thing here is the 1 million token context window that's in beta right now. But what does that actually mean? And it means Claude can read and remember massive amounts of code at once. Like entire repositories. You could drop in all the code for the AI profit boardrooms automation workflows. And Claude would understand the whole thing
Поиск по транскрипциям
half, — that's an anthropic employee, the company that makes Claude, they built an entire product, Claude Co-work, in 10 days, and they built it using Claude code. Let that sink in. The tool you're about to learn built another tool. While the developers just guided it, this isn't some side project. This is the most powerful
jump or anything. It says, yeah, that's pretty poor. That is not a dinosaur, mate. Not a pixelated dinosaur and definitely not a dinosaur. Claude is still coding it out, so wait for that. And we have the code back from Grock 3 as well. So, let's see what we get back here. So far, Gemini is winning...preview, but there's nothing inside the preview, which is strange. All right, so we're just going to copy this code and we'll go to P5JS and just preview this again to see how Claude performed. Pixelated Dino Runner. Let's test it out. Not bad, actually. That is a hard game to play, though. Look at that
preview on the right. But what makes Google Opal really unique is what's going on in the middle here. Typically, when you're in an app builder like Claude Code, what you'll see in the middle is a bunch of code. And if you're not that technical, the code makes zero sense and it's kind
endpoint for user registration with email verification, rate limiting, and proper error handling. Chat GPT 5. 3 result. Working code, but messy. Hard-coded API keys, minimal error handling. I had to refactor 40% before deploying. Claude 4 result, production ready structure, environment variables configured, comprehensive error handling, JWT authentication, rate limiting already...code doesn't just work, it's structured the way production systems are usually built. This is architectural thinking. While Chad GPT often optimizes for speed, Claude tends to generate code that looks closer to something you could maintain in a real project 6 months from now. For professionals, this matters. You need code that survives. And here
like having a coding assistant right in your terminal. Type your question, get real working code back, or you can use it with tools you might already know. Claude Code, yep, works with Quen 3 coder. Klein works there, too. They even made special proxy servers, so you can plug it into almost any coding tool. Now, I know what...doing that with Claude or Chat GPT. But let me give you some real examples of what this thing can do. Someone asked it to build a physics simulation. Not just any simulation, a chimney demolition with controlled explosions. This AI didn't just write the code. It built a complete interactive simulation with realistic physics, particle effects, the works
would you use it? Raph Claude loop is a plugin for Claude that turns it into basically like a non-stop AI worker. So instead of generating code once and stopping it, Claude will just keep going, right, until the task is actually complete, fixing bugs, testing code automatically, and that sort of thing. And it's a huge shift...pretty cool. I'm just going to terminate that. And then what makes this different versus just using something like claw code? Well, it's like you give it the end goal, not every step. Claude figures out the path. It checks his own work and self iterates. It learns from its previous tries. It works with live GitHub repos
Claude Code just launched something called scheduled tasks and it changes everything. You give Claude a job. You tell it when to do that job. And then Claude just does it every hour, every morning, every Monday, whatever you want. You set it up once and it runs on autopilot. Think about that for a second. That
first. So firstly, if you want to update Claude Code to make sure you're on the latest version, you can run claude update, and that will then update to the latest version for you. And running Claude, you should see a fresh coat of paint
that Claude 4 Sonnet would have done better if I used it via Claude Code or something instead. Or it would have done better if I used Opus instead. But Opus is very expensive. And also, I think that GPT-5 is actually cheaper than Claude 4 Sonnet. So honestly, I feel like I might just be using
just want to say thank you for helping me motivate me to jump into vibe coding. I have been working on building an online company for 6 months. Claude Code and Terminal helped exponentially. That's what I'm talking about. about. See, there there's multiple ways to take the advice we give on this channel. There's basically
server the docker image is now built in multi-stage format. That's a fancy way of saying the final image is way smaller. All the build tools source code and extra stuff gets thrown away. You only keep what you actually need to run open core. And there's even a new slim option...another three-hour course right here, and daily updates on the new latest updates. So, for example, recently we compared Keyo Claw versus Open Claw. We also looked at Claude Code skills, which is a way of kind of making um claw code up to the same standard as OpenClaw. We also looked recently at some of the best free
lets YouTube know that this is a good video and you will get recommended more videos like this in the future. And if you are interested in my Claude Code masterclass, then that will be linked down below alongside a coupon code. And I will be updating the class in the next two days with all the new features that
snake games right that's all AI is used for if you want to build a better self-playing snake game then Claude is really good right number one is super fast number two when it codes the UI tends to be better on the games that you build number three you actually get to preview it inside the canvas...canvas right this looks 10 times better than this and so it's the same prompt but different outputs because we're using a better AI right so for coding Claude is really good it already was the best but it's already good now cursor have actually just launched it inside their pform
jump or anything it says yeah that's pretty poor that is not a dinosaur mate not a pixelated dinosaur and definitely not a dinosaur Claude is still coding it out so wait for that and we have the code back from Gro 3 as well so let's see what we get back here so far Gemini's winning...preview but there's nothing inside the preview which is strange all right so we're just going to copy this code and we'll go to p5js and just preview this again let's see how Claude performed pixelated din Runner s Sr not bad actually that is a hard game to play though look at that
just It's weird that this has got a spinning camera. And also, I just think the UI looks a bit nicer inside Gemini. However, Claude did it faster, right? So, Opus coded a lot faster. Now, one of the ways the Claude
model for development output. And without overexplaining, let me just tell you that this thing basically matches the best closed source models in the game like Claude for Sonnet and Opus at its coding ability. But this is open, meaning you could download and run it locally, but it's so damn big that you would need a rig that...already tell you from looking at this one prompt that this is something I would call a proactive model and some of the best coding models are that's what's really good about claude models. You tell them you want A and B and it kind of figures, hey, if he wants A and B, he'll probably want
tell me how much free space I have in my drive. Here we go. And then you can see here it's coded that out for us, right? Directly inside Claude, right? So, we said, "Tell me how much free space I may drive. " It used that MCP that I just told...file settings make sure you have the MCP set up for browser MCP like you can see again you can copy and paste the code from the AI success lab and then using Claude 4 we can navigate our browser. So what we're going to do is make sure we have the Chrome extension set up. connect, right
will admit the overeagerness thing, which they also call responding more precisely to your instructions, is probably far more critical. Anyone who has tried to use Claude for coding, will notice that you ask for one simple change or bug fix and it will rewrite countless files. And sometimes you're watching it go and make these changes...least write something even if it's mathematically incorrect. " Now, before I get to the model welfare or consciousness section where Claude showed a striking spiritual bliss attractor state, let me get to that coding example because I do know that
free models, you just pick one of those at the top. All right. So, let's click on Anthropic. Then, we're going to click on Claude Pro. Authorize app, get that code, paste it into open code here, and now we've connected it as you can see. All right. Now, if you're not sure what to build