You can. People do. It's not perfect at it yet, but there are success stories of this.
It really depends on the area though. Some areas are simple for LLMs, others are quite difficult even if objectively simple.
Granted atm i'm not a big believer in vibe coding in general, but imo it requires quite a bit of knowledge to be hands off and not have it fall into wells of confusion.
For me, that's "just one", and that's why LLM coding doesn't scale very far for me with these tools.
if you have to understand the code to progress, it's regular fucking programming.
I don't go gushy about code generation when I use yasnippet or a vim macro, why should super autocomplete be different?
this is an important distinction because if Karpathy's version becomes real we're all out of a job, and I'm sick of hearing developers role play publicly towards leaders that their skills aren't valuable anymore
The question is how much do you review, and how much does your experience help it? Even if you didn't know code you're still going to review the app. Ideally incrementally or else you won't know what's working and what isn't. Reviewing the technical "decisions" from the LLM is just an incremental step towards reviewing every LOC. There's a large gulf between full reviews and no reviews.
Where in that gulf you decide to call it "vibe coding" is up to you. If you only consider it vibing if you never look at the code though, then most people don't vibe code imo.
I think of "vibe coding" as synonymous with "sloppy/lazy coding". Eg you're skipping details and "trusting" that the LLM is either correct or has enough guardrails to be correct in the impl. How many details you skip though is variable, imo.
Is that where the goalposts are now?
But you can vibe code and auto-edit your way to a good PR. But you're reviewing the code being output when the agent finishes each task. Maybe that's not pure vibe coding?
There are a lot of people who are entering programming via this thing.
In my experience, if you can't review the code and point out the LLM's mistakes to it, the codebase gets brittle fast. Maybe other people are better vibe coders than me, but I never managed to solve that problem, not even with Opus 4.1.
I mean, the parent even pointed out that it works for vibe coding and stuff you don't care about; ...but the 'You can't' refers to this question by the OP:
> I really need to approve every single edit and keep an eye on it at ALL TIMES, otherwise it goes haywire very very fast! How are people using auto-edits and these kind of higher-level abstraction?
No one I've spoken to is just sitting back writing tickets while agents do all the work. If it was that easy to be that successful, everyone would be doing it. Everyone would be talking about it.
To be absolutely clear, I'm not saying that you can't use agents to modify existing code. You can. I do; lots of people do. ...but that's using it like you see in all the demos and videos; at a code level, in an editor, while editing and working on the code yourself.
I'm specifically addressing the OPs question:
Can you use unsupervised agents, where you don't interact at a 'code' level, only at a high level abstraction level?
...and, I don't think you can. I don't believe anyone is doing this. I don't believe I've seen any real stories of people doing this successfully.
My view, after having gone all-in with Claude Code (almost only Opus) for the last four weeks, is ”no”. You really can’t. The review process needs to be diligent and all-encompassing and is, quite frankly, exhausting.
One improvement I have made to my process for this is to spin up a new Claude Code instance (or clear context) and ask for a code review based on the diff of all changes. My prompt for this is carefully structured. Some issues it identifies can be fixed with the agent, but others need my involvement. It doesn’t eliminate the need to review everything, but it does help focus some of my efforts.