ATRIUMsearch → argument graph
ClaimVideo · 5:51 — 7:21

Whether you read AI-generated code should depend entirely on the project: for personal projects and one-off scripts it's fine to auto-accept edits without reading, but for production code you ship to a company or contribute to, you should read it as an engineer.

Scott Tolinski argues the 'do you read the code' debate isn't binary — it depends on whether the project is a disposable personal script or real production code you're shipping. ✦ AI generated

Scott Tolinski · Syntax · 2026-07-06 · original ↗

starts at this moment · 5:51

Elicited by

How much better do the models have to get before you stop reading the code?

if you've seen my takes on this channel, you would expect that yes, I read the code. But I will say for some personal projects, for some one-off scripts, I don't. I do actually turn on auto accept edits... but it when it comes to production code, when it comes to like code that you're shipping for your company or that you're contributing to, you probably should read the code just as an engineer.

verbatim transcript · starts at 5:51

Transcript · around this moment

5:51expect that yes, I read the code. But I will say for some personal projects, for some one-off scripts, I don't. I do actually turn on auto accept edits. And that's because a lot of times those aren't projects that are going to have a long life. It's something that I'm I'm just testing out. I want to get it up and going. So, I'm more than happy to just let the AI write the code because

6:11I'm I'm there to test the functionality or just like test the thing itself. But it it when it comes to production code, when it comes to like code that you're shipping for your company or that you're contributing to, you probably should read the code just as an engineer. Um, if you want to pull up the tweet from Kramer, uh, he responded that says, "No good engineer will tell you it's useless

6:33to read the code. By the way, that's the easiest signal." I I think like it's part of our jobs like we have to care. I I think like if you're too lost in the sauce if you just think that just prompt prompt prompt prompt prompt because that also gets into like you're not necessarily caring about token usage or bill or efficiency or moving too fast and these are all

6:53things that we actually need to care about in real production code. So >> yeah. >> Yeah. I Kramer is always dead on um in my experience and it's so funny the people the people that respond to him and like he like doesn't know what he's talking about like >> bro uh yeah Kramer is like one he's a cracked engineer but he's also built something insanely large so it's like

7:20>> yeah [laughter] he runs a a I mean he he's built this business into a billion dollar company. Like that's crazy to me. So >> yeah, >> if you don't know like Kramer is one of the co-founders, former CTO, former COO of >> of uh Century who who we work for as well. >> Um >> yes, I'm not just big uping my boss either. I'll just say that. [laughter]

7:42No, >> no. I And you could see it from the proof. Like I mean we we have a little more in insight into this because we can see all his messages in Slack and like we hear him from all hands. But like >> this guy he still is even though he's not a engineer or CTO anymore. He's still writing code. He's still using agents. He's still working on workflows.

Around this claim