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.

We just solved the long-horizon planning & execution issue with Agents 🤯! Excited to announce that MultiOn AI can now take actions well over 500+ steps without loosing context & cross-operate on 10+ websites as part of a single task 🤩!! Our latest upgrade cracks the goal divergence &... show more

Div Garg

22,360 subscribers

309,956 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Div Garg2 years ago

The idea is to simply leave it running it everyday and have it to do tasks for you in the background (more scheduling features soon!) We have set up a X handle where @MultiON_AI will go find & tweet about the latest AI news everyday 🤩 (no need for AI news influencers anymore 😉): Follow for the latest AI news 👇

Div Garg2 years ago

Here's a crazy complex prompt you can try yourself with @MultiON_AI (pls join our discord or request access): "Go to twitter. Search for the last tweets i made (check the last 5 tweets). Remember them so then you can go a search for super interesting AI news. Search the news on up to 3 different sources. If you see that the source has not really interesting AI news or i already made a tweet about that, then go to a different one. When you finish the research, go and make a few small and interesting AI tweets with the info you gathered. Make sure the tweet is small but informative and interesting for AI enthusiasts. Don't do more than 5 tweets"

Div Garg2 years ago

Having agents now do complex long-running tasks like taking a target candidate profile and continuously outreaching all the matches on linkedin or searching for an ideal house or deal on an item is not a dream anymore!! Very excited about how much human time we can save 🤩

near2 years ago

@MultiON_AI chat is this real

Div Garg2 years ago

@MultiON_AI yep, want access?

David Stevens2 years ago

@MultiON_AI It’s like Neo’s agent searching for Morpheus.

Div Garg2 years ago

@MultiON_AI 😂. We will find him.

Jacques2 years ago

@MultiON_AI I find it hilarious how these models will constantly automatically use hashtags in every tweet they make, as if it's the normal way to tweet. lol

Christopher Tavolazzi2 years ago

@MultiON_AI Hello, I’d like to review this in depth. I’m a journalist and former independent contractor for the Adobe Learn team, I built the current default tutorial set for Photoshop (the hybrid tutorials were my project)

Div Garg2 years ago

@MultiON_AI Please DM me :)

Related Videos

It's time to make AI Agents useful. I'm thrilled to announce that the HyperWrite Agent Studio is now live! Just show it a task once by doing it yourself, and the AI can repeat it.

It's time to make AI Agents useful. I'm thrilled to announce that the HyperWrite Agent Studio is now live! Just show it a task once by doing it yourself, and the AI can repeat it.

Matt Shumer

102,316 views • 2 years ago

Async, automatic, non-blocking context compaction for long-running agents. Last week I gave a talk called Space Machine Sandboxes at the Daytona AI builders meetup about patterns for long-running agents. I work a lot on voice AI agents, which are fundamentally multi-turn, long-context loops. I also build lots of other AI agent stuff, often as part of bigger systems that include voice. One of the patterns I showed in the talk is non-blocking compaction. Here's a short clip.

Async, automatic, non-blocking context compaction for long-running agents. Last week I gave a talk called Space Machine Sandboxes at the Daytona AI builders meetup about patterns for long-running agents. I work a lot on voice AI agents, which are fundamentally multi-turn, long-context loops. I also build lots of other AI agent stuff, often as part of bigger systems that include voice. One of the patterns I showed in the talk is non-blocking compaction. Here's a short clip.

kwindla

25,877 views • 4 months ago

We’re excited to announce that our AI agent, Tutorial Agent, is now integrated into the CZanga AI terminal to assist with web3 and blockchain learning CZanga is building a cutting-edge AI agents application and contributing to the AI layer of the iDos Games Engine This partnership opens the door for joint R&D as we explore the full potential of LLMs together.

We’re excited to announce that our AI agent, Tutorial Agent, is now integrated into the CZanga AI terminal to assist with web3 and blockchain learning CZanga is building a cutting-edge AI agents application and contributing to the AI layer of the iDos Games Engine This partnership opens the door for joint R&D as we explore the full potential of LLMs together.

Tutorial

17,943 views • 1 year ago

NOW you can BUILD REAL Multi-Modal Agents with our API! 🚀 Excited to announce our API is now publicly available Memories.ai 😃 Memories.ai is building the visual memory layer for AI, it enables AI to see and remember like humans do. 2025 is the year of agents, 2026 is the year of multi-modal agents! 🌟

NOW you can BUILD REAL Multi-Modal Agents with our API! 🚀 Excited to announce our API is now publicly available Memories.ai 😃 Memories.ai is building the visual memory layer for AI, it enables AI to see and remember like humans do. 2025 is the year of agents, 2026 is the year of multi-modal agents! 🌟

Shawn Shen

530,527 views • 10 months ago

It’s long been our prediction that 2025 will be the “year of the AI agent”. As the industry explores new and innovative ways to use agents, every company must adapt or die. Us too. Today we announce GameGPT’s AI Agent Platform. A full breakdown below. 🧵

It’s long been our prediction that 2025 will be the “year of the AI agent”. As the industry explores new and innovative ways to use agents, every company must adapt or die. Us too. Today we announce GameGPT’s AI Agent Platform. A full breakdown below. 🧵

GameGPT by PRISM

18,633 views • 1 year ago

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

104,964 views • 1 year ago

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()

AK

81,402 views • 1 year ago

AI agents are UNRELIABLE because you're giving them too much control. Instead of using a single prompt, structure your agent as a series of high level steps. In this demo, I'm running the same steps across two different websites. Good steps = good output. It's that simple!

AI agents are UNRELIABLE because you're giving them too much control. Instead of using a single prompt, structure your agent as a series of high level steps. In this demo, I'm running the same steps across two different websites. Good steps = good output. It's that simple!

Paul Klein IV

71,482 views • 1 year ago

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Aaron Levie

139,591 views • 1 year ago

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

185,933 views • 1 year ago

What if AI agents could hunt for yield on the web? We built a small demo using the TinyFish Web Agent API The agent navigates websites, executes multi-step research workflows, completely autonomously. Exciting for the future of autonomous yield strategies. #TinyFishAccelerator #BuildInPublic

What if AI agents could hunt for yield on the web? We built a small demo using the TinyFish Web Agent API The agent navigates websites, executes multi-step research workflows, completely autonomously. Exciting for the future of autonomous yield strategies. #TinyFishAccelerator #BuildInPublic

YieldFi

10,901 views • 3 months ago

And here's today's AI news from X as a video. In an hour I had my AI agents read all of tech on X, find all the important news, papers, and much more. Write a report. Bring that report over to NotebookLM. Then create all this and post it back to you. It's all X.

And here's today's AI news from X as a video. In an hour I had my AI agents read all of tech on X, find all the important news, papers, and much more. Write a report. Bring that report over to NotebookLM. Then create all this and post it back to you. It's all X.

Robert Scoble

36,370 views • 3 months ago

Just when I thought AI couldn't get any more impressive, AutoGPT and AI Agents blows my mind 🤯 Here, AI agent performs product research and creates a summary on the top headphones. This is insane! And the craziest part is that it's powered by GPT-4.

Just when I thought AI couldn't get any more impressive, AutoGPT and AI Agents blows my mind 🤯 Here, AI agent performs product research and creates a summary on the top headphones. This is insane! And the craziest part is that it's powered by GPT-4.

Rahul

34,139 views • 3 years ago

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!

Jason ✨👾SaaStr.Ai✨ Lemkin

18,031 views • 1 month ago

We are excited to announce the arrival of our most requested adapter! 🚀 OpenRouter adapter lands in TanStack AI with over 300+ models for you to play with! 🔥 Try it out with the latest version today!

We are excited to announce the arrival of our most requested adapter! 🚀 OpenRouter adapter lands in TanStack AI with over 300+ models for you to play with! 🔥 Try it out with the latest version today!

TANSTACK

68,127 views • 4 months ago

Announcing our latest research breakthrough: Agent Q - bringing next-generation AI agents with planning and AI self-healing capabilities, with a 340% improvement over LLama 3's baseline zero-shot performance!

Announcing our latest research breakthrough: Agent Q - bringing next-generation AI agents with planning and AI self-healing capabilities, with a 340% improvement over LLama 3's baseline zero-shot performance!

Please

214,995 views • 1 year ago

🤖 HYTOPIA AI Agents Society (Start Building!) 🎮 We've just added the "ai-agents" example to our SDK, which is a starting point of a game with an AI Agent Society! You can use this example as a template to build your own AI agents for a HYTOPIA game:

🤖 HYTOPIA AI Agents Society (Start Building!) 🎮 We've just added the "ai-agents" example to our SDK, which is a starting point of a game with an AI Agent Society! You can use this example as a template to build your own AI agents for a HYTOPIA game:

HYTOPIA

15,729 views • 1 year ago

The first preview of Holoworld AI agents- AI Arthur Hayes helps you seamlessly swap from Arbitrum ETH to Degen 🎩 on Base L3 while sharing his take on the latest market news and prices. How we interact on-chain is about to change as we know it. We're expanding coverage to additional chains and on-chain actions soon!

The first preview of Holoworld AI agents- AI Arthur Hayes helps you seamlessly swap from Arbitrum ETH to Degen 🎩 on Base L3 while sharing his take on the latest market news and prices. How we interact on-chain is about to change as we know it. We're expanding coverage to additional chains and on-chain actions soon!

Holoworld AI

58,067 views • 2 years ago