正在加载视频...

视频加载失败

返回首页

Engineering through destruction! 🔨 Dyson's testing philosophy: break it until it fails, then rebuild it better. Here's what that actually means in practice: vacuum batteries go through 1,200 charge/discharge cycles, the Supersonic hair dryer cable gets wrapped and unwrapped 7,800 times, Corrale straightener plates open and close 400,000 times,...

lukas_m_ziegler's profile picture

Lukas Ziegler

55,366 subscribers

279,898 次观看 • 4 个月前 •via X (Twitter)

教育科学技术
LIVE

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

Jerome Bettis shares the 4 things that get you to greatness. 1. Sacrifice - "You've got to have the ability to sacrifice, and a lot of times that means sacrificing the relationships that mean the most to you." Greatness costs something. Are you willing to pay the price? 2. Pain - "You're going to have to endure some type of pain in your life, whether physical or mental. You've got to find a way to endure." Pain is part of the process. You don't avoid it - you push through it. 3. Failure - "You've got to have the ability to understand that you're going to fail, but it's how you recover that makes you a better person." Failure isn't the end. It's the teacher. 4. Love - "If you love it, then it's not a job - it's a passion. If you love it, you're willing to sacrifice for it, you're willing to go through all type of pains for it. You're willing to go through that failure and understand, 'I will be successful.'" Love is what makes the sacrifice, pain, and failure worth it. "If you go through those 4 things and you understand those and you can handle those then success is in your path, and greatness is available to you." Greatness requires you to show up and take action consistently. (🎥 NFL)
1:27

Jerome Bettis shares the 4 things that get you to greatness. 1. Sacrifice - "You've got to have the ability to sacrifice, and a lot of times that means sacrificing the relationships that mean the most to you." Greatness costs something. Are you willing to pay the price? 2. Pain - "You're going to have to endure some type of pain in your life, whether physical or mental. You've got to find a way to endure." Pain is part of the process. You don't avoid it - you push through it. 3. Failure - "You've got to have the ability to understand that you're going to fail, but it's how you recover that makes you a better person." Failure isn't the end. It's the teacher. 4. Love - "If you love it, then it's not a job - it's a passion. If you love it, you're willing to sacrifice for it, you're willing to go through all type of pains for it. You're willing to go through that failure and understand, 'I will be successful.'" Love is what makes the sacrifice, pain, and failure worth it. "If you go through those 4 things and you understand those and you can handle those then success is in your path, and greatness is available to you." Greatness requires you to show up and take action consistently. (🎥 NFL)

Coach AJ 🎯 Mental Fitness

12,356 次观看 • 2 个月前

James Dyson’s advice for founders: “You have to enjoy failure” “If you are exploring new territory, experimenting, and trying to do something different, you’re going to fail many times and you’ve got to bounce back from it,” James Dyson explains. The billionaire inventor argues that you should actually learn to enjoy failure: “Failure is so much more interesting than success — the reason something goes wrong is often very interesting whereas if works you just say ‘great that works’ and don’t even stop to wonder why it works. You’ve got to learn to enjoy failure. That sounds like a difficult thing to do, but you have to enjoy failure if you want to improve things.” He continues: “It always saddens me that school doesn’t really teach that. At school or university, the thing is to be brilliant and get the answer right the first time. There are brilliant people who can do that, but for the rest of us, we’re not brilliant and to get there we have to strive and go through failure. You don’t get it right the first time. You don’t get it right the second time. In my case, and I counted it, it was 5,127 times . . . That sounds like struggle and it was a struggle, but it was a hugely enjoyable struggle. The debt was mounting, and I had three children, a wife, a home, and a mortgage to pay like everybody else, but I had a real aim in life and I had to get there. And the failures were interesting because I learned from almost every single one of them.” James Dyson concludes his autobiography by saying: "Listen, it's easy for me to celebrate my doggedness now. I made $300 million last year, but I'd be lying to you if there weren't times where I went inside my house, had my wife look at me like I'm a failure, and cry myself to sleep. I got up and did it again anyway because excellence is the capacity to take pain.” Video source: David Senra (2025)
1:39

James Dyson’s advice for founders: “You have to enjoy failure” “If you are exploring new territory, experimenting, and trying to do something different, you’re going to fail many times and you’ve got to bounce back from it,” James Dyson explains. The billionaire inventor argues that you should actually learn to enjoy failure: “Failure is so much more interesting than success — the reason something goes wrong is often very interesting whereas if works you just say ‘great that works’ and don’t even stop to wonder why it works. You’ve got to learn to enjoy failure. That sounds like a difficult thing to do, but you have to enjoy failure if you want to improve things.” He continues: “It always saddens me that school doesn’t really teach that. At school or university, the thing is to be brilliant and get the answer right the first time. There are brilliant people who can do that, but for the rest of us, we’re not brilliant and to get there we have to strive and go through failure. You don’t get it right the first time. You don’t get it right the second time. In my case, and I counted it, it was 5,127 times . . . That sounds like struggle and it was a struggle, but it was a hugely enjoyable struggle. The debt was mounting, and I had three children, a wife, a home, and a mortgage to pay like everybody else, but I had a real aim in life and I had to get there. And the failures were interesting because I learned from almost every single one of them.” James Dyson concludes his autobiography by saying: "Listen, it's easy for me to celebrate my doggedness now. I made $300 million last year, but I'd be lying to you if there weren't times where I went inside my house, had my wife look at me like I'm a failure, and cry myself to sleep. I got up and did it again anyway because excellence is the capacity to take pain.” Video source: David Senra (2025)

Startup Archive

14,413 次观看 • 4 个月前

Derek Jeter shares a truth about failure that most people don't want to hear. "Failure is essential. If I can promise you one thing for certain, you will fail. I wouldn't have had the success without the failures." Failure isn't the opposite of success - it's part of the path to it. Successful people don't avoid adversity. They expect it. They know that they must learn from the setbacks and challenges. You can't avoid failure - you have to be relentless in your pursuits and refuse to let it stop you. Failure isn't a destination - it's a checkpoint. It's where growth begins. (🎥 MLive)
1:08

Derek Jeter shares a truth about failure that most people don't want to hear. "Failure is essential. If I can promise you one thing for certain, you will fail. I wouldn't have had the success without the failures." Failure isn't the opposite of success - it's part of the path to it. Successful people don't avoid adversity. They expect it. They know that they must learn from the setbacks and challenges. You can't avoid failure - you have to be relentless in your pursuits and refuse to let it stop you. Failure isn't a destination - it's a checkpoint. It's where growth begins. (🎥 MLive)

Coach AJ 🎯 Mental Fitness

103,870 次观看 • 5 个月前

John Ternus, Apple's SVP of Hardware Engineering, explains why Apple deliberately made the iPhone harder to repair, and why the math says it was worth it: In a conversation with MKBHD, John frames the design challenge by asking you to imagine two extremes: "Sometimes for me I find it helpful to kind of think about the book ends. Like if you imagine a product that never fails, right? That just doesn't fail. And on the other end, a product that maybe isn't very reliable but is super easy to repair." His position is clear: "Product that never fails is obviously better for the customer. It's better for the environment." When pushed on whether infinite repairability and infinite durability have to be mutually exclusive, John acknowledges they aren't always, but explains why the tension is real, using the iPhone battery as an example. Batteries wear out. If you want to extend the life of the product, they need to be replaced. But in the early days of iPhone, one of the most common failures wasn't the battery, it was water: "Where you drop it in the pool or you, you know, spill your drink on it and the unit fails. And so, we've been making strides over all those years to get better and better and better in terms of minimizing those failures." That work led Apple to an IP68 rating, the point where customers fish their phones out of lakes after two weeks and find them still working. But there was a cost to achieving that level of durability: "To get the product there, you've got to design a lot of seals, adhesives, other things to make it perform that way, which makes it a little harder to do that battery repair." That's the deliberate tradeoff. Apple chose tighter seals and stronger adhesives, knowing it would make battery replacement more difficult, because the reliability gains were worth it. John argues the math backs this decision: "It's objectively better for the customer to have that reliability and it's ultimately better for the planet because the failure rates since we got to that point have just dropped. It's plummeted, right? The number of repairs that need to happen and every time you're doing a repair, you're bringing in new materials to replace whatever broke." His conclusion reframes the entire repairability debate: "You can actually do the math and figure out there's a threshold at which if I can make it this durable, then it's better to have it a little bit harder to repair because it's going to net out."
2:27

John Ternus, Apple's SVP of Hardware Engineering, explains why Apple deliberately made the iPhone harder to repair, and why the math says it was worth it: In a conversation with MKBHD, John frames the design challenge by asking you to imagine two extremes: "Sometimes for me I find it helpful to kind of think about the book ends. Like if you imagine a product that never fails, right? That just doesn't fail. And on the other end, a product that maybe isn't very reliable but is super easy to repair." His position is clear: "Product that never fails is obviously better for the customer. It's better for the environment." When pushed on whether infinite repairability and infinite durability have to be mutually exclusive, John acknowledges they aren't always, but explains why the tension is real, using the iPhone battery as an example. Batteries wear out. If you want to extend the life of the product, they need to be replaced. But in the early days of iPhone, one of the most common failures wasn't the battery, it was water: "Where you drop it in the pool or you, you know, spill your drink on it and the unit fails. And so, we've been making strides over all those years to get better and better and better in terms of minimizing those failures." That work led Apple to an IP68 rating, the point where customers fish their phones out of lakes after two weeks and find them still working. But there was a cost to achieving that level of durability: "To get the product there, you've got to design a lot of seals, adhesives, other things to make it perform that way, which makes it a little harder to do that battery repair." That's the deliberate tradeoff. Apple chose tighter seals and stronger adhesives, knowing it would make battery replacement more difficult, because the reliability gains were worth it. John argues the math backs this decision: "It's objectively better for the customer to have that reliability and it's ultimately better for the planet because the failure rates since we got to that point have just dropped. It's plummeted, right? The number of repairs that need to happen and every time you're doing a repair, you're bringing in new materials to replace whatever broke." His conclusion reframes the entire repairability debate: "You can actually do the math and figure out there's a threshold at which if I can make it this durable, then it's better to have it a little bit harder to repair because it's going to net out."

Big Brain Business

384,726 次观看 • 1 个月前

Sam Darnold shares how "failure" became the foundation of his comeback. "You have to embrace failure and you have to learn from your mistakes." Most people run from failure. Successful people know that adversity is inevitable. "Learning from my mistakes early in my career, I feel like, has gotten me to this point." Darnold was the 3rd overall pick. Then came the struggles - the turnovers, the losses, and being cut. "Every time you fail or you lose a game or you don't do exactly what you want to do on every single play - you learn from that." Failure isn't final - it's feedback. Combat unhealthy beliefs about yourself and believe that change is possible. "As long as you learn from it, you can always look ahead to better things and not making the same mistake twice." The most resilient people cultivate resilience over time. The most resilient people accept that sh** happens. They own what they can and focus on what they control. (🎥Seattle Seahawks )
0:32

Sam Darnold shares how "failure" became the foundation of his comeback. "You have to embrace failure and you have to learn from your mistakes." Most people run from failure. Successful people know that adversity is inevitable. "Learning from my mistakes early in my career, I feel like, has gotten me to this point." Darnold was the 3rd overall pick. Then came the struggles - the turnovers, the losses, and being cut. "Every time you fail or you lose a game or you don't do exactly what you want to do on every single play - you learn from that." Failure isn't final - it's feedback. Combat unhealthy beliefs about yourself and believe that change is possible. "As long as you learn from it, you can always look ahead to better things and not making the same mistake twice." The most resilient people cultivate resilience over time. The most resilient people accept that sh** happens. They own what they can and focus on what they control. (🎥Seattle Seahawks )

Coach AJ 🎯 Mental Fitness

45,445 次观看 • 4 个月前

The vlog from Pollen Robotics is out! A fantastic visit in Bordeaux to see myself one of the only European humanoids companies. I visited their HQ and saw how they build and test robots. It's great to see the open source approach that is getting more and more people involved in robotics. True democratization of robotics (thanks clem 🤗, and Hugging Face)! Here's the link to the vlog: Thanks for such a warm welcome Reachy team!💛 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:30

The vlog from Pollen Robotics is out! A fantastic visit in Bordeaux to see myself one of the only European humanoids companies. I visited their HQ and saw how they build and test robots. It's great to see the open source approach that is getting more and more people involved in robotics. True democratization of robotics (thanks clem 🤗, and Hugging Face)! Here's the link to the vlog: Thanks for such a warm welcome Reachy team!💛 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

10,353 次观看 • 5 个月前

From Eric Vishria on how the top AI founders are building products completely opposite of the SaaS era: "One of the things that is really different in the AI world versus the SaaS world, is that in the SaaS world, over and over again, you had people who really understood the customer. And the problem. And then they understood a domain. They understood what the technology was more or less capable of. But it wasn't a real question of if you could build something or not. For example, take Salesforce, Workday, and ServiceNow. CRM existed before Salesforce. HR management existed before Workday. Same thing with ServiceNow. So in every case, Salesforce followed Siebel. Workday followed Peoplesoft. ServiceNow followed Peregrine and Remedy, and others. So they were just kind of, cloud SaaS versions of the prior generation product. They just understood the customers. They understood the problem. And they were just like, here's a better version. And that evolved a little bit over time in SaaS land. But that's what it is. And so product development in that way was done by people who really understood the customer and the problems. And then just took advantage of the next wave. And this is almost diametrically opposite of product development in the AI era. When I look at the teams that are having the most success today, they have intimate knowledge of the models. They are right on the frontier of understanding which models are better at what, and why, and when. And what they're going to be good at and what they're not going to be good at. And what they're spending their time on, is figuring out how do I apply this capability of this model to this domain or to this user. So they're actually working inside out or technology out, versus customer problem in. And of course, they understand the customer problem. And a lot of times they have firsthand knowledge of it. But they're really close to the metal and capability, and they're applying it. And I think this is a really different way to develop products than in SaaS. I started my career as a product manager a long time ago, and it's almost the complete opposite of everything you learned. "Listen to the customer, understand it, then bring it back to the engineering and product teams." If you did that right now, ask a bunch of customers what they want out of AI, and you brought it back, for the most part, it may not be possible today with today's technology. Whereas the teams that are winning right now really understand the technology and are applying it out. And so I think this reversal matters. I think it's a big difference in terms of how companies are getting built. And maybe even the types of entrepreneurs that will be successful. I'm not sure. You're seeing some real change there. Look at the Bret Taylor's at Sierra. That's a super, super technical founder who really gets it. Brett and Clay really get it. You look at Michael and his co-founders at Cursor. They're super technical founders and they get it. They all really understand what these things can and can't do. And that's a pretty different dynamic relative to the way the best SaaS companies got built." Link in bio for the full conversation going deep on the current class of startups going from zero to $100m+ in ARR within 12 months.
5:13

From Eric Vishria on how the top AI founders are building products completely opposite of the SaaS era: "One of the things that is really different in the AI world versus the SaaS world, is that in the SaaS world, over and over again, you had people who really understood the customer. And the problem. And then they understood a domain. They understood what the technology was more or less capable of. But it wasn't a real question of if you could build something or not. For example, take Salesforce, Workday, and ServiceNow. CRM existed before Salesforce. HR management existed before Workday. Same thing with ServiceNow. So in every case, Salesforce followed Siebel. Workday followed Peoplesoft. ServiceNow followed Peregrine and Remedy, and others. So they were just kind of, cloud SaaS versions of the prior generation product. They just understood the customers. They understood the problem. And they were just like, here's a better version. And that evolved a little bit over time in SaaS land. But that's what it is. And so product development in that way was done by people who really understood the customer and the problems. And then just took advantage of the next wave. And this is almost diametrically opposite of product development in the AI era. When I look at the teams that are having the most success today, they have intimate knowledge of the models. They are right on the frontier of understanding which models are better at what, and why, and when. And what they're going to be good at and what they're not going to be good at. And what they're spending their time on, is figuring out how do I apply this capability of this model to this domain or to this user. So they're actually working inside out or technology out, versus customer problem in. And of course, they understand the customer problem. And a lot of times they have firsthand knowledge of it. But they're really close to the metal and capability, and they're applying it. And I think this is a really different way to develop products than in SaaS. I started my career as a product manager a long time ago, and it's almost the complete opposite of everything you learned. "Listen to the customer, understand it, then bring it back to the engineering and product teams." If you did that right now, ask a bunch of customers what they want out of AI, and you brought it back, for the most part, it may not be possible today with today's technology. Whereas the teams that are winning right now really understand the technology and are applying it out. And so I think this reversal matters. I think it's a big difference in terms of how companies are getting built. And maybe even the types of entrepreneurs that will be successful. I'm not sure. You're seeing some real change there. Look at the Bret Taylor's at Sierra. That's a super, super technical founder who really gets it. Brett and Clay really get it. You look at Michael and his co-founders at Cursor. They're super technical founders and they get it. They all really understand what these things can and can't do. And that's a pretty different dynamic relative to the way the best SaaS companies got built." Link in bio for the full conversation going deep on the current class of startups going from zero to $100m+ in ARR within 12 months.

The Peel

209,320 次观看 • 1 年前

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.
4:15

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,118 次观看 • 5 天前

Haters: "You can't launch 100 satellites - you’re self-funded." Us: We don't have to. Through our IRL events, we’ve come across a lot of haters. What they fail to do is understand what we are truly building. Satellite costs have dropped 90%+. That’s why we’re able to research and develop our own proprietary satellites to launch and test. Then, we plan to open-source the satellite designs and combine that with building our open network. This means that any operator can join, launch, and earn fees by running data through their nodes. We're not trying to own the sky. We're building the protocol that decentralizes it. Anything's crazy… until it works. Witness it ⬇️
2:39

Haters: "You can't launch 100 satellites - you’re self-funded." Us: We don't have to. Through our IRL events, we’ve come across a lot of haters. What they fail to do is understand what we are truly building. Satellite costs have dropped 90%+. That’s why we’re able to research and develop our own proprietary satellites to launch and test. Then, we plan to open-source the satellite designs and combine that with building our open network. This means that any operator can join, launch, and earn fees by running data through their nodes. We're not trying to own the sky. We're building the protocol that decentralizes it. Anything's crazy… until it works. Witness it ⬇️

Spacecoin™ 🛰️

331,422 次观看 • 5 个月前

Dyson has a factory in Malaysia that runs 24 hours a day and puts its vacuums through “relentless testing”. Each device goes through 150 tests including: ▫️Dropping 100x from 1 meter high ▫️Vacuuming 750 miles of surface ▫️Running motor non-stop until it dies How long does it take? The typical testing cycle is ~600 hours. Few manufacturers — outside of auto and aerospace — are this rigorous. This exacting process has been done on over 20 million Dyson units sold (the company now does $7B+ a year). It’s also objectively one of the funniest things you’ll ever see.
1:09

Dyson has a factory in Malaysia that runs 24 hours a day and puts its vacuums through “relentless testing”. Each device goes through 150 tests including: ▫️Dropping 100x from 1 meter high ▫️Vacuuming 750 miles of surface ▫️Running motor non-stop until it dies How long does it take? The typical testing cycle is ~600 hours. Few manufacturers — outside of auto and aerospace — are this rigorous. This exacting process has been done on over 20 million Dyson units sold (the company now does $7B+ a year). It’s also objectively one of the funniest things you’ll ever see.

Trung Phan

1,885,013 次观看 • 2 年前

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch
35:25

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

191,430 次观看 • 2 个月前

"It's a superhero movie that is for adults and has adult ideas in it. You don't have to think about it any harder than that. It goes way deeper. If you want to, you can tear it apart like a giant onion and keep peeling it until you're at its core. "But I think that it's cool to experience it just like when I read the comic book for the first time and I didn't know. No one was telling me what it's about or the why of it. You come to it fresh. And sometimes I wish I had that experience because I would love to see the movie or read the book for the first time again because that feeling was for me awesome. "Especially when you go into something with this anticipation that it's just a Hollywood superhero movie which is what a lot of people will think because they don't know. They see some guys fighting and then when you see the film you actually have this experience of it being taken apart. "Those archetypes, those mythological shapes, whether they be Batman or Superman or any of superheroes and how they're just turned around. Whether it's through sexual fetish or fighting, actually killing guys they fight. "Stuff like that or whether it's the end of the movie and there's this moral dilemma that is the end of the movie is also challenging on all those levels."
1:38

"It's a superhero movie that is for adults and has adult ideas in it. You don't have to think about it any harder than that. It goes way deeper. If you want to, you can tear it apart like a giant onion and keep peeling it until you're at its core. "But I think that it's cool to experience it just like when I read the comic book for the first time and I didn't know. No one was telling me what it's about or the why of it. You come to it fresh. And sometimes I wish I had that experience because I would love to see the movie or read the book for the first time again because that feeling was for me awesome. "Especially when you go into something with this anticipation that it's just a Hollywood superhero movie which is what a lot of people will think because they don't know. They see some guys fighting and then when you see the film you actually have this experience of it being taken apart. "Those archetypes, those mythological shapes, whether they be Batman or Superman or any of superheroes and how they're just turned around. Whether it's through sexual fetish or fighting, actually killing guys they fight. "Stuff like that or whether it's the end of the movie and there's this moral dilemma that is the end of the movie is also challenging on all those levels."

Zack Snyder Film

22,225 次观看 • 4 个月前

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:36

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

19,433 次观看 • 5 个月前

Rich Roll on why waiting to "feel like it" is a trap: "You can't think your way into the mood that you seek or the state of mind that you aspire to inhabit. Action is the only thing that can trigger that change." Rich uses running as the perfect illustration of this principle. Imagine you wake up in the morning and you're supposed to do a run because you're training for a race. You don't feel like it. So what do most of us do? "We all resort to that state where we think, 'Well, I don't want to do it right now. I'll just wait until I feel like doing it and then I'll do it then.'" But here's the problem with that logic: "If you're waiting until you feel like doing something, chances are you're probably never going to get to it." The mood you're hoping will arrive on its own? It's not coming. Not without action first. "To take the action despite how you feel about it is the thing that catalyzes the state change." You don't run because you feel motivated. You feel motivated because you ran. He points to what every runner knows from experience: "When they finish the run, they're always glad that they did it. They don't generally regret it. And then they feel better." Notice the sequence. The good feeling comes after the action, not before it. The state change is the reward for showing up, not the prerequisite. And this isn't just about running. As Rich puts it: "That example is applicable to all areas of life." The workout you're avoiding. The conversation you're delaying. The project you're putting off until you're "in the right headspace." You're waiting for a feeling that only exists on the other side of doing the thing.
0:59

Rich Roll on why waiting to "feel like it" is a trap: "You can't think your way into the mood that you seek or the state of mind that you aspire to inhabit. Action is the only thing that can trigger that change." Rich uses running as the perfect illustration of this principle. Imagine you wake up in the morning and you're supposed to do a run because you're training for a race. You don't feel like it. So what do most of us do? "We all resort to that state where we think, 'Well, I don't want to do it right now. I'll just wait until I feel like doing it and then I'll do it then.'" But here's the problem with that logic: "If you're waiting until you feel like doing something, chances are you're probably never going to get to it." The mood you're hoping will arrive on its own? It's not coming. Not without action first. "To take the action despite how you feel about it is the thing that catalyzes the state change." You don't run because you feel motivated. You feel motivated because you ran. He points to what every runner knows from experience: "When they finish the run, they're always glad that they did it. They don't generally regret it. And then they feel better." Notice the sequence. The good feeling comes after the action, not before it. The state change is the reward for showing up, not the prerequisite. And this isn't just about running. As Rich puts it: "That example is applicable to all areas of life." The workout you're avoiding. The conversation you're delaying. The project you're putting off until you're "in the right headspace." You're waiting for a feeling that only exists on the other side of doing the thing.

Kevin Tanaka

10,256 次观看 • 1 个月前

Well the American Century Championship did not disappoint this last week. I may have finished near dead last, but the times that were had were worth it! It is such a wonderful event, in part because of the people that run it, the volunteers that work it, and the money it raises; but also a wonderful event because of the fans and people that attend it! You all make it what it is, sorry to the woman I hit in the foot, and thank you to all that attended!
2:53

Well the American Century Championship did not disappoint this last week. I may have finished near dead last, but the times that were had were worth it! It is such a wonderful event, in part because of the people that run it, the volunteers that work it, and the money it raises; but also a wonderful event because of the fans and people that attend it! You all make it what it is, sorry to the woman I hit in the foot, and thank you to all that attended!

Jason Kelce

188,289 次观看 • 11 个月前

🇺🇸Starship 12’s launch window opens at 5:30 p.m. CT today This time, they’re testing out the new generation Starship and Super Heavy vehicles, the new version of the Raptor engine, and they’re launching it from a newly designed pad at Starbase. Most companies test one new thing at a time; not Elon. And yes, one of them might not work perfectly; that’s the idea of testing, push things to the max so you can find what the flaws are that need improving. Just watch the mainstream media; if one thing goes wrong, they’ll pile on Elon, calling it a failure. And if it all works perfectly, they’ll probably go back to calling him a Nazi 😂
0:24

🇺🇸Starship 12’s launch window opens at 5:30 p.m. CT today This time, they’re testing out the new generation Starship and Super Heavy vehicles, the new version of the Raptor engine, and they’re launching it from a newly designed pad at Starbase. Most companies test one new thing at a time; not Elon. And yes, one of them might not work perfectly; that’s the idea of testing, push things to the max so you can find what the flaws are that need improving. Just watch the mainstream media; if one thing goes wrong, they’ll pile on Elon, calling it a failure. And if it all works perfectly, they’ll probably go back to calling him a Nazi 😂

Mario Nawfal

238,367 次观看 • 23 天前

James Dyson on founder led sales: "Selling goes with manufacturing as wheels do with a bicycle." "Products do not walk off shelves and into people's homes. And when a product is entirely new, the art of selling is needed to explain it. What it is. How it works. Why you might need and want it." Dyson was taught this by his mentor when Dyson was just 21 years old: "I told him I don't know how to sell things." And he said, "Look, you're the engineer. You've chosen every square inch of that product. Everything. You know it all. That means you're the best person to sell it." That was an interesting sort revelation for me because I'd always thought these were separate professions. Sales was one profession, engineering was another, manufacturing was another, and being a manager was another. And suddenly this entrepreneur was saying to me, "Well, look, you're an engineer and designer. You know all about the product, make it, and then go and sell it."
0:37

James Dyson on founder led sales: "Selling goes with manufacturing as wheels do with a bicycle." "Products do not walk off shelves and into people's homes. And when a product is entirely new, the art of selling is needed to explain it. What it is. How it works. Why you might need and want it." Dyson was taught this by his mentor when Dyson was just 21 years old: "I told him I don't know how to sell things." And he said, "Look, you're the engineer. You've chosen every square inch of that product. Everything. You know it all. That means you're the best person to sell it." That was an interesting sort revelation for me because I'd always thought these were separate professions. Sales was one profession, engineering was another, manufacturing was another, and being a manager was another. And suddenly this entrepreneur was saying to me, "Well, look, you're an engineer and designer. You know all about the product, make it, and then go and sell it."

David Senra

42,931 次观看 • 1 个月前

What is the difference between a family deity and a personal deity? Learn all about it through this video. Be sure to watch the video until the end.
0:56

What is the difference between a family deity and a personal deity? Learn all about it through this video. Be sure to watch the video until the end.

Akanksha Awasthi

13,300 次观看 • 7 个月前

Everyone should be aware of this The owners of JBS, the worlds largest meat processing company, has been charged with bribing over 1,800 politicians and officials They’ve been importing cheap foreign meats and using the“Product of the USA” labeling loophole This is a racket. Remember, even though this loophole made by the USDA has finally been closed it won’t be fully enforced until 2026 Until then, “They can import essentially a lower standard beef into America. All they have to do is break it down here so it arrives into America as a frozen slab of beef, essentially. They can turn it into steaks and hamburger from there. And then they can sell it as product of the usa. And they're allowed to label that as product of the usa, which it is not. And it's shot up with who knows what (vaccines)”
1:00

Everyone should be aware of this The owners of JBS, the worlds largest meat processing company, has been charged with bribing over 1,800 politicians and officials They’ve been importing cheap foreign meats and using the“Product of the USA” labeling loophole This is a racket. Remember, even though this loophole made by the USDA has finally been closed it won’t be fully enforced until 2026 Until then, “They can import essentially a lower standard beef into America. All they have to do is break it down here so it arrives into America as a frozen slab of beef, essentially. They can turn it into steaks and hamburger from there. And then they can sell it as product of the usa. And they're allowed to label that as product of the usa, which it is not. And it's shot up with who knows what (vaccines)”

Wall Street Apes

1,228,514 次观看 • 1 年前