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

321–330 of 652 posts

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

#321

Post by kaydub »

rtp4me wrote: post #290
kaydub wrote: post #239

Earlier quoted context omitted.

Happy to see someone else doing this. All code written by an LLM is reviewed by an additional LLM. Then I verify that review and get one of the agents to iterate on everything.

Agreed. From my experience, Claude is the top-level coder, Gemini is the architect, and Codex is really good at finding bugs and logic errors. In fact, Codex seems to perform better deep analysis than the other two.

I just round robin them until I run out on whatever subscription level I'm on. I only use claude api, so I pay per token there... I consider using claude as "bringing out the big guns" because I also think it's the top-level coder.

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

#322

Post by ruszki »

jasondigitized wrote: post #284
GolDDranks wrote: post #219

I feel like I'm taking crazy pills. The article starts with: > you give it a simple task. You’re impressed. So you give it a large task. You’re even more impressed. That has _never_ been the story for me. I've tried, and I've got some good pointers and hints where to go and what to try, a result of LLM's extensive if shallow reading, but in the sense of concrete problem solving or code/script writing, I'm _always_ di…

I feel like I am taking crazy pills. I am getting code that works from Opus 4.5. It seems like people are living in two separate worlds.

Working code doesn’t mean the same for everyone. My coworker just started vibe coding. Her code works… on happy paths. It absolutely doesn’t work when any kind of error happens. It’s also absolutely impossible to refactor it in any way. She thinks her code works.

The same coworker asked to update a service to Spring Boot 4. She made a blog post about. She used LLM for it. So far every point which I read was a lie, and her workarounds make, for example tests, unnecessarily less readable.

So yeah, “it works”, until it doesn’t, and when it hits you, that you need to work more in sum at the end, because there are more obscure bugs, and fixing those are more difficult because of terrible readability.

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

#323

Post by nozzlegear »

GolDDranks wrote: post #219

I feel like I'm taking crazy pills. The article starts with: > you give it a simple task. You’re impressed. So you give it a large task. You’re even more impressed. That has _never_ been the story for me. I've tried, and I've got some good pointers and hints where to go and what to try, a result of LLM's extensive if shallow reading, but in the sense of concrete problem solving or code/script writing, I'm _always_ di…

You're not taking crazy pills, this is my exact experience too. I've been using my wife's eCommerce shop (a headless Medusa instance, which has pretty good docs and even their own documentation LLM) as a 100% vibe-coded project using Claude Code, and it has been one comedy of errors after another. I can't tell you how many times I've had it go through the loop of Cart + Payment Collection link is broken -> Redeploy -> Webhook is broken (can't find payment collection) -> Redeploy -> Cart + Payment Collection link is broken -> Repeat. And it never seems to remember the reasons it had done something previously – despite it being plastered 8000 times across the CLAUDE.md file – so it bumbles into the same fuckups over and over again.

A complete exercise in frustration that has turned me off of all agentic code bullshit. The only reason I still have Claude Code installed is because I like the `/multi-commit` skill I made.

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

#324

Post by nh23423fefe »

jasondigitized wrote: post #285
SCdF wrote: post #267

Earlier quoted context omitted.

I am getting workable code with Claude on a 10kloc Typescript project. I ask it to make plans then execute them step by step. I have yet to try something larger, or something more obscure.

This. I feel like folks are living in two separate worlds. You need to narrow the aperture and take the LLm through discrete steps. Are people just saying it doesn't work because they are pointing it at 1m loc monoliths and trying to oneshot a giant epic?

AI was useless for me on a refactor of a repo 20k loc even after I gave examples of the migrations I wanted in commits.

It would correctly modify a single method. I would ask it to repeat for next and it would fail.

The code that our contractors are submitting is trash and very high loc. When you inspect it you can see that unit tests are testing nothing of value.

   when(mock.method(foo)).thenReturn(bar)
   assert(bar == bar)
stuff like that

its all fake coverage, for fake tests, for fake OKRs

what are people actually getting done? I've sat next to our top evangelist for 30 minutes pair programming and he just fought the tool saying something was wrong with the db while showing off some UI I dont care about.

like that seems to be the real issue to me. i never bother wasting time with UI and just write a tool to get something done. but people seem impressed that AI did some shitty data binding to a data model that cant do anything, but its pretty.

it feels weird being an avowed singularitarian but adamant that these tools suck now.

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

#325

Post by GoatInGrey »

jasondigitized wrote: post #284
GolDDranks wrote: post #219

I feel like I'm taking crazy pills. The article starts with: > you give it a simple task. You’re impressed. So you give it a large task. You’re even more impressed. That has _never_ been the story for me. I've tried, and I've got some good pointers and hints where to go and what to try, a result of LLM's extensive if shallow reading, but in the sense of concrete problem solving or code/script writing, I'm _always_ di…

I feel like I am taking crazy pills. I am getting code that works from Opus 4.5. It seems like people are living in two separate worlds.

That's a significant rub with LLMs, particularly hosted ones: the variability. Add in quantization, speculative decoding, and dynamic adjustment of temperature, nucleus sampling, attention head count, & skipped layers at runtime, and you can get wildly different behaviors with even the same prompt and context sent to the same model endpoint a couple hours apart.

That's all before you even get to all of the other quirks with LLMs.

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

#326

Post by Mashimo »

kaydub wrote: post #248
Mashimo wrote: post #21

Earlier quoted context omitted.

Is Claude through Github Copilot THAT much worse? I know there are differences, but I don't find it to be obstructing my vibe coding.

Yes. Copilot sucks. Copilot is like a barely better intellisense/auto-complete, especially when it came out. It was novel and cool back then but it has been vastly surpassed by other tools.

> Copilot is like a barely better intellisense/auto-complete

As I have never tried Claude Code, I can't say how much better it is. But Copilot is definitely more then auto-complete. Like I already wrote, it can do Planning mode, edit mode, mcp, tool calling, web searches.

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

#327

Post by echelon »

jasondigitized wrote: post #285
SCdF wrote: post #267

Earlier quoted context omitted.

I am getting workable code with Claude on a 10kloc Typescript project. I ask it to make plans then execute them step by step. I have yet to try something larger, or something more obscure.

This. I feel like folks are living in two separate worlds. You need to narrow the aperture and take the LLm through discrete steps. Are people just saying it doesn't work because they are pointing it at 1m loc monoliths and trying to oneshot a giant epic?

I'm using Claude in a giant Rust monorepo. It's really good at implementing HTTP handlers and threaded workers when I point it at prior examples.

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

#328

Post by 0xffff2 »

fsloth wrote: post #53
ncruces wrote: post #42

> The AI had simply told me a good story. Like vibewriting a novel, the agent showed me a good couple paragraphs that sure enough made sense and were structurally and syntactically correct. Hell, it even picked up on the idiosyncrasies of the various characters. But for whatever reason, when you read the whole chapter, it’s a mess. It makes no sense in the overall context of the book and the preceding and proceeding…

"So why do you think a 10 kLoC vibecoded codebase will be any good engineering-wise?" I've been coding a side-project for a year with full LLM assistance (the project is quite a bit older than that). Basically I spent over a decade developing CAD software at Trimble and now have pivoted to a different role and different company. So like an addict, I of course wanted to continue developing CAD technology. I pretty muc…

Neat project, and your experience mirrors mine when writing hobby projects.

About the project itself, do you plan to open source if eventually? LLM discussion aside, I've long been frustrated by the lack of a good free desktop 3D CAD software.

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

#329

Post by GoatInGrey »

brabel wrote: post #304
SCdF wrote: post #267

Earlier quoted context omitted.

I am getting workable code with Claude on a 10kloc Typescript project. I ask it to make plans then execute them step by step. I have yet to try something larger, or something more obscure.

Most agents do that by default now.

I feel like there is a nuance here. I use GitHub Copilot and Claude Code, and unless I tell it to not do anything, or explicitly enable a plan mode, the LLM will usually jump straight to file edits. This happens even if I prompt it with something as simple as "Remind me how loop variable scoping works in this language?".

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

#330

Post by Leherenn »

gedy wrote: post #275
b33j0r wrote: post #253

Earlier quoted context omitted.

I usually do most of the engineering and it works great for writing the code. I’ll say: > There should be a TaskManager that stores Task objects in a sorted set, with the deadline as the sort key. There should be methods to add a task and pop the current top task. The TaskManager owns the memory when the Task is in the sorted set, and the caller to pop should own it after it is popped. To enforce this, the caller to…

What you’re describing makes sense, but that type of prompting is not what people are hyping

I haven't tried it, but someone at work suggested using voice input for this because it's so much easier to add details and constraints. I can certainly believe it, but I hate voice interfaces, especially if I'm in an open space setting.

You don't even have to be as organised as in the example, LLMs are pretty good at making something out of ramblings.

Post reply on HN