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

Cleaning up after AI rockstar developers

codingwithjesse.com

Post reply on HN
Print view View original

141–150 of 401 posts

Re: Cleaning up after AI rockstar developers

#141

Post by skydhash »

magicalhippo wrote: post #109
ChrisMarshallNY wrote: post #54

Oh, yeah. I'm reconciling with the fact, that, if I let AI write a bunch of code, I have to depend on that AI to maintain it. I just spent the last week, hunting down memory issues in the app I'm writing. I had a lot of help from an LLM. It rewrote most of the view controller that implements the map screen. That view controller is now 4,000 lines long (but half of that is comments), but it works extremely well. It to…

So far my take has been that there is code that isn't very important, in the sense that if it works it works, it won't be modified or extended much if at all, and it's easy to verify that it works as expected. This type of code I'm happy with letting the AI go wild on. Then there's important code, like business logic, security related stuff and such. For that I'll happily use AI to brainstorm ideas and avenues, do co…

I’ve never seen code that is unimportant. It’s either being used or not. If it’s boilerplate, it can be abstracted away. There are domains that are riskier than others (debug logging vs crypto for auth), but sometimes bugs in a somewhat safe place can lead to some catastrophic issues (you do not have to break a crypto algorithm if the key can be leaked via logging).

Re: Cleaning up after AI rockstar developers

#145

Post by SkyBelow »

JoelMcCracken wrote: post #41
DenisM wrote: post #26

Earlier quoted context omitted.

In some ways they are giving you a spec and UI mocks to implement.

This is one of the things I keep thinking about. At the very least, these tools make prototyping and idea vetting remarkably cheaper. Then we go back to the old “the prototype works; I’m the boss and I’m telling you to deploy it to production”

One of the major concerns with prototyping, at least in my experience and based on the general vibe I've felt from others over the years, is that clients will generally do some variation of "You have a working prototype? So how many days until it is prod ready? No more than a few weeks, right?" and that will be their expectation. AI makes prototyping easier, but makes this specific drawback much worse. Expectations are going to be misaligned, leading to many disappointments, and likely some number of developers taking undue negative outcomes. I'm not even sure if it will normalize to reasonable expectations, given that this tension never seemed resolved even before AI was in the mix.

Re: Cleaning up after AI rockstar developers

#146

Post by kaydub »

SpicyLemonZest wrote: post #92
patates wrote: post #56

Earlier quoted context omitted.

Believing in that system so much to say something like that might be worse. Noting against the OP, that kind of Stockholm Syndrome can be found in my past as well.

Not sure I understand. Is your contention that the distinction between senior and non-senior engineers is fake and everyone's doing basically the same thing? Or are you just objecting to the (arbitrary) names Microsoft uses for them?

[flagged]

Re: Cleaning up after AI rockstar developers

#147

Post by hightrix »

rfgplk wrote: post #73
anonzzzies wrote: post #19

I like fixing code made by AIs and others (outsourcing code is similar as someone else said already). Last week we found out some client tried to vibe some departmental tool; the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. Now we have to fix it: its basically free 10k-50k euros over and over again for this type of work. V…

> the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. The anti-LLM propaganda is getting ridiculous at this point. No project "needs 10GB" to compile, unless you're working with astronomically massive repos, and _no_ LLM will _ever_ generate that. Lint errors (depending on cause) are either meaningless or a result of poor pro…

Linting is also trivial for LLMs. I’d argue linting is one of the easiest and best use cases for coding assistants.

This story doesn’t add up.

Re: Cleaning up after AI rockstar developers

#148

Post by piva00 »

eithed wrote: post #80
piva00 wrote: post #15

Earlier quoted context omitted.

It's the mandate from top-down. Of course it's a people issue, the problem is that the people creating this issue are exactly the ones paying us. My manager got the mandate she needs to start coding, she doesn't want that, no one in our team wants that, she's a great manager exactly where she is right now. Nonetheless, we are helping her to code to show something for the higher-ups so she can keep her job, we really…

Even if it's a mandate top-down, you can: - show increase in errors and outages caused by this approach - integrate manager changes into your CI pipeline (coding / reviewing / testing / documentation) - discuss how your manager can do the changes they need to do without sidetracking all other work Make it indeed about the money: coding by PM + fixing what was coded + dealing with fallout is greater expense than codin…

I don't know why you assumed it was a PM thing, the mandate is for EMs to be more "hands-on".

On your points:

Manager changes are always going to go through the usual pipeline, we are 10k+ people so there's not even a way to go all gung-ho pushing stuff. They need to be reviewed, approved, etc.

But we don't want our manager to code, nor does our manager, so we are just helping to cross the bare minimum expected from higher ups. For my team it's not an issue with our manager's code (those will be at max small fixes, well-defined, the most trivial stuff), the issue is they are mandating managers to do it.

I don't know what size of company you work at, where I am at there is simply no incentive for me to do all the extra work to show execs/higher management the issues cropping up.

I don't even have access to them, I have to pass through other channels, those might compile reports from many people to try to present a case, if they get to present a case then there's a whole other discussion to happen at director/VP/C-level about what they want to do, and since it goes against their big mandate it most likely will just be thrown out.

In this structure I have no motivation at all to go out of my way to perform data gathering/analysis, wrapping it all in a nice concise document explaining what the data means, potential remediation, etc. just to become a footnote in someone else's document that ultimately will not change anything from the VP/C-level mandate.

Re: Cleaning up after AI rockstar developers

#149

Post by sumeno »

gyanchawdhary wrote: post #84
this_user wrote: post #71

Earlier quoted context omitted.

Compilers are deterministic and they actually possess domain knowledge of what they are trying to do. AI models are non-deterministic, have no real domain knowledge due to lack of an underlying world model, and their way of "writing" software is to spew out something that looks like something that they have been trained on, then iterate on it long enough until it has reached the level of being barely runnable.

[flagged]

I don't think you know what deterministic means

Re: Cleaning up after AI rockstar developers

#150

Post by dawnerd »

anonzzzies wrote: post #19

I like fixing code made by AIs and others (outsourcing code is similar as someone else said already). Last week we found out some client tried to vibe some departmental tool; the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. Now we have to fix it: its basically free 10k-50k euros over and over again for this type of work. V…

Agencies that focus on this sort of work are going to make bank. We’ve already gotten some work like this, and it’s just going to keep coming as people think they can vibe code their products. Like you said, easy money.
Post reply on HN