AI agents are stressing out developers when they break mid-workflow
“One is I've been hearing more and more there's this, like, stress that people feel when their agents aren't working.”
we're we've basically reached that point now, which is which is which is really cool. There's two kind of threads I wanna follow here. One is I've been hearing more and more there's this, like, stress that people feel when their agents aren't working. You fire off all these, you know, codex agents and then you have to keep stay on top of them. Oh, shit. One's not working. I'm wasting time.
Do you do you feel that? Do you feel that across your team at all? Yeah. Yeah. I mean, it happens all the time. And I actually think, like, the this is where the interesting part of all of this lies right now because these models aren't perfect. These tools aren't perfect. And we're still trying to figure out how to best interact with these, with with with codex or with these AI agents to to get work done. We see this come up all the time. There's a particularly
About this clip
OpenAI's Sherwin Wu discusses the unexpected stress developers experience when AI coding agents fail or stop working properly. He explains how teams are still figuring out the best ways to interact with imperfect AI tools like Codex, and highlights the real-world challenges of managing multiple AI agents simultaneously.
Why this clip
This reveals a counterintuitive downside to AI adoption that most people don't consider - the psychological burden of managing unreliable AI agents.
What they said next
AI will create 100x more vertical software startups than we've ever seen
25:40 - 33s · prediction
More from this episode
Similar clips from other shows
From the blog
Want clips like this for your podcast?
We find your top 5-8 clips, write the hooks, and deliver ready-to-post content. First 2 episodes are free.
Get 2 Episodes Clipped Free