Поиск по транскрипциям

looks a tiny bit different  because there's a new design right at the bottom   over here. I don't think it looks quite as good  as the Claude Code design, but it certainly looks   better than the previous design because you can  see right over here, like the input box, it just   didn't look particularly nice. It seems

building but way better than Manis. That's what I'm building. Way better than Mannis. What I'm building is way, I'm just giving these errors to Claude Code as we talk here. This is great. I didn't even schedule this live stream ahead of time. I just went live and we're up to 106 concurrent

check it off? We can check it off. This is a full project management tool that was one shot by Ralph Wiggum, our own new personal development employee. Claude Code was already the most autonomous, incredible AI employee. Ralph Wiggum only makes it more powerful. I hope this was helpful. All the prompts and links you need are down below

Claude Code will do this automatically. But when I have a really long plan, then I tell it to turn that into a task list. So, for example, I have a pretty long plan that I made with the spec developer and I'd say turn this into a task list. And after doing that, I would either say complete

success criteria. This is the most important part. This is what Ralph will check against with every single loop it does because remember all Ralph Wigum plugin is putting Claude code into a loop until it completes a task. So the success criteria is all requirements implemented. So everything we described in the requirement section, no llinter error...good amount. And that's our prompt. Again, I put this down below. Feel free to copy and paste it. Now, we're going to put this inside Claude. So, now we're back in Ghosty. Here's what you want to do is we're going to put the prompt in manually type out. So do slash Ralph

like, "What are you, an idiot? " I exclusively use chat GBT Atlas. Getting this deployment error. Now I'm just copying and pasting all these deployment errors into cloud code so I can fix it. Um, yeah, it has memory. So anything I type into the chat GBT sidebar chat there, it gets saved to my Chad GBT memory...your New Year's Eve to my live stream. Why don't you start up a live stream? We'll see how it goes, bud. You got to try Claude Code Opus plus the front-end design skill. Shad CN MCP. Uh, what does the Shad CNN MCP do? I'm very hesitant to add MCPS. I just

when I find that Claude Code has made a mistake or it just kind of went down the wrong track, but the conversation up until that mistake was still really good. Instead of arguing with it and saying, "No, go back to the previous thing. You should not have done that. " I just rewind to the earlier part

think the part that you really can start with it's pretty simple. You don't have to get too complicated in how you think about like give the claude code three queries around the metrics in a specific domain within your company and actually start to instruct it to build an MCP around that like that. That...kind of trying to build two to three queries that have each of the tables at least one join together um to kind of show cloud code some of these patterns and some of the key fields inside of the codebase and so kind of looking at that trying to rank the top investors trying to add something around kind

have the vocabulary. Like when I look at like my co-founder Max, right, and his technical vocabulary, how he can describe the problem to a coding agent is so much more sophisticated than I'll ever be able to do it. And so the output quality that he can get from this is at a like a level that...show notes. — Yeah, I'll give you a list of them so that you can pass them on. — Phantom Blaster instantly. Like, I'm not even talking about like Claude Code and stuff like that. you like you've done your research, you found the tools and you know I think that's why a lot of people listen

operating on my Mac Mini. I'll go ahead and fire up the terminal. Move to a temp directory. And so, let's go ahead and boot up a claude code instance here. Let's run a ping just to make sure we're all good on the device. Good. And actually, we don't even have the library installed

freaking love Cloud Code skills. I think you do, too. But sometimes they're a little bit unreliable. I would say about 70% of the time I run a skill, I get an intended...output. About 30% of the time, it's a bag of rocks. What I wanted to do in this video is I wanted to show you how to combine Claude Code skills with a new development in the AI space called Auto Research to achieve significantly higher reliability, accuracy, and allow your skills to quite literally improve themselves overnight

super powerful and also like cloud code and the CLIs if you're into that entire world are super powerful yet 9% of the people don't use claw code regularly and don't use like advanced automation workflows with like aentic elements in the middle but everyone can use a browser agent where they just click a button...cannot emphasize enough how surprised I am by how well this works. And I think one of the big reasons is because they took everything they learned from Claude Code and its success over the past months and implemented that into this new model and this agent. And I wonder if like the competitors are even going to be able

like this is how I'm basically translating  the application into different languages. And what I'll do is make a brand new  skill where every time Claude Code   adds a brand new string into application,  then it adds it into these two files here,   and it finds a relevant point to add it into.   You can also do that

night rather than Saturday morning. Let's see what does the poll say. Poll says 66% Friday night 6 p. m. All right. The crowd wants a claw new Claude code video tonight in the next few hours. So make sure to subscribe and turn on notific everyone all together. Turn on notifications immediately. Everyone all 100. Biggest Friday live

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

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

skills are offered now on all major platforms. We've all adopted them. So you have codec skills, you have Gemini skills, uh, and then you also have Claude code skills and they have very particular specs and they look really, really similar to one another. So, it's worth me at least going over to high level what they

thread, the main general-purpose agent, and then I can say, I can say "continue with that sub-agent, resume it" to explicitly resume that sub-agent. And then Claude Code should be able to find that sub-agent and then resume the session that it was having with it. And if I review the transcripts for that particular session

previously if you made a change to skill or made  a new skill, you'd have to restart Claude Code,   but now you don't have to because it's like  automatically monitoring any changes that   are happening. Now, this should also work with  specifying the model in the skill frontmatter

building out our codebase, we are evolving our test base, our codebase, and our AI layer. And man, does that compound over time. And so, going back to Cloud Code here, I'll just give you a really simple example of this. So, one thing that I did do to iterate once off camerara is I worked on the style...back to the start of the video, you'll see that I kind of forgot to talk about the style, exactly how I wanted the site to look. So, Claude Code just kind of made its own assumptions there and it didn't look the best. And so, I had to iterate on that. And so one thing that