Cleaning up after AI rockstar developers • Hacker News Board

Re: Cleaning up after AI rockstar developers

#91

Post by Hasz » Tue, Jun 09, 2026, 2:20 PM UTC

I think this is fine? Code used to be very expensive to generate, now it is cheap. Building glue logic between well-defined, well-documented APIs has never been easier or faster. There is a time and place for throwaway code that quickly automates a task. It is fast food to fine dining -- not everything needs to be a Michelin star experience.

However, as always, AI usage is a matter of taste. Including your style rules in the prompt matters. Introduce new paradigms/tools/code into the main codebase because they solve a business problem, not because they are technically interesting. Careful development does not break 7 things to introduce one new feature, etc.

Re: Cleaning up after AI rockstar developers

#92

Post by SpicyLemonZest » Tue, Jun 09, 2026, 2:20 PM UTC

patates wrote: post #56

MobiusHorizons wrote: post #51

Earlier quoted context omitted.

It’s not like the op invented Microsoft’s leveling system. It looks like junior engineer is 59 and 63 is something like senior engineer. I know at google there is a very meaningful difference in the work and responsibilities expected between our equivalent of 63 (L5) and 61(L4).

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?

Re: Cleaning up after AI rockstar developers

#93

Post by alfredoh07 » Tue, Jun 09, 2026, 2:22 PM UTC

laszlojamf wrote: post #70

this resonates with me, but fortunately one difference between LLMs and rockstar developers, is that LLMs will at least _try_ to explain what they are doing, and why something has to be certain why. I've gotten quite a lot of mileage from being a five-year-old with Claude and just asking "why" until I'm satisfied

[flagged]

Re: Cleaning up after AI rockstar developers

#94

Post by nuggetdm » Tue, Jun 09, 2026, 2:23 PM UTC

baxtr wrote: post #67

rzmmm wrote: post #48

Earlier quoted context omitted.

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

100% - one of the biggest advantages of software is its mutability, so why not use it to prototype properly?

[dead]

Re: Cleaning up after AI rockstar developers

#95

Post by albedoa » Tue, Jun 09, 2026, 2:24 PM UTC

tyleo wrote: post #45

red75prime wrote: post #42

Is the "Cleaning up after hundreds of AI rockstars" part a description of an actual experience? I don't feel that it is. I would expect much more swearing if it were the case.

It could be but there’s always been so called “10x developers” who just make 10x messes. I think it’s the continuation of an existing phenomenon. https://www.tyleo.com/blog/the-terminal-star

This is a confusion that you could not have predicted, but primed by your comment, I expected "terminal star" to refer to a suggested predecessor of the AI rockstar. No, it refers to the animated Claude Code star :P

Re: Cleaning up after AI rockstar developers

#96

Post by pu_pe » Tue, Jun 09, 2026, 2:25 PM UTC

SlinkyOnStairs wrote: post #50

pu_pe wrote: post #38

Earlier quoted context omitted.

Absolutely. I really don't think the future will be humans reading and picking apart an AI-generated codebase, there will be tech debt agents or whatever running overnight.

I think you misunderstand why tech debt lingers around. It's not a capacity or capability problem. Organisations just don't want to deal with the accountability involved with "touching cold code". Whether it's a human or "AI agent" doesn't change the "It worked in prod, you touched it, you broke it, never touch anything again" dynamic.

That's one dimension of it, but in the context of this thread we are talking about how maintainable a codebase is for other humans. If your codebase is messy you depend on a few key employees and it might be hard to onboard new ones, so there has always been financial incentives to reduce tech debt.

Re: Cleaning up after AI rockstar developers

#97

Post by LtWorf » Tue, Jun 09, 2026, 2:28 PM UTC

jhack wrote: post #89

Sometimes I wonder if any of this will even matter in a few years. How many of us compile code and then have to clean up the assembly, or even worry about what a compiler generates as long as it's correct?

We are finding out that ram is neither cheap and unlimited.

Re: Cleaning up after AI rockstar developers

#98

Post by bluGill » Tue, Jun 09, 2026, 2:29 PM UTC

rzmmm wrote: post #48

JoelMcCracken wrote: post #41

Earlier quoted context omitted.

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”

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

The problem is those shoddy foundations can support a lot of weight before they finally fail. A prototype you write in a day - not a big deal to throw away. However if you have been working for a while that is a lot of effort/money.

Worse, often you need to spend years before you realize how an initial design decision was a mistake - not only are you proposing to throw away millions of dollars worth of work - you also don't know that your proposed better design is really better.

Re: Cleaning up after AI rockstar developers

#99

Post by bbminner » Tue, Jun 09, 2026, 2:30 PM UTC

One argument I heard from a college that the experimental llm written code (not production ofc) should be "write only" - you specify the requirements and constraints and let the machine figure it out - you specifically avoid "fixing it" or "cleaning it up" or reviewing the code because it disrupts the state of this discrete optimizer (over code). Not saying that it is right, or that it should be applied in prod, just noting that this is one potential way to go for non-critical code with clear "win conditions".

Re: Cleaning up after AI rockstar developers

#100

Post by conductr » Tue, Jun 09, 2026, 2:30 PM UTC

maerF0x0 wrote: post #35

I've met a handful of people across my life that i'd call truly brilliant. Like, holy heck how in the world is this person this smart? Two things I've noted about really smart people are (usually mutually exclusively) 1) Sometimes they do not realize how smart they are, because it's simple to them, or because they know the subject they assume everyone else, say with a computer science degree, knows and recalls and un…

> Imagine walking through life and everything is clear, obvious, easy to process and having to watch humanity make stupid choices over and over and over again when the answers have been long known...

I don’t claim to be book smart or have a high IQ or whatever but I feel this way about small things that I feel are common sense. It’s maddening to me to watch people fumble around. Or do X when obviously it will result in -Y a bad thing. I really have learned to just not vocalize it, most of the time. It’s especially unhealthy for my close family relationships as I just see so much of it that I could nag them to death.