Cleaning up after AI rockstar developers • Hacker News Board

Re: Cleaning up after AI rockstar developers

#381

Post by bluGill » Wed, Jun 10, 2026, 1:03 PM UTC

karmakurtisaani wrote: post #190

shrikant wrote: post #114

Earlier quoted context omitted.

Well, there's nothing as permanent as a temporary solution...

"So we all agree this is not ideal, but let's use it for now and focus on ..." Heard it so many times.

More than half the time it is correct - until you figure out those things you are asking to focus on you won't know what really works. Going for ideal now just means when you get to those things you discover another thing you hadn't thought of in advance and so you are no better off.

Experienced developers in a domain can sometimes anticipate the issues, but experience only comes from failing.

The real answer is allowing some budget to fix things and then fixing them as you go along.

Re: Cleaning up after AI rockstar developers

#382

Post by datadrivenangel » Wed, Jun 10, 2026, 1:24 PM UTC

godelski wrote: post #312

prodigycorp wrote: post #214

Earlier quoted context omitted.

Thought experiment: would a junior developer armed with a modern day gpt-5.5 or opus 4.8 in 2015 would have been considered a 10x developer (assuming nobody knew they were using AI)?

> considered a 10x developer The 10x developer never existed. You're telling me these people are doing a year's worth of work in 1.2 months? Seriously?! 10x?! In a year you can probably learn to program from scratch and participle if you're working 8hrs per day 5 days a week We need to stop exaggerating so much. A 2x dev would be insane! A 1.5x dev does a year's work in 8. A 1.1x dev does it in 11. Saving a whole mon…

The research referenced in Fred Brook's The Mythical Man Month found that there was a 10x difference in programming task completion time between the FASTEST and the SLOWEST developers, but only a ~2.5x increase from the median to the fastest.

Re: Cleaning up after AI rockstar developers

#383

Post by morserer » Wed, Jun 10, 2026, 1:53 PM UTC

conductr wrote: post #169

pjm331 wrote: post #106

Earlier quoted context omitted.

i feel fairly certain everyone has some set of activities or tasks they feel this way about my wife and i have two non-overlapping sets haha you can imagine how that plays out

Same wrt my wife and I. She’s quite clumsy and to my assertion doesn’t always think things through. So it’s a bad combination for “accidents” to always happen which I think are very preventable and quite obvious to occur using her approach. A lot of it is just mental errors that I don’t make, but it’s not that I’m perfect I probably just make different mistakes (I think less volume too ;) Yesterday she literally fail…

Does your wife have ADHD? She may not be physically capable of learning from her mistakes without the use of frameworks built to address the disorder.

If she's unsure, it's worth looking into. The immediate relief available by way of the strategies that documentation on the disorder provides can be life-changing and don't require medication nor therapy in order to be put to use.

Re: Cleaning up after AI rockstar developers

#384

Post by mustardo » Wed, Jun 10, 2026, 2:41 PM UTC

datadrivenangel wrote: post #382

godelski wrote: post #312

Earlier quoted context omitted.

> considered a 10x developer The 10x developer never existed. You're telling me these people are doing a year's worth of work in 1.2 months? Seriously?! 10x?! In a year you can probably learn to program from scratch and participle if you're working 8hrs per day 5 days a week We need to stop exaggerating so much. A 2x dev would be insane! A 1.5x dev does a year's work in 8. A 1.1x dev does it in 11. Saving a whole mon…

The research referenced in Fred Brook's The Mythical Man Month found that there was a 10x difference in programming task completion time between the FASTEST and the SLOWEST developers, but only a ~2.5x increase from the median to the fastest.

This! I've worked with a few developers I would consider net negative to their team and product, in that their removal would have increased 3-4 other team members productivity by say 20% each. Coincidently these developers were almost exclusively Indian immigrants. In organisation with poor corporate culture and the ZIRP (Zero Interest Rate Policy) days of hiring to signal growth and managers hiring to increase the number of reports (to signal importance) compounded the problem

Re: Cleaning up after AI rockstar developers

#385

Post by freediddy » Wed, Jun 10, 2026, 3:04 PM UTC

Capricorn2481 wrote: post #313

freediddy wrote: post #126

Earlier quoted context omitted.

Then you add an agent that goes through the code and simplifies it. Before every sprint, you get the agent to simplify whatever it can without losing fidelity. It's really that simple.

I should probably know better than to interact with a 3 month account called "freediddy", but here we go. > Then you add an agent that goes through the code and simplifies it Can you? I just asked Opus to generate a sum function. def sum(a, b): return a + b Then I asked if it could simplify it further. I would expect it to say this is simple enough, or just use the actual `sum` function, but it did this. add = lambda…

> If you ask it to simplify something, it will make changes whether it needs to or not.

This is false. You can prompt it to only make changes that will have a material effect on the performance. You can create performance tests and have it run the test after every change and if nothing changes then back it out.

You're not thinking creatively enough about how to use AI to your advantage.

Re: Cleaning up after AI rockstar developers

#386

Post by jghn » Wed, Jun 10, 2026, 3:56 PM UTC

Veserv wrote: post #319

godelski wrote: post #312

Earlier quoted context omitted.

> considered a 10x developer The 10x developer never existed. You're telling me these people are doing a year's worth of work in 1.2 months? Seriously?! 10x?! In a year you can probably learn to program from scratch and participle if you're working 8hrs per day 5 days a week We need to stop exaggerating so much. A 2x dev would be insane! A 1.5x dev does a year's work in 8. A 1.1x dev does it in 11. Saving a whole mon…

Of course they do. Have you literally never run into a problem that the average developer can not solve, but a expert can solve? That is infinity times more productive. Even assuming that maybe the average developer could come to learn how to solve the problem you can easily see the gap between taking months to learn how to solve a problem versus already knowing how to solve it on short notice being over 10x. Large p…

> a problem that the average developer can not solve, but a expert can solve?

Yes these exist. The rate at which they exist is grossly exaggerated. Every company likes to think that their problems are special snowflakes. Nothing could be further from the truth.

In these discussions we try to solve for a 0.00001% problem by claiming it's common to encounter.

Re: Cleaning up after AI rockstar developers

#387

Post by maxothex » Wed, Jun 10, 2026, 4:01 PM UTC

[flagged]

Re: Cleaning up after AI rockstar developers

#388

Post by dang » Wed, Jun 10, 2026, 6:20 PM UTC

LearnYouALisp wrote: post #243

sumeno wrote: post #149

Earlier quoted context omitted.

I don't think you know what deterministic means

[flagged]

It's not ok to post slurs to HN and we ban accounts that do it, so please don't do it again.

https://news.ycombinator.com/newsguidelines.html

https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

Re: Cleaning up after AI rockstar developers

#389

Post by SlinkyOnStairs » Wed, Jun 10, 2026, 7:09 PM UTC

pu_pe wrote: post #326

SlinkyOnStairs wrote: post #129

Earlier quoted context omitted.

> so there has always been financial incentives to reduce tech debt. Yes. In practice, this does not weigh against organisational resistance. AI really makes it worse by adding an explicit numerical cost to doing anything.

Um, no, actually AI makes it better because the cost is lower now. I'm not sure what point you're trying to make here, obviously organizations already fight against tech debt all the time through a variety of means?

The point there is that it is MUCH easier to get corporate to agree to something when the cost is nebulous and being paid anyway. If you get a senior dev to clean up some tech debt, how much did that cost the company? The dev will have some multiple things at the same time, so you can't cleanly assign a number of hours, maybe multiple people are involved. It's practically just an unknowable. Practically, $0.

Anthropic will sent a concrete number bill.

Re: Cleaning up after AI rockstar developers

#390

Post by LearnYouALisp » Wed, Jun 10, 2026, 7:10 PM UTC

dang wrote: post #388

LearnYouALisp wrote: post #243

Earlier quoted context omitted.

[flagged]

It's not ok to post slurs to HN and we ban accounts that do it, so please don't do it again. https://news.ycombinator.com/newsguidelines.html https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

Has nothing to do with that. If someone is looking for something, they can find it anywhere. If you want to say "prevalent in [place name]... etc" The emphasis is on the tech culture. The factors are multiple. Parallel: Do you know about chauvinism, etc.?