recognize our own reflections. I’m sorry for the part I played. And thank you for the good days. The ones where nothing mattered but our breathing, in sync. Thank you for holding me when no one else could hear me breaking. I love you. But only the version of you that didn’t resent me. Because one day, you won’t. One day, it will just be. #progress #gettingsoberverysoon #ilovedthisjourney #tweaker

skyfullofglass

84,161 views • 4 months ago

This short clip is a masterclass from Mike Krzyzewski: "The very first thing is that in order to get better you change limits. And when you change limits, you're gonna look bad and you're gonna fail." Life Hack: Embrace the embarrassment of being a beginner. The only way to accomplish something meaningful is to endure days, weeks, months, or even years of embarrassing failure. Every expert started out as a beginner. Those who embrace the embarrassment will eventually win. Coach K adds: "You're not gonna get there alone. Be on a team. Surround yourself with good people, and learn how to listen." Surround yourself with people who have: 1. High Expectations: They see you for your full potential. They are willing to hold you to that standard. 2. High Support: They provide the love and tangible support to help you meet those high expectations. The combination is powerful. The concluding insight is one of his best: "I just like to work hard every day...make every day like it's my first day, but with the experience of 42 years." Lesson: Show up with the hunger of Day 1, but the knowledge and wisdom of Day 1,000. If you do that, you'll be unbeatable.

This short clip is a masterclass from Mike Krzyzewski: "The very first thing is that in order to get better you change limits. And when you change limits, you're gonna look bad and you're gonna fail." Life Hack: Embrace the embarrassment of being a beginner. The only way to accomplish something meaningful is to endure days, weeks, months, or even years of embarrassing failure. Every expert started out as a beginner. Those who embrace the embarrassment will eventually win. Coach K adds: "You're not gonna get there alone. Be on a team. Surround yourself with good people, and learn how to listen." Surround yourself with people who have: 1. High Expectations: They see you for your full potential. They are willing to hold you to that standard. 2. High Support: They provide the love and tangible support to help you meet those high expectations. The combination is powerful. The concluding insight is one of his best: "I just like to work hard every day...make every day like it's my first day, but with the experience of 42 years." Lesson: Show up with the hunger of Day 1, but the knowledge and wisdom of Day 1,000. If you do that, you'll be unbeatable.

Sahil Bloom

319,943 views • 2 years ago

“The World is Bigger than you. “ As bad of a day you are having someone is having a worse one, as hard of a job you have someone has a harder one. Use the understanding that we are merely specs in the grand scheme of this Earth, when you’re individual life feels too overwhelming. There is a freedom is knowing the world doesn’t start and stop with you, a pressure that is taken off. But on the flip its important to understand what things in your world make it: is it your loved ones, your faith, your possessions. It’s a balancing act of zooming in and zooming out. There’s something to be grateful for every step of the way if you look hard enough

“The World is Bigger than you. “ As bad of a day you are having someone is having a worse one, as hard of a job you have someone has a harder one. Use the understanding that we are merely specs in the grand scheme of this Earth, when you’re individual life feels too overwhelming. There is a freedom is knowing the world doesn’t start and stop with you, a pressure that is taken off. But on the flip its important to understand what things in your world make it: is it your loved ones, your faith, your possessions. It’s a balancing act of zooming in and zooming out. There’s something to be grateful for every step of the way if you look hard enough

Meech

14,238 views • 3 months ago

Fellow Cybertruck owners, you may want to comment with your experience, I will with mine in the reply to this post. My Cybertruck, I took delivery of on 11/04/2025, was a demo vehicle with about 500 miles on the odometer. Yes, it is a Cyberbeast, but with my previous FS CT, I drove 46,892 miles all the way to the service center on the same day I took delivery of the CT I am driving now. Tires were worn, of course but they looked still better than the ones you see in the video below. I have not been on a race track, I work from home, so the majority of miles on it are due to long distance driving. I don't do burn outs or whatever abusive behavior one can apply, my driving style has been consistently equal with both of them. When I took delivery, I was wondering a bit that the tires looked used up for only 500 miles. Long story short, here we are. The tires have been rotated as recommended every 6k miles.

Fellow Cybertruck owners, you may want to comment with your experience, I will with mine in the reply to this post. My Cybertruck, I took delivery of on 11/04/2025, was a demo vehicle with about 500 miles on the odometer. Yes, it is a Cyberbeast, but with my previous FS CT, I drove 46,892 miles all the way to the service center on the same day I took delivery of the CT I am driving now. Tires were worn, of course but they looked still better than the ones you see in the video below. I have not been on a race track, I work from home, so the majority of miles on it are due to long distance driving. I don't do burn outs or whatever abusive behavior one can apply, my driving style has been consistently equal with both of them. When I took delivery, I was wondering a bit that the tires looked used up for only 500 miles. Long story short, here we are. The tires have been rotated as recommended every 6k miles.

Andy ze German

64,089 views • 2 months ago

This week's Weekly Tokimeki Question is on reflecting on the small joys of your day! Sometimes life feels too busy to reflect on the good things that happened, but we hope this is a gentle reminder to look back at your day and appreciate even the smallest things! It can truly change your perspective on your day ✨ Try this out: 1. Take a moment to close your eyes and take a deep breath. 2. Slowly reflect on your day. What is one joy-sparking thing in your life that you want to thank? 3. Take a photo of the thing that gives you Tokimeki. 4. We'd love for you all to QRT your little joys of the day and spread Tokimeki together! We'll be compiling some of your photos in a community collage soon, so don't forget to share your little joys with us!

This week's Weekly Tokimeki Question is on reflecting on the small joys of your day! Sometimes life feels too busy to reflect on the good things that happened, but we hope this is a gentle reminder to look back at your day and appreciate even the smallest things! It can truly change your perspective on your day ✨ Try this out: 1. Take a moment to close your eyes and take a deep breath. 2. Slowly reflect on your day. What is one joy-sparking thing in your life that you want to thank? 3. Take a photo of the thing that gives you Tokimeki. 4. We'd love for you all to QRT your little joys of the day and spread Tokimeki together! We'll be compiling some of your photos in a community collage soon, so don't forget to share your little joys with us!

The Art of Tokimeki

51,574 views • 20 days ago

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 views • 1 month ago

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

Emm | scenario.com

192,765 views • 1 year ago

A student built a whole faceless passive business by creating AI backyards. I kept seeing these AI backyard builds hitting 50M views and thought it took months of editing, but I was wrong. The creators aren't starting with a dirt lot. They start with the perfect final image and make the AI work backward. And the secret is stupidly simple: generate the final picture first, and let the AI reverse-engineer it. Here is the exact 3-step system you can use to build this: - The Blueprint: Upload your finished backyard to the "Restoration Timelapse" GPT. It reverse-engineers the final image into text prompts for the empty lot. - The Setup: Paste those prompts into Dzine. This generates your "before" images with perfectly matched geometry. - The Animation: Upload your empty lot and finished yard into Kling 3.0 to animate the build. Once Kling spits out the video file, drop it into CapCut, keep the raw construction audio, and export. I broke down the complete, step-by-step architecture with GPT + GROK + CAPCUT in my full guide below 👇

A student built a whole faceless passive business by creating AI backyards. I kept seeing these AI backyard builds hitting 50M views and thought it took months of editing, but I was wrong. The creators aren't starting with a dirt lot. They start with the perfect final image and make the AI work backward. And the secret is stupidly simple: generate the final picture first, and let the AI reverse-engineer it. Here is the exact 3-step system you can use to build this: - The Blueprint: Upload your finished backyard to the "Restoration Timelapse" GPT. It reverse-engineers the final image into text prompts for the empty lot. - The Setup: Paste those prompts into Dzine. This generates your "before" images with perfectly matched geometry. - The Animation: Upload your empty lot and finished yard into Kling 3.0 to animate the build. Once Kling spits out the video file, drop it into CapCut, keep the raw construction audio, and export. I broke down the complete, step-by-step architecture with GPT + GROK + CAPCUT in my full guide below 👇

Spivach

17,421 views • 2 months ago

One of the toughest parts of being a founder is putting your ideas into the world, seeing if anyone cares (usually they don't - or worse, are rooting against you), and then seeing if you can actually pull it off (usually way more setbacks along the way than you thought!). You have to: (1) develop thick skin and find a way to ignore the haters (2) still take advice from people who have your best interests at heart (3) have the wisdom to know the difference Then move from one setback to the next with no loss of enthusiasm for longer than you thought. Be borderline delusional, get after it every day for a decade, and turn out to be right. Finally, when your tenth or hundredth approach to a problem doesn't work, just keep coming up with more ideas. Had a great day at Base Batches yesterday, meeting founders building on Base and hearing about the latest onchain innovations. Shout out to all the founders!

One of the toughest parts of being a founder is putting your ideas into the world, seeing if anyone cares (usually they don't - or worse, are rooting against you), and then seeing if you can actually pull it off (usually way more setbacks along the way than you thought!). You have to: (1) develop thick skin and find a way to ignore the haters (2) still take advice from people who have your best interests at heart (3) have the wisdom to know the difference Then move from one setback to the next with no loss of enthusiasm for longer than you thought. Be borderline delusional, get after it every day for a decade, and turn out to be right. Finally, when your tenth or hundredth approach to a problem doesn't work, just keep coming up with more ideas. Had a great day at Base Batches yesterday, meeting founders building on Base and hearing about the latest onchain innovations. Shout out to all the founders!

Brian Armstrong

93,160 views • 2 months ago

cwjltma performance behind 🐰 i have a funny story, after day 1 got over, me, taehyun and beomgyu were eating dinner together 🐿️ 😭😭😭 THAT WAS SO UNFAIR TO ME 🐰 during cwjltma, the move starts on the right side but that day, taehyun made a mistake in the center so after that, me and beomgyu went “taehyun, you have to start from the left” and we told him to do it that way 🐰 on day 2, i realized that it starts from the right side and i was doing it on the right side from habit but this guy started from the left 🐿️ even right before we went on, i was telling myself to do it like “left side left side left side” 🧸 that’s why on day 2…i hadn’t really thought about it, i was just doing it according to muscle memory so i was like “huh i told taehyun it starts from the left so why does it feel so comfortable starting from the right side…” so during verse 2, i remembered telling taehyun to start from the left so i started from the left side too and i looked to the side and me & taehyun were the only ones starting from the left side and everyone else was starting from the right 🐰 the cutest freaking thing about taehyun was that, because he was getting confused with the right and left side, he just did it in the center on day 1 🐿️ it wouldn’t have been obvious since i was in the center so i just did it like that 🦊 so on day 1, you didn’t make an obvious mistake but on day 2, you made an obvious mistake 🐿️ yeah, i got it right today 🧸 after i finished, i was like “taehyun, it was the right side” 🐧 you should’ve talked to this hyung (🦊) 🐿️ our performance direction team was there yesterday and i was out of stamina so i didn’t understand what you said, i thought you said “taehyun, you did well” but then the pd team came up to me and went “was cwjltma a symmetrical choreography???” ⭐️ 😭😭😭 🐿️ and i was like “no it wasn’t???” 🦊 you asked the wrong people 🐧 you should’ve asked this guy 🧸 you should’ve asked the right person 🤣

cwjltma performance behind 🐰 i have a funny story, after day 1 got over, me, taehyun and beomgyu were eating dinner together 🐿️ 😭😭😭 THAT WAS SO UNFAIR TO ME 🐰 during cwjltma, the move starts on the right side but that day, taehyun made a mistake in the center so after that, me and beomgyu went “taehyun, you have to start from the left” and we told him to do it that way 🐰 on day 2, i realized that it starts from the right side and i was doing it on the right side from habit but this guy started from the left 🐿️ even right before we went on, i was telling myself to do it like “left side left side left side” 🧸 that’s why on day 2…i hadn’t really thought about it, i was just doing it according to muscle memory so i was like “huh i told taehyun it starts from the left so why does it feel so comfortable starting from the right side…” so during verse 2, i remembered telling taehyun to start from the left so i started from the left side too and i looked to the side and me & taehyun were the only ones starting from the left side and everyone else was starting from the right 🐰 the cutest freaking thing about taehyun was that, because he was getting confused with the right and left side, he just did it in the center on day 1 🐿️ it wouldn’t have been obvious since i was in the center so i just did it like that 🦊 so on day 1, you didn’t make an obvious mistake but on day 2, you made an obvious mistake 🐿️ yeah, i got it right today 🧸 after i finished, i was like “taehyun, it was the right side” 🐧 you should’ve talked to this hyung (🦊) 🐿️ our performance direction team was there yesterday and i was out of stamina so i didn’t understand what you said, i thought you said “taehyun, you did well” but then the pd team came up to me and went “was cwjltma a symmetrical choreography???” ⭐️ 😭😭😭 🐿️ and i was like “no it wasn’t???” 🦊 you asked the wrong people 🐧 you should’ve asked this guy 🧸 you should’ve asked the right person 🤣

💬

136,175 views • 5 months ago

Six months ago you could generate almost anything with AI image and video tools. That window is closing fast. A creator recently stress-tested Nano Banana Pro, Kling, and Seedance 2.0 on this RISKY video project. Midway through production, Seedance 2.0 tightened its filters so aggressively that outputs it generated days earlier were suddenly blocked. Same prompts. Same workflow. Different results overnight. They had to fall back to older APIs and manual image-to-video seeding just to maintain visual consistency across the project. This is happening across every major model. Filters get stricter after launch, not before. The capabilities you test on day one aren't guaranteed on day thirty. If you're building any creative workflow around AI generation tools, you need to know this: the models you're relying on today are not the same models you'll have access to next quarter. Document your workflows. Save your outputs. And stop assuming the tools will stay as open as they are right now.

Six months ago you could generate almost anything with AI image and video tools. That window is closing fast. A creator recently stress-tested Nano Banana Pro, Kling, and Seedance 2.0 on this RISKY video project. Midway through production, Seedance 2.0 tightened its filters so aggressively that outputs it generated days earlier were suddenly blocked. Same prompts. Same workflow. Different results overnight. They had to fall back to older APIs and manual image-to-video seeding just to maintain visual consistency across the project. This is happening across every major model. Filters get stricter after launch, not before. The capabilities you test on day one aren't guaranteed on day thirty. If you're building any creative workflow around AI generation tools, you need to know this: the models you're relying on today are not the same models you'll have access to next quarter. Document your workflows. Save your outputs. And stop assuming the tools will stay as open as they are right now.

Alex Prompter

22,305 views • 2 months ago

Over the past 6 weeks, I've automated dozens of hours of grunt, repetitive work. Every Friday, I spend a few minutes writing down everything I do more than once during the week: 1. I automate what I can automate 2. I improve what I can't automate Two levels of unlock here: 1. Start using voice 2. Start using voice-to-action agents The team reached out to partner with me. I've been testing them, and this is precisely what they do. First, if you are still typing your prompts, stop. Start using voice. Go from typing to dictation on your computer. This alone will save you hours every year. Second, move from asking questions to using an agent that automates tasks for you. Lemon is a VOICE-TO-ACTION agent (instead of a voice-to-text model): • You press a button • You say what you need • Lemon executes the task in whatever app you are using Lemon works across Mac apps, so you can drive them all with your voice. Lemon is currently free. 100% worth trying.

Over the past 6 weeks, I've automated dozens of hours of grunt, repetitive work. Every Friday, I spend a few minutes writing down everything I do more than once during the week: 1. I automate what I can automate 2. I improve what I can't automate Two levels of unlock here: 1. Start using voice 2. Start using voice-to-action agents The team reached out to partner with me. I've been testing them, and this is precisely what they do. First, if you are still typing your prompts, stop. Start using voice. Go from typing to dictation on your computer. This alone will save you hours every year. Second, move from asking questions to using an agent that automates tasks for you. Lemon is a VOICE-TO-ACTION agent (instead of a voice-to-text model): • You press a button • You say what you need • Lemon executes the task in whatever app you are using Lemon works across Mac apps, so you can drive them all with your voice. Lemon is currently free. 100% worth trying.

Santiago

20,566 views • 5 months ago

This guy started the day with just twenty bucks, hoping to flip something into $500 by sunset. He went to the thrift store looking for furniture, but didn’t find anything worth buying. Luckily, he came across a free vintage TV on Facebook Marketplace and decided to turn it into a cat bed instead. What followed was a full day of sanding, painting, staining, fixing a broken leg, and giving the whole piece a fresh makeover. In the end, he didn’t hit his money goal — but he created a really cool retro-style cat bed. Instead of selling it, he decided to give it to some friends as a housewarming gift, and their cat immediately claimed it. Have you ever started a project with one goal in mind and ended up with something even better than you planned?

This guy started the day with just twenty bucks, hoping to flip something into $500 by sunset. He went to the thrift store looking for furniture, but didn’t find anything worth buying. Luckily, he came across a free vintage TV on Facebook Marketplace and decided to turn it into a cat bed instead. What followed was a full day of sanding, painting, staining, fixing a broken leg, and giving the whole piece a fresh makeover. In the end, he didn’t hit his money goal — but he created a really cool retro-style cat bed. Instead of selling it, he decided to give it to some friends as a housewarming gift, and their cat immediately claimed it. Have you ever started a project with one goal in mind and ended up with something even better than you planned?

End3of6Days9 (Helen) 🇺🇸

374,134 views • 2 months ago

How to setup some Scaffolding using AI tools..... I'm calling scaffolding the barebones that will speed up the developer on your team. Some notes: * I'm not a coder. * I'm not Gen Z so I don't like appearing on camera. * You might be able to hear my grandfather in the background rummaging through office supplies, but you should still be able to hear everything/see the prompts...try them for yourself. * Hopefully it helps some of you get closer to using AI tools in your day to day life. * This is ideal for someone who has a software developer on their team and has avoided becoming a programmer but has ideas of what they want to build or which customers they want to target. * Get the and pro versions to get the most out of this. (Full disclosure - I collab with the rollout crew.) If you found it productive, I plan on producing a few more behind my subscription wall. Hat tip to Yash Bhardwaj for dragging me into AI tools. Give him a follow and give this tweet a like if you found it remotely useful.

How to setup some Scaffolding using AI tools..... I'm calling scaffolding the barebones that will speed up the developer on your team. Some notes: * I'm not a coder. * I'm not Gen Z so I don't like appearing on camera. * You might be able to hear my grandfather in the background rummaging through office supplies, but you should still be able to hear everything/see the prompts...try them for yourself. * Hopefully it helps some of you get closer to using AI tools in your day to day life. * This is ideal for someone who has a software developer on their team and has avoided becoming a programmer but has ideas of what they want to build or which customers they want to target. * Get the and pro versions to get the most out of this. (Full disclosure - I collab with the rollout crew.) If you found it productive, I plan on producing a few more behind my subscription wall. Hat tip to Yash Bhardwaj for dragging me into AI tools. Give him a follow and give this tweet a like if you found it remotely useful.

Kumar🇺🇸

12,827 views • 1 year ago

⚡ My first advanced simulation with Grok 3! Finally your OS windows act like REAL windows 🤣 As you know, I've spent more than 2 years sharing all kinds of simulations and mini-games made with Claude, ChatGPT (o3-mini-high), etc. It’s been ages since I last wrote a single line of code. But pretty often, once you hit over 1,000 lines, it turns into a debate against the LLM and you frequently get stuck in a loop that’s hard to break out of. Everyone was raving about Grok 3’s ability to generate code, but until now, I hadn’t really put it to the test. So I decided to challenge it with a prompt that both ChatGPT and Claude were seriously struggling with (debate loop). The initial prompt was: "Use Python and a 2D physics library to create a world where I can generate different static objects like squares, triangles, circles and rectangles. I should be able to move them with the mouse, rotate, scale, and delete them. The cool part is that we’ll see this world through 1 to N operating system windows. In other words, the windows will be like real windows! When one of these windows is active and I hit the spacebar, balls affected by physics should appear and interact with the static objects. You can start with placeholders, but later I'll send you a series of PNG images so they all become beautiful sprites." After a few iterations, I got the result you see in the video. Insane, right? 🤯 Now, with Grok, we have the power to create anything that pops into our mind with just a couple of prompts. It’s mind blowing. Ever since I was 9 and messing around with BASIC on my MSX, I've been hooked on visual simulations... And now I can create them using nothing but natural language. It's f***** amazing that we're living in this historic moment!

⚡ My first advanced simulation with Grok 3! Finally your OS windows act like REAL windows 🤣 As you know, I've spent more than 2 years sharing all kinds of simulations and mini-games made with Claude, ChatGPT (o3-mini-high), etc. It’s been ages since I last wrote a single line of code. But pretty often, once you hit over 1,000 lines, it turns into a debate against the LLM and you frequently get stuck in a loop that’s hard to break out of. Everyone was raving about Grok 3’s ability to generate code, but until now, I hadn’t really put it to the test. So I decided to challenge it with a prompt that both ChatGPT and Claude were seriously struggling with (debate loop). The initial prompt was: "Use Python and a 2D physics library to create a world where I can generate different static objects like squares, triangles, circles and rectangles. I should be able to move them with the mouse, rotate, scale, and delete them. The cool part is that we’ll see this world through 1 to N operating system windows. In other words, the windows will be like real windows! When one of these windows is active and I hit the spacebar, balls affected by physics should appear and interact with the static objects. You can start with placeholders, but later I'll send you a series of PNG images so they all become beautiful sprites." After a few iterations, I got the result you see in the video. Insane, right? 🤯 Now, with Grok, we have the power to create anything that pops into our mind with just a couple of prompts. It’s mind blowing. Ever since I was 9 and messing around with BASIC on my MSX, I've been hooked on visual simulations... And now I can create them using nothing but natural language. It's f***** amazing that we're living in this historic moment!

Javi Lopez ⛩️

209,470 views • 1 year ago