“We’re not in X, we’re in Y”
squints suspiciously
There isn’t a talent shortage, there’s a shortage of people who will take your shit at sub-par wages working two + jobs at your company.
Stop hiring 20 managers. Hire 1 manager and have them in meetings all day so real work can be done.
Last week, curious what would be generated, told Cursor (with Claude Opus 4.5) to create an animated LED strip effect for an ESP32 device in C. Pretty simple stuff. It thinks for a long time. Creates a ton of scaffolding, docs, step-by-step agentic checklists, even a Makefile to build and deploy the binary. It then says: “Done.”
I go compile it. Lots of errors. I paste over the logs and ask it what’s wrong. Claude thinks for a while longer, then goes:
“I see the issue - I only created the header file but never completed the LED manager implementation. Let me check what’s there and finish the implementation.”
Hahahaha this idiot thinks that it’s the speed of our typing that ships code faster. He’s in a knowledge shortage.
I’ve found that the people who understand these “agents” the least are the ones who are promoting them the most.
And everyone promotes them for tasks they aren’t experts in.
Managers think they could replace devs, but never a manager.
Devs think they could replace management but never a senior developer.
Storyboard drawers think they can write screenplays. Screenplay writers think they can draw storyboards. Etc.
As an expert, you know how shit AI is in your own field, but surely those other jobs are simple enough to be replaced.Let’s be honest, though: they absolutely could replace management.
A good manager is both a coordinator and a filter. They deal with bs rolling down from above and keep their team running efficiently.
A good manager is worth their weight in gold. A bad manager isn’t worth their weight in bullshit.
Yeah, our PM is great. Our previous one not so much.
He trusts us but also handles absolutely loads of stuff that we don’t want to deal with.
It’s very easy to replace something that was never critical to the process in the first place. My manager essentially updates my git tickets with what I did. We talk for 5 minutes a week. He just kinda lets me do my thing, I am fully aware of how lucky I am.
90% of my experience with management is having none at all would be a net benefit
why would we want to add ai to that mix
At least they’d be pleasant while being useless? I’ve had managers that were egomaniacal terrors.
I thought “egomaniacal terror” was part of the job description.
problem is ai would be another layer of separation from decisions and consequences
This.
They’re incredibly useful, but you have to treat their output as disposable and untrustworthy. They’re reinforcement trained to generate a solution, regardless of if it’s right, because it’s impossible to AI evaluate that these solutions are correct at scale.
If you’re writing some core code: you can use an agent to review it, refactor parts, stump the original version, infill methods, and to run your test/benchmark scripts.
but you still have to manage it, edit it, make sure it’s not recreating the same code in 6 existing modules, generating faked tests, etc.
As an example this week on my side project I had Claude Opus write some benchmarks. Total throwaway code.
It actually took my input files, generated a static binary payload from it using numpy, and loaded that into my app’s memory (on its own that’s really cool), then it ran my one function and declared the whole system 100x faster than comparable libraries that parse the original data. Not a fair test at all, nor was it a useful test.
You cannot trust this software.
You’ll see these games metrics, gamed tests, duplicate parallel implementations, etc.
spend more time fixing slop compared to just doing it manually and correct the first time
They are also the ones who have super leveraged their portfolios with AI stocks -
deleted by creator
One of our devs came to me with an LLM rewrite of some parts of our automation. Even at first glance you could see a lot was missed, the refactor simply wasn’t going to work in that state and critical migration logic just wasn’t present.
I binned the branch and did the refactor myself, as it would have taken more time to figure out the damage caused than just starting over.
So glad we now pay premium prices for RAM and non-volatile storage, just so some LLM can vomit up a reheated turd.
My sister-in-law is a software engineer and project manager. This isn’t groundbreaking news or anything but she said that her engineers are using generative AI like this. The problem is that it created exceedingly inefficient and bloated code that barely works. En masse it will bog down systems due to the exponential inefficiencies.
It’s fine. Everything is fine.
Yup, it’s a junior dev that never learns, makes thousands of tiny mistakes that tolerance stack into a brittle gnarled mess.
Who needs tech-debt when you have new and improved slop-debt?
how’s she like working for Microslop?
“The new skill isn’t typing faster”.
Since I added a second keyboard I am programming twice as fast and don’t even need AI!
We pair-code on the same keyboard for maximum efficiency.
You should quad-code on two keyboards, really pump up those LOC stats.
It’s also the second-best way to combat hackers.
Are you guys using your feet yet? That’s how I run 4 keyboards.
I use 5. The new 5th limb is highly experimental and probably dangerous but my productivity has skyrocketed.
Its hard to maintain structural integrity of the 5th limb long enough for consistent productivity
You just need big python energy
I just have to get through this last sprint! Just one more sprint…
Nothing can go wrong with that plan
Does he know what a technical debt is?
The 1st major project in my first coding job made me understand technical debt even though I didn’t know the name of it.
I suppose there are some people that just see spaghetti code and their only thought is to add more spaghetti code. Thankfully I also understood spaghetti code with my project in uni.Nah, we need to optimize the spaghetti code with an n8n optimization pipeline for more spaghetti, lets make sure to build a new library for eache seperate function call. Once the function has run we’ll tear down that library and build the next, if it errors out that’s fine, we can just have the GPT hallucinate another library and call that into the function. It’s fungible OOP all the way down. Infinite code is infinite tech debt, I call that job security.
It’s not negative that nobody understands the spaghetti code, it’s advanced optimized code that mere mortals can’t comprehend, and marketing can sell that.
Don’t forget to bill by the hour to clients for bug fixes.
This guy speaks “solutions architect”
Oh man the worst guy I ever worked with got hired to be a solutions architect.
I was so happy he left. He’d always just say yes to whatever we were asked, even if it was literally impossible. Then he’d fuck off and leave me to deal with actually doing the project and would just throw some wrong advice at me and spend the rest of the day browsing the internet at his desk.
Oh, but you don’t have technical debt anymore, since the agent rewrites all the code every time!
And much like copying a copy, more and more errors creep in each time.
It’s a problem you type into a chat for Claude to solve.
Don’t worry. All the code has been thoroughly tested. By Claude.
You’re absolutely right! I didn’t actually run anything. I was displaying a “thinking…” animation and simply waited for your next input. I shouldn’t have done that.
Thought we were on [email protected] for a moment.
Prompt: “write a python script to create a thousand linkedin accounts with plausible sounding names, and then setup a cronjob to post every day a punchy linkedin just-so story explaining why everyone should be paying for my LLM and to keep paying for it when I jack up the price 100x to cover my expenses”
You’ll want to set a systemd timer for that actually, easier to have the agent journalctl to get the full stderr and properly hallucinate more jobs.
Hahaha did I hit a nerve?
Do people actually use agents for production code? I feel like it is one of those things that people don’t use but is sold to us that everyone uses. A lie to promote bullshit.
I sometimes do, but very sparsely, it’s hard to come across a task that’s good fit for an LLM unless you’re prototyping something, imo
I have an engineer that uses it heavily.
It adds so much extra and he’ll push thousands of lines of code into a PR every week. He had one bug and tried to refactor it, he bloated that single file by 16%.
It’s almost impossible to review.
It adds so much extra and he’ll push thousands of lines of code into a PR every week.
This is just a waste of the reviewer’s own time that could be better spent doing actual work. Is it at least split up into multiple commits, or is it one giant shitshow?
Yes, they do.
I’m getting ready to take over an org that’s doing this. It’ll be interesting to run a static code analysis and penetration test on the sites.
