Loading video...

Video Failed to Load

Go Home

"Hey Codex, show me how you'd fix this bug" The new tldraw plugin lets ChatGPT map a problem on the canvas and sketch a few fixes. Comment on the drawing to ask for changes and watch it update live. Here's Max trying it on one of our bugs:

29,575 views • 13 days ago •via X (Twitter)

8 Comments

Asmir's profile picture
Asmir13 days ago

i'm a cli person so a canvas inside codex is the first ui thing that makes sense to me, when the problem is a flow rather than a line, text is a bad way to describe it and you end up typing a paragraph to say what one arrow would

Mateo Lafalce's profile picture
Mateo Lafalce13 days ago

cool

Hashim Warren's profile picture
Hashim Warren13 days ago

Can you do a demo that starts from the prompt? How do I tell ChatGPT to use tldraw

tldraw's profile picture
tldraw13 days ago

Now in the ChatGPT plugin store →

Ronny Khalil's profile picture
Ronny Khalil13 days ago

great example!

천하제일도's profile picture
천하제일도13 days ago

claude code는?

Andrew Pouliot's profile picture
Andrew Pouliot13 days ago

do you have to @ it? seems slightly more friction than expected

Ahmed Raza Ch's profile picture
Ahmed Raza Ch13 days ago

Would still keep the original state beside each edit so the fix stays reversible. Also a review loop to point at the problem, ask for a change, see the result wouldn't be bad.

Related Videos

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 views • 1 year ago