Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vibe coding creates fatigue?

tabulamag.com

Post reply on HN
Print view View original

81–90 of 174 posts

Re: Vibe coding creates fatigue?

#81

Post by kelipso »

crazygringo wrote: post #22
happytoexplain wrote: post #7

Earlier quoted context omitted.

Yes, I'm getting increasingly confused as to why some people are broadening the use of "vibe" coding to just mean any AI coding, no matter how thorough/thoughtful.

It's because the term itself got overapplied by people critical of LLMs -- they dismissed all LLM-assisted coding as "vibe coding" because they were prejudiced against LLMs. Then lots of people were introduced to the term "vibe coding" in these conversations, and so naturally took it as a synonym for using LLMs for coding assistance even when reading the code and writing tests and such. Also because vibe coding just…

Lol, I say I am vibe coding even when I create little code snippets through AI that I have read and understood every line. It’s a fun term!

Re: Vibe coding creates fatigue?

#82

Post by sixothree »

Zigurd wrote: post #10

I don't want to be that contrarian guy, but I find it energizing to go faster. For example, being able to blast through a list of niggling defects that need to be fixed is no longer a stultifying drag. I recently used a coding agent on a project where I was using an unfamiliar language, framework, API, and protocol. It was a non-trivial project, and I had to be paying attention to what the agent was doing because it…

I am currently only vibe-coding my hobby projects. So if that changes, my view could very well change.

But I 100% agree. It's liberating to focus on the design of my project, and my mental model can be of how I want things to work.

It feels like that switch to test driven development where you start from the expected result and worry about the details later.

Re: Vibe coding creates fatigue?

#83

Post by kelipso »

habinero wrote: post #47
viccis wrote: post #31

Earlier quoted context omitted.

I'm not sure how common this is in other countries, but Americans would rather add another definition to the dictionary for the misuse before they'd ever tolerate being corrected or (god forbid) learning the real meaning of a word. I got dogpiled for saying this about "factoid" the other day here, but sometimes when people misuse words like "bricked" or "electrocuted", the ambiguity does actually make a difference, m…

Languages evolve, my dude. It's common everywhere.

I think he is complaining about that exact philosophy maybe being applied too broadly lol.

Re: Vibe coding creates fatigue?

#84

Post by blitz_skull »

Zigurd wrote: post #10

I don't want to be that contrarian guy, but I find it energizing to go faster. For example, being able to blast through a list of niggling defects that need to be fixed is no longer a stultifying drag. I recently used a coding agent on a project where I was using an unfamiliar language, framework, API, and protocol. It was a non-trivial project, and I had to be paying attention to what the agent was doing because it…

I think it's less "going fast" and more "going fast forever."

To your point, you can blow through damn-near anything pretty quickly now. Now I actually find myself problem-solving for nearly 8 hours every day. My brain feels fried at the end of the day way more than it used to.

Re: Vibe coding creates fatigue?

#85

Post by OptionOfT »

stuffn wrote: post #59
Zigurd wrote: post #10

I don't want to be that contrarian guy, but I find it energizing to go faster. For example, being able to blast through a list of niggling defects that need to be fixed is no longer a stultifying drag. I recently used a coding agent on a project where I was using an unfamiliar language, framework, API, and protocol. It was a non-trivial project, and I had to be paying attention to what the agent was doing because it…

I think the counter-point to that is what I experience. I agree it can be energizing because you can offload the bullshit work to a robot. For example, build me a CRUD app with a bootstrap frontend. Highly useful stuff especially if this isn't your professional forte. The problems come afterwards: 1. The bigger the base codebase generation the less likely you're going to find time or energy to refactor LLM slop into…

Ergo instant tech debt.

Re: Vibe coding creates fatigue?

#86

Post by agumonkey »

Rperry2174 wrote: post #41
Zigurd wrote: post #10

I don't want to be that contrarian guy, but I find it energizing to go faster. For example, being able to blast through a list of niggling defects that need to be fixed is no longer a stultifying drag. I recently used a coding agent on a project where I was using an unfamiliar language, framework, API, and protocol. It was a non-trivial project, and I had to be paying attention to what the agent was doing because it…

I think both experience are true. AI removes boredome AND removes the natural pauses where understanding used to form.. energy goes up, but so does the kind of "compression" of cognitive things. I think its less a quesiton of "faster" or "slower" but rather who controls the tempo

> the kind of "compression" of cognitive things

compression is exactly what is missing for me when using agents, reading their approach doesn't let me compress the model in my head to evaluate it, and that was why i did programming in the first place.

Re: Vibe coding creates fatigue?

#87

Post by agumonkey »

nosianu wrote: post #73
visarga wrote: post #52

Earlier quoted context omitted.

>Red flag. In other words you don’t understand the implementation well enough to know if the AI has done a good job. Red flag again! If your protection is to "understand the implementation" it means buggy code. What makes a code worthy of trust is passing tests, well designed tests that cover the angles. LGTM is vibe testing I go as far as saying it does not matter if code was written by a human who understands or no…

> What makes a code worthy of trust is passing tests (Sorry, but you set yourself up for this one, my apologies.) Oh, so this post describes "worthy code", okay then. https://news.ycombinator.com/item?id=18442941 Tests are not a panacea. They don't care about anything other than what you test. If you don't have code testing maintainability and readability, only that it "works", you end up like the product in that pos…

I wonder if for a large class of jobs, simple unit tests will be enough to be a negative that the llm output will try to match. Test driven delegation in a way.. that said i share the same worries as you. The fact that the LLM can wire multiple files / class / libs in a few seconds to pass your tests doesn't guarantee a good design. And the people who love vibe coding the most are the one who never valued design in the first place, just quick results..

Re: Vibe coding creates fatigue?

#88

Post by Askiir »

zephyrthenoble wrote: post #12
Jeff_Brown wrote: post #8

Earlier quoted context omitted.

Agreed. Some strategies that seem to help exist, though. Write extensive tests before writing the code. They serve as guidance. Commit tests separately from library code, so you can tell the AI didn't change the test. Specify the task with copious examples. Explain why yo so things, not just what to do.

Interesting, I haven't tried tests outside of the code base the LLM is working on. I could see other elements of isolation being useful, but this kind of feels like a lot of extra work and complexity which is part of the issue...

The way I do it is write tests, then commit just the tests. Then when you have any agent running and generating code, before committing/reviewing you can check the diff for any changes to files containing tests. The commit panel in Jetbrains for example will enumerate any changed files, and I can easily take a peek there and see if any testing files were changed in the process. It's not necessarily about having a separate codebase.

Re: Vibe coding creates fatigue?

#89

Post by zahlman »

lukan wrote: post #49
iLoveOncall wrote: post #37

Earlier quoted context omitted.

Words don't have meaning in 2025. A negative but courteous remark is "slamming", a tweet is an "attack", etc. So yeah I'm not surprised that people conflate any use of AI with vibe-coding.

Words changed meaning all the time through history, it just happens faster.

There is a world of difference between natural semantic drift and blatant disregard for accuracy by someone seeking to create drama for attention.

Not to mention all the attempts we see nowadays at deliberate redefinition of words, or the motte-and-bailey games played with jargon vs. lay understandings of a concept.

Re: Vibe coding creates fatigue?

#90

Post by prmph »

vidarh wrote: post #25
colechristensen wrote: post #15

Earlier quoted context omitted.

Build tools to keep it in check.

Really, this. You still need to check its work, but it is also pretty good at checking its work if told to look at specific things. Make it stop. Tell it to review whether the code is cohesive. Tell it to review it for security issues. Tell it to review it for common problems you've seen in just your codebase . Tell it to write a todo list for everything it finds, and tell it fix it. And only review the code once it'…

So why can't the deterministic part of the agent program embed in all these checks?
Post reply on HN