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.

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).

There is no such thing as just a tool.

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.

I guess calling them reverse centaurs visualizes the change that is happening in the relationship between human and machine. We used to be the head but we’re the butt now. It makes you reconstruct the image in your head.

In truth there already was a downward trend before LLM’s exploded where tools were continuously used against people. “Enshitification” most people call it but it’s really just free range capitalism. Generations of economy majors have been doing exactly what they were taught. Increase short term shareholder value at any cost. It’s unsustainable and LLM’s are just another accelerant.

I guess calling them reverse centaurs visualizes the change that is happening in the relationship between human and machine. We used to be the head but we’re the butt now. It makes you reconstruct the image in your head.

Yes, but the minotaur is frequently just a person with the head of a bull, instead having to invert a centaur, which is already not a familiar image. In talks, Doctorow defaults to “Bojack Horseman”, an acknowledgment that reverse centaur is perhaps too much imaginative labor for his audience.

Agree on the MBAs–capitalism eating itself.

Yeah, my shovel sometimes convinces me to commit suicide while evaporating water to keep it running.

Sweat is an evaporatve cooling system used to regulate the temperature of the mechanism that keeps a shovel moving. And if you’ve never considered killing yourself over the prospect of spending all day with a shovel, I can at least be confident you’d make an -excellent- archeologist.

(But mild humor aside, I do understand your point.)

I can´t figure out why he didn´t call minotaurs

Minotaurs still convey the idea of super human strength, he was trying to convey the idea of limited power output of a human with the limited mental capacity of a horse.

Ah, thank you. The problem has been bedevilling me for weeks and I think this is the solution.

I initially thought it could be because the Minotaur isn’t exactly half-man/half-animal as the centaur is, but a hybrid of the two; often represented with hoofs for feet, etc., which is another expression of what you’re saying.

Also it’s a really shitty tool that doesn’t actually fix a problem. Unless you are rich and that problem is ‘I have to pay my employees’

There are several valid use cases for LLMs. It does solve problems, quite literally.

Corey Doctorow didn’t invent that term, but I’m glad people are talking about it.

It comes from “centaur chess” which is chess where both players are assisted by a computer. The humans are “riding” the computer in the centaur analogy — benefitting from the computer’s ability to process the best tactical move, while the human handles the strategy. They found out that computers win chess against humans every time; but humans with computers win against the computer every time.

By definition not. The majority of the code in GitHub is some volunteer project on a permissive licence .

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.

That’s how every ecosystem eventually grows. First come the weeds aimed at colonizing new areas as fast as possible. Then come the small plants, then the shrubs, the trees until it’s a self sustaining forest of different species.

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…

no this is just bad engineering

you can do what you want with or without ai or capitalism

if you skip the engineering part it will be very likely, shit

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’ve heard similar things from the people I know forced to us AI for work. That at the output requirements are now novel and highly accelerated under the assumption AI will make it possible.

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.

I felt that way until I just stopped using it entirely

I’ve only tried it the once but it did a great job and caused me the consternation from my previous comment.

It is disappointing knowing it actually works some of the time. I guess I just don’t care. I have my lines and I don’t cross them.

I’m sure there are some great uses of Microsoft software or Nvidia hardware, but I’m not going to use them unless forced to by work.

It basically added three small functions and their command line args to a sub-500 line Python script. I’m sure if helped that my function and variable name are verbose, like dictionary_of_fruits_with_dictionary_of_attributes.

My work provided the tool and asked me to try it.

I like to give it unnecessarily complex tasks and work on a hobby.

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.

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 just started using it as well under a push at work. I’ve so far only used it to write out a script that I knew what I needed and how to do it but it ended up saving me a couple hours. I suppose there wasn’t an interesting problem to solve there so it makes sense to use it but I worry about relying on it since it seems just capable enough to start trusting before the rug gets pulled from under you.

I have that worry too, but luckily the worst case for me would be one of my simple tools becoming unmaintainable.

Makes the day really easy ngl and I make cool stuff for my team 🤷

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

The coder does the first 4 hours, Claude does the next 9. You team up the next day to review each others work at lunch. Log 13 hours on your timesheets. 14, because you worked during lunch.

And that’s not even talking about code review.

No time for that, we’ve got to hit the sprint end date!

ALTblack panther we don’t that here meme

Just let AI do it! What could go wrong???

I wish that were purely a joke, but co-workers are unironically suggesting we deal with the avalanche of AI code by sending an AI to review it.

Oh my place too. It is starting to slow down as it turns out parsing AI reviews is a massive pain. Especially since they flag the dumbest things.

They just need that fancy controller openAI made. Then it’ll be an approve button instead.

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.

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.

You absolutely can do that tbh.

I can attest this does work well. Having LLMs review your plans for how to do something and point out what you missed works well too. I also have my local LLM review creative writing without writing anything, give feedback about my Blender renders and other artistic things, and be a sounding board for ideas in general. Be warned that Qwen has no mercy and will shit all over your passion projects.

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

Forget “human in the loop” - let’s shoot for “reviewed by AI”

yeah uh, nah, thanks. I would not trust it any more than I trust the current shit show.

The guy is working at a shitty sweat shop and blame AI for his misery instead of moving his ass to another job.

Let’s ask Claude to write an article about it.

ALTi5s884q8tLMwO51.jpg

If I’m forced into Claude Code or something similar, I will be looking for a new job. Ideally a different role in my company to keep my benefits and not have to completely start over, but if I have to jump ship, I will. Fortunately, our security and GRC teams have explicitly blocked Claude Code for the time being. I still have the tools built into Visual Studio, but I seldomly use them, and when I do it’s basically as stack overflow, and that only when I can’t find what I’m looking for through web searches first.

We had someone from our Networking team come over the other day and say that he could tell our summer interns were gone because our AI usage dropped by over $1000 / month.

Look I’m all for the AI hate but this is just stupid. I’m aware this might not be the most popular opinion here but be warned

Honestly if I were to change jobs atm asking about their AI policy and usage would be one of the first questions that I’d do and if they don’t use it well and haven’t figured out how to integrate it in their company (as a tool, not necessarily as a product) then I’d end the meeting then and there.

I’d quit my current company if they prohibited AI tools. Fortunately they don’t force us to use them, nor but we’re all encouraged to find actually uses for it (which in Software Engineering are a ton). If one of my colleagues wouldn’t use AI in any way I no only would consider them less productive, I’d consider them a worse engineer because it shows they can’t adapt.

AI in general and Claude Code as an example is an AMAZING tool. You just gotta use it properly. I still own the code I ship even if I understand it in less detail than before (that’s the trade off by being able to ship many more features than I could in the past).

I’ve been in this company for a few years now and just in the past months there are so many projects I have done that there was never an opportunity to do so ever since I joined because it would be days/weeks of work and now it’s a couple of hours while I work on other shit.

And people/companies that spend hundreds of thousands of dollars in AI every month are idiots who are just throwing shit at a wall and seeing what sticks. My company pays me a 100$ month subscription and many colleagues have even cheaper ones. Thats like 1% of my salary and it for sure increases my productivity many orders of magnitude of that.

I have not found AI code to be so helpful. I actually use it a lot less and more strategically than back when it first became viable. It can save a lot of time in the right situation though.

Honestly if you don’t find AI code to be helpful that tells me more about you than AI.

It is incredibly helpful barring some very specific niches

Nah, fuck AI. I will pivot careers. Anyone that claims to be a developer but generates all of their code is just a modern day script kiddie. Idgaf about efficiencies because the ethical implications of AI are far worse than the extra money I can make for a company.

I will never be an AI code reviewer, because that’s all prompting is. Like I said, I’ll pivot careers out of dev work before I do that. Pick up a trade and work until I’m 80 if I have to, but that’s still better than being one of Claude’s bitches.

Outside of the ethics of AI, the idea of sitting in front of a screen and being a “prompt engineer” takes everything I enjoy out of coding. If it was that or death, I’d choose death.

Replace all of that but instead of AI use computers or calculators.

I’m sorry but that is absolutely deranged talk. And you won’t have a choice about pivoting careers. You will be forced to in the same way that nobody in this millennium will hire someone that does their accounting with an abacus. And that’s a good thing.

Now, am I happy that a lot of people will be out of a job and the profits of that will be funneled into a few pockets? Absolutely not, but this doomsday, Amish like talk won’t help that conversation because the problem isn’t the technology. It’s who owns it

The reality is that these tools are not going away. Thinking that will happen is not realistic.

They’re part of the deal now. People who refuse to use them will simply become obsolete. It starts in technology, but it will quickly move around.

Thinking you can just avoid it isn’t practical. It is no different from cars displacing horses and computers displacing typewriters.

Think of how absurd it would sound if you came across someone who refuses to use a computer and only a typewriter.

Hey what’s up. I’m a published author and I do all my first drafts on a typewriter. No distractions, no notifications. Transcribing the text onto my computer provides a natural editing process.

I obviously still use computers for fun, but when it’s time for serious work, I bust out my manual typewriter from 1957.

Cars were displaced by horses because they’re cheaper (you don’t have to pay to feed your car when you’re not driving it). Jury is still out on if AI is cheaper, which is why none of these AI companies have turned a profit—and why I’ll be surprised if this stuff is still around in 10 years.

There are AI models that you can get for free right now that will run locally on your machine. They aren’t as good as the top/paid ones right now but they probably will be in the future.

So yes it is and will always be cheaper.

Your typewriter example is also extremely cherry-picked. From a computer you need basically a notepad and writing itself is extremely low technology because of it. But how would you feel if you went to a doctors office or government office and they took your data in a typewriter??

You’re right, and the person you’re replying to is, too.

My take is an analogy (strictly from the cells in my brain lol) -

The “ground” we all stood on, that previously felt ~flat (trying to be brief here) rapidly shifted under all of us, and very suddenly merely standing in one place, meaning anything from keeping a job, retaining enjoyment (even understanding) of the craft and crafted thing, an ideological stance, a hundred other things -

The ground sloped suddenly, and merely remaining in one place became a struggle not to slide and tumble downhill. And so we all are, tumbling downhill, at varying rates of speed and control, and it seems like the slope might be getting steeper, though at least much more slowly, now…probably.

Resulting from the sudden slope, the most experienced became wildly capable, that shit is real (at least at present). The least experienced? Those who need to get the experience, and to pay their bills, experience their lives, and to maybe later become the wise arbiters? Well, fuck them. Fell into the bottom of that new slope. Fuck everyone else, too, actually, hits everyone in lotsa ways, slope don’t care.

It’s all fucked, the ground has become a maw.

spoiler

Sidenote (most important note) - when there is a swing back - doggedly insist on training, helping, spending time with the juniors, it’s your biggest and truest value throughout this all, AND SEPARATELY your heaviest punch back

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”.

Our place measures PR counts so a ton of tiny ass PRs is actually the move.

I’m sorry for your shitty workplace.

Yeah it’s not fun. Between that and now quarterly performance reviews things have really gone downhill.

Quarterly? Wow. Some MBA was probably like public companies need to report quarterly so we should put employees on the same schedule! Dumbass idea.

It’s so bad. It’s an absolute waste of time and resources.

Leadership is like “just use AI to speed things up”. But if I’m just pasting slop in and my manager is using slop to parse and give feedback what’s the goddamn point???

My slop machine says you’re not slopping slopply enough! Get back to slopping, and we’ll slopback in few months!

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.

I want to get off Mr. Bones’ Wild Ride.

I would like to apply for this software engineer job where all you do is press enter. I’m willing to work from home or go to the office everyday. I will press enter on holidays and weekends as well.

Will you accept a $20,000 a year salary without dental and vision?

20.000 a year without hope or prospects.

Depends on how many times I need to hit enter during my 8 hour shift. If it’s something like 200 times then yes. If you need something more like 7,200 enters pressed in an 8 hour shift then that would break down to 15 enters per minute which requires a little more dedication. I that event I would like to ask for $23,000 a year.

I would also like for the company to pay for any repairs or replacement of my Enter button in the event something stops working.

1. Accept 10 jobs
2. Make a script that presses enter on repeat
3. Deploy script
4. Collect 10 salaries

I like where your head is at but I’m an Enter pressing purist. Scripts fail and don’t give you the the confidence to know your true enter pressing quantity.

If the company wants enter pressing slip then scripts are the way to go. If they want to know with 100% accuracy no enter presses were skipped then I’m their guy.

Oo! Them! Hire this one!!

Their resume says “Enter Pressing Specialist” so they have the edge

😂

Claude tested my script, all I had to do was press enter

/s in case it wasn’t obvious

I know some people think like you, but it’s the most soul crushing shit in the world when all you do is wait for others.

Corporate jobs has always been soul crushing, and that’s why the cushy office jobs pays nicely. Because it drains you

Agents are brain gang banging him.

I was going to say i could automate pressing enter if they give me a job

Sorry, you need a degree and twenty years of experience for this entry-level position.

And no, being one of the developers for the code that came out three years ago isn’t good enough. We need at minimum 5 years experience.

oh no a tech worker is whining about something again. Quick everyone rush to their defense. They must remain perfectly comfortable and happy inside their air conditioned luxury office.

Its work and you’re paid well for it. Suck it up or put your skills to use at a different company.

Okay, Mr. Spacely.

Your tongue is so good at cleaning boots. Very well done!

Oh it’s way worser than that. Its erasing our skill

If you’re just hitting enter you’re doing it so wrong.

I‘d love if I could just hit enter but the garbage it shits out unsupervised is just soo bad.

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.

AI in engineering is an accelerator.

Yes, and most engineers effect on the product can be graded on [-1, 1] scale. And I find that the -1s accelerates faster.

If teams are producing high-quality software

I had one of those. My seniors are getting dumber though, and we have twice as many prod bugs as a year ago. I had an outage because someone didn’t properly trim an input for fucks sake recently.

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).

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.

Even without external libraries, it routinely comes up with solutions that are at least 3-4x the complexity and LOC than how I would implement it.

It’s because the average quality of code that they are trained on is like that. Most code that is written by humans is slop, and the models represent that.

Producing overly complicated solutions to uncomplicated problems

It often can do it better if you prod it though. Its just so weird that its really hard to get it to do that. It knows how even if it is trained on poor over complicated stuff.

How much time does that prodding take vs how long would it take you to just write the (better) code yourself?

Its usually just 1 or 2 messages saying i dont like this so its only the time it takes to read it and say try again. A minute or two?

Its faster to just ask to do it again in most cases.

The times itd probably be quicker to do it on my own are the more complicated ones where it gets something wrong but it wasnt so blatantly obviously bad that I just tell it to try again, so I spend time with the wrong stuff, see its wrong with a little work, then toss it and try again, or re work it myself from that.

This is maybe the main reason why I don’t fuck with AI. “Oh it accesses all of the writing on the public internet!” That never inspired a lot of confidence. 99% of Internet posts are crap.

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?

Obviously when I work I don’t run the entire suite, that’d be a waste of time. When I’m finished, I run the entire suite, I don’t sit and run the tests I’ve been testing against as I’m working because I already expect those to pass.

If they don’t, that’s caught when I run the entire suite. I don’t sit and run individual tests followed by the entire suite.

I guess the AI isn’t iterating over its “ideas” and code yet. I come up with overcomplicated and overcomplex code too. But my natural neural network keeps reevaluating the code while I think about it, write it down, test it, and often even come back to it later after I moved on to another part of the codebase.
It looks to me like AI is using the infamous waterfall method to write code. It does the “thinking” phase and does bugfix iterations when compilation or tests fail. But never does it question the design it came up with after it wrote it down. It doesn’t reevaluate whether the last round of fixes made tests work that test irrelevant implementation details. It doesn’t question whether there really need to be four methods sharing 90% of their body for doing the basically the same thing only subtly different.
I hold the suspicion that AI will be as slow as humans when it becomes as reliable because what makes us reliable is the redundancy in our thinking processes. The constant reevaluation in subtly different states of mind helps to catch design flaws and silly mistakes.

Reevaluation of finalized code is probably not something you can just put into memory. You would need to modify the harness to automatically inject a new prompt triggering reevaluation of the design and implementation after each step. This would likely increase token use and execution time by an order of magnitude. And if you do it by spawning fresh agents, there would be a high chance of having the AI go in circles, switching between a few different versions of the same shitty design or implementation. So you need to keep the context, which grows each iteration. So context rot may become a real problem. The AI might deviate from the initial goal just like some human devs tend to do…

And natural neural networks learn on the job. They adapt to the codebase and industry they are working with/in. claude.md and memory text files help a lot. But they are still sometimes ignored. And I don’t know why. Also, human rules are almost always somewhat fuzzy. Long lines are to be avoided - but unit tests and that one massive dict of dicts really are a lot more readable when ignoring that rule. There might be a lack of good training material on what makes code readable for humans.

That actually makes a lot of sense and goes with how ill code something larger as well.

Get a rough version working, sometimes horrible code. See how it functions. Reassess it and optimize it. Go bug hunting, which will often result in more optimizing, then finish all the error handling I probably skipped and only logged. More bug hunting, then review my code like a code review before submitting it for a code review.

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…

Brilliant.

Ive had it do stuff like that completely ignoring that I already have a library in my app that should handle some sort of task. But removing it first is chefs kiss.

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

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.

Same!

I’d have more sympathy if he got off fucking twitter tbh

Sex joke about getting off from fucking twitter

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

12 hour shifts?

The sad reality is that most apps are regurgitated CRUD with new design language. The llms are really good are regurgitating this stuff, so the only interesting part left is the 10% that was already interesting before. I just take 2h lunches and spend time with my family while the llms puke out the CRUD, then thoughtfully work through the 10%

Humans are obsolete dead meats