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

Vibe Debugging: Enterprises' Up and Coming Nightmare

marketsaintefficient.substack.com

Post reply on HN
Print view View original

31–40 of 69 posts

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#31

Post by dogleash »

seadan83 wrote: post #23
itsdrewmiller wrote: post #9

> I suspect best practices for "vibe coding" will end up like test-driven development: a proven method for writing better software that many engineers still choose to skip. I’d like to see the proof for TDD; last I heard it slowed development with only minor reliability improvements.

The proof for TDD is usually looking at bug detection rates. Similar for code review. OTOH, the "design damage" of TDD is something overlooked by those metrics. What it boils down to: - TDD in the hands of a junior is very good. Drastically reduces bugs, and teaches the junior how to write code that can be tested and is not just a big long single method of spaghetti with every data structure represented as another di…

Your comment doesn’t distinguish between having a robust automated test suite and doing TDD.

I’ll take your comment as testing is good and constraining your workflow to TDD is worthless.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#32

Post by hinkley »

Half the problem will be lack of a coherent commit history, to piece together what the goal of certain changes might have been. Large check-ins lose resolution here which magnifies the number of possibilities.

When you’re trying to preserve features but fix bugs this information saves a lot of time and helps prevent regressions.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#34

Post by bootsmann »

riku_iki wrote: post #11
unzadunza wrote: post #4

> 81% of developers agreed that AI increases their productivity I've had a few AI generated PRs come my way and the code-review process is, shall we say, not fun. It takes me a lot more time to review these PRs, there is way more back-and-forth between me and the 'developer', and it takes much more time to get the PR merged. That's not saying anything about the increased difficulty in modifying this code in the futur…

AI search makes me personally way more productive, e.g.: write snippet how to do X using library Y I never touched before.

Maybe as a small anecdote: I had a coworker ask an AI to write them a function to auth to aws using boto3 and environment variables. The LLM happily complied and gave them a 30 line snippet but it failed to point out that if they were to open boto3 docs it would tell them that it will already default to environment variables when it has no credentials and the whole function is just reinventing the wheel.

If you’re throwing the LLM at APIs you don’t know, how could you possibly verify it is using them properly?

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#35

Post by hinkley »

manoDev wrote: post #22

AI makes it quicker and cheaper to ship something. The problem with most companies is shipping the wrong thing. VCs hope that with AI they can have a larger portfolio, shipping more things, so that by sheer luck, one is a success. That's why many employees are critical of the AI hype while VCs and C-level love it. The whole discussion about maintainability doesn't even register on the radar, employees vs. VCs and C-l…

It’s based on the same category error that says I can buy a company but lose the employees and still have the value.

You don’t. You either don’t get that, or you do but would rather people not know that you really just wanted to destroy a competitor and snake some of their customers.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#37

Post by astrobe_ »

"Isn't it just temporary, and AI will get better?"

There are 2 instances of the word "understand" in the first paragraph, 3 if you count the beginning of the second.

In my book, "understanding" is a synonym for "intelligence" - the roots of the word are "read between the lines", where something else that just knowledge is, the ability to use and manipulate knowledge [1].

But the thing is, despite this tech being classified as "artificial intelligence", it does not understand a thing - or so little.

So, if we extrapolate Betteridge's law of headlines, no it is not temporary for this type of technology. But I think connecting it with formal computations - inference engines for formal logic, calculators [2], etc. could be amazing.

[1] https://en.wiktionary.org/wiki/intelligence - well, yes, that's a bit cherry-picked.

[2] https://arxiv.org/abs/2406.03445 - amazing result, and maybe will find out that it is exactly what we do "under the skull", but doing arithmetic with Fourier transforms is not the best use of a microprocessor.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#38

Post by rbongers »

>The discipline required to use AI tools responsibly is surprisingly difficult to maintain

I don't find that this requires discipline. AI code simply requires code review the same as anything else. I don't feel the need to let AI code in unchecked in the same way I don't feel the need to go to my pull request page one day and gleefully hit approve and merge on all of them without checking anything.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#39

Post by hinkley »

seadan83 wrote: post #23
itsdrewmiller wrote: post #9

> I suspect best practices for "vibe coding" will end up like test-driven development: a proven method for writing better software that many engineers still choose to skip. I’d like to see the proof for TDD; last I heard it slowed development with only minor reliability improvements.

The proof for TDD is usually looking at bug detection rates. Similar for code review. OTOH, the "design damage" of TDD is something overlooked by those metrics. What it boils down to: - TDD in the hands of a junior is very good. Drastically reduces bugs, and teaches the junior how to write code that can be tested and is not just a big long single method of spaghetti with every data structure represented as another di…

Developers have selective amnesia and only count dev time when working on what they want to work on rather than including time spent fixing things they’ve already mentally marked as done.

The worst actors find ways to make other people responsible for fixing their bugs.

Re: Vibe Debugging: Enterprises' Up and Coming Nightmare

#40

Post by riku_iki »

bootsmann wrote: post #34
riku_iki wrote: post #11

Earlier quoted context omitted.

AI search makes me personally way more productive, e.g.: write snippet how to do X using library Y I never touched before.

Maybe as a small anecdote: I had a coworker ask an AI to write them a function to auth to aws using boto3 and environment variables. The LLM happily complied and gave them a 30 line snippet but it failed to point out that if they were to open boto3 docs it would tell them that it will already default to environment variables when it has no credentials and the whole function is just reinventing the wheel. If you’re th…

The question is how fast and well dev unfamiliar with that API would achieve the goal alone compared to being assisted by LLM: he could set up snippet, run test, see what are the error, ask LLM to check why error could happen.
Post reply on HN