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.

Introducing MakeReal in jupyter-tldraw ✨ Now you can hand-draw a plot on a tldraw whiteboard and turn it into Matplotlib code directly in a notebook.

Jan-Hendrik Müller

2,297 subscribers

239,726 views • 2 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Jan-Hendrik Müller2 years ago

You can find the source code and installation instructions here

Hari Subramonyam2 years ago

@tldraw @matplotlib I'm eager to learn about potential use cases. Based on the current demo how is this better than, say choosing the plot type from a dropdown list?

Jan-Hendrik Müller2 years ago

@tldraw @matplotlib Same here, I'm also very interested in use-case investigation! One advantage I can see in hand-drawn plots is that I can exactly describe what I want. E.g. this example would not be possible to find in an example gallery with this level of custom details.

Hannah2 years ago

@tldraw @matplotlib Have I ever told you that I really want a detexify type search of the gallery?

Jan-Hendrik Müller2 years ago

@tldraw @matplotlib Oh, absolutely! One could even think of an open source language model trained on the matplotlib gallery.

Robert Haase2 years ago

@tldraw @matplotlib I'm curious how this works! Is it powered by gpt-4-vision? 🙃

Jan-Hendrik Müller2 years ago

@tldraw @matplotlib Yep, the model is called `gpt-4-vision-preview` and here is how I sent the request Under the hood, I'm using traitlets with #anywidget to transport the image. That's very modular, so it would also be possible to connect other large language models.

iandanforth 🦋 @iandanforth.bsky.social2 years ago

@tldraw @matplotlib Who is doing that freehand drawing? I couldn't draw something that steady if my life depended on it.

Jan-Hendrik Müller2 years ago

@tldraw @matplotlib I'll plan a more paw friendly interface!🐕 😉

Pawel Jastrzebski 🇵🇱 🇬🇧2 years ago

@tldraw @matplotlib Jaw-dropping!

Related Videos

This is tldraw in a notebook, connected to the new GPT-4o vision API. This video is at original speed, and it shows how Matplotlib plots are generated from scribbles.

This is tldraw in a notebook, connected to the new GPT-4o vision API. This video is at original speed, and it shows how Matplotlib plots are generated from scribbles.

Jan-Hendrik Müller

261,892 views • 2 years ago

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Leandro von Werra

200,291 views • 1 year ago

Google vibe coded so hard we can now code frontend by drawing on it like a whiteboard 😂 While you're in Google AI Studio, just grab the drawing tools, mark up any UI element, and watch Gemini turn your scribbles into actual code. oh yea now we don't write code anymore, we draw it

Google vibe coded so hard we can now code frontend by drawing on it like a whiteboard 😂 While you're in Google AI Studio, just grab the drawing tools, mark up any UI element, and watch Gemini turn your scribbles into actual code. oh yea now we don't write code anymore, we draw it

corbin

187,730 views • 8 months ago

AI coding just arrived in Jupyter notebooks - and bhupesh ganger (Jupyter co-founder) and I will show you how to use it. Coding by hand is becoming obsolete. The latest Jupyter AI - built by the Jupyter team and showcased at JupyterCon this week - brings AI assistance directly into notebooks. Most AI coding assistants struggle with Jupyter notebooks. Jupyter AI was designed specifically for them. This is the first course to teach it. In this course, Brian and I teach you to: - Generate and debug code directly in notebook cells through an integrated chat interface - Provide the right context (like API docs) to help AI write accurate code - Use Jupyter AI's unique notebook features: drag cells to chat, generate cells from chat, attach context for the LLM We've integrated Jupyter AI directly into the DeepLearningAI platform, so you can start using it immediately. Since Jupyter AI is open source, you can also install and run it locally afterward. Whether you're experienced with notebooks or learning them for the first time, this course will prepare you for AI-assisted notebook development. Start using Jupyter AI (free):

AI coding just arrived in Jupyter notebooks - and bhupesh ganger (Jupyter co-founder) and I will show you how to use it. Coding by hand is becoming obsolete. The latest Jupyter AI - built by the Jupyter team and showcased at JupyterCon this week - brings AI assistance directly into notebooks. Most AI coding assistants struggle with Jupyter notebooks. Jupyter AI was designed specifically for them. This is the first course to teach it. In this course, Brian and I teach you to: - Generate and debug code directly in notebook cells through an integrated chat interface - Provide the right context (like API docs) to help AI write accurate code - Use Jupyter AI's unique notebook features: drag cells to chat, generate cells from chat, attach context for the LLM We've integrated Jupyter AI directly into the DeepLearningAI platform, so you can start using it immediately. Since Jupyter AI is open source, you can also install and run it locally afterward. Whether you're experienced with notebooks or learning them for the first time, this course will prepare you for AI-assisted notebook development. Start using Jupyter AI (free):

Andrew Ng

118,164 views • 8 months ago

I've done analyses in Jupyter notebook for years. Now Code Interpreter can write all the code, but I haven't used it daily because you can't tweak code, re-run analyses, install packages, etc. I built Juno w/ Alexi Robbins to bring GPT into Jupyter for the best of the worlds

I've done analyses in Jupyter notebook for years. Now Code Interpreter can write all the code, but I haven't used it daily because you can't tweak code, re-run analyses, install packages, etc. I built Juno w/ Alexi Robbins to bring GPT into Jupyter for the best of the worlds

Andrew Mauboussin

49,846 views • 3 years ago

This is the coolest tool you'll see today! Introducing Drawdata! 🚀 It allows you to draw a 2-D dataset of any shape in a jupyter notebook. A very handy tool for learning & understanding the behaviour of ML algorithms! Check this out👇

This is the coolest tool you'll see today! Introducing Drawdata! 🚀 It allows you to draw a 2-D dataset of any shape in a jupyter notebook. A very handy tool for learning & understanding the behaviour of ML algorithms! Check this out👇

Akshay 🚀

112,197 views • 2 years ago

Did you know that you can use GitHub Copilot in notebooks? Accept and run generated code with just a click. You can even attach variables from the Jupyter kernel in your requests ✨

Did you know that you can use GitHub Copilot in notebooks? Accept and run generated code with just a click. You can even attach variables from the Jupyter kernel in your requests ✨

Visual Studio Code

44,371 views • 1 year ago

How to Create a Spinning Globe 🌍 with Your Own Data Layers (No Coding Required) Learn how to create a spinning 3D globe map without writing any code using a simple web-based tool. In this step-by-step geospatial tutorial, you'll see how to build an interactive spinning globe, overlay raster and vector data layers, and visualize datasets directly in your browser or in a Jupyter Notebook environment. Web-based demo: Jupyter notebook demo: Video tutorial: #geospatial #opensource #python #jupyter #maplibre

How to Create a Spinning Globe 🌍 with Your Own Data Layers (No Coding Required) Learn how to create a spinning 3D globe map without writing any code using a simple web-based tool. In this step-by-step geospatial tutorial, you'll see how to build an interactive spinning globe, overlay raster and vector data layers, and visualize datasets directly in your browser or in a Jupyter Notebook environment. Web-based demo: Jupyter notebook demo: Video tutorial: #geospatial #opensource #python #jupyter #maplibre

Qiusheng Wu

12,678 views • 4 months ago

Introducing "Save to Notebook" Now you can save agent outputs directly into SciSpace Notebook — all content and citations automatically transferred. No more copy-pasting, just seamless research workflows. Collect, refine, and get publish-ready in no time.

Introducing "Save to Notebook" Now you can save agent outputs directly into SciSpace Notebook — all content and citations automatically transferred. No more copy-pasting, just seamless research workflows. Collect, refine, and get publish-ready in no time.

SciSpace

18,174 views • 5 months ago

Run MATLAB code directly in Jupyter notebooks, JupyterLab, and JupyterHub using the MATLAB kernel. Just open a browser-based MATLAB environment from Jupyter to directly access MATLAB apps and features. Get started with our repo: #Jupyter #Coding

Run MATLAB code directly in Jupyter notebooks, JupyterLab, and JupyterHub using the MATLAB kernel. Just open a browser-based MATLAB environment from Jupyter to directly access MATLAB apps and features. Get started with our repo: #Jupyter #Coding

MATLAB

13,874 views • 1 year ago

This is the future of data science development. Zerve is a new web-based IDE. It's block-based like a Jupyter notebook but follows a different philosophy, and the experience is much different. Check the attached video. I'll walk you through a simple example. Zerve is not a fork of Jupyter. It's a completely reimagined experience where collaboration is a first-class citizen. But there's something else: Unlike in a regular notebook, you can deploy your models directly from Zerve. They store and cache every asset we use and generate inside a notebook, so it takes seconds to deploy your work. A few additional notes about Zerve: 1. It's web-based, so you can access your work anywhere. 2. Collaboration is a first-class citizen. 3. You can deploy your code without going anywhere. 4. It promotes code modularity by using blocks. 5. You can use multiple languages together. 6. You can run code blocks in parallel. Zerve organizes your code as a DAG. Each block inherits the state of every block before it. Everything runs in a serverless architecture. Zerve is free. You can start using it right now by visiting Thanks to the team for answering my questions and sponsoring this post.

This is the future of data science development. Zerve is a new web-based IDE. It's block-based like a Jupyter notebook but follows a different philosophy, and the experience is much different. Check the attached video. I'll walk you through a simple example. Zerve is not a fork of Jupyter. It's a completely reimagined experience where collaboration is a first-class citizen. But there's something else: Unlike in a regular notebook, you can deploy your models directly from Zerve. They store and cache every asset we use and generate inside a notebook, so it takes seconds to deploy your work. A few additional notes about Zerve: 1. It's web-based, so you can access your work anywhere. 2. Collaboration is a first-class citizen. 3. You can deploy your code without going anywhere. 4. It promotes code modularity by using blocks. 5. You can use multiple languages together. 6. You can run code blocks in parallel. Zerve organizes your code as a DAG. Each block inherits the state of every block before it. Everything runs in a serverless architecture. Zerve is free. You can start using it right now by visiting Thanks to the team for answering my questions and sponsoring this post.

Santiago

84,664 views • 2 years ago

Introducing 3D Motion. You can now turn any image into a 3D motion video on Morphic.

Introducing 3D Motion. You can now turn any image into a 3D motion video on Morphic.

Morphic

221,935 views • 11 months ago

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

Charlie Clark

44,335 views • 7 months ago

You can now edit HyperFrames’ Timeline directly! Drag in preview → video updates When Claude Code struggles with timing, you can give it a hand Experimental, open sourced in @hyperframes/player $ npx hyperframes upgrade RT + Comment "Timeline" for source code (must follow)

You can now edit HyperFrames’ Timeline directly! Drag in preview → video updates When Claude Code struggles with timing, you can give it a hand Experimental, open sourced in @hyperframes/player $ npx hyperframes upgrade RT + Comment "Timeline" for source code (must follow)

HeyGen

727,759 views • 2 months ago

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

Riley Brown

73,418 views • 7 months ago

Built an open-source Jupyter Notebook that brings the power of OpenAI's code interpreter into your local Python development environment. Watch how easy it is to use Thread to edit code I wrote, chat with my notebook, or generate charts just using prompts. We built Thread using Next.js, Chakra and Project Jupyter and you can install it by running: pip install thread-dev

Built an open-source Jupyter Notebook that brings the power of OpenAI's code interpreter into your local Python development environment. Watch how easy it is to use Thread to edit code I wrote, chat with my notebook, or generate charts just using prompts. We built Thread using Next.js, Chakra and Project Jupyter and you can install it by running: pip install thread-dev

Ali Shobeiri

112,638 views • 2 years ago

Introducing Bifrost, a tool that uses AI to turn anything from Figma into clean React code automatically. How it works: - Generates usable code for anything in Figma - Drops the code directly into your code editor - Learns how to structure code just like yours 1/4

Introducing Bifrost, a tool that uses AI to turn anything from Figma into clean React code automatically. How it works: - Generates usable code for anything in Figma - Drops the code directly into your code editor - Learns how to structure code just like yours 1/4

kartik

756,127 views • 3 years ago

Introducing Runable Sketch Some ideas live only in your head. You try to describe them. You try to explain the visuals. But it's never quite the same. Now you can simply draw a rough sketch and turn it into a pitch deck, landing page, or video ad. From imagination → reality. Try it today

Introducing Runable Sketch Some ideas live only in your head. You try to describe them. You try to explain the visuals. But it's never quite the same. Now you can simply draw a rough sketch and turn it into a pitch deck, landing page, or video ad. From imagination → reality. Try it today

Umesh Kumar

21,530 views • 4 months ago

Project organization is here: Introducing notebooks in Gemini. You can now keep multiple projects organized and even add past chats and relevant files as sources, so you have a dedicated space to focus on the task at hand. Select “New notebook” in the side panel to get started.

Project organization is here: Introducing notebooks in Gemini. You can now keep multiple projects organized and even add past chats and relevant files as sources, so you have a dedicated space to focus on the task at hand. Select “New notebook” in the side panel to get started.

Google Gemini

2,785,426 views • 3 months ago

You can now push what you’re building in Claude Code directly into Figma. With the latest updates to the Figma MCP server, build a working prototype in code, then send it to a Figma canvas to explore multiple versions.

You can now push what you’re building in Claude Code directly into Figma. With the latest updates to the Figma MCP server, build a working prototype in code, then send it to a Figma canvas to explore multiple versions.

Claude

4,312,922 views • 4 months ago