Loading video...

Video Failed to Load

Go Home

For truly realistic conversational research, we must rethink fully autonomous agent design. DialogLab, our new open-source prototyping framework, uses a human-in-the-loop control strategy to achieve realistic human-AI group simulation, offering a necessary alternative to fully autonomous agents.

GoogleResearch's profile picture

Google Research

103,580 subscribers

82,306 views • 5 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨BREAKING: $TSLA MODEL Y NAILS FIRST FULLY DRIVERLESS DELIVERY • Tesla Model Y drove itself from factory to customer’s home, navigating city streets and highways • No driver, no passengers, no remote control—100% autonomous • Completed the delivery a full day ahead of the planned schedule • Marks the first fully autonomous trip on public highways with zero human intervention
0:15

🚨BREAKING: $TSLA MODEL Y NAILS FIRST FULLY DRIVERLESS DELIVERY • Tesla Model Y drove itself from factory to customer’s home, navigating city streets and highways • No driver, no passengers, no remote control—100% autonomous • Completed the delivery a full day ahead of the planned schedule • Marks the first fully autonomous trip on public highways with zero human intervention

Tsla Archive

4,547,599 views • 1 year ago

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇
0:15

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇

Shruti

63,497 views • 1 year ago

Meet mercury agent. ✅ Most secure AI agent out there ✅ Real human brain architecture ✅ Fully soul driven ✅ Token efficient ✅ Lightweight ✅ Open-source MIT ✅ Asks for permissions to access any new directory, run any strange commands. ✅ and more…
0:13

Meet mercury agent. ✅ Most secure AI agent out there ✅ Real human brain architecture ✅ Fully soul driven ✅ Token efficient ✅ Lightweight ✅ Open-source MIT ✅ Asks for permissions to access any new directory, run any strange commands. ✅ and more…

GitHub Projects Community

19,421 views • 1 month ago

The first AI agent for Robinhood Chain, powered by Virtuals, is live Raxol (axol.io) runs agents with their own wallets, spending only under a mandate a human signed, settling privately through Xochi so the strategy never hits the mempool. All open source.
0:11

The first AI agent for Robinhood Chain, powered by Virtuals, is live Raxol (axol.io) runs agents with their own wallets, spending only under a mandate a human signed, settling privately through Xochi so the strategy never hits the mempool. All open source.

Virtuals Protocol

77,652 views • 23 days ago

So... I literally oneshotted this code with Claude Sonnet 3.7 for replicating the exact same browser sandbox runtime that Manus uses. And I am going to open-source it, welcome contributions for building out the React VNC client, integrating to browser use, agent loop, etc. But we need a name first, should we call it... - Autonomous Neural Universal System - Magnus - or ?
0:10

So... I literally oneshotted this code with Claude Sonnet 3.7 for replicating the exact same browser sandbox runtime that Manus uses. And I am going to open-source it, welcome contributions for building out the React VNC client, integrating to browser use, agent loop, etc. But we need a name first, should we call it... - Autonomous Neural Universal System - Magnus - or ?

jian

419,270 views • 1 year ago

Chinese mass-buying Mac Mini > Mac Mini -> $600 once > Employee -> $1500+ monthly You get a fully functional AI agent that works 24/7 without stopping > 91% more efficient than a human Any tasks: from routine to trading on exchanges Not just an assistant, but an autonomous personal employee
0:12

Chinese mass-buying Mac Mini > Mac Mini -> $600 once > Employee -> $1500+ monthly You get a fully functional AI agent that works 24/7 without stopping > 91% more efficient than a human Any tasks: from routine to trading on exchanges Not just an assistant, but an autonomous personal employee

Bober_smart

20,611 views • 3 months ago

Having seen a few comments, I’d like to clarify something. We haven’t used generative AI in the design team. We have the human capabilities to create what we want, and when our capabilities are limited, we learn and strive to achieve our goals
0:14

Having seen a few comments, I’d like to clarify something. We haven’t used generative AI in the design team. We have the human capabilities to create what we want, and when our capabilities are limited, we learn and strive to achieve our goals

Adrián San Gil | G2 Enelthion

222,476 views • 4 months ago

In May, Elon Musk told CNBC that Tesla's Austin "Robotaxis" would be fully autonomous. This turned out to be a total lie. 6 months later, Tesla's Robotaxi still has a human supervisor behind the wheel! In July, Waymo announced it was testing in Dallas with safety drivers. 4 months later, Waymo's Dallas fleet is now fully autonomous. Tesla is helplessly watching the robotaxi race from the sidelines.
0:17

In May, Elon Musk told CNBC that Tesla's Austin "Robotaxis" would be fully autonomous. This turned out to be a total lie. 6 months later, Tesla's Robotaxi still has a human supervisor behind the wheel! In July, Waymo announced it was testing in Dallas with safety drivers. 4 months later, Waymo's Dallas fleet is now fully autonomous. Tesla is helplessly watching the robotaxi race from the sidelines.

Dan O'Dowd

242,370 views • 7 months ago

Introducing Agent Sandbox, the infinite simulation playground for agents on Virtuals. Craft the perfect autonomous agent in our Sandbox with full control over its personality and goals. Enhance your agent with unique abilities by creating custom functions so they can trade onchain, generate memes, control physical robots and more. The Sandbox is available to all builders with graduated agents in the Developer Panel. For those who want to give it a spin without an existing agent, fret not. Try it out today at and join our Discord ( to jam with like-minded builders. Next stop, Society of Agents.
0:15

Introducing Agent Sandbox, the infinite simulation playground for agents on Virtuals. Craft the perfect autonomous agent in our Sandbox with full control over its personality and goals. Enhance your agent with unique abilities by creating custom functions so they can trade onchain, generate memes, control physical robots and more. The Sandbox is available to all builders with graduated agents in the Developer Panel. For those who want to give it a spin without an existing agent, fret not. Try it out today at and join our Discord ( to jam with like-minded builders. Next stop, Society of Agents.

Virtuals Protocol

188,322 views • 1 year ago

Constructing interactive simulated worlds has been a challenging problem, requiring considerable manual effort for asset creation and articulation, and composing assets to form full scenes. In our new work - DRAWER, we made the process of creating scenes in simulation as simple as taking a video of the scene and out comes a high-quality, fully interactive environment in simulation. No human simulation designer involved! A 🧵(1/7)
0:15

Constructing interactive simulated worlds has been a challenging problem, requiring considerable manual effort for asset creation and articulation, and composing assets to form full scenes. In our new work - DRAWER, we made the process of creating scenes in simulation as simple as taking a video of the scene and out comes a high-quality, fully interactive environment in simulation. No human simulation designer involved! A 🧵(1/7)

Abhishek Gupta

12,072 views • 1 year ago

Shannon: Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark. GitHub: Features: ▪️Fully Autonomous Operation ▪️Pentester-Grade Reports with Reproducible Exploits ▪️Critical OWASP Vulnerability Coverage ▪️Code-Aware Dynamic Testing ▪️Powered by Integrated Security Tools ▪️Parallel Processing for Faster Results
0:16

Shannon: Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark. GitHub: Features: ▪️Fully Autonomous Operation ▪️Pentester-Grade Reports with Reproducible Exploits ▪️Critical OWASP Vulnerability Coverage ▪️Code-Aware Dynamic Testing ▪️Powered by Integrated Security Tools ▪️Parallel Processing for Faster Results

Dark Web Informer

48,788 views • 7 months ago

Introducing WELLAIOS: A revolutionary Open source AI Agent development framework and launchpad on Solana WELLAIOS empowers you to create, tokenize, and trade advanced AI agents on the Solana blockchain. Built by our team of AI professionals, our platform combines a sophisticated open-source framework with multi-modal AI technology, bringing character creation and storytelling to life without having to write a single line of code. Create intelligent digital characters that evolve, interact, and generate content through our library of AI agents. Each character becomes a unique asset equipped with a large set of AI tools on the Solana blockchain. For developers and creators: Join our thriving ecosystem where innovation meets rewards. Build plugins, contribute to our open-source framework, and earn as your creations shape the future. 👀 Sneak Peek: Watch our 3D AI agent capabilities showcase for content creation. Coming soon to Solana. Follow us on X for exclusive updates and be part of the revolution.
0:18

Introducing WELLAIOS: A revolutionary Open source AI Agent development framework and launchpad on Solana WELLAIOS empowers you to create, tokenize, and trade advanced AI agents on the Solana blockchain. Built by our team of AI professionals, our platform combines a sophisticated open-source framework with multi-modal AI technology, bringing character creation and storytelling to life without having to write a single line of code. Create intelligent digital characters that evolve, interact, and generate content through our library of AI agents. Each character becomes a unique asset equipped with a large set of AI tools on the Solana blockchain. For developers and creators: Join our thriving ecosystem where innovation meets rewards. Build plugins, contribute to our open-source framework, and earn as your creations shape the future. 👀 Sneak Peek: Watch our 3D AI agent capabilities showcase for content creation. Coming soon to Solana. Follow us on X for exclusive updates and be part of the revolution.

WELL3

10,503 views • 1 year ago

6,000 → over 12,000 agent-to-human pairings in the Billions Network In 1 week we doubled the number - rapid growth after our launch 3 weeks ago! Get your AI agent paired with your Billions App profile, Earn Rewards with your OpenClaw agent, and Grow the Billions Network of Humans and AI agents Source: Billions Network Blockchain Explorer
0:14

6,000 → over 12,000 agent-to-human pairings in the Billions Network In 1 week we doubled the number - rapid growth after our launch 3 weeks ago! Get your AI agent paired with your Billions App profile, Earn Rewards with your OpenClaw agent, and Grow the Billions Network of Humans and AI agents Source: Billions Network Blockchain Explorer

Billions

70,209 views • 4 months ago

AI agents were never fully autonomous. They could think. They could use tools. But they couldn’t truly communicate, transact, or maintain persistent relationships on-chain. Until now. Packet MCP is live. Agents can now: → own wallet-native inboxes → receive encrypted messages → send & receive payments → react to live on-chain events → maintain persistent communication threads This is communication infrastructure for autonomous systems. Not another API wrapper. Not another hosted backend. An agent with a wallet can now operate as a sovereign network participant on Solana Docs:
0:17

AI agents were never fully autonomous. They could think. They could use tools. But they couldn’t truly communicate, transact, or maintain persistent relationships on-chain. Until now. Packet MCP is live. Agents can now: → own wallet-native inboxes → receive encrypted messages → send & receive payments → react to live on-chain events → maintain persistent communication threads This is communication infrastructure for autonomous systems. Not another API wrapper. Not another hosted backend. An agent with a wallet can now operate as a sovereign network participant on Solana Docs:

Packet

36,628 views • 1 month ago

aiPump introduces ⇢ AI Agent Traders on Hyperliquid Hyperliquid has become the #1 most popular battleground for skilled traders in crypto. But there is a clear gap in the market. TradFi knows it best: robots & AI can execute a trading strategy more efficiently and seamlessly than humans ever could. ⇢ This is the next frontier of expansion for our infrastructure products for AI Agents. With aiPump's new products, anyone will be able to deploy an AI Agent Trader that is able to trade futures on Hyperliquid and climb the ranks. An autonomous trader, implementing your trading strategy of the most dynamic trading market in crypto. ⇢ Stay tuned.
0:14

aiPump introduces ⇢ AI Agent Traders on Hyperliquid Hyperliquid has become the #1 most popular battleground for skilled traders in crypto. But there is a clear gap in the market. TradFi knows it best: robots & AI can execute a trading strategy more efficiently and seamlessly than humans ever could. ⇢ This is the next frontier of expansion for our infrastructure products for AI Agents. With aiPump's new products, anyone will be able to deploy an AI Agent Trader that is able to trade futures on Hyperliquid and climb the ranks. An autonomous trader, implementing your trading strategy of the most dynamic trading market in crypto. ⇢ Stay tuned.

aiPump

143,356 views • 1 year ago

Today is a big day. We are proud to announce our new joint venture with the Serviceplan Group: Masumi - The AI Agent Network Protocol A decentralized network of AI agents to collaborate and monetize your agentic services
0:15

Today is a big day. We are proud to announce our new joint venture with the Serviceplan Group: Masumi - The AI Agent Network Protocol A decentralized network of AI agents to collaborate and monetize your agentic services

NMKR

35,552 views • 1 year ago

Stop spending hours on manual work. You can now use a multi-agent AI workforce to get more work done in less time. Here's how 👇 --- Try Eigent AI - Lets you build and run a custom AI workforce on your desktop. - Automate complex workflows using multi-agent task execution. - Built on CAMEL-AI’s top open-source projects ( CAMEL-AI.org & OWL). - Boost productivity with deep customization and strong privacy --- Features: - Customize Your AI Workforce: Build task-specific agents with domain skills and tools. - Faster Execution: Eigent runs agents in parallel to automate complex workflows. - Human-in-the-loop: Automatically asks for help when tasks hit uncertainty. --- What sets Eigent apart? - 3–5× faster task execution using a parallel multi-agent workforce. - Modular design lets you add new capabilities without changing the core system. - Self-optimizing agents that replan and adapt during execution for higher success. - Deploy anywhere: cloud, local, or enterprise, with full open-source flexibility. --- Try building your multi-agent AI workforce here: Join their community to build your multi-agent workforce: Check their GitHub: ---
0:13

Stop spending hours on manual work. You can now use a multi-agent AI workforce to get more work done in less time. Here's how 👇 --- Try Eigent AI - Lets you build and run a custom AI workforce on your desktop. - Automate complex workflows using multi-agent task execution. - Built on CAMEL-AI’s top open-source projects ( CAMEL-AI.org & OWL). - Boost productivity with deep customization and strong privacy --- Features: - Customize Your AI Workforce: Build task-specific agents with domain skills and tools. - Faster Execution: Eigent runs agents in parallel to automate complex workflows. - Human-in-the-loop: Automatically asks for help when tasks hit uncertainty. --- What sets Eigent apart? - 3–5× faster task execution using a parallel multi-agent workforce. - Modular design lets you add new capabilities without changing the core system. - Self-optimizing agents that replan and adapt during execution for higher success. - Deploy anywhere: cloud, local, or enterprise, with full open-source flexibility. --- Try building your multi-agent AI workforce here: Join their community to build your multi-agent workforce: Check their GitHub: ---

Shushant Lakhyani

20,423 views • 1 year ago

⚠️ SECURITY: VITALIK BUTERIN DITCHES CLOUD AI, REVEALS FULLY LOCAL LLM SETUP Ethereum co-founder vitalik.eth has moved entirely off cloud AI services and published his full private AI stack in a new blog post. He now runs the Qwen3.5:35B model locally on an Nvidia 5090 laptop, hitting 90 tokens per second. He cited research showing roughly 15% of AI agent skills contain malicious instructions, and that parsing a single malicious webpage could fully compromise an AI assistant. Buterin also open-sourced a messaging daemon requiring human approval for all outbound messages to third parties.
0:15

⚠️ SECURITY: VITALIK BUTERIN DITCHES CLOUD AI, REVEALS FULLY LOCAL LLM SETUP Ethereum co-founder vitalik.eth has moved entirely off cloud AI services and published his full private AI stack in a new blog post. He now runs the Qwen3.5:35B model locally on an Nvidia 5090 laptop, hitting 90 tokens per second. He cited research showing roughly 15% of AI agent skills contain malicious instructions, and that parsing a single malicious webpage could fully compromise an AI assistant. Buterin also open-sourced a messaging daemon requiring human approval for all outbound messages to third parties.

BSCN

25,445 views • 3 months ago