Loading video...

Video Failed to Load

Go Home

We're launching Computer Use in smolagents! 🥳 -> As vision models become more capable, they become able to power complex agentic workflows. Especially Qwen-VL models, that support built-in grounding, i.e. ability to locate any element in an image by its coordinates, thus to click any item on a screenshot....

43,850 views • 1 year ago •via X (Twitter)

11 Comments

m_ric's profile picture
m_ric1 year ago

Try the demo here 👉

MightyBot's profile picture
MightyBot1 year ago

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

Dhruv Diddi's profile picture
Dhruv Diddi1 year ago

@Thom_Wolf Multimodal models are going to pick up real fast ⚡️

Oli's profile picture
Oli1 year ago

i think ui tars 1.5 7b would work better here its much better at this

Piyush's profile picture
Piyush1 year ago

Awesome! Gonna try this out! 😁

ぽいロード@音技術者's profile picture
ぽいロード@音技術者1 year ago

Hey Computer use AI ,please use 3d modeling soft and create this

Van Tuan Bui's profile picture
Van Tuan Bui1 year ago

Congrats on the launch! 🎉

Sam Woods's profile picture
Sam Woods1 year ago

Smolagents with computer use powered by vision models like Qwen-VL sounds really powerful

蕭夫SioFU's profile picture
蕭夫SioFU1 year ago

@huggingface cool

Trelis Research's profile picture
Trelis Research1 year ago

nice, what vlms did you test out that work best?

gladosb5's profile picture
gladosb51 year ago

hmmmmmm

Related Videos

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

170,335 views • 1 year ago