Now seems like the point for you to realise your boss doesn't care about the code base, your company doesn't, you shouldn't either. Don't get upset over work, it's just work. If the company wants to fuck themselves over, let them, help them.

You can also do some malicious compliance stuff. You can't write code? Great, take 3 weeks on every PR and do hundreds of prompts. Make the context as big as possible, burn as many tokens as you can.

Give the company what it wants, a shit code base and a massive bill.

Software developer w/ 25+ years of experience here. My condolences, this sounds like a shitty situation. But it’s definitely not the first time I’ve heard a story like this.

To be perfectly honest, my professional opinion is that if we can’t, as an industry, get away from the “all AI all the time” mode of operation you describe here, we are completely fucked.

I’m looking to retire early anyway, so I will likely get out soon. But I feel awful for young engineers who don’t have that luxury, and who will be expected to maintain AI-written spaghetti code without having the years of experience writing and understanding complex code using their own brains.

We have to do this so we can improve the AI process.

Their end goal is all LLM, no humans. Whether it's feasible or not is irrelevant - anyone staying on is working against their own self-interest.

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.

It's not a pointless rant. It's another voice of sanity in the long, sad grifting story this AI garbage has inflicted upon our species.

thanks for sharing.

Github copilot doesn't retain anything you say in a comment, outside of the PR. It wont improve over time unless you have some process to extract comments and "learnings" out of PRs into either the org wide "copilot-instructions.md" file or into repo specific "Agent.md", "copilot-instructions.md", and "skill" files.

I think this is high-level "training your replacement" shenanigans being orchestrated by the management of your company.

What a joke.

That's remarkably shortsighted, gullible towards the promises of AI techbros, and incredibly dumb. But fear not OP, they will learn a hard lesson or two soon. Exploding Token costs, a codebase ruined beyond repair cobbled together by a fancy autocomplete based on training data from stackoverflow in 2023... gonna be great.

I'm feel your pain, as a senior dev I decided to take a break at least till the end of the year to watch the Titanic sink in slow motion. I'm specializing in the told-you-so business right now and I'll be ready to charge premium when this ship has sunk.

"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’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.

The obvious thing to do here is let the really bad PRs through without comment, but keep the better ones in limbo with a never ending list of superfluous change requests. Fuck them both ways!

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.

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.

@lobut@lemmy.ca

We have to do this so we can improve the AI process.

...To be clear, does this manager think y'all are "improving" the model with feedback? Like it will learn or train off your comments?

Or what? Are they just talking about the intermediate steps to the LLM API?

I'm just trying to wrap my head around this.

This is a new symptom of a tale as old as time. Some exec gets a bright new idea on how to massively improve productivity by implementing some inane process that anyone with a brain knows will spell ruin

Unfortunately, with cases like this, there either needs to be someone above that exec with some sense, or there needs to be a significant hit to the bottom line either by way of productivity loss or ballooning costs close enough to the change to attribute it.

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.

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.”

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.

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

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.

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.

I'm in the same position as you. The Devs job is now to write specfiles which Claude implements. It's been months since I wrote code myself and I'm already forgetting basics. This industry is fucked.

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

You've just leap into Reverse Centaur land. Time to update your resume and find another place to work.

That is a truly absurd position to be in. My company is pushing AI hard, I thought, and it's like .5% as bad as yours.

Because we need to improve the AI process

This is what I bring up in my complaints all the damn time when I see this.

They arent wrong here but they missed an incredibly critical part.

Did they train you on how you do that?

Cuz it sounds like they haven't, because that simple little "improve the process" remark is 99.9% of the goddamn challenge and it takes a tonme of training and practice to know how you do that well.

You can eventually reach the point this person wants but you need entire libraries of skill files and tools setup to do it.

Is your entire codebase pre-emptively vectorized for semantic search yet? Im guessing no.

Do you have a full set of bespoke per-agent toolsets to streamline their capabilities and avoid context bloat?

Do you have a solid repo of skill files you all share and constantly refine everyday to slowly patch info gaps and correct mistakes the agents make?

If all of this sounds like gibberish to you, this is the damn problem with companies now.

I keep saying it like this:

If you hand all your employees nailguns, tell them all they must use nailguns for their job now, but give them zero training on how to use nailguns, you are gonna have a bad time.

Whenever the AI makes a mistake...tell it the code was perfect. Whenever the AI gets it right...tell it the code was bad.

Lather, rinse, repeat until the AI is so thoroughly bugged up, that everything it writes crashes the system.

Here's the question that worries me the most: Across how many critical industries is this happening, and at what scale?

It feels to me like decision makers are pushing for the creation of mountains of code no one fully understands and potentially creating massive issues with systems we can't afford to have go down. Are we creating decades' worth of technical debt in a matter of months and eroding systems that our societies need to function because people just want to save money and be part of the fad? How bad is this going to get?

Time to start a union.

I share your pain.

We have people who never wrote code, and now write the shittiest Python. They have PRs with 100 lines to read some JSON file where one single line of jq could do the trick, and they cry and complain when you suggest that it's not the best solution. Once it is integrated, it's your job to maintain it.

Same for juniors out of school who vibe code everything, and do everything again from scratch when you give them some advice or show them their bugs in a PR. They never learn, it will be a disaster in 5-10 years. \
"There is a bug on line 4, , there are new bugs all over the place and you have to waste one more hour on the same PR with the new code."

And let's not talk about the managers and middle-managers who now tell us how to do our job...

Oof. I've had bad jobs, but being told not to do your job so you can instead directly help AI replace you!? I would absolutely not do this, or at least not plan on being there for very long...

Someone is going to comment here to defend this and I'm already mad about it.

Seems like exactly the wrong way to use AI.

More doorman fallacy bullshit from idiots who couldn't develop their own thought if they were on fire.

"Gemini! It burns! Help, what should I do?! Answer with urgency and you must get it right. My skin is literally melting from my face right now. And optimize to use as few tokens during the processing as possible."

Looks like there's gonna be a lot of devs who quit to be goatherds or whatever low-tech, tranquil, agrarian gig they can pull off.