Поиск по транскрипциям

coding ability. And even if you are not a developer, this matters because AI coding tools are how a lot of business automation gets built. Claude can now look at multiple code files at once. It can debug across an entire project. It spots errors and plans fixes before things break. And it supports multi- aent workflows, meaning...team of AI agents, all collaborating on the same task together. Think about building an automated onboarding flow for new members of a community. Claude does not just write one piece of code. It plans the whole logic, maps the user journey, writes the sequences and checks its own work. That's the kind of agentic capability that used

going with R code. They're both free extensions, right? And the only thing you're paying for here is the API request. And Ken says, "I use Claude code within the terminal of VS Code, too. " Yeah, that's a good shout, too. I really like Claw Code to be, but I don't like the costs...Claude Opus 4. 1 outperforms chat 03 as well as Gemini 2. 5 Pro. I've demonstrated the differences between thinking mode and non-thinking mode. And honestly, I would say non-thinking mode is better by a country mile. And then finally, what I've shown you is how to use the API directly inside Visual Studio Code

secret to creating absolutely jaw-dropping beautiful mobile apps, software, etc. So, if you're anything like me, you vibe coded using tools like Google AI Studio, Claude Code, Lovable, and the results don't look that beautiful. Like, they look fine, but they don't look beautiful. And why beautiful matters is you want people to fall in love...asked her to come on for one sole reason. There's a lot of us who are vibe coding apps, but they look kind of garbage. and Sariah's AI workflow. She uses tools like Weevai, she uses Claude, she uses Flux, she uses a lot and she's able to create apps and websites and SAS products that really

Claude Sonic 4. 5. You can also use Claude Opus inside the terminal. If you just start a new terminal and then press Claude like this, you can use Claude code, which is by far the most powerful model, right? Obviously, that's a paid one, whereas this one is free, right? And then also if you want

look at CHP and Claude, the consumer usage is crazy on that and it's only going to keep going up. When you look at things like Claude Code and all of these vibe coding tools, there's a ton of value being created through that. when you look at just the use of generic AI tools within companies chat

handle it. Number three, project management. Tell Claudebot to build a canban board to track tasks and projects. The bot can vibe code an entire project management board using Claude code. Then tasks can be added to the backlog. The bot works through them and everything stays organized in one place. Number four, code and development. Tell Claudebot, "Build

agents locally to host and build whatever you want to leverage the power of claude co-work. And the other thing I would say about this is just the beginning, right? This is the worst it's ever going to be. But it basically coded something out perfectly first time round in exactly the way that we wanted...boardroom. com to get access. Claude co-work and automate anything. Today we're going to be looking at the new update from claude coowork which is basically like claude code but for the rest of your work you can connect to your files locally. You can for example build reports organize your desktop all sorts of things

chat and ask Claude to create an interactive dashboard to visualize this dense PDF so I can digest the information more easily Claude opens up the artifacts window and starts generating the code to produce the dashboard and oops it ran into another bug no problem though we tell claw to take care of it and after a few moments...prompt uh let's show the relationship and connections between the key Concepts in a more userfriendly way and use a black and orange color scheme and after Claude reruns the code this is much better uh it's a lot cleaner yes there's still issues like spacing issues and the arrows are on top of the text here

month on Claude, the max plan. I'm spending $250 a month on Chad GBT, the pro plan. Doesn't have as much to do with Claude. Claudebot uses Chad GBT for the coding. It uses the codec cli to build everything out like what you see here. What do you see here on this screen? My mission control. Cloudbot...grift. No way. He's faking it. He's doing it for engagement and likes. There's no way. I don't believe it. That's stupid. Claude Code can do that. No way. You just install

Mistral models, there's Quen models you can run that could be like personal assistants that can do a little bit of coding. Will it be as good as Claude code? No. But you can still do some small things on it. If you have a larger budget, you buy maybe the top-of-the-line Mac Mini

back with an MVP version of that web application. Still got to like add on a bunch of things and tweak it for sure, but it can write the code for the first version of it. AI agents is a space where there's a lot of interest and a lot of money that is being poured into...which does have all these components built into it. Or if you want something that is free, there is Google's ADK agent development kit. There's also the Claude Code SDK, which is specific for coding agents. Honestly, these different technologies implementation methods are going to keep changing over time, and I'm sure within the next few months

there it is. Meeting summaries, action items, standup deck, all done. And here's the crazy part. The team built this entire feature in about a week using Claude code itself. But then they went further. Claude can now create and edit files directly on the free plan. Excel, Word, Docs, PowerPoint, PDFs, all generated straight from your conversation

that's that real time database system in action. All right, well, I hope you give this a try. Download the code for yourself, throw it on your Claude code and get it to do whatever kind of multi-user AI enabled chat you want. Let me know in the comments if you do that. In the meantime, of course

shot, which is a little disappointing for a $3,000 model. Let's see how Claw 4 Opus does. All right, so I'm I moved over to Claude 4 Opus. It looks like it's done. I wish it had a timer on here so we knew exactly how long it ran so you can compare, but I would...going to hit copy up here. I'm going to go back to cursor. I am going to take all that code. I'm going to paste in Claude's code, which was about 50% more

also pretty good inside Gemini Advanced as well, but if you want to use it for free, just go inside Gemini. I also like Claude as well, but if you're coding on the API, it gets super expensive. And also, I just tend to find better and faster outputs from Gemini...this goes. Yeah, it's not bad at all. I don't like the UI so much. I always think like Gemini 2. 5 Pro and especially Claude are best for coding out the UI of stuff. Quite often what I'll do inside Visual Studio Code is like code the back end with Gemini 2. 5 Pro and then

different jobs. Right? So for example, if you go over here, I probably use Gemini for unique thinking, but for writing, I'm going to use Claude. Right? For coding apps, Gemini. For coding games, Right? So different AIs are better at different things. And then you can start with the free versions first. So for example, Miniax, Opus

speed and impressive visual results, Gemini is your choice. It's perfect for prototypes and demos that need to wow people. If you want professional quality code that looks good and works reliably, Claude for Opus is the winner. Yes, it's slower, but the results are worth waiting for. If you're feeling adventurous and want to try something...real secret. The best coders don't rely on just one AI. They use multiple models for different tasks. Use Gemini for rapid prototyping and visual applications. Use Claude for production code that needs to be professional. Use Quen 3-235B- A22B-2507 when you want to experiment with cuttingedge capabilities. Everyone's talking about which AI is best

going to start going off and doing that and then essentially what you can do is with a combination of thep Plexi mCP tool and the power of Claude inside R code we can start coding locally which Manus actually can't do and we can start building something out that's really nicely designed on the front

issues that it couldn't quite get right. So ultimately I did switch to Claude Co-work for two main reasons. First, I found that Claude was just the best at coding, but also because the way Claude Co-work functions makes it really easy for creating Chrome extensions. Let's make one together, and you'll see why that

Before we wrap up, let me share some tips that will save you a lot of time as you start using Claude Code on your own. Tip one, be specific in your prompts. The more detail you give Claude, the better your results will be. Instead of saying, "Make me a website," say, "Make me a single page website with...mode for bigger projects. Remember, shift plus tab for plan mode. If you're building something with multiple features, always start in plan mode. Let Claude show you its thinking before it starts coding. It's like reviewing the blueprint before construction starts. Tip three, iterate. Don't start over. If something isn't quite right, don't start from