Transcription
Andre Kapathy, co-founded OpenAI, was the head of AI at Tesla, and even had the creator of Claude Code, thanking him for feedback on his AI model. So, when a man of this caliber makes a tweet that gets seen by 7.7 million people about how he thinks we're all using Claude code wrong, I'm all ears.
And according to Andre Kapathy, you can 10x the quality of your output from Claude and leapfrog your competitors simply by installing this one file. So, in this video, I'm going to show you exactly what this file is. How do we get it installed? And then we're going to put it to the test to see if we can transcend what Andre Kapathy is calling the sloth apocalypse. All I ask in return is you hit that like button below and let's jump in.
So, it all started here from Andre Kapathy's official Twitter account where he put out, no other way to describe this, a longass tweet that's extremely technical talking about the four main problems that he sees with current LLMs like Claude. Now, I'm still shocked myself that these things get 7.744 million views on a highly technical tweet like this, but it just shows the amount of truth that is in here and the amount of need for something like this.
Now, normally if we're not in the AI world, we'd go through this whole post together and then try to tweak whatever processes we're doing in our businesses to fit it. However, welcome to 2026. Welcome to the modern world where someone can take that Twitter file and turn it into what's called a Claude MD file and upload it to the internet so we can all download it in one line of code. And I'm going to show you exactly how to do that and then have our Claude codes operate in line with everything that Andre Kapathy says would make it better.
And so this file is currently hosted on something called GitHub. And you can see it's had 131,000 stars, which if you have no idea what stars are, it's one of the most popular files on this website.
Now, in this really long tweet, Andre Kapathy identified four main problems with the current setup of LLMs like Claude or Claude Code. It doesn't think before working. It doesn't plan out what it wanted to do. It just gets started and it might be running in the wrong direction. It over complicates the output. Lines of code, maybe 500 lines of code when it could have created what it created in a hundred lines. It's hard to thin slice edits. So, you see AI these days making full uh 5 minute movies and you're like, "Oh, can we tweak at the 3 minute mark this guy smile to make him smile a lot bigger?" And all of a sudden it deletes the whole file and the whole thing's corrupted because it's really hard to sniper pinpoint edit whether that be in a video, whether that be on a website or whatever it is that you're creating with AI.
And then finally, this is my favorite one right here. At the moment, AI is work driven. It's not goal driven in its execution. It works to work, not working to a goal that you may have for it. And Andre Kapathy says that this is costing you hours every week. And it's actually costing you a lot more than that in the output of your AI agent. And as I said, the actual creator of Claude Code, Boris Churnney, replied to this longass tweet and said that all these points resonate and he's actually going to be looking to try and fix those issues himself. And even Elon Musk responded, says, "Sums up the zeitgeist because AI has been trained on the entire internet. It's going to have basically average IQ, average creativity, average everything because everything is regressing to the mean because there's too much crappy training data in there."
Now, the quickest way to get this file installed so we can start to test it for ourselves is to come over to the GitHub. You can copy paste the actual URL uh or you can come down to this thing here and it'll give you the URL to clone and copy it. This is the awesomest thing about AI is you go to your Claude code. So whether you use that in terminal like I do or maybe you use it in the app, it doesn't matter. All you have to do is say, "Please install this file for me," and then paste the URL and it's going to go ahead and pull that entire MD file down onto your local device so it can start operating through Andre Kapathy's upgraded skill set.
So now that it's installed, let me show you the difference that this makes to you operating your business. We're going to go through in the categories that we went through of the four fundamental upgrades that Andre Kapathy is recommending that your LLM makes. Starting with thinking first, when you give Claude code some instructions, it's going to start sprinting. Unless you have this file installed, this is going to make sure that it sprints in the right direction. It's going to not assume things. It's going to make sure it never hides confusion, and it doesn't surface trade-offs. It's even going to push back when warranted and stop when confused. It's not going to build for building's sake and it's going to ask you more questions.
Okay, so I've pulled up two versions of Terminal, which again, if you don't use it in terminal, it's going to look cody and advanced. Don't worry about it. It's just the exact same as running inside the app, but you have way more features. I actually have a full video on this and showing you how simple it actually is. But I've typed the same prompt into both of these terminal windows, one with the Kapathy MD file installed and one without. So I said, "Can you make me a lead magnet for DreamLab?" So something that I can put into this video and then get an email in return for and add people to my email list. The first instance which does not have the Kapathy MD file installed says, "I'll check the Dream Labs context first, then build the lead magnet." It went ahead and just literally built the lead magnet based on this very, very vague prompt. However, it's not bad because it did link straight into my active campaign and straight into the right email folder and then hosted it on the correct website. Once again, if you want to see exactly my setup, I have a video breaking that down. But it did make a lot of assumptions.
On this second instance of terminal where this Kapathy file is installed, I said, "Can you make me a lead magnet for DreamLabs?" He says, "Before I build anything, per section three of the rule book, ask first on stack decisions and section 7.1, think before acting. I need four things from you. What hook do you want? What format do you want? What list do we add them to? And what URL slug? Where does it host it?" Once I have those four, I'll draft the page in the standard dark aesthetic single file HTML, show it to you locally, and I'll only deploy it once you give me the green light." Which of course is going to lead to way higher quality outputs. But if more context and higher quality outputs isn't enough, because initially you're like, "Wait, that's just more work on my behalf." Yes, of course it is, but you're going to have masterpieces, not slop.
The second part, however, is even stronger than that. It's simplicity, which is basically minimum code. Everything's built from code. Whether it's videos, photos, websites, lead magnets, PDFs, it's all going to be code. We are training our Claude to be as simple as possible. So as we continue to build on top of it, its foundations are clear and clean. And so when I ask the terminal window that does not have this Kapathy file installed for a lead magnet, this is what it gave me. "Get my exact AI command center, full install config, hands-free voice control on Mac, every skill and agent and MCP I run, how to point it at your own business," which is pretty good cuz I have given it a lot of context on my business. "Send me the setup, put your email in here, and it's all hosted on my actual website." It's not bad at all, but it is 212 lines of code where the Kapathy version of it mocked up the exact same page. So, this is the old one and then this is the Kapathy version. Literally no difference. It's almost pixel perfect, but it has about half the amount of coding lines that go into it, which is pretty impressive, especially as you scale these things and load time. You want to be as quick as possible. And then building on top of it, you want that foundation to be as clean as possible. And we get all this efficiency just by downloading that one file.
Now, the third skill we get in this beautiful skill pack is surgical changes. So, it wants Claude to touch only what it must touch. Clean up its own mess after creating it. And when editing existing code, don't improve adjacent code, comments, or formatting. Don't refactor things that aren't broken. Match existing style, even if you do it differently. And if you notice unrelated dead code, mention it. Don't delete it. Because Claude is historically bad. If you ask for the color of this button to be changed, it might tamper with, say, this box up here and all of a sudden the title is also a different color. But with this file, it's going to have precise edits. And I mean, let's run the test together. Let's see if we can get an orange button here. So, I'm just going to paste that URL right here. I'm going to say, "Make the button orange, please." P, should I say? And he says, "Done. The button is now an orange gradient." I'm going to refresh this page and it is orange and nothing else has changed.
So, now let's actually go back and test the original one. I'm going to copy the URL. I'm going to come back to our original terminal here without the Kapathy file installed. I'm going to say, "Can you please make the button green?" Okay, so it says it's changed the button. I'm going to come back and refresh it. And the whole site is green. That's obviously a joke, but I'm sure you've had your Claude code just touching things that it shouldn't be touching.
Now the last one, which is my favorite upgrade to my Claude since insomnia file, is it makes every action goal driven. You get to actually define success criteria for every task or project that you are giving your AI and it's going to loop and continue to work until it's verified hit that goal and become successful in its efforts. So it's going to basically give itself test results and make sure that it's hitting the A+ in the criteria that you gave it. is when you see those jokes where it's like, "Make me a hundred million business, make no mistakes, keep working until we have 100 million in the bank." And so, for example, if you have something that has a bug in it, you can come in and write something like, "Fix the bug." And it's going to transform that input into, "Write a test that reproduces the bug so we know exactly how we got it, then make it pass." And it will not stop working until actually passes that criteria. And the best example of this is actually in my other Andre Kapathy video where I show you exactly step by step how to set up Andre Kapathy's second brain for business that is centered around your business goals and needs. I'll pop it up here on the screen somewhere, so go and watch that. And if you haven't, hit that subscribe button below. Thanks so much. I'll see you in the next video.