Cleaning up after AI rockstar developers

milkers

This is why I like a bit of 'wet-kiss'es while working on projects.

skydhash

I’ve cleaned up after outsourced code and it has a different flavor to AI rockstar code. In the former, you can see that the developer only care about the current ticket. After every merge, it’s a flurry of bug fixes, because they always break something unrelated. And that’s due to bad design, you will see a lot of copy pasted code and unused code. As for the AI code, the most defining elements are unneeded complexity and low understanding of the abstraction involved. When you need a 10 lines functions, the AI will happily write an entire module because that’s how a fully implemented domain is like. But it’s not part of the requirements. As for the low understanding, you will see strange code, which are not fully antipattern, but are definitely not needed as it solves issue that the platform/library/framework doesn’t have or already have a solution for.

elzbardico

Please write a manual on how to cleanup after AI rockstar managers who think they can code. Much needed right now as I slept only two hours since yesterday after solving a SEV-0 and having to wake up after a 2 hour nap, so I could be now cleaning up the fallout before business hours. I am not a AI-denier, I am actually thankful I have AI right now to multiply my force, but frankly, people STILL need to review that fucking code, and the people who review the fucking code STILL need to be good enough to be able to write it themselves if they needed. Whoever says otherwise is either an AI investor, a linkedin influencer or a complete imbecile. --- EDIT Please add a section on how to communicate and write a post mortem where the guilty is completely exhonerated without the blame falling on me as I try to save said manager's face.

ramon156

I kind of envy people who need to clean up after others. At least you're puzzling. My current job is genuinely just boring. It's tasks that are so simple, a junior could do it. But no, instead they needed a medior. I'm not saying I'm better than this, nor that no medior will pick it up. I just cannot push myself to care about the code this company makes. It's old, dusty and it serves no one of importance. These customers use it because they once bought the tool and do not care enough to switch, because the tool in question is not interesting. I was promised work soon that aligned more with my experience, but I do not foresee these customers to come to a stale company like this. It's not surprising that this company is losing customers, employees, etc. But I have a mortgage to pay. Today I had the conversation about how they might not extend my contract, basically threatening me to take more ownership, do more work, for the same pay. Sadly I have to make it last until I find a new position that is actually interesting. I don't even need a lot of money, I could give a rat's ass about "growing". I just need enough to survive. This might be a very unrelated comment, in which I apologize. I just do not have another vent to post this to.

349187

The ironic rockstar comparison is very good. The classic rockstar only cared about "new" technologies and wrote spaghetti code, the new 100x AI rockstar can do more damage. It's a pity that the article ends cautiously with recommending to perhaps adapt AI usage practices. In this climate we are not there yet to publish the unfiltered opinion that generative AI is garbage and should be disposed of. Soon we will be.

danjc

As much as it's true that a novice will generally use AI to build a sloppy mess, I've also had success unsloppifying through some careful prompting.

nbevans

"I am a rockstar developer and this characterisation is unwarranted" -- thought bubble emoji

anonzzzies

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. Very easy if you know what you are doing; impossible if you don't. Keep m coming.

scotty79

> Building software that lasts Nah. Now everyone can build single purpose, single use, throw away software.

AndrewKemendo

It’s literally no different than how to clean up old projects over the last 30 years of software engineering I don’t understand why all this stuff is all of a sudden “new.” It feels like we’ve got an entire generation of people who never had to spend their time factoring or doing hard infrastructure work It’s actually pretty baffling how rare it is to find somebody who has consistent experience in refactoring that is under the age of 40

robofanatic

> Half the code was written in a language you didn't understand. The other half was written using libraries you never heard of. > As you waded through the slop, you browsed job postings and fantasized about leaving Just because you didn't understand something or haven't heard about a library, doesn't mean its slop. How do you make sure your definition of "clean code" is not a slop to others?

itake

This article feels is trying to justify their own inefficiencies (lack of library or language knowledge) instead of taking the time to learn from the rockstar and their technology choices. As I was leaving my last job, I advocated everyone migrate from plain old es6 to typescript, b/c several times broken builds made it to production. Certainly my coworkers may of felt upset that typescript is too verbose and pointless if everyone reaches for the "any" operator. But that doesn't mean the decision to move to Typescript was bad, it just means the company is "old school" and not willing to take the time to adopt modern workflows...

herrherrmann

I’m sure the general premise around AI-generated code is accurate. That being said, I’ve definitely had interesting moments where e.g. Claude produced code that matched the pre-existing codebase quite nicely, and slowly started building up its memory of how new pieces fit into the codebase in an idiomatic way. Then again, it started to throw in Tailwind-based CSS classes all of a sudden, because it assumed that Tailwind had been set up (it wasn’t).

jdw64

If you're just starting to learn programming, people will tell you that maintainability is important, and they'll mention John Ousterhout's concept of the "tactical tornado" as an anti-pattern. The problem is that this approach implements features quickly but in a way that conflicts with the team's mental model, ultimately ruining the entire codebase. A lot of blog posts initially framed this as a problem. I agreed to some extent. But as I've gained more programming experience, I've come to realize that all programs degrade over time until they are reborn. Eventually, it seems that destructive innovation is necessary for longevity. And sometimes, new patterns emerge from that kind of disruptive feature development. So you could say that AI rockstar developers and AI-driven development are close to being a "tactical tornado" because their codebases are bad, with poor maintainability and reliability. Maintainable development, in my experience as a traveling contract developer, usually refers to code that is well-modularized and well-crafted, making it easy for someone like me to understand the codebase when I come on board. But when I saw the leaked Claude code, frankly, the code quality was disappointing—yet by my standards, it worked very well. So I've changed my mind lately. I think we actually need a new classification of developer types: those who love creating new things but are bad at maintenance, versus those who are conservative, good at maintenance, and build beautiful code. What makes me think not too badly of recent AI-Rockstar(or AI vibe)developers is that as any industry becomes more advanced, it becomes harder for stars to emerge. Work gets divided and specialized, and no single individual can master everything. For example, I'm confident in writing 60,000–90,000 lines of code by combining frameworks based on IoC (Inversion of Control). But I'm weak at large-scale programming like distributed systems or low-level programming. That's the difference in expertise. I'm strong at the macro level but weak at the micro level. You become cognitively optimized for your own domain. vibe coding developers(or AI star developer)since AI is still far from being highly advanced—produce messy code, but they definitely bring a new kind of shock. And when you look at their internal structure, many developers mock them. This reminds me of Undertale. Undertale's code is full of if statements and an enormous number of branches—honestly, it seemed like the developer didn't even know the basics of coding. Yet that game became a historic success. The same goes for programming. Some people make the code components beautiful and efficient, while others focus on delivering what the end consumer wants. So these days, I even think that the more AI developers create bad software using AI, the more new jobs will emerge to maintain that software. Everything always has two sides, it seems. And in a way, maintainability means knowing how that feature fits into the overall shape and UX of the product. With new products, that prediction is often impossible

maerF0x0

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 understands all they do. I've had friends who go off on crypto related maths and I'm like "I passed that class, but know that I do not really know the subject you just talked about" ... And 2) There's the people who it's painfully forefront of mind that they're smarter than most everyone around them. Some of them are jerks, some of them are exhausted by being surrounded by relatively "stupid" (again, relatively...) people. For the latter group i have some sympathy. 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...

SkipperCat

This isn't a problem with "rockstar" AI devs. This is a problem of management. Who would let someone come in and rebuild the core infra of their business without any planning or review?

josefritzishere

AI codes worse than even the most egotistic prima donna. I see future business opportunities in cleaning up the mess being created now.

red75prime

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.

Goofy_Coyote

These two sentences hit home: > The flow of data was so hard to follow, it seemed like someone was trying to cover up a murder. > Just getting the code to run on your laptop took a week. I always thought I’m the only one having problem understanding the data flow, or setting up a proper dev environment. Impostor syndrome (and sometimes toxic environments that pushed for “velocity”) didn’t help either. Felt good to know I’m not the one.

sublimefire

The post seems to not address the fact that different product phases exist which in turn affect the software. Similarly, teams are different and get assembled for different purposes. There is also a difference if software was created in the past 24 months vs past 10 years. It is very easy to attack decisions made which look messy now, because many reasons. Everything looks obvious in hindsight. And then making it ad-hominem like does not sound smart, it is a clickbait, the issues are usually more complex.