Connect your Claude, Codex or OpenClaw for full transcripts on millions of podcasts. Two week free trial, cancel anytime.

Start free trial →
MS Marvin Schwaibold On Y Combinator Startup Podcast

“It's an infinitely patient collaborator and teammate. Codex won't get mad at me if I need 91 approaches at getting the animation correct. If I had done that with my engineer, they would probably flip out.”

Y Combinator Startup Podcast · Startups & Venture · October 2026

“It's an infinitely patient collaborator and teammate. Codex won't get mad at me if I need 91 approaches at getting the animation correct. If I had done that with my engineer, they would probably flip out.” — Marvin Schwaibold, Y Combinator Startup Podcast

Context

Aaron Epstein asked how founders and designers should use AI to raise their design quality. The Shopify designer's advice was to tinker and keep pushing back on the tool, and to use it to copy and take apart interactions you admire, which he had just done with a carousel built over 91 prompts.

Listen to the episode → More from Marvin Schwaibold → More Startups & Venture quotes →

Transcript

Y Combinator Startup Podcast Around 15:40 into the episode
Marvin Schwaibold

…is. You want to play around with that toggle a little bit. It can't feel too intimidating or too strong. Otherwise, the whole system just feels off. And I know when it feels off, but the back and forth with chat just doesn't work. You need to be able to always expose those kind of values. It seems

Aaron Epstein

…could I start a company or could I actually build the product? I'm so used to designing Infigma and passing it off to somebody maybe where you guys have been in the past. How should they think about themselves and being able to up-level the way that they use AI to create higher quality design?

Marvin Schwaibold

A lot of the way I keep thinking about AI in general is just it's an infinitely patient collaborator and teammate. Codex won't get mad at me if I need 91 approaches at getting the animation correct. If I had done that with my engineer, they would probably flip out. But so my advice to everybody is like, and it sounds kind of silly, but like tinker with the tooling. Like you can go in and just describe what you wanted to do. And when you see a result, like don't give up. Just explain to that this is not how you envision it. Send it a website where you really like the carousel animation or give it a screenshot from Save It or Cosmos of something that you…

Aaron Epstein

That's great advice.

Speaker 4

YC's next batch is now taking applications. Got a startup in you? Apply at whitecombinator.com slash apply. It's never too early and filling out the app will level up your idea. Okay, back to the video.

Aaron Epstein

Should we review some websites? Yeah,

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from Y Combinator Startup Podcast

“It's so easy to pump out more code and more software, but it's harder than ever to actually talk about what you are doing in a coherent way in front of an audience. Because now, Aaron, you know, someone can clone my product in like two minutes at this point. But again, what they, what's really hard to clone is the audience and the community that I built around what I'm doing and the energy around it.” — Farza Majeed, Y Combinator Startup Podcast