link in the comments in description. Completely free. You can get all the notes from here. You can get the code that I've used to set all of this up. It is free to use inside Claude. And then additionally, if you want to upgrade and get, for example, an amazing community focused on making more money and saving...success lab. Claude 4 has just dropped. I'm going to show you a way to basically turn the new version of Claude, which is the most powerful model in terms of coding the world has ever seen. If you're using Claude Opus, and you can turn it into an AI super agent. This is Claude Sonic
Поиск по транскрипциям
version of Gemini 2. 5 Pro. There's no canvas option. So, we're going to have to run the code that we get back from AI Studio inside LiveWeave just to test the outputs. Whereas Claude Forson can actually preview stuff directly inside the canvas. I also want to see how these models perform in terms of speed...waiting for these, let's run through the benchmarks here. So, if you go to open router, we can actually compare these side by side versus claude for Opus. Now, if you're coding with the API, this is going to cost you money for either model, right? It's a Gemini 2. 5 Pro and the API of Claude
some point as models write more and more of our code, those are gonna be the same mitigations that are protecting us from a potentially misaligned Claude inserting very similar vulnerabilities into our code. And so one of the things that I think is pretty promising about control is that in practice the things you would wanna do to implement
that. We'll take that code and then we'll go to p5 js over here. In some ways, claude is already winning because it can actually preview the code directly inside the browser when it's using p5 js. But let's plug this in. So, we got the code right here from the game. We'll compare these...here? It doesn't make sense to have that empty space. So if I had to pick one, I'm going to go with Claude simply because it created a nice UI and also it coded out faster and additionally it allowed us to preview directly inside the browser. Let's test another one now. So if we go back
close that. All right. And you can see how this works, right? So, we've got three options. We've got chat, co-work, and code. If you want to get uh Claude desktop, all you need to do is navigate to Claude, make sure you've got a pro account and then download Claude. Right. Once you've downloaded
models better tools helps improve their quality. But what about the UX of actually using these coding agents? There's been a lot of exploration with coding CLI from OpenAI's codeex to claude to Cursor's own CLI. And the idea here is to find the most minimal abstraction over the model, kind of iterate on the harness
wondering, okay, what is Claude 2. 0, what is it, etc. How does it work? So, it's a revolutionary AI coding assistant, and it's powered by Claude Sonet 4. 5, which literally just came out. Now I'm going to walk you through exactly how to use it and how to save time with use it and build
kind of see the mocks right here of what it looks like. And um I already have it open and running on cloud code right now. So I'm in the repository Claude Cafe. I have kind of Claude open and running. So the first thing I tend to do is ask Cloud to help me preview this...auto accept edits modes. This is also your best friend if you're not necessarily understanding every line of code that's changing. Uh, auto accept edit modes just lets CL claude make the changes and then you can come back and see the final product. Uh, one really fun thing that I like to do is watch the changes
just click on the delete icon over here. So just to recap what are scheduled tasks? Well scheduled tasks are a feature inside the claw code desktop app. They tell they let you tell Claude to do something automatically on a repeating schedule. It's kind of like a recurring reminder. So instead of you except instead of just reminding...Claude actually does work, right? So some real examples, review my code every morning at 9:00 a. m. and flag any bugs. Check if any of my software packages need updating. Pull my calendar and inbox every weekday morning and write me a briefing or run all tests every six hours and let me know if anything breaks
also the most expensive and the slowest model, but oh my gosh, it is so good at code especially like that's what I use it the most for, which is amazing that you can just use Claude Opus 4. 6 six with the thinking mode um as part of perplexity without an additional subscription. So I'm going...like the less fancy version of Opus that's a little bit more usable, but it still has the really good like writing style of Claude Opus and it has really good coding skills as well, which is what I spend a lot of my time on. My favorite use case for Claude Sonnet is asking it to build something
part of the code and then start editing it like so you can already do this and honestly like for me I genuinely think for example Claude 3. 7 is much better for codeing so for example if we go back to this file right here the backlink value calculator we say edit the back link...budget maybe chat cheapy is better but if you on the Real McCoy then for sure Claude is just it's the best I think it's unbeatable right now for Content writing for coding for everything and by the way if you want
chart is, it performs close to on par with models like Claude Haiku, Quinn 380B, and Quinn 3. 5122B. Also, when it comes to coding, we can see it outperforms GPT OSS, Claude, Haiku, Quinn 3, and is about on par with Quinn 3 Next 80B and Quinn 3. 5122. And then in math we can see it's pretty
Drop a comment below if you try this system. Let me know your results and I'll see you in the next one. Anthropic just dropped Claude Sonet 4. 5 and it can code for 30 hours straight. No breaks, no sleep, just pure coding power. I tested it myself and what I found is crazy. This AI can build...entire apps while you sleep. It fixes its own bugs. It writes tests. It even opens pull requests. Early tests show it might be the best coding AI on the planet right now. GitHub Copilot just added it. Amazon added it. Google added it. Today I'm showing you exactly what makes it so special and why developers are losing
Claude 4 has just dropped. I'm going to show you a way to basically turn the new version of Claude, which is the most powerful model in terms of coding the world has ever seen. If you're using Claude Opus, and you can turn it into an AI super agent. This is Claude Sonic
running through exactly how to use Google Antigravity. If you've never used anti-gravity, basically it's a free way to code with Google and you can also get access to Claude as well. And it's completely free. You can code locally with this. You can build some amazing stuff with this. And you can download
running through exactly how to use Google anti-gravity. If you've never used anti-gravity, basically it's a free way to code with Google and you can also get access to Claude as well. And it's completely free. You can code locally with this. You can build some amazing stuff with this and you can download
fast and you don't want to be left behind. Okay, back to what I was saying. The performance numbers on this thing are insane. On coding benchmarks, it's trading blows with Claude Sonic 4. On some tests, it's actually better. Live Codebench, it scored higher than almost every other model. Code Forc's ELO rating
newer and more capable model from applying the even better practices that it has within itself to your code base. It's also why many of these random things that people are finding on Twitter and sticking inside their CLAUDE. md file, hoping it will suddenly fix everything, ends up performing worse because either you're essentially wasting space...this or stuff like not seeking clarifications when needed. And this is also why some people notice a new model performs better on a brand new code base that does not have a CLAUDE. md file, because it's not being held back by any constraints that you wrote in your CLAUDE. md file to handle bad behaviors in older
update from Klein as they've just released a new update to their autonomous coding agent and you can now use Claude 3. 7 thinking mode directly inside Cent I'll show you how to set this up how to use it how to code with the AI agents and also how to use free apis inside client as well
Today I'm going to show you the brand new AI model that just shocked everyone. It's called Kimmy K2 and it's crushing GPT4 at coding tasks. The crazy part, it's completely open source and free to use. This changes everything for your business and I'm going to show you exactly...mean. Kimmy K2 just scored 65. 8 on something called S. Bench verified. That's the gold standard for testing how good AI is at real coding tasks. GPT4 only got 54. 6. Claude 4 Opus hit 72. 5. But here's the thing. You can't even access Claude 4 Opus yet. And when you can, it'll cost