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

A guide to Gen AI / LLM vibecoding for expert programmers

stochasticlifestyle.com

Post reply on HN
Print view View original

71–80 of 122 posts

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#71

Post by bgwalter »

The author's 200 GitHub packages not withstanding, the startups he is involved in are both founded on machine learning, so I don't consider him unbiased.

It is always the founder type who is trying to peddle fantasies like this:

Vibe coding turns any individual into the CTO leading a team of 20, 30, 50, 60 interns.

How much does his new hobby cost?

On my $200/month Claude 20x Max subscription I used enough tokens for about $5,200 of compute in the first month. This is obviously not sustainable, but hey, it’s a startup world and VCs are paying for it right now.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#72

Post by ako »

recursive wrote: post #46
GuB-42 wrote: post #26

I think the article could be more accurately titled "A Guide to Gen AI / LLM Vibecoding for Programmers who hate their job" To me, someone who actually love programming, it makes vibe coding look like hell. > The workflow of vibe coding is the same as managing scrums or helping a student through a research thesis Which programmer wants that?! Just hearing the word "scrum" makes me want to run away and I know I am not…

I think I enjoy programming. Vibe coding removes most of the parts that I like. It already looks like hell. I'm probably a minority, but I don't think I'm alone in this.

I really like creating software solutions, vibe coding removes the part that is most tedious. LLMs allow me to experiment with different solutions and different designs faster.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#73

Post by polishdude20 »

afro88 wrote: post #62

> The moment you see it go off the rails, just throw it out. That problem is too hard for Claude, it’s for you now. Or, any of: - the problem was too big in scope and needed a stepped plan to refer to and execute step by step - your instructions weren't clear enough - the context you provided was missing something crucial it couldn't find agentically, or build knowledge of (in which case, document that part of the co…

I totally agree. I've recently been using Cursor to help create a new react project with a lot of functionality. I realized I need to have it do more smaller steps that I get to have lots of input on rather than say "this is the big picture now go forth".

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#74

Post by jpollock »

theLiminator wrote: post #69
jpollock wrote: post #66

I've just spent the better part of two weeks trying to convince a LLM to automate some programming for me. We use feature flags. However, cleaning them up is something rarely done. It typically takes me ~3minutes to clean one up. To clean up the flag: 1) delete the test where the flag is off 2) delete all the code setting the flag to on 3) anything getting the value of the flag is set to true 4) resolve all "true" ex…

Might make sense getting it to instead create a CST traversal that deletes feature flags by their id. Then you have a re-usable trustworthy tool that you can incrementally improve/verify.

That was the lesson I was learning. I should use the LLM to generate the tools that I use for consistently repeatable tasks.

Then I can rinse and repeat using the tool, fixing the bugs in the tool myself instead of repeating the expensive (in time) cost of using the LLM.

That was my last attempt, but I ran out of time.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#75

Post by polishdude20 »

leptons wrote: post #22
shortrounddev2 wrote: post #9

Earlier quoted context omitted.

If you have to describe the code to the ai and then read through each line of it anyways, why not just write the code yourself?

It takes way more time to explain, and then re-explain, and then re-re-re-explain to the LLM what I want the code to do. No, it isn't because I don't understand LLMs, it's because LLMs don't understand , period. Trying to coax a fancy word predictor to output the correct code can be extremely frustrating especially when I know how to write the code.

Usually if you have to re re re explain, it means you didn't leave those details in the first prompt. So writing out the code yourself, you'd still get into this trap because you discover as you write. Just like you discover the details as the LLM writes.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#76

Post by jpollock »

polishdude20 wrote: post #68
jpollock wrote: post #66

I've just spent the better part of two weeks trying to convince a LLM to automate some programming for me. We use feature flags. However, cleaning them up is something rarely done. It typically takes me ~3minutes to clean one up. To clean up the flag: 1) delete the test where the flag is off 2) delete all the code setting the flag to on 3) anything getting the value of the flag is set to true 4) resolve all "true" ex…

Which LLM? How are you prompting it? I've been using Cursor for the last few months and notice that for tasks like this, it helps to give examples of the code you're looking for, tell it more or less how the feature flags are implemented and also have it spit out a list of files it would modify first.

I gave it explicit ordering, instructions on what tools to _not_ use, and before/after examples from the codebase. A full page of instructions.

After iterating on that for a while, I did a bunch manually (90) and then gave the LLM a list of pull requests as examples, and asked _it_ to write the prompt. It still failed.

Finally, I broke the problem up and started to ask it to generate tools to perform each step. It started to make progress - each execution gave me a new checkpoint so it wouldn't make new mistakes.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#77

Post by Sharlin »

JohnMakin wrote: post #44
GuB-42 wrote: post #26

I think the article could be more accurately titled "A Guide to Gen AI / LLM Vibecoding for Programmers who hate their job" To me, someone who actually love programming, it makes vibe coding look like hell. > The workflow of vibe coding is the same as managing scrums or helping a student through a research thesis Which programmer wants that?! Just hearing the word "scrum" makes me want to run away and I know I am not…

almost every job ive ever had has been to build stuff. frequently programming is used to build stuff. programming is not my job, building stuff is. it’s perfectly normal (and a sign of a more mature engineer, imho) to prefer building stuff to the annoying stuff that gets in the way of building stuff, especially since many languages are obnoxious to work with.

Yes; in particular English is an incredibly obnoxious language to try to build software with. (Replace English with any natural language if you want.)

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#78

Post by cheema33 »

GuB-42 wrote: post #26

I think the article could be more accurately titled "A Guide to Gen AI / LLM Vibecoding for Programmers who hate their job" To me, someone who actually love programming, it makes vibe coding look like hell. > The workflow of vibe coding is the same as managing scrums or helping a student through a research thesis Which programmer wants that?! Just hearing the word "scrum" makes me want to run away and I know I am not…

If someone enjoys building houses with a hammer and nail, they still can. Other like using tools.

You will always be able to write code by hand. But you will not be able to keep up with other engineers who master using AI tools. I am a software engineer, I like building things. And I don't use binary or assembly, or C or any other lower level languages for good reasons. AI is just another higher level abstraction. A tool that allows me to build things a little faster. I use it every day.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#79

Post by qzw »

simonw wrote: post #43
EagnaIonat wrote: post #11

Earlier quoted context omitted.

> Not a single soul on this planet can review the thousands of lines of vibe coded bullshit that LLMs spit out. Even if you could the code can't be copyrighted.

Citation needed on that one. If that is true, how come huge companies like Microsoft and Salesforce and Google keep boasting about the increasing percentage of their code that is written by LLMs? What do you know that they don't?

I’m with you here. No way these companies are labeling all the AI code as such. They must all be commingled with human code and copyrighted.

Re: A guide to Gen AI / LLM vibecoding for expert programmers

#80

Post by wsintra2022 »

cheema33 wrote: post #78
GuB-42 wrote: post #26

I think the article could be more accurately titled "A Guide to Gen AI / LLM Vibecoding for Programmers who hate their job" To me, someone who actually love programming, it makes vibe coding look like hell. > The workflow of vibe coding is the same as managing scrums or helping a student through a research thesis Which programmer wants that?! Just hearing the word "scrum" makes me want to run away and I know I am not…

If someone enjoys building houses with a hammer and nail, they still can. Other like using tools. You will always be able to write code by hand. But you will not be able to keep up with other engineers who master using AI tools. I am a software engineer, I like building things. And I don't use binary or assembly, or C or any other lower level languages for good reasons. AI is just another higher level abstraction. A…

IDE’s are tools, languages are tools, LLMs are code generators, not quite the same thing.
Post reply on HN