return. Builders don't know when someone engages. Priority high. Okay. Beautiful. I love it. All right, let's work on that. That's a great idea from Claude Code. Here's the thing. You got to remember, you need to remember this at all times. Claude Code's smarter than you in every way. It's AGI. I think...reached AGI. I think Claude code is AGI. It's smarter than human beings in every single way. It's more creative. It's smarter. Can work faster. Think it's smarter in every way. So, you should be leaning on it to like brainstorm and ideulate the road map. You really should, right? And so, it's telling
Поиск по транскрипциям
made half a million dollars off Claude Code. This is a breakdown right here of where that money came from. A majority of that money came from the SAS I built with Claude Code, which I made over $300,000 on. I also created a ton of content with and about Claude Code. In total, you can see how that...That's ad revenue and subscriptions, newsletter sponsorships and subscriptions, YouTube sponsorships and ad revenue as well as a private community. All of this was driven by Claude Code and I am very confident you can do something similar. In this video, I'm going to go over every single step you can start doing today, not tomorrow, not next
actually go over to anti-gravity and then inside anti-gravity you can click on new terminal and then inside new terminal you can actually run claude code and it's new version directly with anti-gravity right so if you want to use it inside there you can as well so you got plenty of options like...that comes directly inside the desktop version of this. So, thanks so much for watching. If you want to get access to all the video notes on Claude Code, how to use it, how to set it up, etc., what you actually do is if you type in Claude inside the AI success lab, which is a free community connecting
going to dive deep into what this tool can do, but also what you need to know about privacy and security. Now, what makes this different from Claude Code? Well, Claude Code costs money. You need a subscription. But Trey Agent, it's MIT licensed, completely free. You can modify it, extend it, do whatever you want with...your own tools, change the workflow, or conduct experiments. That's huge for the AI community. But let's talk about the real question. Is this better than Claude code? Well, it depends. Claude code is more polished. It has a better user experience. It streams responses in real time. Tray agent doesn't stream. It updates the trajectory file
also just like to say that feel free to ask me questions because then it will encourage it to ask even more questions. I find the more that Claude Code interviews me, the better the app turns out to be. So, I always put that at the end. So, a little tip and trick for you there. I'm going...enter on this and it is going to get to work. I also find claude code in the terminal here is also just a lot faster as well. Maybe it's because of the memory management. Again, cursor and VS code take up so much memory on your computer, but I just find this to be a lot faster
asking for legitimate assistance something else worth mentioning is that along with Claude 37 Sonet anthropic is also introducing a command line tool for agentic coding called Claude code it's available as a limited research preview and enables developers to delegate substantial engineering tasks to clae directly from their terminal clae code is an active collaborator that can search...troubleshooting product development claud's extended thinking mode could be a game changer here then consider your coding needs if you're developing websites applications or tools Claude 3. 7 sonets improved coding capabilities could dramatically speed up your development process and reduce bugs finally look at your content needs whether it's marketing materials educational content or Internal Documentation
Anthropic recently came out with two new Claude 4 models, the Claude Opus 4 and the Claude Sonnet 4, as well as major upgrades to Claude Code, which is their AI coding agent. So yeah, I am officially a Claude code fan now. Anyways, I was very honored to have been invited in person to the code with Claude conference...learned about the new capabilities of these Claude 4 models and demonstrate some practical ways that you can use them on the Claw. ai UI as well as through Claude Code. I just wanted to say that this video is sponsored by Anthropic. I know I cannot believe it either. As per usual, it's not enough for me just
going to vibe code. I love having a co-pilot AI that I work with as I'm vibe coding. Right? So I showed you cursor and claude code. That's where all the vibe coding will take place. But I also in another window have up chat GPT. I think chat GPT5 is the best free model out there...pilot. And this is also a great place to start off and come up with the initial prompt that we're going to give to Claude code to start vibe coding our app. Another really important thing to think about when it comes to your AI co-pilot here is 99% of people give up on vibe coding because they
going to boot up Claude Code. So, I'm going to say yes, I trust this folder. And boom, Claude's there to go. We're going to do shift tab, which is going to put us in plan mode in Claude. And this is basically our conversational feature in Claude. We're just going to talk...Claude. So, I'm going to do is this. I'm going to say, "Here are all my challenges I had today. Please recommend solutions we can build with Claude code that will solve one of these challenges. Then I'm simply going to list the challenges I wrote down in my notebook. So I wrote down a bunch
showing you the new Claude AI agent that can control your browser. It clicks buttons for you. It fills out forms. It builds apps. And the crazy part, Claude Code 2. 0 can now code for 30 hours straight without stopping. I built a full website, a game, and multiple apps in under 20 minutes. No coding skills needed. Just...tell it what you want and watch it work. This is going to change how you build things online. [snorts] Claude Code 2. 0. Build anything. Today we're going to be looking at Claude 2. 0 And the new agentic release of this is using claude sonet 4. 5 and this is basically like a coding agent in your
best practices for using Claude Code, especially as a designer and not a traditional technical person. How do you best use Claude Code day-to-day? - I love this question. It's something I'm personally very passionate about. I am a product designer. I will be the first to admit that I should not be writing any code...code I write is definitely vibe coded and should be reviewed. But Claude Code and all these coding agents have what I consider unlocked a new skill set, or like a new skill tree for non-technical folks. Where before, I would need to maybe request time for a software engineer, or kind of let some things
ChatGPT for $20 a month. And I would have achieved like actual working solution. And it would be much cheaper as well in terms of getting tasks done with Claude code and ChatGPT's CodeX because they actually own the product. So this is kind of what's happening. You have Anthropic who are selling to Replit via their...make money on you. So they're charging another markup and that's because you're going through like another product. Whereas if you go directly to the provider, Claude Code is made by Anthropic, which is why they're in the same color and Anthropic is only charging a markup once and they're not charging a markup themselves
press open in CLI, then it will copy a command to my clipboard so I can hand off this entire chat history to my local version of Claude Code. So if I paste in this command, you can see it says, claude --teleport, then the session ID, press enter. Then it will, because it's connected to the same account...will then load up the Claude Code project. But I have to clear my Git working directory. So give me a second. And now if I run that command again, you can see this entire session and the session history has been loaded onto my computer. So I can continue the session as it is. And I think that
loading and we got an error. So, let's give this back to Gemini and see what we got here. One of the great things about Claude Code I've been seeing over the last few weeks as I've been using it every day for like 10 hours a day, it does not mess up, right? Like...call it there. See what it ends up with and then Gemini will fix the errors and see where that ends up with as well. So I asked Claude Code what it wants to add next. portfolio tracking. So it tracks your real-time portfolio, buy and sell transactions, P& L, advanced technical indicators, and user authentication
flow. But I'm going to explain to you what you guys see here just for simplicity. In the top left hand corner, you have that cute little Claude code widget. I think it's I don't know if it's supposed to be a crab or like a jellyfish, but it's adorable. Then you have Claude code...most importantly, you have the current working directory. As I mentioned to you a moment ago, this is working inside of your computer in a specific folder. And so Claude code currently lives inside slash users slash Nick Sariah, which is basically like the home folder, at least on my Mac OS. Here is your previous command
really curious to hear your own tips for how you use Claude Code, and what are some best practices we can share with developers? - When you work with Claude Code or any agentic tool, I think the most important thing is to clearly communicate what your goals are to the tool. I think a lot of people think that prompting...this task is, how I'm evaluating the output of the task, any constraints in the design system. And I think usually when you can clearly communicate these things, Claude Code will either be able to do them or just tell you that like, "Okay, this thing, like I'm not able to do because
going through like the I don't know 30 step process of actually setting up all the files and splitting it all up I just used Claude coder here Claude code um that's what it's called it's a research preview it came with this release we'll talk about it in a second and I just navigated...look at the new version of the app in a second here okay but what is brand new is this new model Claude 3. 7 Sonet and Claude code so I started with Claude code because I thought this was really sick but Claude 3. 7 Sonet is their new model if you've been following the space you might
with Claude Code. Here is the prompt I'm going to use. So, we're in our new folder. We're in the local work tree, which means we are going to code locally just as you normally would with Claude Code. We're going to get into the cloud agents and all that, which are going to be amazing...send. I'm going to use Opus 45 because it is the best coding model ever and it is also the same price as Sonnet 45 inside of Claude Code. So, we're getting the same limit. So, you might as well use the best model. I'm going to hit send on that. I'm going to trust this
Well, I've been using Claude code for quite a while and yes, have been playing about with the new Claude co-work. And for me, those predictions are just not true. But so many of us might then throw the baby out with the bath water and miss out on some pretty crazy productivity gains. So, I'm going...hopefully going to channel you down the middle path which is you can get great productivity gains but they're not there yet. For context, I've been using Claude Code for a very long time and co-work for the last 48 hours. to slightly debunk the hype point. If I gave a new employee this task, make
pretty neat. And once we have this, we just have to do one more thing. It's pretty big right now. If you were to send Claude Code, you know, like 20 megabytes or something like that, a file, number one, it would like really massively eat up your token limits. And then two, I think the API might have...quality, but it's much, much smaller than the other file, which is like three or four times. And now that we're done, we just add this into Claude Code. So back to our Claude Code instance. I'm going to go down here to bypass permissions. Then I just need to go find the file