正在加载视频...

视频加载失败

Cline now uses Anthropic's new "Computer Use" feature to launch a browser, click, type, and scroll. This gives him more autonomy in runtime debugging, end-to-end testing, and even general web use!

66,298 次观看 • 1 年前 •via X (Twitter)

10 条评论

Berte Adama ✌️🇨🇮 的头像
Berte Adama ✌️🇨🇮1 年前

The fact that Cline is free and you're working full time on it 🤯. Thanks ∞

Matthew Sabia 的头像
Matthew Sabia1 年前

You are a true gem, Saoud. When I saw that instead of just having the API execute the out-of-the-box computer use functions and open a new browser window, you implemented this charming animated version into the UI, you gained so many points with me. Great work.

Saoud Rizwan 的头像
Saoud Rizwan1 年前

Cline is a UX to interfacing with AI models that do all the heavy lifting. So it’s my job to make that experience feel as good as possible! Thank you for the kind words Matthew

Chris Fraser 的头像
Chris Fraser1 年前

Was not expecting this. Nice upgrade!

אבי בריטמן 的头像
אבי בריטמן1 年前

You have developed an amazing and huge tool, which does not require a monthly subscription of a high amount... You deserve a programmer productivity award!

Danny Ferrin, CFA 的头像
Danny Ferrin, CFA1 年前

Cline is amazing. Great work and the fact that it leverage existing tooling such as vs code and it allows direct usage of different ai model providers is a great advantage.

Kwaku Kwaku 的头像
Kwaku Kwaku1 年前

I love how Cline's new abilities are opening up more possibilities for runtime debugging and web use. This kind of autonomy is exactly what's needed for more efficient testing and development.

Vladstudio 的头像
Vladstudio1 年前

both Claude and you are incredible. What a time to be a developer!

OutVersus 的头像
OutVersus1 年前

This is incredible! 👏

Philip Fung 的头像
Philip Fung1 年前

Nice dude - burning the midnight oil!

相关视频

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

170,305 次观看 • 1 年前