AI code assistants currently are like that senior dev who knows everything, has experience in everything, and always likes to help everyone. But sadly he does a lot of shrooms in his spare time and sees things that aren’t there. He also has quite the opinionated ideas about what good code should look like.
That implies that you just can’t let him do the quality assurance. He can write code. You can ask him stuff. And he excels at debugging.
But you can’t let him plan the architecture. You can ask him about his ideas and select the ones that are actually good, though.
And you definitely can’t let him review his own code. Someone else has to do that.So if they literally just let the AI do everything, there is absolutely no way anyone has a chance to ever review the result because AI code is harder to review (for now), and AI loves to repeat itself (for now).
And sure, they can tell it to write tests. But AI is dogshit at writing tests. It tends to forget the important cases, test the wrong thing, and/or obsess about completely irrelevant implementation details.
I also tried the multi-round approach with a committee of agents trying to iteratively find and fix flaws. It only works well for finding bugs, not fixing them (for now).But while AI can’t replace me, it is really nice to have as a tool - just like I have syntax highlighting in the IDE, I have a code assistant that can autocomplete a few lines of code, find out why my code misbehaves, or tell me what some library method is supposed to do. Sure, I have to still verify the results. But often, finding the bug or information was the hard part.
Coding assistants are great. Just don’t let them write too much code at once. You need someone who still actually understands the codebase. That sadly can’t be an AI (yet).AI code assistants currently are like that senior dev
More like a junior dev.
That’s how i always describe them. Over-eager junior devs that are trying to impress you with how fast they can get stuff done. Have a lot of book learning but don’t know when to apply certain things. Sometimes, i feel like it should really only be a tool for senior devs because it feels a lot like mentoring a team of noobs
I really love when I ask the AI to do something, and it gives me 40-50 lines to do it, and I tell it there’s no way something like that should take that much code, and it’s like oh, ya you’re right, here’s a 5 line version using something from from the standard sdk.
I’ve tried to put in its memory to not do things like that, but it keeps doing it.
I watched it remove a JSON library include from the code because it wasn’t used yet, and then in the very next prompt where we needed our again, it attempted to write a basic parser from scratch…
Possibly motivated to do more complex problems to spend more tokens?
I can believe this. I’ve been put on slop duty, and had the slopmachine go all
Time to run the test to ensure everything is good. It passed. Good. Let’s run the entire suite to ensure no regressions. All tests passed, yay.
And I’m here thinking, if you’re gonna run the whole suite anyway, why’d you run an individual test? That’s just redundant.
It’s pretty much what i do when i think i’m done. Run the test(s) for the stuff i touched, then the whole suite to make sure nothing else broke. Why would i take all that time to run the whole suite every time?
Reminder here that the culprit is capitalism, not LLMs.
Voxium said he wouldn’t mind the situation if workers were given more time to check the code.
“Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude,” he added. “There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore.”
Some people might look at this and wonder what the problem is – who wouldn’t want to be paid to do very little? But most people struggle when their work has no meaning. Voxium told Business Insider that if engineers lose the opportunity to understand the code and solve difficult problems, “there is nothing left … Not even our soul. There will be no purpose.”
He added that the real problem is corporate leaders’ obsession with pushing out more features. He said management often judges success by sprint cycles, pull requests, and the sheer number of features shipped, even when those additions do little to improve the product for users.
I like this take.
Capitalism was the jet fuel that got us here, but now we need to shed our boosters and switch engines to something made to run longer.
Yeah, still a sweatshop with air conditioning and free coffee and junk food.
who wouldn’t want to be paid to do very little?
Oh that’ll change soon enough as well in the downwards direction.
to do very little?
…for 12 hours a day…
Capitalism created LLMs.
People are clever; we invent things.
LLMs are just a tool. Tools can be used by people; the problem is when people are used by tools, which is what is happening in this case.
See Corey Doctorow’s latest tour of YouTube promoting his idea of reverse centaurs (which, for the life of me, I can´t figure out why he didn´t call minotaurs).
Sure. You can talk about the LLM gestalt, if you’d like, that’s worth examining, as with any other tool; especially stuff like progressive brain rot.
But listening to the complaints people have about LLMs, it’s mostly that it’s being improperly used to replace human labor. Improperly in the sense that it can’t actually do the job it is replacing humans in, which is a separate discussion of what kind of world it will be when there are no jobs for humans to do.
LLMs are used responsibly by people doing their own work. For instance, Linus Torvalds used Claude to find errors in the Linux kernel (I think), that he then fixed himself.
The problem is that capitalism, especially oligoplic capitalism, will create worse products at lower prices (or higher profits), and it will do so on the shortest timeline, ignoring things like future lawsuits over security flaws and future lack of programming talent and erosion of consumer trust.
The engineer added that employees are now pressured to ship products as fast as possible, leaving them with little time to review Claude’s output or understand the code being created.
Companies have always pressured software teams to ship products as fast as possible.
What’s new is the part where all of the worst coders can shit out code a lot faster and pretend like they’re doing a good job. It used to take them a while to write garbage that they didn’t understand or review themselves, but now they can do it so quickly that it makes the actual good coders look like they’re taking a long time.
This is why you absolutely have to have documented coding and review standards. The idea that you’d ship any code that has never been reviewed by a human is horrifying.
The idea that you’d work 12 hour days is so stupid to start with. I’ve seen people consistently work that long and… surprise, they don’t actually work that long. They work about the same as anybody else and goof off the rest of the time. I doubt you can even just press enter for that long. People just don’t work that way.
This is exactly it. I’ve worked with 2 different teams in this new era. One has all strong engineers and good review and testing standards. The other has 20% bad engineers that should have been fired years ago and’s weaker testing culture. The result is the strong team is delivering higher quantity software faster than ever, and the other team is going fast with much worse results. The quality is very bad, and the good engineers still there are quitting.
The good engineers spend their whole days just trying to keep the ship afloat and minimizing the harm from the bad engineers. They hate it and are burning out fast.
AI in engineering is an accelerator. If you are producing slop software, which most teams are, then it’s just going to accelerate the rate at which you can produce shitty software and bad code.
If teams are producing high-quality software, then it accelerates those teams’ ability to deliver that quality.
My company made my job soul-sucking to the point I was doing the bare minimum a long time ago. They didn’t even need AI for that. Just some really shitty managers.
Humans are obsolete dead meats
Fucking snow flake anti ai nerds, like you weren’t just pressing keys all day anyway, who cares if now it’s just one key??
/s
I don’t hate Claude Code or whatever. I hate the company pushing you to constantly churn out shit so you need to turn to these tools to keep up pace or get fired.
Architecture decisions or code quality? Fuck it just ship.
You have concerns about an approach? You’re the enemy to your coworker’s promotion. Get out of the way.
It’s all just so depressing. It will all come crumbling down. It’s a matter of when not if. But god I hate this ride right now.
Time to lean into the slop extra hard. Use AI to create massive PRs, use AI to approve the PRs. Automate sending slack alerts when a feature ships. Be loud, really show some massive “Productivity”.
A guy I don’t really like at work does all sorts of AI induced PRs. I think he thinks it makes him look good. It probably does, to management.
I got reprimanded for asking if a guy’s extremely weird code was something he wrote himself. He went crying to my boss about how I’m mean on PRs. Fuck you, William. I hope your house catches fire and you pass out while asking Claude for help.
Hey William, I’m having trouble understanding this code, it looks a little weird, can you walk me through it in detail, and explain how you came to writing it like this?
The responsible, corporate, way of being. Definitely should have done that. I just want people to feel uncomfortable when they have fucked up. Everyone’s just so polite. No one faces social consequences.
This is the same place where they don’t pay for holidays. My boss told me to stop saying things like “I don’t get paid, so it won’t be that good” when they say “have a good holiday”. If grand-boss, ghoul, and preeminent “We don’t pay for holidays” enforcer Anne was locked in a burning building, maybe I’d just say “happy holidays!” and walk away.
To be fair, if i was annoyed enough id maybe ask if they wrote it too hah. That you got reprimanded is ridiculous.
Agents are brain gang banging him.
I’ve heard the same from developers at work “doing this using AI makes it boring, but at the same time I feel silly if I write everything from scratch”.
I’m not a developer but I do make little tools for myself at work. I used an LLM to assist with adding some features recently, nothing I couldn’t easily do myself. It did a fine job and made minimal changes, all totally readable and for the most part the same way I would have done it.
I have a new tool I want to make, and it’s hard not to just turn to the LLM, since it’ll save me many hours on a script that nobody else will ever see. It’s really taken the fun out of it. I’m proud of what I made, even though nobody else will care, but doing this my usual way will feel like I’m using the wrong tool out of perversity.
I dunno. I hate everything.
Hey thanks for sharing I’m in basically the exact same boat. There are also pressures in the work place to use it because of the time savings. Personally I try to keep a balance and work on things myself most of the time and if the LLM is used it’s more like a buddy coder than a magic code generation tool, but sometimes it’s just too easy to use it that way. I think it’s important to take pride in your work, so keep doing things your way when you want!
I look at it this way: if you prompted an LLM to generate it, then you didn’t “do” it, you basically installed an outside piece of software that just happened to be generated on-the-fly.
That maybe true if youre single shotting. At some point, but that’s rarely the end. It takes iteration and experience to get LLMs to do useful work in most cases.
People are working 12 to 13 hours a day
yeah I’d write a diatribe about the best work in the world under those circumstances too
workers spend 12-hour days pressing enter
If only that could be automated somehow.
I feel like you are being sarcastic, but this actually is a solved problem :
An elegant solution. I wonder if it is more efficient than a 1TW data centre.
Seriously, though, we use AI in the worst way possible. I like writing code, I hate checking someone else’s code. Why aren’t AIs doing the checking and engineers doing the coding?
Forget “human in the loop” - let’s shoot for “reviewed by AI”. Deep down, we know the humans are barely paying attention when they check Claude’s homework.
The drinking bird only works if it’s dipping it’s velvert covered head into water, the lower water temp creates a temo difference moving the liquid in the glass tube within the bird
One… use --dangerously… they asked for speed, thats how you get it. Two… if you have great tests, you don’t really need to know every detail of the code. The risk just shifts from a dev designing bad code, to a dev designing bad tests.
I dunno I’ve seen too many times where Claude Code will just rewrite a test it doesn’t like and say it’s good. Combining that with —dangerously or —yolo is a recipe for disaster.
You do have to keep some tests for yourself, and don’t let claude touch those (or even see them ideally).
Though I have been reading that you can actually have a second agent manage tests. That way it’s motivation is to find bugs. So if anything it will hallucinate failures.
That said… if corp is pushing AI, then they get the result. Most of the time it will be fine. When it isn’t it’s the AI we have been encoraged to use’s fault.
If you’re just hitting enter you’re doing it so wrong.
