Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

GLM-5 introduces Agent Mode. • Breaks tasks into steps and executes them with tools • Turn uploaded data into instant insights & visuals • Go from outline to finished draft in one place • Upgraded AI Slides + Full-Stack for complex workflows

Hugging Models

52,392 subscribers

30,003 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AI browsing that’s safe for work? Yes, please. Copilot Mode in Edge for Business: 🤖 Agent Mode: Automate multi-step workflows and crush repetitive tasks 🧠 Multi-tab reasoning: No more tab-hopping — Copilot pulls insights from up to 30 tabs ✨ Summarize, analyze, create: Turn pages, files, and ideas into action — all in one place Preview coming soon. Learn more: [

AI browsing that’s safe for work? Yes, please. Copilot Mode in Edge for Business: 🤖 Agent Mode: Automate multi-step workflows and crush repetitive tasks 🧠 Multi-tab reasoning: No more tab-hopping — Copilot pulls insights from up to 30 tabs ✨ Summarize, analyze, create: Turn pages, files, and ideas into action — all in one place Preview coming soon. Learn more: [

Microsoft Edge

311,718 views • 10 months ago

Today we're announcing Planning Mode in Roblox Assistant. Planning Mode breaks down complex ideas into actionable tasks, executes them, and iterates based on real-time feedback. This is another step in our quest to compress the gap between imagination and creation.

Today we're announcing Planning Mode in Roblox Assistant. Planning Mode breaks down complex ideas into actionable tasks, executes them, and iterates based on real-time feedback. This is another step in our quest to compress the gap between imagination and creation.

David Baszucki

233,599 views • 5 months ago

Grok is now in Google Workspace. Install one add-on for Sheets, Slides, and Docs. Turn research into reports, build decks from outlines, and draft documents in place with Grok.

Grok is now in Google Workspace. Install one add-on for Sheets, Slides, and Docs. Turn research into reports, build decks from outlines, and draft documents in place with Grok.

Grok

852,983 views • 1 month ago

QwenWork is now live — the all-in-one AI productivity platform for global teams. Turn briefs into documents, slides, and web pages, and generate images, audio, and video in one place. Analyze data, process spreadsheets, and let AI handle repetitive work.

QwenWork is now live — the all-in-one AI productivity platform for global teams. Turn briefs into documents, slides, and web pages, and generate images, audio, and video in one place. Analyze data, process spreadsheets, and let AI handle repetitive work.

Alibaba Cloud

838,524 views • 18 days ago

You can also now make decks, docs, and designs in your conversation. Draft the one-pager in Claude Docs, turn it into a deck with Claude Slides, and mock up a matching visual in Claude Design, all from one place.

You can also now make decks, docs, and designs in your conversation. Draft the one-pager in Claude Docs, turn it into a deck with Claude Slides, and mock up a matching visual in Claude Design, all from one place.

Claude

3,374,870 views • 4 days ago

New course in collaboration with CrewAI, and taught by its Co-Founder and CEO, João Moura! In "Design, Develop, and Deploy Multi-Agent Systems" you'll go deep into building teams of AI agents that collaborate to handle complex, end-to-end workflows. You’ll design systems that plan, reason, and coordinate, with tools, memory, and guardrails that make them reliable and production-ready. Learn more and enroll now 👉 Featuring insights from Weaviate AI Database, Snyk, Exa, and AB InBev, whose work with CrewAI demonstrates how multi-agent systems are being applied in the field today.

New course in collaboration with CrewAI, and taught by its Co-Founder and CEO, João Moura! In "Design, Develop, and Deploy Multi-Agent Systems" you'll go deep into building teams of AI agents that collaborate to handle complex, end-to-end workflows. You’ll design systems that plan, reason, and coordinate, with tools, memory, and guardrails that make them reliable and production-ready. Learn more and enroll now 👉 Featuring insights from Weaviate AI Database, Snyk, Exa, and AB InBev, whose work with CrewAI demonstrates how multi-agent systems are being applied in the field today.

DeepLearning.AI

33,849 views • 10 months ago

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:

LangChain

24,885,978 views • 7 months ago

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar

355,631 views • 1 month ago

Farmers can now get early warnings about crop stress, even before it becomes visible. With support from the Gates Foundation & partners, Vassar Labs uses satellite imagery & AI to turn complex data into simple, actionable insights, helping farmers take timely, preventive action.

Farmers can now get early warnings about crop stress, even before it becomes visible. With support from the Gates Foundation & partners, Vassar Labs uses satellite imagery & AI to turn complex data into simple, actionable insights, helping farmers take timely, preventive action.

Gates Foundation India

1,386,357 views • 3 months ago

AI is transforming the way we create content. From a simple idea to a complete AI-generated video with visuals, storytelling, and editing — FlovaAI makes the creative process faster and easier. No complex tools, no production setup. Just bring your imagination and let AI turn it into reality.

AI is transforming the way we create content. From a simple idea to a complete AI-generated video with visuals, storytelling, and editing — FlovaAI makes the creative process faster and easier. No complex tools, no production setup. Just bring your imagination and let AI turn it into reality.

MR ANDERSON

34,598 views • 11 days ago

Say hi to OK Computer, Kimi's agent mode 🤖🎸 Your AI product & engineering team, all in one. ✨ From chat → multi-page websites, mobile first designs, editable slides ✨ From up to 1 million rows of data → interactive dashboards ✨ Agency: self-scopes, surveys & designs ✨ Natively trained on tools: file system, browser, terminal ✨ More steps, tokens & tools than chat mode, with turbo K2 An agentic model with its own computer, K2 now has true agency.

Say hi to OK Computer, Kimi's agent mode 🤖🎸 Your AI product & engineering team, all in one. ✨ From chat → multi-page websites, mobile first designs, editable slides ✨ From up to 1 million rows of data → interactive dashboards ✨ Agency: self-scopes, surveys & designs ✨ Natively trained on tools: file system, browser, terminal ✨ More steps, tokens & tools than chat mode, with turbo K2 An agentic model with its own computer, K2 now has true agency.

Kimi.ai

303,057 views • 1 year ago

Turn data into insights, faster. 🛰️ Aurora, Pixxel’s Earth observation studio, just got smarter. With Aurora Intelligence, its AI-powered assistant, you can ask questions in natural language, set up your Area of Interest, find the right indices/models to run, and interpret the outputs without navigating complex workflows. Explore now:

Turn data into insights, faster. 🛰️ Aurora, Pixxel’s Earth observation studio, just got smarter. With Aurora Intelligence, its AI-powered assistant, you can ask questions in natural language, set up your Area of Interest, find the right indices/models to run, and interpret the outputs without navigating complex workflows. Explore now:

Pixxel

10,885 views • 3 months ago

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!

Andrew Ng

64,623 views • 9 months ago

Introducing 𝙾𝚙𝚎𝚗 𝚃𝚎𝚊𝚌𝚑 Better Claude Teach that works with any agent, any model, and with your own data. Features: -> Embed Open Teach into your own custom agents -> Learn from in-browser activity and from agent interactions -> Self-hosted for full data sovereignty -> Future proof and cross-stack Get early access:

Introducing 𝙾𝚙𝚎𝚗 𝚃𝚎𝚊𝚌𝚑 Better Claude Teach that works with any agent, any model, and with your own data. Features: -> Embed Open Teach into your own custom agents -> Learn from in-browser activity and from agent interactions -> Self-hosted for full data sovereignty -> Future proof and cross-stack Get early access:

Atai Barkai

38,882 views • 2 months ago

Turn prompting into a jam session with Teams Mode for Microsoft 365 Copilot. Once in the chat, Copilot can orchestrate multi-step tasks, draft content, and even surface relevant files from your Microsoft 365 ecosystem. Learn more:

Turn prompting into a jam session with Teams Mode for Microsoft 365 Copilot. Once in the chat, Copilot can orchestrate multi-step tasks, draft content, and even surface relevant files from your Microsoft 365 ecosystem. Learn more:

Microsoft 365

23,439 views • 10 months ago

Google Brain founder, Andrew Ng: "One of the most important skills of the future is the ability to tell a computer exactly what you want so it can do it for you." In this talk, he explains why the biggest opportunity isn't just using AI. It's learning how to turn work into agentic workflows, break tasks into steps, give agents the right tools and context, add evals, and make the whole system reliable. That's the difference between prompting an AI and engineering an agent that actually works. Watch it today, then read the full guide in the article below.

Google Brain founder, Andrew Ng: "One of the most important skills of the future is the ability to tell a computer exactly what you want so it can do it for you." In this talk, he explains why the biggest opportunity isn't just using AI. It's learning how to turn work into agentic workflows, break tasks into steps, give agents the right tools and context, add evals, and make the whole system reliable. That's the difference between prompting an AI and engineering an agent that actually works. Watch it today, then read the full guide in the article below.

Rahul

14,431 views • 1 month ago

🏆 Introducing TARS 1/ Your AI Executive Assistant that Turns Natural Language into Action. -> With TARS, you can seamlessly orchestrate multiple AI agents to gather insights, automate tasks, and take actions across platforms — all in one place. -> Build upon the 1st productized multi-agent orchestration (MAO) ecosystem designed for AI Agentic workflow. 🏠 Explore more:

🏆 Introducing TARS 1/ Your AI Executive Assistant that Turns Natural Language into Action. -> With TARS, you can seamlessly orchestrate multiple AI agents to gather insights, automate tasks, and take actions across platforms — all in one place. -> Build upon the 1st productized multi-agent orchestration (MAO) ecosystem designed for AI Agentic workflow. 🏠 Explore more:

Questflow

85,907 views • 2 years ago