Поиск по транскрипциям

basically gives them um gives us the uh you know green light to use this. But you can scrape the images. And what I did was I just told Claude Code to look for any alt text file names, examine the page that it's on, and scrape the highest quality images. And then what I did is I told

also access in this key. ai. So we give it the start frame, end frame and here's what I did for my prompt. I actually went over to Claude and I gave it the start and end frame and said, "Help me make an AI video prompt where I want the lid to float off. I want fruit...works is that you will have to have ffmpeg which basically just extracts frames from videos. It's a free tool and if you don't have it installed, Claude Code will help you install it. It'll just do it for you, so don't worry about that. But now you can see it's asking us some questions

Google's brand new AI coding agent that just dropped and it's completely free. This thing can build entire apps from your terminal. It can fix broken code. It can even create slide decks from your GitHub projects. And here's the crazy part. It takes less than 2 minutes to set up. I'm going to walk...helping clients get more leads and customers, I'm here to help you get the latest AI updates. Let me be real with you. I've tested Claude Code. I've tested all the other AI agents, but this one is different. Google just released something that could put a lot of paid tools out of business, and most people

want to see more Claude Code related news  in the future, then do subscribe to the   channel and like the video because it lets me know that I should make more of   this stuff and also lets the algorithm  know to recommend this to more people.   Anyways, if you are interested  in improving your vibe coding and   vibe marketing skills

their like 4. 5 or 5 model pretty soon   to basically catch up with GPT-5 and  also win back many of the customers   who are switching over from Claude Code  to Codex CLI. Anyways, I will be making   more videos about Codex-CLI-related news,  especially as they add more features. So   do subscribe to the channel

example, you've got Claude Code over here, but you also have Cursor and Cursor can use board as well. And then you have GitHub as well. And you can see the comparisons here in terms of how they work, right? So for example, there's no native checkpoint system inside cursor compared to claw code according to this

Google's brand new AI coding agent that just dropped, and it's completely free. This thing can build entire apps from your terminal. It can fix broken code. It can even create slide decks from your GitHub projects. And here's the crazy part. It takes less than 2 minutes to set up. I'm going to walk...helping clients get more leads and customers, I'm here to help you get the latest AI updates. Let me be real with you. I've tested Claude Code. I've tested all the other AI agents. But this one is different. Google just released something that could put a lot of paid tools out of business. And most people

summarize everything that we just did to hand off to another agent or the same agent after memory compaction. And then we have the built-in compact command in claude code. This is going to summarize our conversation, then wipe the conversation and put the summary at the top of our context window. Now, the handoff is really powerful because

connector. So, I think we can connect Gmail to this. Let's see if it can send emails for us. All right. So, now we've connected Gmail inside code. If we go back here to cowwork, we'll say, okay, email the message to julian goldie@gmail. com. And we'll just make sure our connectors are added here...agent following my screen. Pretty nice. And bear in mind, you can have this running in the background, right? So, you could say, "Okay, tweet out 10 things about claude code. " And then inside the desktop, it just goes off and tweets them for you in the background. And let's see where we're up to. It should have

mention completely free. So that's Kimmy K 2. That is the model that is changing the industry. Now listen, am I going to get off of Claude Code now because of this? Probably not. I'm paying the $200 a month. I've been able to build really awesome applications with it. I'm very used to the workflow

kind of how I built this directory that outlines this sevenstep process on how I'm using cloud code and an open- source GitHub repo called craw for AAI to handle any kind of data curation. So, this is where I kind of just want to show people how to tackle that data side because I've seen probably...like write custom Python scripts before, and it's just not necessary nowadays. So, I built this in under 250 bucks. $100. Yeah, $100 of that was my Claude Code Max subscription. Another $100 was for the data. Um, and then $50 for some Clawude API credits to do some deep cleaning, which we'll talk about in a moment

hold up three fingers, please? " And that's three fingers, right? That's I'm definitely not an AI. Uh yeah. And let's have a look here. So Claude code can work more autonomously. can actually generate. Let's have a look here. This is using the clawed Chrome extension, right? Or is it clawed browser...think that's Yeah, that's been around for a while, wasn't it? That's been a thing for a while. those for those who need equal code. Here's how I would control my browser, right? And I think you can use Google for this. So, you can just install Nano browser, which is what someone else

completely free. I give out free value in my newsletter every week. At the end of my newsletter, I say, "Hey, you thought that was valuable? Join Vibe Code Academy or sign up for Creator Buddy. " Same thing. It's called a lead magnet. It's classic. I mean, you think about your funnel, right? Your top of the funnel...Convex. " But then that's all they say. They don't ever say, "Oh, because of this, this or this reason. " How can I make Claude code show the difference between the existing file and the proposed changes before applying them? Isn't there like a diff command you can do? What's a diff? I don't know. There

this is how we train kind of claude code to learn to draw in paint and it should able to paint a dog here now playing in snow. Okay, so this is going to be the dog. Let's see how it's turned out. Yeah, at least he got four legs and a tail. And all right, that...course cloud code. We have our browser navigation that we set up using uh Chrome debugger and it can do screenshots and stuff like that to kind of compare because uh the third part is kind of the test part, right? But for us that's just going to be compared to our image when Claude tries to draw

page? Can we move the app updates from the main part to the left sidebar above the share section? Vibe corner. Not bad. Finship. Yep. Finning is the new Claude code updates. Do I just make it all about myself? Everyone wants me to make it about myself. Last one. Ship Buddy. But Ship Buddy I feel like

competitive code, if you can benchmark it, they can crush it. These models, indeed, even other model families are essentially eval maximizers. As I touched on in my video from what 4 hours ago, for PhD level science, you can see the results here, 83. 3 and 81. 4. For reference, Gemini gets 84% and Claude 3. 7 Sonnet gets...taken the lead, it hasn't taken the cost effective lead on Codeex CLI, their agent that you can run from your terminal, they're clearly taking aim at Claude Code, but obviously given that it's only been around 2 and 1/2 hours, I haven't had time to test it. Of course, that may be turbocharged if OpenAI

ability to talk to an AI and say, "Hey, write out this entire note for me or summarize this note for me. " So, let's plan this out with Claude code. We'll go back in here. Here we'll go into planning mode again with shift tab plan modes on. Now I want to talk to you about thinking

models and how it compiles that data. So, my prompt here is I'm going to try to have it compare the top frontier models, which is now Claude 4, Gemini 2. 5, and chat GPT. And we'll see what it comes up with. And if you click this right here, web search is on by default...arena leaderboard is Gemini. Well, this just came out so this has not been updated in this one in the LM arena which ranks all the different top models. Coding Claude Opus is the winner again. reasoning Gemini 2. 5 Pro multimodal capability 2. 5 Pro okay memory and context is a tie 1 million context window although Gemini does

best practice. It takes you through the proper process for how to build apps and breaks everything down really moduly. So when we scope out these projects, we use claude code along with this BMAD method to have a really stable way along with knowing technical skills as well. — Mhm. — But that's how we bolt on the extra

project and then I'm going to show you how to integrate Claude code in a second. All right. So if you check here, for example, it's loading up the browser and it's going to open up a typing test app that we've built, right? And so with this type in test app, we've built