Поиск по транскрипциям

cloud code. This is something I do a lot. I do a lot of experimentation. I have a change around features to see how it works and sometimes I mess up and I give it a bad command. So, for instance, in this project management tool, I want to experiment with the colors and notes. I made...blue. I don't like the blue. It's not really standing out against the black background. So, let's rewind this. In a brand new update to Claude Code they just released, you can now rewind super easily any changes you made that were mistakes. You do this by hitting escape twice. Double escape and it goes back

hoping they would add some more  features over the last couple weeks,   like by having sub agents or some of the other  features that are available in Claude Code,   because I think I'd rather see faster models  and just more features at this stage instead. But I will actually be trying out GPT-5 Codex  mini more over

basically it  seems that I used $13. 34 in credits out of 25,   and I basically don't have a working solution.   Or for example, I could have used Claude code

Today I'm going to show you how to build anything with Claude code and Google Anti-gravity. It's actually pretty easy to integrate the two. And you can use Google Anti-gravity for free. You can also get Claw for free directly inside there if you want access to the free API for this is a really powerful

particular use case, for example.   But it is worth bearing in mind that even though   you have a lot of MCP servers with a lot of MCP  tools, Claude Code should be able to handle them   pretty well. Because there's a benchmark over here  called LiveMCPBench, and basically they compare a   lot of leading models to see which performs...tools. So   they asked each of these models to complete  a bunch of real-world tasks, such as booking   train tickets and stuff. And you can see that  Claude Sonnet-4 and Claude Opus-4 is basically   in a league of its own when it comes to accuracy,  when given a lot of MCP tools. So this setting

things into perspective. And this is the tweet that I saw yesterday. David Breier says, "A reminder that you're in a bubble. more people Google WordPress than Claude Code. And it just goes to show, I mean, how much of a bubble there is in terms of AI people. And it's not like the current AI stock market

make sure that it is done. And so this isn't extremely difficult, but it is a concept that trips up a lot of people. So the fact that Claude Code just handles this automatically for us is pretty cool. And of course, we don't have to set up the different API calls to make the different requests

actually like extraordinarily different. It's the way you build them that's extraordinarily different. They're so so much easier to build now using tools like cloud code and trigger. dev. And we're not just limited to having automations that are pretty deterministic and on a schedule. Here's an example of one that we would trigger...brief on Lovable. We got some recent news. We got some growth signals, all this kind of stuff. And keep in mind, I built this by literally saying to Claude Code, I want an AI agent that can see tasks in ClickUp, do research, and then send me a brief. I didn't give it like anything else besides obviously

this is completely separate from the last task I did. That's important here. You don't want to give overlaps to these agents because their code might conflict. So, this is a completely different component we're working on. I'm going to hit send on that. And now we have three AI agents working on different visual tasks...filter by certain bet size or certain traders or anything like that. This is a pretty big piece of functionality. So, I'm going to go into claude code in the IDE and I'm going to say let's add filters to the homepage. I want to be able to filter the large bets

files you've uploaded to your knowledge base. So, you'll have to recreate those inside of Claude. And if you click this little download icon right here, Claude also goes a lot beyond the cloud. ai website. For example, they have something called Co-work. In the last two weeks, it's been the number one AI tool that...reason why I upgraded to the $200 plan. It really opens up a lot of different usabilities here for me. And it works internally in your computer and claude code. Now co-work, I recently just made a video covering all kinds of different use cases for co-work. So I'll put that video right here

since uh Devon has really improved over the past couple months and claude code came out I have dropped my cursor usage by like 70% or so. I still start fresh projects in cursor. sometimes things that I just want to explore or build myself or have an opinionated view on how to build. But I would say seven

else pretty interesting that I came  across is this Claude Code viewer. And this basically helps you see what's happening  under the hood because I think it's intercepting   the requests that are happening to the Anthropic  API servers and then like passing the requests   and putting them in a nice UI. You can see what  kind of tool

access to into   subagent frontmatter by doing something  like skills and then your skill names,   which is like find to do and like GitHub release  notes. You can get Claude Code to now reliably

tools, how to use DeepSeek, how to use Gemini CLI, how to use for example this design agent, how to use Google Workspaces and workflow, and also the new Claude Code Opus update that just literally came out yesterday. So this literally gets updated daily as well. You can learn so much from this group and is absolutely amazing right

figure out how it works,   basically you need to have the context  fork enabled on your skill frontmatter   and then any of the subagents that are  available in Claude Code. So for example,   I have a macOS log analyzer  subagent that is a Haiku subagent. If you then specify this in a skill,  such as this example find

have your business model in the middle and then you wrap an AIOS around it. And right now these things are being built with a tool called Claude Code which despite the name does not actually require you to be a coder just so you know. And this is not a chatbot that you open in some browser

testing this out is just using the free Olama as you can see over here, right? any bugs or anything like that, just go over to Claude Code and say, "Can you help me fix this? " or "This isn't working," blah blah. That's what I did when I had a couple of problems with

personal assistant. Easy to install. You can deploy it. It was fairly easy to set up. What I would say is when you're using this, use something like Claude Code to help you get it set up because it can be a little bit of work unless you're super technical. And you can see an example right here

changing, and anyone can build anything. When I, when I started playing with, with this new tech, I got a dopamine hit every time. Back then I started with Claude Code. When it got something right and it was like maybe 30% or 40% chance. But to me it was like, BOOM - like literally mind blowing because I had this

what to track. It's real collaboration. And speaking of collaboration, if you want to learn how to save time and automate your entire business with AI tools like Claude Code Agent Teams, you need to check out the AI profit boardroom. This is where we teach you exactly how to implement these cuttingedge AI systems into your business