Pointless rant. Please ignore. I’m a software developer and we all know how AI has changed our industry. How we work or why we’re fired and why we can’t afford PCs.
Anyways, we’re already all forced to use AI already and we’re already atrophying the minds of our juniors. It’s great.
New team meeting and one of our managers tells us that we’re never going to write code anymore at all. The AI will read the JIRA ticket and create the pull request (change request to the codebase) on GitHub. Our job is to only review the code on GitHub and then rank how well AI did and then comment and then get AI to fix it. We have to do this so we can improve the AI process. Which is funny because none of the people who plan this AI shit are data scientists. The only way they can change things is by promoting, it’s not like we’re releasing our own coding models but anyways … He’s like, now you should be able to do much more work and just review PRs all day now and that we should never be doing only one thing. You can only tell AI through a GitHub comment to fix a mistake and then you can start reviewing the next thing.
We were like, if it’s a simple fix why can’t we just fix it?
“Because we need to improve the AI process”
But then, I have to context switch.
“Yes that’s the point you can come back to it later”
Why come back to it later when we can solve it now? We can even use AI to solve it now.
“No, we want you just comment on the PR so the bot can handle it”
Context switching is free apparently… It’s actually infuriating because apparently we’re not using IDEs any more. I personally use the GitHub plugin to review PRs in my IDE but no one else seems to do it so I don’t think they even took that into account.
These guys have auto merged AI code that’s taken us weeks to unravel and which we still haven’t fully been able to fix. They just merge shit all the time and a lot of it is fucking slip. AI merged hundreds of tests and no one cares when they break. They didn’t configure prettier because AI doesn’t use it so it breaks out formatting when humans do it.
I ranted to my own manager for 30 minutes about it today and he was just as upset because every developer is now asking what exactly are they doing. My manager asked me what I would do. I said the process sucks but what are we supposed to do as devs. If I review 20 PRs a day, how is the company going to ensure my skills are gonna be sharp? What are we doing about taking in ideas from regular devs? How do we ensure code ownership when we’re just merging tickets we don’t write and code we had no hand in shaping?
Sorry. I actually thought I had faith in my company with AI because they were coming up with thoughtful approaches but it seems like utter incompetence.
You misunderstand - your job is no longer to ensure there is functional code. Your job is now to train the AI to replace you. They are making you go out and choose the perfect switch to then get beaten with.
“Where’s the fix for ticket #6618?!?”
“Sorry boss, the AI hasn’t gotten it right yet.”
“You said it was a quick fix!”
“For a human it would be. But we’re on infinite monkey time now. It may never be done.”
“It was the best of times…it was the blurst of times”
This is a “Cover your ass and wait for the fireworks” scenario. Get every stupid request in writing. Document everything you do. When it all blows up in their faces, be ready to roll up your sleeves and start unfucking the mess (but only if they’re paying for the overtime).
You will not convince them this is a bad idea as long as it appears to be working. In IT and software dev we’re all engineers; we like to fix things, so our instinct is always to try to at least make a bad process work better. Fight that instinct. Follow their stupid instructions to the letter. You want this to fail as quickly as possible so that you have hard data to point to.
This man is a straight shooter with upper management written all over him
If I were you, I would burn soooo many tokens. This is a malicious compliance dream scenario.
Fuck the owner class, get paid, and watch it all burn.
Opus large 1m context. /Plan and thinking mode. Use cli. Converse with it Think deeply. Think step by step. Read the entire codebase every turn. Bloat context. Wait. Sharpen your skills and wait for the accountants to be the new heroes
If you’re the only one doing this - if only your token budget is through the damn roof - then you’re just volunteering to take the blame. Now it’s not “AI is really expensive”, instead it’s a “problem employee.”
True. You have to work together to unoptimize your tools
This happened at our shop fifteen years ago. We were instructed to outsource everything to offshore.
That didn’t work at all, because with a few rare , bright exceptions the people the offshore company have us could only achieve an outcome if they had a list of steps for that specific thing.
It’s going to be exactly the same thing with vibe coding. It kind of works in the hands of somebody with a deep understanding of the tech, but they expect to hand it to juniors and get good result.
So we’ll either have to pick up the pieces or let them flounder.
It’s not just you. This is happening everywhere in the industry.
Management has no idea what they are doing, and thinking this AI shit and these nonsense workflows will somehow work. I predict within the next two years there will be so much broken unfixable spaghetti code, entire large scale systems will no longer be maintainable. There will be so much confusion on even what kind of approach to take to fix this. This will be what people thought Y2K was going to be.
Y2K is the opposite of this. It was engineers foreseeing a real catastrophic future issue and getting the resources to fix it in time. Which they did so thoroughly that people now think that it wasn’t real or serious.
Real y2k is Unix time running out in 2038. This is where real problem happens, and for years FOSS devs are preparing to avoid issues.
Jesus that’s approaching fast
I’ve been out of the game for 10 years, but I developed professionally, some very high level shit…
I’ve done tons of business analysis and all that baloney
This AI fucking bullshit is going to present the greatest financial opportunity ever seen by individuals who are competent at programming and can do it without AI
Now is the time to see the opportunity, buckle down, and start finding ways to create solutions and products that solve the problems AI makes
This whole situation is complete bullshit, I’m not trying to be forgiving towards it. But those who are truly rock star developers and know what they’re doing, can become millionaires with some hard work
In some ways I wish I didn’t intentionally walk away from technology 10 years ago… My skills have lapsed to the point that they’re not relevant anymore beyond the core skills… But if I was still remotely in the game, I would be looking for any business opportunity where I can improve the output of companies that have shot themselves in the foot
The reaper is going to come calling for the companies that went all in on this… Just wait 6 more months man (or person) and watch the fallout
Income was supposed to be a metric of usefulness, but it no longer is because the metric itself has become the goal. Now, its perfectly normal to say things like: “If you just ignore your moral issues and work hard, you could be rich!”.
I think you might be missing the point of the complaint in this post a slight bit.
You are not wrong, but why bother fixing their shit? Those are malicious but foolish people at the very least. Why not just let them bankrupt when their time comes, so that they have less a chance of harming other people and the society? There are better companies out their who needs your talent.
Why bother fixing their shit?? Are you for real?
The answer is as follows:
$
Or you could become their competetor and buy up all the devs that they fired, making a better product without all the AI tech debt and productivity losses
Then you get:
$$$
Sounds like a plan to make tech debt skyrocket and make productivity tank.
If I were you, I would start looking for another job. And, once you get an offer, tell them in your resignation letter why: you see the company is going to crash compared to its competitors due to wasteful use of AI and the loss of productivity that comes with it
Run like fifty agents in parallel and get lauded for how “productive” you are while you find another job and hopefully before they get the bill.
This, but only after you have the other job’s offer in hand
So my coworker and I discuss this all the time and we figure we’re old enough to just not give two shits, follow the process, pick up a FOSS project or two to keep our skills up, and wait for the inevitable of when they figure out AI slop is killing them and then charge outrageous prices as contractors when AI2K hits.
Better yet, clone a big repository like Linux kernel or Firefox and let it crawl all day while you’re still working there. Let them pay for the tokens and win the tokenmaxxing game.
AI2K
Ooh, I’m gonna try to use this one
Remember, when they call you asking to return you can gouge the price the fuck up. Beauty of capitalism
I’m having early 2000s flashbacks. Overseas developers were going to replace us all for a fraction of the cost. We had to turn over our code…almost like training AI. That lasted until the first SQL server update that broke, literally, everything they did. Then they wanted a huge amount of money and weeks to get it working again. That really put management in a bind because they told us not to touch their code. Ooookay, fine. Meanwhile, I’m looking at 2,000 character URL string containing the database admin account and password in plain text.
Maybe letting people who ‘own’ things have all the decision/planning power doesn’t make for great outcomes?
In case it wasn’t already clear to you, they’re having you train the AI so it can literally take your job and they can lay you off.
Oh no they don’t, they think they’re having them train the AI to lay them off, but it’s absolutely not what’s actually happening.
You can’t just train the AI. Not unless you own some of the more sophisticated RAG-based solutions that tell the AI how they should behave. Or if you’re producing your own LLMs. But in both cases - the process is vastly different if you want it to actually work (for RAG, you have to actually write some consistent knowledge base and build a MCP server around it). Now they’re just chatting with the robot.
Like - buddy, your coffee machine ain’t gonna get better the more times you click the espress button.
Source: I’m engineering my own kb framework for AI to know how to write code EXACTLY like I do. And I need that only because I want to focus on architecture and devops now that I mastered and burned out of fullstack.
You mastered fullstack?
Not that I learned every single fullstack technology, library, pattern, etc. By mastered I mean I have accumulated enough experience to be able to deliver an entire medium-scaled fullstack project all by myself in the spacific stack and architecture that I have at this point tested through and through.
I have my set of personal patterns, practises, habits, guidelines and designs that I can just describe in my personal wiki and believe it or not, I’m still super early into this project and AI is already really good at replicating my way of thinking.
Now with that I can focus on stuff that interest me the most right now, which is Rust and DevOps. And all that without sacrificing my fullstack expertise, because by documenting it into the wiki, I also solidify all my progress in a form that I can get back to and unfreeze things that I may forget.
And all that without sacrificing my fullstack expertise, because by documenting it into the wiki
Are you writing this wiki by hand?
Idk dude this sounds pretty delusional. Think about what you’re saying here.
AI is already really good at replicating my way of thinking
Ok maybe this checks out then
Are you writing this wiki by hand?
I mean yeah, that’s the whole point. Why wouldn’t I? I’m obviously not teaching the AI the common knowledge, I’m just cherrypicking what’s the best of it and also explaining my personal concepts. It’s not that much content really, it’s not like you have to be a galaxy brain to write good software.
AI can already write complete software, but it’ll be horribly unstable. You can’t have a stable app without clean architecture, and you can’t have clean architecture by mixing billions of concepts and unrelated solutions. It’s just a mess - there’s so many ways to solve a problem, AI knows them all and is super bad at staying consistent.
Shitty input means shitty output. Most code on the world is trash, so obviously AI is already deranged. You have to provide clean, simple and consistent input and that’s what I do, really. I just pick my dream team of concepts, make sure they never overlap and that it is complete.
But it doesn’t eliminate the human out of this loop. Obviously you can’t prepare AI for anything. AI is great at covering the vast expanses of repetitive parts. But if you have some more niche problems, or ones that require a more dedicated and creative approach - you still have to jump in.
And it’s much easier to do so when you’re stepping into a codespace that already looks very familiar to you.
South Park needs to revisit and update that episode. Dey Turk er jerbs!
Seems like exactly the wrong way to use AI.
I just went on a 3-week burner vibe coding shit. Everything was garbage, and it barely works. But I had an impossible deadline.
I’m now going back to manually coding most things. Using AI to debug or make changes. Which is especially helpful when there’s changes to be made across a large codebase.
You could silently sabotage the system. Approve code with obvious defects, bad code smell, and vulnerabilities. Let the product go to production, crash, and let the company spend a bunch of money refactoring the horseshit vibecoded stack they doubled down on.
Im sorry youre going through this. It’s fucking frustrating. Just get that money, fuck the system, and find joy elsewhere
We have to do this so we can improve the AI process.
Do they think that the LLM will “learn” based on feedback? If so, that’s fucking hilarious. “I had to turn the car to keep it from going off the road! Next time it will learn not to go off the road because of my teaching.”
I presume they’re gathering this as training data and hope to later get rid of OP.
That’s why cursor went for $60bn. Anyone can make a harness. The real value is that it gathers data on which changes are accepted/ integrated.
Training a model is a hugely expensive endeavor; that’s why only the huge money-burning companies do it. You can’t tweak a model in the wild. You pay the (grossly subsidized) fee and that’s what you get.
You don’t need to train a foundation model from scratch. You can fine tune an existing coding model or only a LORA layer on a budget.
You could also just use the feedback to optimise system prompts, skills/ guidance or verification tools.
Yes you can update prompts but that won’t make it code any better. The model codes like the model codes.
That’s demonstrably incorrect. Different instructions give different outcomes.
And in a different context the instructions that worked before sabatoge the work being done. So unless you are solving the same problem day after day, those instructions or LORA become out of date
And sometimes the same instructions give different outcomes. Which is why it’s all non-deterministic bullshit.
That’s not necessarily true either. You can make inference deterministic by setting the RNG seed and having the model select the highest likelihood token/ sequence instead of choosing at random.
The same instructions give different outcomes. That’s what the bullshit machine does.
No manager is “gathering training data.” Virtually no company knows how to finetune anything, they just use Claude API.
Perhaps not fine-tuning weights but they can certainly use feedback from PR comments to optimise guardrails etc. And it’s definitely possible to have an agent experiment with that. And yes the Devs are the guinea pigs in that context!
It’s got “Intelligence” right in the name. Intelligent things learn. Therefore AI can learn! Besides, Arnold specifically said in Terminator 2 that if a particular switch is flipped within his CPU, then he can learn! /s
Lol why are you training it? You’re a software dev with a product, not ai qa. Wild times we’re in. Should really just cut your losses and gut all ai and go back to where you were before it. If you can’t do that, then your company no longer has a purpose.
