I'm working on a project right now, that is heavily informed by AI. I wouldn't even try it, if I didn't have the help. It's a big job.

However, I can't imagine vibe-coders actually shipping anything.

I really have to ride herd on the output from the LLM. Sometimes, the error is PEBCAK, because I erred, when I prompted, and that can lead to very subtle issues.

I no longer review every line, but I also have not yet gotten to the point, where I can just "trust" the LLM. I assume there's going to be problems, and haven't been disappointed, yet. The good news is, the LLM is pretty good at figuring out where we messed up.

I'm afraid to turn on SwiftLint. The LLM code is ... prolix ...

All that said, it has enormously accelerated the project. I've been working on a rewrite (server and native client) that took a couple of years to write, the first time, and it's only been a month. I'm more than half done, already.

To be fair, the slow part is still ahead. I can work alone (at high speed) on the backend and communication stuff, but once the rest of the team (especially shudder the graphic designer) gets on board, things are going to slow to a crawl.

▲

Mengkudulangsat 19 hours ago | parent | next [-]

> However, I can't imagine vibe-coders actually shipping anything.

I'm a vibe-coder, and I've shipped lots! The key is to vibe-code apps that has a single user (me). Haven't coded anything for 15 years prior to January too.

	▲	ChrisMarshallNY 14 hours ago \| parent \| next [-]
		I suspect we have different definitions of “ship.” I am usually my principal customer, but I tend to release publicly.
	▲	hunterpayne 14 hours ago \| parent \| prev [-]
		So your the dev who wrote Tea then huh

▲

enraged_camel 21 hours ago | parent | prev | next [-]

>> I no longer review every line, but I also have not yet gotten to the point, where I can just "trust" the LLM.

Same here. This is also why I haven't been able to switch to Claude Code, despite trying to multiple times. I feel like its mode of operation is much more "just trust to generated code" than Cursor, which let's you review and accept/reject diffs with a very obvious and easy to use UX.

	▲	majormajor 21 hours ago \| parent [-]
		Most of the folks I work with who uninstalled Cursor in favor of Claude Code switched back to VSCode for reviewing stuff before pushing PRs. Which... doesn't actually feel like a big change from just using Cursor, personally. I tried Claude Code recently, but like you preferred the Cursor integration. I don't have the bandwidth to juggle four independent things being worked on by agents in parallel so the single-IDE "bottleneck" is not slowing me down. That seems to work a lot better for heavy-boilerplate or heavy-greenfield stuff. I am curious about if we refactored our codebase the right way, would more small/isolatable subtasks be parallelizable with lower cognitive load? But I haven't found it yet.

▲

MattGaiser 17 hours ago | parent | prev [-]

Is there a reason you don’t use a hook to make all code pass your linters before you look at it?

	▲	ChrisMarshallNY 15 hours ago \| parent [-]
		I’m probably gonna do that (I use SwiftLint[0] -Note: I no longer use CocoaPods anything, these days. I wrote that, years ago.), but I tend to be quite strict, and didn’t want to be constantly interrupting myself, polishing turds. It was really kind of a joke. I haven’t turned it on, yet, because of the velocity of the work, but I think I’ve found my stride. [0] https://littlegreenviper.com/swiftlint/