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

After two years of vibecoding, I'm back to writing by hand

atmoio.substack.com

Post reply on HN
Print view View original

511–520 of 652 posts

Re: After two years of vibecoding, I'm back to writing by hand

#511

Post by threethirtytwo »

ActorNightly wrote: post #468
threethirtytwo wrote: post #338

Earlier quoted context omitted.

It’s not. There are tons of great programmers, that are big names in the industry who now exclusively vibe code. Many of these names are obviously intelligent and great programmers. This is an extremely false statement.

Non sequitor. You don't have to be bad at coding to use LLMs. The argument was specifically about thinking that LLMS can be great at accomplishing complex tasks (which they are not)

Wtf are you talking about. Great programmers use LLMs for complex tasks. That was the point of my comment

Re: After two years of vibecoding, I'm back to writing by hand

#512

Post by fn-mote »

recursivedoubts wrote: post #8

AI is incredibly dangerous because it can do the simple things very well, which prevents new programmers from learning the simple things ("Oh, I'll just have AI generate it") which then prevents them from learning the middlin' and harder and meta things at a visceral level. I'm a CS teacher, so this is where I see a huge danger right now and I'm explicit with my students about it: you HAVE to write the code. You CAN'…

The problem is: now they also need to learn to code with an LLM assistant. That goes beyond "coding it by yourself". Well, it's different, anyway. Another skill to teach.

Re: After two years of vibecoding, I'm back to writing by hand

#513

Post by AtomicOrbital »

after+30 years writing code in a dozen languages building systems from scratch I love vibe coding ... it's drinking from a fire hose ... in two months I vibe coded a container orchestration system which I call my kubernetes replacement project all in go with a controller deciding which VM to deploy containers onto, agents on each host polling etcd for requests created by the controller ... it's simple understandable maintainable extendable ... also vibe coded go cdk to deploy AWS RDS clusters, API gateway, handful of golang lambda functions, valkey elasticache and a full feature data service library which handles transactions and save points, cache ... I love building systems ... sure I could write all this from scratch by hand and I have but vibe coding quickly exposes me to the broad architecture decisions earlier giving me options to experiment on various alternatives ... google gemini in antigravity rocks and yes I've tried them all ... new devs should not be vibe coding for the first 5 years or more but I lucked into having decades of doing it by hand

Re: After two years of vibecoding, I'm back to writing by hand

#515

Post by abcde666777 »

This will sound arrogant, but I can't shake the impression that agent programming is most appealing to amateurs, where the kind of software they build is really just glorified UIs and data plumbing.

I work on game engines which do some pretty heavy lifting, and I'd be loath to let these agents write the code for me.

They'd simply screw too much of it up and create a mess that I'm going to have to go through by hand later anyway, not just to ensure correctness but also performance.

I want to know what the code is doing, I want control over the fine details, and I want to have as much of the codebase within my mental understanding as possible.

Not saying they're not useful - obviously they are - just that something smells fishy about the success stories.

Re: After two years of vibecoding, I'm back to writing by hand

#516

Post by radium3d »

I actually haven't come across situation 1 2 or 3 mentioned in the attached video. Generally I iterate on the code by starting a new prompt with the code provided, with enhancements, or provide the errors and it repairs the errors. Generally it gets it within 1-2 iterations. No emotions. Make sure your prompts do not contain fluff, and are straight what you want the code to accomplish and how you want it to accomplish it. I've gone back to code months later and have not had what you described as being shocked about bad code, it was quite easy to understand. Are you prompting the AI to also write variables and function names logically and utilize a common coding standard for whichever type of code you are having it write, such as wordpress coding standards or similar? Perhaps claude isn't the best, I have been experimenting with grok 4.1 thinking and grok expert at the mid-level paid tier. I'll take it a step further and adjust the code myself, start a new prompt and provide that updated code along with my further requests as well. I haven't hit the road blocks mentioned.

Re: After two years of vibecoding, I'm back to writing by hand

#517

Post by mrtesthah »

charcircuit wrote: post #493
mrtesthah wrote: post #462

Earlier quoted context omitted.

That's a false analogy. Product managers, designers, API implementers, kernel developers, etc. all understand what they're building and how that fits into a larger picture.

They may know the area they are responsible for, but they don't know all of the details of everything else and just have to trust that other people are doing the right thing and following contracts correctly. It doesn't require anyone to have full global understanding. Having local experts is good enough.

Local experts still need to have a shared mental model of how what they’re building fits into the overall system.

Re: After two years of vibecoding, I'm back to writing by hand

#518

Post by c1505 »

It still feels like gambling to me when I use AI code assistants to generate large chunks of code. Sometimes, it will surprise me with how well it does. Other times, it infuriatingly doesn't follow very precise instructions for small changes. This is even when I use it in the way that I often ask for multiple options for solutions and implementations and then choose between them after the AI tool does the course rating.

There are many instances where I get to the final part of the feature and realize I spent far more time coercing AI to do the right thing than it would have taken me to do it myself.

It is also sometimes really enjoyable and sometimes a horrible experience. Programming prior to it could also be frustrating at times, but not in the same way. Maybe it is the expectation of increased efficiency that is now demanded in the face of AI tools.

I do think AI tools are consistently great for small POCs or where very standard simple patterns are used. Outside of that, it is a crapshoot or slot machine.

Re: After two years of vibecoding, I'm back to writing by hand

#519

Post by permo-w »

nonethewiser wrote: post #188
rich_sasha wrote: post #41

I came to "vibe coding" with an open mind, but I'm slowly edging in the same direction. It is hands down good for code which is laborious or tedious to write, but once done, obviously correct or incorrect (with low effort inspection). Tests help but only if the code comes out nicely structured. I made plenty of tools like this, a replacement REPL for MS-SQL, a caching tool in Python, a matplotlib helper. Things that…

The hardest part of coding has never been coding. It's been translating new business requirements into a specific implementation plan that works . Understanding what needs to be done, how things are currently working, and how to go from A to B. You can't dispense with yourself in those scenarios. You have to read, think, investigate, break things down into smaller problems. But I employ LLM's to help with that all th…

vibe coding applies to very few people in this thread. almost all the people here are talking about using LLMs to do something they could do anyway, to save time, or getting the LLM to teach them how to code something. this is not vibe coding. vibe coding is lacking coding experience and slapping in some prompts to just get something that works

Re: After two years of vibecoding, I'm back to writing by hand

#520

Post by SecretDreams »

frankc wrote: post #46
orev wrote: post #27

Earlier quoted context omitted.

It’s like weightlifting: sure you can use a forklift to do it, but if the goal is to build up your own strength, using the forklift isn’t going to get you there. This is the ultimate problem with AI in academia. We all inherently know that “no pain no gain” is true for physical tasks, but the same is true for learning. Struggling through the new concepts is essentially the point of it, not just the end result. Of cou…

I think this is a pretty solid analogy but I look at the metaphor this way - people used to get strong naturally because they had to do physical labor. Because we invented things like the forklift we had to invent things like weightlifting to get strong instead. You can still get strong, you just need to be more deliberate about it. It doesn't mean shouldn't also use a forklift, which is its own distinct skill you al…

> people used to get strong naturally because they had to do physical labor.

People used to get strong because they had to survive. They stopped needing strength to survive, so it became optional.

So what does this mean about intelligence? Do we no longer need it to survive so it's optional? Yes/No informs on how much young and developing minds should be exposed to AI.

Post reply on HN