Maybe this is what will turn software engineering into an Engineering field.
Right know, prompters are setting up whole company infrastructure. I personally know one. He migrated the companies database to a newer Postgres version. He was successful in the end, but I was gnawing my teeth when he described every step of the process.
It sounded like "And then, I poured gasoline on the servers while smoking a cigarette. But don't worry, I found a fire extinguisher in the basement. The gauge says it's empty, but I can still hear some liquid when I shake it..."
If he leaves the company, they will need an even more confident prompter to maintain their DB infrastructure.
As a junior dev there is this pressure to produce code, add features, and investigate bugs within unprecedented time period. I know whole code base is fking up but i will still add that feature or do a sloppy bug fix without digging deeper.
In my experience, AI really lowered the bar for bad code in the name of delivering faster.
I have seen people write highly complex code where all the complexity was not necessary. Think: deep unnecessary branching, pointless error handling and retries which make no sense in our context, hand-coded parsing using regexps, haphazard data flow, functions which seem purely computational but slyly make API calls, pointlessly nullable model fields, verbose doc comments which describe the implementation instead of the contract. I could go on.
The worst part is, even when "prompted" by bad coders, it works in the end. Even has tests (ostensibly mock-ridden, a pet peeve of mine which always falls on deaf ears). So I cannot reject the PR without being an asshole.
I am no luddite. I make heavy use of AI, with all the skills / AGENTS.md / style guides and clear specs, then review every line of code, prefer testing with minimal mocking. I'd even say with right prompting, it can write better low level code than me (eg: anticipating common error conditions).
But my biggest fear about AI is how it enables normies with little to no understanding of CS principles to produce code faster which looks correct but slowly poisons the codebase.
So many fallbacks. So many function_exists. So much pointless type casting. I swear it’s like the system prompt is designed to waste as many tokens as possible.
I have a friend, smart guy, who is writing web services and “connecting them together” for a large firm; he has absolutely no programming experience.
Talking to him, he told me he couldn’t even reverse a string. He is at once many times more valuable than ever before to his company, but also far more dangerous than ever before.
This is what fascinates me. I have a friend, also a smart guy, who has made it to the point he’s at by being a kind of solutions expert. He’s an IT guy, basically. He’s very technical but has never claimed to be a software engineer. He’s writing software with Claude now. The other day he sent me a screenshot of some other team at his work asking him to shut off something he made that was brutalizing an API of theirs. I asked him if he had ever heard of a 429 or exponential back offs. He said no. How do you meta-prompt for that without knowledge?
You can create an agent in Claude with the role of Technical Lead / Architect and have it review your code. That depends on your agent specification. Just have ChatGPT generate that first.
If you get the logs you can feed them in and ask for improvements, that sometimes helps.
> In my experience, AI really lowered the bar for bad code in the name of delivering faster.
I would've believed that 6 months ago, but not now.
If you have a good codebase with proper rails, hygiene and architecture, AI will produce better code than most engineers out there.
People forget that 90% of the field has always been charlatans barely able to implement a fizz buzz or go much beyond trial and error googling.
I'll say even more. I'm in the 10%, and it's increasingly clear to me that AI writes in minutes code that's better than mine.
Even stellar and respected OSS engineers are nowadays leveraging AI and guiding it less and less everyday beyond giving indications of what kind of data structure they may want for a complex problem or the kind of architecture they are looking for.
In any case, I don't like this field anymore, I have no joy from it, way too much work, way too many changes a human can cope with both on product and technological level (not even counting AI and its tooling itself). The interesting parts of thinking an entire afternoon or week experimenting to get that design right disassembling the pros and cons are gone.
Even if you want to do that, it's just faster to launch 6/7 worktrees with the different ideas and judge the results. But you don't get as intimate with the problem and the amount of information is way more than you can process.
Forgive my ignorance, but if the corpus of coding data was always 90% bad, isn't that the same data being used for training LLMs? How are they magically any better than that average?
When I read the discussions about AI making code worse I keep bringing the same argument: people made bad code even before AI. Average coder is barely functioning and that's a fact.
And we were safe from them because they couldn’t produce a mountain of code every day. But soon many places will be buried under a planet of unmaintainable code. It’s adding friction and operational cost and often not adding value.
> Maybe this is what will turn software engineering into an Engineering field.
Oh man, I think you may have touched the third rail here.
My first job out of high school was as an AutoCAD/network admin at a large Civil & Structural firm. I later got further into tech, but after my initial experience with real Engineering, "software engineering" always made my eyes roll. Without real enforced standards, without consequences, it's been vibe engineering the whole time.
In Civil, Structural, and many other fields, Engineers have a path to Professional Engineer. That PE stamp means that you suffer actual legal consequences if you are found guilty of gross negligence in your field. This is why Engineering firms are a collective of actual Professional Engineer partners, and not your average corporate structure.
The issue is that in software dev, we move fast, SOC2 is screenshot theater, and actual Engineering would slow things way down. But, now that coding is fast, maybe you are correct! Maybe vibe coding is the forcing function for actual Software Engineering!
___
edit: I just searched to see if my comment was correct, and it turns out that Software PE was attempted! It was discontinued due to low participation.
> NCEES will discontinue the Principles and Practice of Engineering (PE) Software Engineering exam after the April 2019 exam administration. Since the original offering in 2013, the exam has been administered five times, with a total population of 81 candidates.
What makes it a profession is not just the certification, it's the burden of responsibility for consequences. Your lawyer, accountant, and real engineers carry "we need insurance for this" level of risk in their work, all the way up to "can go to prison for getting things really wrong".
Until and unless software is held to that standard, software will never be engineering and always just a craft that can be performed to any or no standard.
Note that other types of engineering are also often vibes based. The mechanical engineering for a rocket engine is extremely rigorous but the engineering for an injection molded housing for a cheap cell phone is a lot more about following a few heuristics and getting it out the door. Even in robotics where I work, it’s mostly about making parts that pass whatever acceptance tests you come up with. In civil engineering and aerospace failure costs human lives and millions or billions of dollars. In robotics maybe you have some machines fail in the field but in many instances you have one overarching safety system and many of the parts are irrelevant to that. The camera housing for example. So no paper trail or mathematical design validation is required to prove you designed it right. Often those are desirable but if you just manufacture it and test it a lot you’re probably fine.
This was something I noticed in my early career in mechanical engineering and later doing PCB design and software for robotics. It’s easy to find firms that just need adequate parts without the professional certifications or ass-covering calculations of other engineering fields.
All this to say, it’s not just software versus the rest of them. From my position, civil and aerospace seemed more like the exception while much of the rest of the engineering world is more vibes based.
> Maybe this is what will turn software engineering into an Engineering field
I think it’ll be the opposite. Maybe it’ll be what will eventually cement the field as “talent” based field. Just like it was difficult to quantify what makes a flute player better than another, how good your are at endlessly prompting a blackbox machine would be the only measure. The engineers of ol’ whoe developed kernels and drivers would be thought of as the “crazy people who put the flute against their temple to tune it” LOL. we don’t need people like that. You can just buy a flute tuning device. who gives a fuck? Can you make the next “Shake it, Shake it”?
This is the pattern you will see when medium-successful ignorant people take o ver a system that was based on some kind of standard.
You can see the same approach is taken by Trump and other people.
“You have TDS!! He is actually doing good. He doesn’t follow rules because the system is rigged etc.”
These arguments border on religion because it is predicated on you believing their ignorant point of view in the first place.
Engineering and science is built on rigor and empirical evidence, it is not built by scammers/businessman/ignorant-people/politicians because that is just not how it works
I work at software in a medical setting. We are piloting an integration with a startup for measuring [some bodily variable relevant in ICU setting]. They are obviously vibecoding (docs are telling) and their API is failing in unexpected ways that they are not able to resolve. I am just waiting when this are going to harm somebody.
Now imagine if you’re one step removed. You don’t see the cigarettes, smell the gasoline, nor see the fire extinguisher gauge. You only see the servers running business-as-usual. Those “engineering” guys are always drama queens, you think. We have processes and fire extinguishers when shit hits the fan, right?
That’s basically every M2, and many if not most M1s, in the last 10 years. So fuck it. Why does any of it matters?
For every argument against AI slop, you will get a variation of it's the future, or I'm 10x more productive now, I've shipped 3 applications in 2 days, etc.
They won't stop talking about it and defending it. But I can't get anyone to share their amazing work with me.
There is a reason the Show HN projects that are mostly vibecoded don't get much response. It's because they aren't any good. Comments that are AI generated are hollow. Videos that AI generated a shell of their sources.
Obvious slop still makes it to the front page of HN, and sometimes farms GitHub stars.
These posts also usually get all these glowing comments from users who clearly haven't checked the code. It's even worse when authors get busted and claim "Okay, Claude wrote it, but the design is mine" despite clearly not understanding the output themselves.
Unfortunately, that makes high-effort projects less visible. The SNR will probably keep getting worse until slop can be flagged on HN.
One thing I learned is that AI written text is not hard to spot. Usually, when I meet slop, I close it one or two paragraphs in. Although tools like this will become more common, they usually serve to win an argument, or confirm what you already believe.
Also, it was painful to learn that my very first blog post I wrote in 2013 is AI generated. But I'm fine with it because I read this:
> A short punchy opener (≤10 words) followed by two or more substantially longer elaboration sentences — the LLM "hook then evidence pile" rhythm.
... and realized that the entire app is AI generated.
If you can spot it, an AI can spot it too. We have a website with some AI generated content (about AI). I added a skill to correct AI slop. Content got a lot better when I put that in place. I actually made codex research slop patterns and it came up with a list of known AI slop linguistic anti patterns. It now fixes its own content using that list. I also put a guard rail in place to do a critical review of all produced content as a final quality gate. That actually catches a lot of baseless claims, and other slop. And there's another skill that ensures we use the right SEO relevant language (a list that is produced by a separate agent).
It's actually starting to generate interesting content based on me giving it a few bullets and ideas. I won't claim it's perfect but it does a decent enough job.
I have my reasons for doing this (we help people set up agentic work flows) and I appreciate that not everybody likes the idea of AI generated content. But I think it will start getting harder and harder to spot AI slop. Basically slop is what you get without guard rails and quality gates. Of course, most people still lack the skills to configure their AI tools properly. Particularly non technical people. But it's not that hard and I bet there are a few handy journalists out there getting better at this. Also, for technical writers this is not going to be optional.
Since voting is that power we say we have in the US. Does the public get to vote on this? If not...
> Voting, we might even say, is the next to last refuge of the politically impotent. The last refuge is, of course, giving your opinion to a pollster - Neil Postman
The US is a representative democracy, not a direct democracy. You don't get to vote on specific federal policies, you vote on the people who vote for those policies.
Voting with your wallet doesn't exist. Try to boycott Amazon by blocking the AWS IP ranges and see how unusable the internet becomes for everyday tasks. Corporations continue to push the personal responsibility narrative so they can externalize costs of unethical business practices.
how are you making them lose money by blocking their ip ranges? Your are pretty much giving them money because now they dont need to pay for bandwidth.
We can also engage in direct action the other 364.9 days of the year. Call/email your representatives, go to a town hall, call the leaders of both parties of both senate and house, go to a march or protest. There are other ways we can be heard, be substantive and thoughtful, they tally and track messages which are not hyperbole or copy-paste. If you can make it personal, even better. It only needs to be a few sentences.
You can look up Maroun Al-Ras [0] and it's map coordinate [1]. If you search for the name, you find a garden of the same name, but not the village. The instagram reel that was posted earlier had more context [2].
From wikipedia:
> In October 2024, IDF forces operated in the village as part of its invasion of southern Lebanon. The Israeli flag was raised, after the victory.
Which Apple might use as a justification. There is a Israeli flag, so it must belong to them.
One thing that will be incredibly useful is to limit comments from brand new accounts. A combination of vouching, limiting the posts velocity (5 daily limit), clear rules for new accounts, etc.
I understand we often see insightful comments from new accounts, but I always find it suspicious when non-throwaway accounts are created just in time only to make a quip.
This was discussed before. People will age accounts and buy/hack inactive ones. Meanwhile, often a link gets posted, the project owner (or someone affiliated) finds out, and they make a new account to comment; it would be a shame to lose these people.
800 is a huge achievement. But I have to admit, around 2011 I had completely given up on the Simpsons. Story and content aside, they did something with the audio. The quality of the voice is so clear that it sounds un-natural. You can see the same effect on many shows around that time. The voice is disconnected from the background music and sfx.
Anyway, they also improved the way the characters are drawn so much that it lost it's crude nature.
The cell layers constraint led to better art. The detail in the background was minimal and the artists world compensate for it by interesting framing and lighting. Go back and watch one fish two fish or the black widower episodes from early seasons - just incredible animation.
You can see the number of lines drawn go up like crazy around season 10 or so, making it feel less realistic. Coincidentally, the writing also started to get worse around this time.
The app didn't work for me. One that was shared right here on HN. I selected 25 miles radius, same ethnicity. Naturally I was matched with a person 700 miles away, of different ethnicity. So we got married... and deleted the app.
We were interviewed as a success story and our faces are plastered on the Internet now. My friends didn't find the same success, I concluded that they didn't know how to date. (wear the right clothes, etiquettes, conversation, navigate ghosting, etc.)
"What if the app could teach you how to do just that?" That's what I asked in our interview. That part was never published.
There’s no need to fear the construction of mass surveillance anymore. It’s already here. We built it one convenience at a time [0]. When I see all my friends with Alexa devices at home, ring cameras, and a million food apps on their phones, it feels like it’s already too late.
Right know, prompters are setting up whole company infrastructure. I personally know one. He migrated the companies database to a newer Postgres version. He was successful in the end, but I was gnawing my teeth when he described every step of the process.
It sounded like "And then, I poured gasoline on the servers while smoking a cigarette. But don't worry, I found a fire extinguisher in the basement. The gauge says it's empty, but I can still hear some liquid when I shake it..."
If he leaves the company, they will need an even more confident prompter to maintain their DB infrastructure.
reply