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.

CODE EXECUTION IN CANVAS🎨 Canvas becomes an automated SWE and a data scientist. Search for API docs, ask the model to write code and execute, get the plot!

Karina Nguyen

43,232 subscribers

46,579 views • 1 year ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

trenchwarrior691 year ago

wheres epsilon

Mahaoo1 year ago

Next step is to create files directly on the file system via the desktop app

lucas1 year ago

can see better jupyter notebook is taking shape. ai native, reproducible experiment trace.

Tanvi1 year ago

Cool got it

Pseudonym 🦅1 year ago

just let me import my git repo. The copy paste workflow is dumb.

Aleeeex19881 year ago

Tried to scrape some test data , did not work out. Also many libs are not installed I.e making a Pac-Man game , that would be so cool!

TESKH1 year ago

Do you know if this is coming to the windows app as well or just web?

Youssef KH (ucefkh.eth)1 year ago

Cna you execute assembly?

GoTech Roofing1 year ago

Canvas worked well the 1st day. Then too many concurent users - cant even code now....

Joel Oliveira1 year ago

We need seamless integration with vscode. That’s the way.

Related Videos

I've always liked the infinite canvas as an exploration medium, but I could never get into Figma because I'm faster at designing in code So this weekend I made an app that combines canvas with code editor - write React, and it appears in the canvas

I've always liked the infinite canvas as an exploration medium, but I could never get into Figma because I'm faster at designing in code So this weekend I made an app that combines canvas with code editor - write React, and it appears in the canvas

nanda

78,206 views • 1 month ago

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

Andrew Ng

128,085 views • 1 year ago

Tired: code or canvas Wired: code AND canvas Introducing Claude Code to Figma

Tired: code or canvas Wired: code AND canvas Introducing Claude Code to Figma

Figma

3,065,382 views • 3 months ago

Attachment issues (resolved) You can attach 30+ file types (docs, data, media, and code) directly in Make, so you can move beyond placeholders and design with real inputs from code to canvas.

Attachment issues (resolved) You can attach 30+ file types (docs, data, media, and code) directly in Make, so you can move beyond placeholders and design with real inputs from code to canvas.

Figma

34,917 views • 2 months ago

With Canvas in Gemini, you can: ⌨️ Write, iterate & preview React/HTML code 📝 Draft & edit comprehensive documents 🎨 Build interactive prototypes, games & visualization …and more. Simply select ‘Canvas’ in your prompt bar and you can write and edit documents or code, with changes appearing in real-time: Try it today and share your Canvas creations by tagging us here!

With Canvas in Gemini, you can: ⌨️ Write, iterate & preview React/HTML code 📝 Draft & edit comprehensive documents 🎨 Build interactive prototypes, games & visualization …and more. Simply select ‘Canvas’ in your prompt bar and you can write and edit documents or code, with changes appearing in real-time: Try it today and share your Canvas creations by tagging us here!

Google Gemini

414,938 views • 1 year ago

The world’s most intuitive AI canvas is here. We built an agentic canvas for generating pro-level creative assets. Think Figma meets Sora. Comment “Canvas” and we’ll DM you an invite code.

The world’s most intuitive AI canvas is here. We built an agentic canvas for generating pro-level creative assets. Think Figma meets Sora. Comment “Canvas” and we’ll DM you an invite code.

konstantinpaulus

13,538 views • 11 months ago

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.

Google AI Developers

16,481 views • 7 months ago

For the first time we are fundamentally changing how humans can collaborate with ChatGPT since it launched two years ago. We’re introducing canvas, a new interface for working with ChatGPT on writing and coding projects that go beyond simple chat. Product and model features: 1/ Ask for in-line feedback. With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give in-line feedback and suggestions with the entire project in mind. 2/ Directly edit the model's output and select a specific area for targeted editing. You control your creative work on canvas. You can directly edit text or code. 3/ Menu of shortcuts. There’s a menu of shortcuts for you to ask ChatGPT to adjust writing length, debug your code, and quickly perform other useful actions. You can also restore previous versions of your work by using the back button in canvas. 4/ Use search with canvas for research writing! As we are moving towards the new paradigm of reasoning we are fundamentally evolving the chat interface into a more collaborative human-AI interaction. Today you can say “browse / use browsing to find XYZ on the internet and write a report in canvas”

For the first time we are fundamentally changing how humans can collaborate with ChatGPT since it launched two years ago. We’re introducing canvas, a new interface for working with ChatGPT on writing and coding projects that go beyond simple chat. Product and model features: 1/ Ask for in-line feedback. With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give in-line feedback and suggestions with the entire project in mind. 2/ Directly edit the model's output and select a specific area for targeted editing. You control your creative work on canvas. You can directly edit text or code. 3/ Menu of shortcuts. There’s a menu of shortcuts for you to ask ChatGPT to adjust writing length, debug your code, and quickly perform other useful actions. You can also restore previous versions of your work by using the back button in canvas. 4/ Use search with canvas for research writing! As we are moving towards the new paradigm of reasoning we are fundamentally evolving the chat interface into a more collaborative human-AI interaction. Today you can say “browse / use browsing to find XYZ on the internet and write a report in canvas”

Karina

845,496 views • 1 year 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

200,281 views • 1 year ago

LlamaAcademy: a factory that teaches LLaMA's how write API code. ChatGPT Plugins, but no manifest file is needed -- it just reads the API docs like a human would! For example, here is a finetuned model that learned how to talk to Notion by reading its API docs:

LlamaAcademy: a factory that teaches LLaMA's how write API code. ChatGPT Plugins, but no manifest file is needed -- it just reads the API docs like a human would! For example, here is a finetuned model that learned how to talk to Notion by reading its API docs:

Daniel Gross

582,076 views • 3 years ago

Introducing Codex to Figma: Roundtrip between code and canvas through the Figma MCP server

Introducing Codex to Figma: Roundtrip between code and canvas through the Figma MCP server

Figma

179,484 views • 3 months ago

Canvas—a new way to work with ChatGPT to draft, edit, and get feedback on writing & code—is now available to all users in our 4o model. It’s fully rolled out on web and the ChatGPT desktop app for Windows.

Canvas—a new way to work with ChatGPT to draft, edit, and get feedback on writing & code—is now available to all users in our 4o model. It’s fully rolled out on web and the ChatGPT desktop app for Windows.

OpenAI

653,714 views • 1 year ago

HTML canvas has always been a black box to the browser, but not anymore. The HTML-in-Canvas API lets you integrate real DOM elements directly into the canvas, making them fully searchable, accessible, natively translatable, and inspectable. Fuse shaders and semantics to build new UI, eliminating the need for separate DOM overlays → The web is about to get a whole lot more whimsical and we can't wait to see it 🎨

HTML canvas has always been a black box to the browser, but not anymore. The HTML-in-Canvas API lets you integrate real DOM elements directly into the canvas, making them fully searchable, accessible, natively translatable, and inspectable. Fuse shaders and semantics to build new UI, eliminating the need for separate DOM overlays → The web is about to get a whole lot more whimsical and we can't wait to see it 🎨

Chrome for Developers

40,487 views • 4 days ago

🎨 Students, coders, professionals – our new Canvas feature is for everyone! 🎨 From documents to code, the Google Gemini App helps you create with confidence and bring your ideas to life. 👉

🎨 Students, coders, professionals – our new Canvas feature is for everyone! 🎨 From documents to code, the Google Gemini App helps you create with confidence and bring your ideas to life. 👉

Google Workspace

19,178 views • 1 year ago

Something we have been working on recently is an improved chat export for ChatGPT to Markdown, including support for ChatGPT search results and sources, canvas, code blocks, advanced data analysis, o1 chain-of-thought summaries, and timestamps for all messages - give it a try in AIPRM for ChatGPT version 1.3.1.3

Something we have been working on recently is an improved chat export for ChatGPT to Markdown, including support for ChatGPT search results and sources, canvas, code blocks, advanced data analysis, o1 chain-of-thought summaries, and timestamps for all messages - give it a try in AIPRM for ChatGPT version 1.3.1.3

Tibor Blaho

33,723 views • 1 year ago

👋 Meet Canvas, a new interactive space in Gemini that simplifies creating, refining, and sharing your work. Canvas is like a shared whiteboard where you and Gemini can work together. You can refine documents, write code, design prototypes and more while Gemini collaborates with you in real-time to make improvements. Try Canvas today here: and share your creations with us in the comments!

👋 Meet Canvas, a new interactive space in Gemini that simplifies creating, refining, and sharing your work. Canvas is like a shared whiteboard where you and Gemini can work together. You can refine documents, write code, design prototypes and more while Gemini collaborates with you in real-time to make improvements. Try Canvas today here: and share your creations with us in the comments!

G3mini

63,795 views • 1 year ago

Most API docs only show HTTP endpoints, but developers write code with SDKs. We're doing things differently with the Stainless Docs Platform, now available in early access. Stainless Docs are SDK-native. They update automatically when your API changes. Devs see your docs in the language of their choice with method signatures, types, and accurate code snippets.

Most API docs only show HTTP endpoints, but developers write code with SDKs. We're doing things differently with the Stainless Docs Platform, now available in early access. Stainless Docs are SDK-native. They update automatically when your API changes. Devs see your docs in the language of their choice with method signatures, types, and accurate code snippets.

Stainless

25,732 views • 7 months ago

Design → code → canvas → feedback → repeat. The Figma MCP server is now bidirectional. GitHub Copilot users can pull design context into code and push working UI back to the Figma canvas, all from Visual Studio Code . No handoffs or context switching. Just flow.

Design → code → canvas → feedback → repeat. The Figma MCP server is now bidirectional. GitHub Copilot users can pull design context into code and push working UI back to the Figma canvas, all from Visual Studio Code . No handoffs or context switching. Just flow.

Mario Rodriguez

105,567 views • 3 months ago

Introducing Explore — an all-new experience for slicing, dicing, and visualizing data. Explore gives everyone the analytical powers of Hex in a familiar, no-code UI, with: 🐉 Drag & drop - Add dimensions and measures to a visual canvas 🎨 Pivots & viz - Customize, color, and group data to make insights pop 📊 Spreadsheet calculations - Build custom logic with formulas 🪢 No-code joins - Join tables with automatic key detection and fan-out deduplication Plus new powers for Magic AI ✨, conditional notifications 🔔 for data apps, and semantic model sync 🤝 for LookML and MetricFlow. Learn more at

Introducing Explore — an all-new experience for slicing, dicing, and visualizing data. Explore gives everyone the analytical powers of Hex in a familiar, no-code UI, with: 🐉 Drag & drop - Add dimensions and measures to a visual canvas 🎨 Pivots & viz - Customize, color, and group data to make insights pop 📊 Spreadsheet calculations - Build custom logic with formulas 🪢 No-code joins - Join tables with automatic key detection and fan-out deduplication Plus new powers for Magic AI ✨, conditional notifications 🔔 for data apps, and semantic model sync 🤝 for LookML and MetricFlow. Learn more at

Hex

25,316 views • 1 year ago