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

Why I don’t vibe code

jacobharr.is

Post reply on HN
Print view View original

81–90 of 119 posts

Re: Why I don’t vibe code

#81

Post by em-bee »

jmcodes wrote: post #48
retinaros wrote: post #29

To experienced devs. Why are you enjoying vibecoding? It is soulless and the job is really becoming unbearable having to discuss with an agent that alternates between “good at” and totally consensual and low iq.it feels miserable to have a few turns then seeing the tool Became so bad and so low iq that you stuck in doing things garder than if you did it by yourself I get the conversational aspect and value of it I ju…

I was already spending a lot of time reviewing other people's code. It makes no difference to me if it's coming from an agent or a person. I can pick and choose which parts of the problem deserve my attention and which can be done by the LLM with me just keeping an eye on it while I mostly work on something else. I don't have metrics but I feel like I am doing higher leverage work with less friction. Setting up the s…

but it's not fun for everyone. reviewing code for people vs agents is a massive difference for me. with people i can teach them. with LLMs i can't. it makes me feel helpless. just like i feel helpless using broken non-free apps. i can tolerate the same bugs in FOSS application, because i potentially can fix them even if i don't actually do it. i don't feel helpless, i feel like i have a choice. with LLMs i don't get that choice.

most of the other things you mention feel tedious to me. i like diving into the code, understanding how to solve a problem, figuring out how to make the code structure look elegant and readable. find and comment on a clever short-cut, even if it means that i may not be clever enough to debug it later.

i don't get any of that with LLM generated code. i'd spend more time to clean up and fix the LLM code than i would writing it from scratch. to use LLM code efficiently, i'd have to give up all that. but i don't want to do that.

using LLM to code feels like gambling. every time i put in a prompt, its like rolling the dice. am i going to get a useful solution this time? and then reroll until i get a useful result rather than building up the application one step at a time.

Re: Why I don’t vibe code

#82

Post by Aurornis »

tasuki wrote: post #76
Aurornis wrote: post #70

Earlier quoted context omitted.

> Most people can easily get to work without a car. This is statistically very false. It does a good job of proving my point that people within this bubble have a hard time understanding what the rest of the world is like.

You're the one in a bubble. [Edit:] That wasn't very helpful of me, let me expand: I live in a city of 400,000 people. It can be crossed on foot in an hour, faster by bicycle. For people who can't or don't want to, the public transport is good. And yet there are traffic jams everywhere. I used to live in Amsterdam, which is a bigger place. I cycled around 13 km each way, which isn't entirely unusual. I stand by my po…

> You're the one in a bubble.

The average one-way commute in the United States is 27 minutes. Source https://www.census.gov/newsroom/press-releases/2021/one-way-...

Unless you were making a statement about your city, it's not true that most people could easily get to work without a car.

> I stand by my point that most people can easily get to work without a car.

This probably feels true if you're in a bubble where everyone is like you: Presumably healthy, younger, not having to drop kids off at school(s) and then pick them up with your work day in between, and the weather is walkable.

It's cool that you could bike 13km each way to work. I bike a lot and could do that in my sleep. However I'm not going to start throwing out accusations that everyone is lazy and unmotivated, because I know everyone has different circumstances.

I had a 35 minute commute at 65mph for a while and there was not much traffic. I had no choice. The office was relocated and I had to make the drive until I found another job. Not possible to walk that distance. If I biked it I would have been biking for hours every day with no chance to see the kids before school or pick them up.

Your generalizations are why I said people who make these claims live in a bubble: If you think most people could easily ditch their car for work, you don't understand the diversity of how people live.

Re: Why I don’t vibe code

#84

Post by runarberg »

satvikpendem wrote: post #74
dpatterbee wrote: post #31

Earlier quoted context omitted.

People only need cars because people have cars and cars make cities worse for everyone outside of one. If nobody owned cars everyone would get by just fine. It's a race to the bottom.

Sure, but that doesn't change the fact that today people need cars. In an ideal world I'd also love a European or Asian city model but American cities are not like that.

Most American cities have decent enough public transit where it is viable (or even a preferable) alternative to driving. I can think of Seattle, New York, Chicago, San Francisco, etc. Not every city in America is like El Paso or Phoenix. But even in cities like El Paso or Phoenix, the hostility towards public transit is a political choice and an alternative policy is available if politicians want it.

I my self live close to the good American cities and even though my community is rather rural (I literally live across the street from a dairy farm) I still prefer biking to town. And when I go to the city, I rarely bring my car with me, as I prefer the bus over waiting in the ferry line and dealing with parking in the city.

Re: Why I don’t vibe code

#85

Post by jmcodes »

em-bee wrote: post #81
jmcodes wrote: post #48

Earlier quoted context omitted.

I was already spending a lot of time reviewing other people's code. It makes no difference to me if it's coming from an agent or a person. I can pick and choose which parts of the problem deserve my attention and which can be done by the LLM with me just keeping an eye on it while I mostly work on something else. I don't have metrics but I feel like I am doing higher leverage work with less friction. Setting up the s…

but it's not fun for everyone. reviewing code for people vs agents is a massive difference for me. with people i can teach them. with LLMs i can't. it makes me feel helpless. just like i feel helpless using broken non-free apps. i can tolerate the same bugs in FOSS application, because i potentially can fix them even if i don't actually do it. i don't feel helpless, i feel like i have a choice. with LLMs i don't get…

Yeah I can kind of see that and if you don't like them you don't like them. Not all tools are for all people.

I personally draw the line at plugins that try to set up entire workflows and take the human completely out of the loop. Those are next to useless imo for an engineer who knows what they are doing and are exactly how you end up with crappy code/products.

But to give my thoughts to your points I guess I just don't really care that I can't teach LLMs? It doesn't bother me because I do also still teach people, it's not one or the other.

On what you like about coding. I like that too, I still do it where I want to or where it is needed.

I agree with you on what parts are enjoyable but I guess I don't feel that I'm giving them up? I get to pick the problems I work on that way now. The only disagreement there is around 'clever' shortcuts. I get pleasure out of making things debuggable and traceable for humans.

I wish my odds at gambling were as high as they are with LLM generated code lol.

I do run into the whole 'this session was a waste, need to restart', but like once in a blue moon? Not nearly enough to turn me off from using LLMs daily.

On the teaching point again, my learnings around coding standards, architecture -> problem mapping, how to debug, are applied at the system prompt level and around a few key skill files, so when I say "implement ..." or "I'm seeing this behavior, where in the codebase is the most likely root cause? Why?" It does so close to how I would've done it.

I cannot speak for people who are using these things raw in the harnesses provided by the companies, or god forbid in the browser but you can definitely increase the odds of a good roll enough to be productive by changing the environment around the llm and to me that is the opposite of feeling helpless when it comes to LLMs.

I feel enabled to get more done, at my standards, on my time.

Re: Why I don’t vibe code

#86

Post by retinaros »

jmcodes wrote: post #48
retinaros wrote: post #29

To experienced devs. Why are you enjoying vibecoding? It is soulless and the job is really becoming unbearable having to discuss with an agent that alternates between “good at” and totally consensual and low iq.it feels miserable to have a few turns then seeing the tool Became so bad and so low iq that you stuck in doing things garder than if you did it by yourself I get the conversational aspect and value of it I ju…

I was already spending a lot of time reviewing other people's code. It makes no difference to me if it's coming from an agent or a person. I can pick and choose which parts of the problem deserve my attention and which can be done by the LLM with me just keeping an eye on it while I mostly work on something else. I don't have metrics but I feel like I am doing higher leverage work with less friction. Setting up the s…

nothing is really fun in trying to hack around a model to make him do things you want knowing that its barely patching it until the next disease shows up. its painful.also it is probably a temporary step before everything close up behind closed software and closed API (like anthropic tries to) and the harness wont be yours it will be on a remote cloud server. then you will just spend the time review llm generated code. also the scale and ambition of a LLM generated piece of code can be daunting. the most basic pattern since LLM can code well is overdoing. docs are longer, blogs are longer, ppt are longer, PR are longer while quality naturally drop because more people can produce this kind of content now

Re: Why I don’t vibe code

#87

Post by sublinear »

pijon wrote: post #62
ge96 wrote: post #51

I'm getting tempted to because I have so much work to do for my "startup" and after my 8hr day job I'm burnt. It's not even that I don't know what to do it's a lot of work... swift iPhone app, the api, the web app and gcp. get that feeling of being overwhelmed and also end of day brain just feels like shit, thinking I'll drink more caffeine after gym eg. 6:30 PM will see if I can sleep.

if you are serious about building a startup the best choice you could make is to learn to use these tools intelligently. ESPECIALLY if what you are building is an app… virtually everyone building a startup uses these tools to automate a huge chunk of the work. you have no real chance otherwise. my advice is to get on the cheap claude code sub and to check out the superpowers plugin. the idea of the plugin is to help…

> virtually everyone building a startup uses these tools to automate a huge chunk of the work. you have no real chance otherwise.

Huh? Do you mean people "building a startup" without any experience at all? The list of tasks in the comment you're replying to are well within the skillset of any software engineer that has that old job description classic "3 to 5 years experience".

Not to be rude, but if the code is the hard part for anyone, they never had a chance at the rest of it either.

Re: Why I don’t vibe code

#88

Post by basch »

Aurornis wrote: post #3

I thought this was going to be an article about intelligent use of LLM tools without vibecoding, but it's actually entirely against LLMs altogether. The person who wrote it used a free trial of some tool (most likely not a frontier model) and then gave up forever when the trial ran out. > I then tried using one of the AI tools to analyze my code in a project and a few other small tasks before it all came to an awkwar…

People have a very strong tendency to go "current gen technology cant achieve x, therefore its impossible for this class of technology to ever achieve x"

Many many many of the problems with current gen ai will go away.

Re: Why I don’t vibe code

#89

Post by jmcodes »

retinaros wrote: post #86
jmcodes wrote: post #48

Earlier quoted context omitted.

I was already spending a lot of time reviewing other people's code. It makes no difference to me if it's coming from an agent or a person. I can pick and choose which parts of the problem deserve my attention and which can be done by the LLM with me just keeping an eye on it while I mostly work on something else. I don't have metrics but I feel like I am doing higher leverage work with less friction. Setting up the s…

nothing is really fun in trying to hack around a model to make him do things you want knowing that its barely patching it until the next disease shows up. its painful.also it is probably a temporary step before everything close up behind closed software and closed API (like anthropic tries to) and the harness wont be yours it will be on a remote cloud server. then you will just spend the time review llm generated cod…

- building a reliable enough system out of unreliable parts is pretty fun for me. It's a different kind of puzzle.

- pi-agent or code your own harness, it is not hard.

- codex for now allows you to use it in any harness but if they ever don't open models are catching up

- Reject low quality PRs the same as before. If management doesn't enable to you do that then that's a different problem.

Re: Why I don’t vibe code

#90

Post by tasuki »

Aurornis wrote: post #82
tasuki wrote: post #76

Earlier quoted context omitted.

You're the one in a bubble. [Edit:] That wasn't very helpful of me, let me expand: I live in a city of 400,000 people. It can be crossed on foot in an hour, faster by bicycle. For people who can't or don't want to, the public transport is good. And yet there are traffic jams everywhere. I used to live in Amsterdam, which is a bigger place. I cycled around 13 km each way, which isn't entirely unusual. I stand by my po…

> You're the one in a bubble. The average one-way commute in the United States is 27 minutes. Source https://www.census.gov/newsroom/press-releases/2021/one-way-... Unless you were making a statement about your city, it's not true that most people could easily get to work without a car. > I stand by my point that most people can easily get to work without a car. This probably feels true if you're in a bubble where ev…

> The average one-way commute in the United States is 27 minutes

A bubble right there.

> Unless you were making a statement about your city, it's not true that most people could easily get to work without a car.

It appears you're making a claim about the US, while I was making a general claim, not necessarily specific to the US.

And I'm not claiming everyone can get by without a car, I'm claiming most of the world population could easily commute without a car, if they wanted to.

Many people just don't want to.

> you don't understand the diversity of how people live.

Respectfully, if you think most people can't but drive a car to work, you're the one who doesn't understand diversity. This is further supported by your US-centric worldview.

Post reply on HN