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.

FDM-1 completes complex tasks and navigates interfaces well enough to use CAD applications. Forking VMs allow us to snapshot when a successful operation completes (extrusion, selection, etc.), letting us apply test-time compute to computer use.

Standard Intelligence

10,409 subscribers

59,736 views • 8 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Teaching bimanual robot hands to perform very complex tasks has been notoriously challenging. In our work, Bidex: Bimanual Dexterity for Complex Tasks, we’ve developed a low-cost system that completes a wide range of highly dexterous tasks in real-time.

Teaching bimanual robot hands to perform very complex tasks has been notoriously challenging. In our work, Bidex: Bimanual Dexterity for Complex Tasks, we’ve developed a low-cost system that completes a wide range of highly dexterous tasks in real-time.

Kenny Shaw

40,146 views • 1 year ago

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent

Leandro von Werra

17,126 views • 1 year ago

3/ computer use: it can operate desktop, browser, and mobile. muse spark 1.1 is trained to know when to automate and when to use interfaces directly. it scripts when that’s faster, clicks when direct interaction is simpler, and batches actions at each step.

3/ computer use: it can operate desktop, browser, and mobile. muse spark 1.1 is trained to know when to automate and when to use interfaces directly. it scripts when that’s faster, clicks when direct interaction is simpler, and batches actions at each step.

Alexandr Wang

163,323 views • 4 months ago

Introducing Computer Use in TREX. TREX now spins up the relevant services for your changes and uses computer use to test them end to end. It can test desktop apps, click through a web app in a browser to simulate user flows, or use a terminal to test your CLI.

Introducing Computer Use in TREX. TREX now spins up the relevant services for your changes and uses computer use to test them end to end. It can test desktop apps, click through a web app in a browser to simulate user flows, or use a terminal to test your CLI.

Greptile

15,863 views • 9 days ago

Airbus #A400M Firefighting Kit completes a successful test campaign in France. Learn more:

Airbus #A400M Firefighting Kit completes a successful test campaign in France. Learn more:

Airbus Defence

21,233 views • 1 year ago

True computer use is fully general. FDM-1 uses arrow keys on a computer to steer a car in San Francisco with less than 1 hour of fine-tuning data. The action policy is critical: tuning FDM-1 to drive gets much higher accuracy than tuning just the video encoder on the same data.

True computer use is fully general. FDM-1 uses arrow keys on a computer to steer a car in San Francisco with less than 1 hour of fine-tuning data. The action policy is critical: tuning FDM-1 to drive gets much higher accuracy than tuning just the video encoder on the same data.

Standard Intelligence

72,532 views • 8 months ago

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:

Andrew Ng

170,689 views • 1 year ago

2/ Task Bridge Computer use agent that reads through your slack messages, identifies tasks, and submits them to Asana Zero effort task management with computer use

2/ Task Bridge Computer use agent that reads through your slack messages, identifies tasks, and submits them to Asana Zero effort task management with computer use

Alex Reibman 🖇️

43,619 views • 1 year ago

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

Shubham Saboo

64,206 views • 1 year ago

This might be the most advanced AI agent to date. It’s called Runner H by H, and it automates complex, multi-step tasks from just a prompt. You basically describe what you want and it takes over your computer to complete it. Some key features: - Outperforms competitors like Anthropic’s Computer Use on the WebVoyager benchmark. - Navigates web interfaces through pixel-level interpretation and semantic understanding. - Adapts to UI changes automatically. - Handles complex workflows like e-commerce and financial services onboarding. They have already raised $220M and looks like we are entering the agentic era! You can sign up to their waitlist now (link below).

This might be the most advanced AI agent to date. It’s called Runner H by H, and it automates complex, multi-step tasks from just a prompt. You basically describe what you want and it takes over your computer to complete it. Some key features: - Outperforms competitors like Anthropic’s Computer Use on the WebVoyager benchmark. - Navigates web interfaces through pixel-level interpretation and semantic understanding. - Adapts to UI changes automatically. - Handles complex workflows like e-commerce and financial services onboarding. They have already raised $220M and looks like we are entering the agentic era! You can sign up to their waitlist now (link below).

Alvaro Cintas

86,907 views • 1 year ago

So Microsoft has just announced its own OpenClaw?! Copilot Tasks will be able to: → Create a plan → Use a web browser → Use your apps (Outlook, Google Calendar, etc.) → Generate docs, spreadsheets, presentations And schedule tasks when you want.

So Microsoft has just announced its own OpenClaw?! Copilot Tasks will be able to: → Create a plan → Use a web browser → Use your apps (Outlook, Google Calendar, etc.) → Generate docs, spreadsheets, presentations And schedule tasks when you want.

Paul Couvert

100,382 views • 8 months ago

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

Claude

78,398,496 views • 7 months ago

Our agent scientist, Agent S4, just got an open 27B model to beat GPT-5.5 and Claude Opus 4.8 on OSWorld V2, with the model's weights left exactly as they were. With the interfaces S4 evolved, Qwen3.8-27B completes 21.3% of the 108 tasks, the highest binary success of any open-source computer-use agent and 3.8x the same model with fixed interfaces. It costs $1.10 per task, against $25.50 for GPT-5.5 and $72.40 for Opus 4.8 💸 Full write-up:

Our agent scientist, Agent S4, just got an open 27B model to beat GPT-5.5 and Claude Opus 4.8 on OSWorld V2, with the model's weights left exactly as they were. With the interfaces S4 evolved, Qwen3.8-27B completes 21.3% of the 108 tasks, the highest binary success of any open-source computer-use agent and 3.8x the same model with fixed interfaces. It costs $1.10 per task, against $25.50 for GPT-5.5 and $72.40 for Opus 4.8 💸 Full write-up:

Simular

607,464 views • 14 days ago

Internet Computer's Caffeine is Now Available in Claude Internet Computer (DFINITY Foundation)'s Caffeine launches a direct integration with Anthropic’s Claude, enabling the instantaneous generation of production-ready applications through natural language interfaces. This deployment enables "vibe coders" and enterprise teams to use caffeine’s modular frameworks to build, iterate on, and deploy complex software without leaving the LLM environment.

Internet Computer's Caffeine is Now Available in Claude Internet Computer (DFINITY Foundation)'s Caffeine launches a direct integration with Anthropic’s Claude, enabling the instantaneous generation of production-ready applications through natural language interfaces. This deployment enables "vibe coders" and enterprise teams to use caffeine’s modular frameworks to build, iterate on, and deploy complex software without leaving the LLM environment.

BSCN

31,917 views • 4 months ago

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

Bowen Wang

93,360 views • 1 year ago

Russia declares war on Elon Musk. "They won't allow us to use Starlink. We must use nuclear weapons in space and eliminate Musk's satellites."

Russia declares war on Elon Musk. "They won't allow us to use Starlink. We must use nuclear weapons in space and eliminate Musk's satellites."

Jürgen Nauditt 🇩🇪🇺🇦

120,988 views • 9 months ago

France falling into line behind the United States using the same playbook as the UK - refusing to allow the US to use French bases to bomb Iran offensively while allowing the US to use French bases to bomb Iran defensively.

France falling into line behind the United States using the same playbook as the UK - refusing to allow the US to use French bases to bomb Iran offensively while allowing the US to use French bases to bomb Iran defensively.

Saul Staniforth

56,458 views • 8 months ago