📹 YouTube AI | Сьогодні · 17 відео

[music] >> Hi, welcome to another video. So, if you remember, I had talked before about how you can use good models for free through Nvidia NIMS or basically the Nvidia API catalog. And I had also shown that workflow in Kilo CLI. That setup was already really good because you could use stuff like Kimmy, GLM, and the older MiniMax models without immediately paying per token in the usual painful way. But now there is a new model there, and this is the part that makes it much more interesting

So this tutorial we're going to focus on why AI projects fail. Really important topic. So war stories from real customer deployment. So Raja Cababal is going to be taking you through this incredibly important lesson um on where things tend to go wrong. Um and this especially tends to happen at the point of when you go to deploy in the real world. So we'll look at how you know failure happens and some steps organizations can take to avoid failure. So I'll hand it over to Raja to start the tutoria

Good morning everyone. How's it going? Today we have Aritra here who's going to be joining us. He's from the developer advocacy team. He's a developer advocate here at Hugging Face and he works with very closely with Transformers. He's a machine learning expert and he's here to share some secrets about MOEs and life at Hugging Face. So, welcome Aritra. Thank you very much for joining us. Namaskar. I am Aritra and that is how I say hello to everybody. I am Aritra in my native tongue. I am a devel

[music] >> Hi. Welcome to another video. So, today I want to talk about Multica because this is one of the more interesting open source agent platforms I have seen in a while. If you use tools like Claude Code, Codex, Open Claw, or Open Code, Multica is basically trying to turn those coding agents into actual teammates instead of just terminal sessions that you babysit one by one. And that is really the main pitch here. Instead of copy-pasting prompts into a single AI tool all day, Multica

Welcome back. Um so our next session is basically you know solving agentic IIA's infrastructure crisis powering agentic inference with Salmanova. So this tutorial demonstrates sort of going from single agent configurations to more uh fully distributed systems. So, you're going to be using, you know, Google ADK, um, the A2A protocol and cloud run. Um, and you'll create and implement a kind of scalable multi- aent architecture that kind of, you know, mimics actual production processes. Um, so you'

Let's learn as simple as possible what on earth a cursor automation is and how we can start leveraging it in a workflow. Therefore, by the end of this video, you're going to find easy plug-and-play cursor automations you can do for your software or your app that you can start using right away. Does that sound good? Let's jump in. Welcome back, y'all. First off, if you want to access this, just go to cursor.com. Make sure to log in and then you'll notice in your sidebar here automations. This is

[music] >> Hi. Welcome to another video. So, today I want to talk about a GitHub repo that looks extremely simple on the surface. But I think it is actually one of the more useful things you can add to your AI coding workflow right now. It is called Andrej Karpathy skills. Now, despite the name, this is not really about some giant bundle of flashy skills or crazy automation. The main idea is actually much simpler than that. It is basically a lightweight instruction layer derived from Andre

All right, welcome back everybody. Um, so our next item for today is uh we're looking at AI agent on AMD GPUs. Um, so this this tutorial basically teaches you how to create, you know, a personal AI agent from scratch um without the need for those sort of third-party dependencies um or those sort of like ongoing API fees. So you'll learn how to put together um a tool using agent that is private, it's adaptable, you know, designed for actual workflows uh using openw weight models hosted on AMD GPU

Clude managed agents a direct competitor to open claw but a managed version. Here is the managed agent in cloud console having the ability to send message to my slack and running 24/7. Integrate with any of your application with detailed traces work is changing. Previously AI answered questions but now AI does the work. Your agent has an identity, a name, a role, and a home. That is the environment. Previously, it generates text about the work. Now, it does the work, writes and run the code, exe

[music] >> Hi. Welcome to another video. So, Hermes Agent has just received its V0.8.0 release on April 8th, 2026. And I genuinely think this is one of the most meaningful updates it has had so far. If you remember my previous video, I had already talked about using Gemma 4 with Hermes Agent and Open Claw, especially through Ollama for a proper local setup. But now, Hermes Agent V0.8 changes the story in a pretty interesting way. Because it is no longer just about local Ollama usage. They

Let's learn that simple as possible, what on earth eight open claw skill is. By the end of this video, you're not only going to have the ability to access a pre-made ecosystem of a bunch of skills that upgrade your open claw, but in addition, I'm going to show you how to make custom ones that maybe only you care about. Does that sound good? Let's jump in. Two things. First thing, if you're like, "Corbin, I don't even have open claw set up." You got to watch my videos. Just find the video where I

Hi, welcome to another video. So today I want to talk about Muse Spark because I think this is one of those models that can look a bit confusing if you judge it the wrong way. Now as I am making this in April 2026, Meta is positioning Muse Spark as the first model in this new Muse family. And from the way they are talking about it, it is clearly meant to be a small and fast foundation for bigger things later on. So if you go into this expecting it to be the one model that just destroys everythin

[music] >> Hi. Welcome to another video. So, a new model kind of has dropped and it is called Mythos. This is by Anthropic and is not generally available. I won't talk too much about the already existing common knowledge around the model. This model is apparently very big and the capabilities are so good that, according to people at Anthropic, it can't be generally released. I have seen more and more people concerned about it. So, I wanted to share my two cents on it, which is not much, bu

Currently, we're doing an experiment with folding t-shirts with robots, fully autonomous. So, we're doing every little step from collecting data to training the models, doing evaluations, and also trying to learn and democratize all the little steps and details that are needed to do this. So, you can now put different kinds of t-shirts, different sizes, and different colors, etc. in front of the the robot initially in a flattened state, and it will fold it nicely and put it on the side. And the

Finally, after months and months of hard work behind the scenes, I am unveiling the new Archon, a massive overhaul of the AI command center that I was working on last year. It is now the first open-source harness builder for AI coding. So, similar vision, but a very different and powerful use case. Harnesses are the future. It's the layer on top of your coding agents that orchestrates different sessions. It's what makes AI coding deterministic and repeatable. We'll talk about what that means. An

In this video, I'm going to be showing you Composeio, which is a platform that allows you to connect your AI agents to over a thousand applications. Now, the great thing with Compose is because what they provide is effectively all of the different connectors to all of the different services that you want to leverage. All that you need to do is point it at your AI agent, give it a little bit of natural language instruction, and once it has that, it's going to have the ability to interact with a w

Zap your SDK just dropped. Let's find out if it's any good. And by the end of this video, you're going to understand fundamentally the difference between Zapier CLI SDK, how to integrate it into your agent workflow. Corbin, I don't know what any of these terms mean. Don't worry, that's why you clicked on this video. Let's find out. Let's jump in. Welcome back, y'all. Today's video is sponsored by Zapier. They said, Corbin, we had a major update. Major update. and that is now we have the ability

[music] Hi, welcome to another video. Most AI workflow tools look great in a demo, but the moment you want multiple agents, your own models, your existing tools, and something a real team can actually run, things get messy very fast. That is exactly why on demand is interesting. On demand is a centralized platform where you can discover, assemble, and automate AI agents using a curated suite of agentic tools and the models you want to use. So today, let me show you what it is, how you can use it

This year I'm super bullish on a few of things that are a bit intertwined uh and they are a bit like the team is um like gen like generalization of vision to world and taking actions. So in my opinion this year the there's something called world models and world models are a bit like compression of the world like that's what also Yanikun says a bit um he says that um you cannot really learn a world through text tokens and for instance the you can see this trend with uh J&3 by deep mind like

About a year and a half ago, Dario Amade, the CEO of Anthropic, put out an essay titled Machines of Loving Grace. This was an article that he wrote basically describing of what it could look like of having a country of geniuses as he describes within a data center. Basically, a world where AI accelerates science, cures disease, and transforms the economy. Fast forward to today, they released something called Project Glasswind, as well as a preview at their latest model, Claude Mythos Preview. In

Hi, welcome to another video. So, Deepseek site is now rolling out a new model and a new interface. There isn't much info about it, but most people are claiming that it is Deepseek V4. It is being rolled out and I've now got access. So, I tested it with my tests and I believe that it is Deepseek V4 as well. Why do I think that? Well, let's look at the generations and the oneshot tests that I did. First of all, this is what it looks like. You can see that we have two options here, which are insta

Good morning everyone. How's it going today? Uh today we're going to be taking a look at HugenFac's storage bucket which is a wonderful development released by the team just a couple weeks ago and uh it is great. It's the first time that the hub has a new nature of a repository. So usually you have models, data sets and spaces and now you also have buckets. So the first thing that we're going to see today is what actually are storage buckets and how they are so important, how they are a drop in

[music] Hi, welcome to another video. So today I want to talk about a GitHub repo that is actually very practical if you build frontends with AI agents and that is awesome design MD by Volta Agent. Now, at first glance, this can look like just another awesome list. And technically, yes, it is a curated collection. But the reason I think this repo matters is that it is solving a very real problem with AI generated UI. Most agents can write code. That part is no longer surprising. The issue is tha

Let's face it, every week you and I are playing the game, what's the latest and greatest in the AI space, right? It changes every single week. And right now, everyone is focused on LLM knowledge bases, which originated from this tweet from Andre Karpathy. And there are a lot of really cool ideas here that I want to get into with you. And I built my own memory system on top of this. I think you're really going to like it's simple, but super effective. So, more on that in a bit, but let's get into

Greetings fellow learners. In this video, we are going to talk about the core of Dolly autoenccoders. And um this is going to be like the first in a two-part series on Dolly where Dolly is going to take some text and generate an image related to that text. So one core component of this is a discrete variational autoenccoder. And so before explaining Dolly as a system, I thought it would be nice to understand the progression of ideas that made Dolly possible. And specifically, it's the evolution

Let's find out as simple as possible what is CLI. I'm going to be explaining CLI or command line interface as if you've never developed in your entire life. This is as easy as it's going to get. So, let's jump in. Welcome back, y'all. I already know you clicked on this video because everyone seems to be talking about CLI. What is a CLI and why are we using CLI with artificial intelligence? Whether it's CHBT, cloud, perplexity, all of it. So, as you know these style videos, we're going to go over

I think it all happened very fast especially recently like I remember when I was first following vision and I think basically it all started with the vision transformers like before that we were working with convolutional neur networks and stuff with vision transformers I felt like they are more scalable and um also it's the fact that you can do a lot of transfer learning with them so like with vision transformers. The vision had its own birth moment, >> right? >> And then um we were

[music] Hi, welcome to another video. So, Anthropic finally made the OpenClaw situation official. As of April 4th, 2026, clawed subscription limits no longer cover third party harnesses like OpenClaw. So, if you still want to use Claude through OpenClaw, you now have to use extra usage, which is basically pay as you go build separately from your subscription. And honestly, I think this confirms something much bigger. Subscriptions are dead for serious agent workflows. Now, I do not mean every su

[music] Hi, welcome to another video. So, Qen has launched another new model and this one is QN 3.6 Plus. And to be honest, this looks like a really good model for sure, especially if you care about coding, repo level tasks, front-end generation, and generally getting useful output instead of fluff. This was made live on April 20, 2026. And from what QN is saying officially, this model is focused very heavily on agentic coding, practical reasoning, and completing real work rather than just sound

In this video, I'm going to be taking a look at self-improving agents. Specifically, how a new project extends ideas from Andre Carpathy's auto research into something that is arguably even much bigger. Now, if you've been following the channel, I covered things like self-improving skills, continual learning, as well as how to run clog code autonomously. And one of the interesting things and areas that more and more people are starting to look at is this idea of actually autonomously improving t

What is the difference between CLI and MCP? By the end of this video, I'm going to explain as if you've never developed in your entire life what the difference is and why you should even care. So, it's fight night, baby. Put your gloves on. CLI verse MCP. CLI. Welcome back, y'all. All right. I'm not here to waste your time, so I'm just going to tell you one sentence the difference between the two, and then we're going to do two very specific examples. Two, two. Number one, CLI. Why do we use CLI

Hi, welcome to another video. So, Google has launched Gemma 4 and I think this is one of the most interesting open model releases they have done so far. This is their new open model family built from the same research and technology as Gemini 3. And they are saying that Gemma 4 is the most capable model family you can run on your own hardware. And honestly, at least on paper, it really does seem like that. It is also now under Apache 2.0, which is a really big deal for people who actually care a

[music] Hi, welcome to another video. So, I wanted to revisit Kilo Codes rebuilt VS Code extension because there are now basically two important dates here. Kilo published the post saying they had completely rebuilt the VS Code extension. At that point, it still had that beta or pre-release feeling. But now there is a newer post from April 2nd, 2026 called New Kilo for VS Code is live. And that changes the framing quite a lot. This is not just some early preview anymore. This is basically the re

Wow, it's been an amazing week for open audio models. Models that speak, model that transcribe. Just today, Mistra released Vauxra 4B texttospech model. It's a state-of-the-art model. You can try it in this space built by Mistral. Let's type in some text. This model and let's pick Curious Jane as our speaker. This model is fast. Now, >> what's an enentic harness? What does it mean? >> Really fast and expressive. So that's Voxrol TTS. Try it out on Hiden Face. Next, I want to give som

Open claw is powerful but if it doesn't know what to do then nothing to do much with this that's when we have skills. You add skills to open claw and it'll become powerful. It can even create its own skill. So I'm going to take you through step by step how you can create skills from scratch and all the features available validating the skills to make sure what you created is available. Just few lines of code and you have created your custom skill. Also, I'm going to take a real world use case. I

I'm going to explain as simple as possible as if you've never touched a piece of code in your entire life how to use claude code. And by the end of this video, you'll have a complete comprehensive idea of the two major reasons why you need to start using cloud code because trust me, it's not just for the nerds. You can genuinely use this in a lot of context. Let's jump in. Welcome back, y'all. Today's video, let's go over everything you need to know about Cloud Code. First thing you need to know

In this video, I'm going to be showing you Agent 4 from Replet. Now, Replet, if you're not familiar, it started out as a cloud IDE and now it's evolved into a platform with just natural language. You're able to build as well as deploy and scale your applications. Effectively, all that you need to do is you can write and run code in your browser. There's no local setup. You can also do this from your mobile phone. And since they've added their AI agent in 2024, now you can build full apps with ju

[music] Hi, welcome to another video. So in this one I want to talk about Hermes agent, why I think it is a better alternative to something like openclaw for a lot of people and why I have personally switched to it for a lot of my day-to-day agent work. Now this does not mean OpenClaw is bad. Openclaw is still a very capable project and if you already use it well then that is completely fine. But for me, Hermes Agent feels more complete, more practical, and honestly, just easier to live with on

I've been building my second brain with Claude code for the last 3 months and it's gotten to the point where it saves me at least a dozen hours of work and I promise you I'm not exaggerating for the sake of this video. So right now I want to show you all of the components of my second brain. Talk about the skills and the use cases, the things that I'm automating. I've been running a very similar business for the last year and a half. And so I know how long it takes for me to do a lot of these th

Let me show you probably one of the most simplest, easiest way to get OpenClaw running and then have it do a real task. As you and me both know, when setting up OpenClaw, it can get very complex very fast. So, I'm going to show you how to do it in one click, but on top of that, show you this really cool native integration that allows us to create anything we'd want in software via Hostinger. Therefore, if you want the best and easiest way to set up OpenClaw, let's jump in. Welcome back, y'all. T

Hi, welcome to another video. So, as of March 31st, 2026, there are some more anthropic leaks floating around. And honestly, the most interesting one is not even Methos or Capiara anymore. It is something called Epitaxi. And if these leaked clips are real, this looks like a new Clawed Code web mode. or maybe a new clawed desktop mode that ties local and web execution together in one cohesive interface. And honestly, it looks pretty cool. Now, before we get into the speculation, let's talk about

Claude Code just got leaked. How do we use it for free? Oh my gosh, it's open source. Welcome back, y'all. In today's video, we're going to go over this new big leak of Cloud Code and what that even means for you. I'm here to shatter your dreams and burst your bubble. No, you cannot download all of Claude Code source code and then all of a sudden use it for free. But what you can do, and the implications of this open source code, is the following. I got Mal here, and Mal made an absolutely beaut

[music] Hi, welcome to another video. So today I want to talk about a GitHub repo that is way more important than at first looks. It is called Superpowers by Ora. And if you just glance at it, you might think, okay, this is another prompt pack, another plugin, another little productivity trick for Claude Code. But that is not really what this is. Superpowers is basically an agentic software development methodology packaged as skills. It teaches your coding agent to stop acting like a fast intern

The biggest problem in AI right now can be described with a single word, sick fancy. You've probably heard of this before, but it means that AI models tend to agree with us and reinforce our opinions and their own way too much. They have too much bias. And the problem here is that fancy, it actually seems to be getting worse as large language models are getting more powerful, not better. Now, when people talk about psychopancy and AI, they're usually referring to the more broader sense of just a