Поиск по транскрипциям

preferences. The more context you give, the better the results. And here's a pro tip. When Claude builds something complex, ask it to explain the architecture. Have it walk you through how each piece works. This helps you understand the code and makes modifications easier. You're learning software design from an expert while getting working code...hours. Cut costs dramatically increase output. The ROI pays for itself in the first month. Now let me wrap this up with the big picture. Claude 4. 5 is the most capable coding AI ever released. The benchmarks prove it. My tests confirm it. Real world usage shows it. This is not hype. This is measurable performance that changes what

building products where you want to integrate cloud code into what it is that you're building, then I think you should check out cloud code. Should you consider switching over to Claude products at all? This is what I would say. If you are a casual chatbot user, your normal chat GBT user, your Gemini user, then

cause you can do so much more so much faster. And there's still some stuff where I'll have to dip down and hand write code, but now I dread it, 'cause Claude is just so good at it. - Interesting. - And I think increasingly as models get more capable, these windows where you have to hand write code either

Getting started. Very clean. Uh there's a bunch of commands you can run. Claw. md. What to include and not to include. How to prompt claude plan then build pattern. Verifying the code with tests hooks MCPS permission security context and common mistakes to avoid and key takeaways. So this is a pretty good presentation, right? It's very

Okay, but why better? Yeah, I mean like if you want to code locally, then you would use Windsurf, but if you want to, you know, do something quick like I've shown you today and just preview it instantly, then you can use something like Claude in the chat. I would say that's easier and faster than...much for watching. You've seen all the Black Friday deals today. Hope to see you inside a profit boarding showing you exactly how to use Claude Opus 4. 5 and how to code with it. some of the cool stuff we've built with it like this landing page. Um, exactly how it works step by step. Thanks

description, paste it into your settings. You're good to go. Next, we're in models. So when it's using AI to generate its code, it's using the best models. Claude 3. 5 Sonnet is the best, but I have the other one set up just in case it needs to use them to save us time. Then...into beta. We want to enable composer. Composer is a brand new feature for cursor that actually is probably the most powerful feature it has. It makes generating code and implementing it as fast and easy as I've ever seen in my entire life. Uh, and then make sure all your settings match up here. So, let's close

building charts. It's creating interactive filters. It's adding summary statistics. And boom. I now have a custom dashboard built in minutes. No code, no complexity, just a prompt and Claude's reasoning. Custom analytics, dashboards, data visualization tools, business intelligence platforms. You just built one with a conversation. You could use this for sales dashboards, for influencer analytics

temperature snowfall wind speed calculate probability boom Shack lacker that works perfect first time round absolutely amazing we got R clim for free we got claude's API for free we just coded a website in one single click and it worked perfectly of right how amazing is that now let's compare

work our way to an outline. Once I have an outline, we start writing. So there's just this file is across all my projects, coding, writing, tasks, everything. I just want Claude to know like this is what I like. And it's not very long. This file doesn't go much further behind be beyond this...later, I'd be like, "Oh, Claude, in order to do this task, I feel like you need to know about my differentiators. Maybe interview me. " And I literally claude will interview you can just be like interview me about my business and then it will ask you a bunch of questions and then it will write a context file

performs the best in terms of outputs and which one gives us the best UI as well, the best experience. Right? So, they're all coding out directly here. It looks like Claude is leading the way with chat GPT 03 coming in second and then Gemini on the right hand side performing

used the information from perplexes API in the API server and the mCP server to create a beautifully designed landing page and we've coded all of this for free with Claude 3. 5 Sonic and it actually looks really cool right so it's taken the key research findings the market impact so for example you know it mentions...once you've logged into netlify click on add a new site and import an existing project then we're going to grab that folder the client created and coded all the elements into we'll drag that in and this is going to help us host the project all right so you got the project ready to be deployed

ones like Grock or Gemini, or you can use their Zen service or plug in your own API keys if you have them. I'm using Claude because it's the best for coding. Right

video and it's going to use my laptop my machine all the skills I have configured. And that's the difference between just having cloud code on your phone or just the claude app on your phone. You're actually using your laptop's resources or your remote servers resources whatever it is. I mean, look, it's going

modern like this is a bit more 2023 whereas this one is more like a 2025 style design and it was exactly the same prompt even Claude is one of my favorite AI coding tools of all time right but if we have a look at this like it's messy a responsive design is not that nice it doesn

wins in literally every single benchmark category you possibly can have except and this is a big one for bench verified which is the coding benchmark which it just falls behind Claude Sonnet 45 but every other category humanity's last exam math reasoning video knowledge everything it absolutely dominated and for a lot of these is actually not even

sure the game is fun, dopamine inducing, crazy colors, etc. Then we're going to hit let's go. And what you can see here is Claude Cowork is going to begin to code that out and build it out. Right? Whilst we're waiting for that to load, someone asks, is there an offer on right

give you some advanced tips. These are power moves. First, use a multimodel strategy. Run Claude for reasoning heavy ops. GPT4 for coding. Gemini for creative content. All behind one maltbot gateway. You route by channel or task. Second, use channel routing. WhatsApp is your personal life assistant. Telegram or Slack is your business ops assistant. Different access levels, different

five pro model. It just works better than anything out there for the general purpose queries especially business related tasks that I love for writing and coding. I myself am still torn between claude and chat GPT with Gemini being super strong too. But when in doubt GPT5 Pro, oh my god, enough talk. Let me actually show...just go to Thinking Mini here. I'll just say yes, CSV for Notion import. And then this is just going to run some Python code as all the tools seamlessly integrate into this. And let's see if I open up notion here. Say import and give it the daily activity logs. There you go. That

model called the gpt2 chatbot that has been surpassing other AI systems namely mainly GPT 4 and of course other state-of-the-art models like Claude Opus in reasoning tasks and in coding tasks and like I said before many people are now speculating which as to what this model could really be so some people have stated

with you how I'm using sub aents right now because I'm using them for literally everything. All of my research, all of my AI coding workflows. Now, for the longest time, Claude Haiku 4. 5 has been my model of choice whenever I want something extremely cheap and fast for my sub agent usage. So, I'm using...tokens and $5 output tokens. So, it's still not extremely cheap. And so now we have GPT 5. 4 nano and mini. Even nano is more powerful than claude haiku 4. 5. And it is a fifth of the price. And look at the throughput here. 188 tokens per second according to the 5. 4 nano listing on open