I have already vibe-coded countless number of scripts and two side projects that were on my "list" for years, these projects would have never seen the light of day if not for Cursor. That's the whole point.
This is the learning to fish problem. If you understand git well, a solution isn't very hard (eg, rev-parse each branch and compare to the rev-parse of the current branch and deleting if they match). If you don't understand git well, you shouldn't be turning into a script-kiddy pasting in whatever the AI spits out and hoping that it works.
You are using "script-kiddy" as an ad hominem rather than making an argument with proper justification. "script-kiddy" refers to website vandalism and cracking. That has nothing to do with using AI to learn what rev-parse does.
Learning about `git rev-parse` through documentation and learning about `git rev-parse` through AI fundamentally have the same outcome at the end of the day: you have learned how to use `git rev-parse`.
I’m using it as a pejorative (not an ad hominem) for people who blindly trust unknown code because they don’t have any real understanding. It’s a shortcut for a whole, well-known and obvious argument about the danger of playing with things being your understanding.
If you are using AI to learn, understand, and verify what it spit out, by definition, you aren’t a script kiddy. My argument was about how you use AI rather than a commentary on if you should.
It is an ad hominem. "you shouldn't be turning into a script-kiddy" is guilt by association, see Wikipedia[1] or ask AI[2]. If you think that learning from AI is dangerous you should articulate why you think that. I find it neither "well-known" or "obvious".
> Learning about `git rev-parse` through documentation and learning about `git rev-parse` through AI fundamentally have the same outcome at the end of the day: you have learned how to use `git rev-parse`.
IDK, there are a lot of little chores that I find needing done that previously would have been ten minutes of research and cli fiddling that are a prompt and copy paste now.
It doesn't feel that different but it is a little faster
If you don't understand what the copy/paste is actually doing, you shouldn't be script-kiddying it in your project. If you do understand, then the AI is just quickly writing what you already intended.
If you are having to understand something you didn't understand, it's probably taking a bunch of time to read and verify what the script does. This can be a good learning experience and reveal unknown unknowns, but probably isn't a massive speedup.
This seems false to me. I vibe code shell scripts all the time. I understand what it's doing perfectly, but it would have taken me ages to look up all the bash syntax and get it all correct. Is it one square bracket pair around if statements, or two?
You are in the category I mentioned that already know the answer and are using AI to write the code you already understand faster. This is rather different from “vibe coding” in my opinion.
But the amount of time saved because one could vibe code it rather than search through Google’s terrible results is immense and a benefit in and of itself.
Maybe. But anytime I take on the task to automate something, it was a nice opportunity to check how others do it, what other things the program can accomplish.
The decision to automate is already done, no need to rush through it.
Parts of it could probably already exists in the LLM's corpus, but being able to join them together to build new things is what makes "vibe coding" so useful.
Even though, from personal experience, at scale it still falls apart
I think it is somewhat similar to the emergent translation capabilities, it doesn't need to have trained on a translation of a text to do one of it. But it does need good coverage of the area.
Is it. For small scripts like these you can get far with basic search and sources like docs/github/SO. Maybe cursor is more “fun”, “engaging”, and the like, but it’s not like it was a difficult job before.
If you could throw your endless todo list of side projects at an LLM, and can see at least some of them implemented overnight effortlessly, why not? You can still take credit because you had the idea in the first place and went through the effort to write it down and describe it well enough to be achievable. It's definitely more fun especially if you have limited hobby coding time.
If you're fine with running them blindly and having one of those scripts recursively remove your home directory, then sure. Otherwise it's very much not a zero effort affair. More like overseeing an overconfident overenthusiastic amphetamine-doped junior developer (or running his output blindly and hoping for the best).
I really do feel like we're living in completely separate worlds, so many people are very enthusiastic about LLMs, and every time I try them, they leave me completely disappointed.
Now imagine if your car didn’t have a steering wheel or pedals, but instead you had to explain to it where to go and it would misunderstand you 60% of the time.
Only when the road permits it for that type of car. And if it’s a common road, it’s better economically to build a a train (framework, library) than to use a car (code generation). Then you could use a bycicle (short burst of code) for the parts that matter.