Technology

Loudly announcing your increasing incompetence to the world seems like a weird career move, maybe consider lying about that?

You still need to review and verify the code, actually implement it, and improve it if you use AI.

If you just blindly accept it then you're just lazy to begin with.

Software Engineers

Oftentimes I wonder what civil or mechanical engineers think about webdevs-turned-prompt-writers calling themselves "engineers".

That’s the problem. This is one of those things that you gain momentum in, not simply experience. You can lose that momentum.

Tech bros are going to end up enslaving us to this shit.

Things I've realized while working with AI (Claude code):

• It's fantastic for very small macros and medium length scripts. Think dev ops stuff, pre-commit hooks, transforming data. Keep it small enough to manually review and something you can run without destroying anything important. This can massively boost your codebase QoL. [Double bonus for not wasting tokens to solve the same problem over and over]
• It's decent-to-good at debugging but not consistent with fixes. It can find some utf encoding edge case that might have taken you 1hr+ but suggest the dumbest bandaid fix you've ever seen. Also very good at spinning up unit test suites for basic edge cases.
• Due to obvious training bias, it's pretty good with common libraries and cloud platform infrastructure. It could probably help with writing a complex cron call, debugging regex or fixing an IaC config. On the flip side it won't bother to use the latest package version or know your niche/new library.
• It does better with greenfield because exploring your codebase introduces a ton of bias. It might try to fit in an ugly hack when a refactor to simplify everything is way easier.
• It's absolutely garbage with UI, just throws the most disorganized HTML together that isn't reactive or reusable. OK enough for ugly internal stuff but God help anyone relying on it for that.
• This is setting up to be the biggest rug pull in history. People that buy into it heavily just to save a couple bucks on engineer payroll are going to be fucked when they start ratcheting up the token price.

All in all it can be useful when used with care but will never be a magic bullet.

Solution is simple, learn to code.

ha

Oh no... who could have... possibly... foreseen this...

We use it at work and I now have disabled it for all the typeahead stuff. Far too many times it guesses what I am doing incorrectly and it made using my TAB key (which inserts the propper two spaces) impossible.

The only place I still use it is for reading and identifying compiler errors. Even then it is only about 50% correct as most times it falls into the "Oh you are right, X isn't the solution. Have you tried X?" I have had few bad interns and even they were smart enough to not forget what they said in their previous sentence.

Nah, AI isn't that good. When you don't properly review every single line twice, you get the most absurd bullshit you've ever seen.
I use Claude Code Opus daily btw.

Lol! Losers. I've been programming for almost two decades and extensive use of AI hasn't compromised my skills AT ALL! These slop machines can't hope to compete with the quantity and magnitude of subtle bugs I write. My code was terrible long before I made bots have mental breakdowns trying to work with it.

I weap for the environment and our future water and electricity availability.

I want to become a software entomologist, you know, so I can study all their bugs.

(X) Doubt

As a Sr. Engineer, I completely get that my situation may be wildly different from what's cited in the article.

Right now, I'm using AI "in the loop" rather than "as the loop". That's a big difference. And I'm getting my ass kicked routinely on review for dumb-ass things that I'm letting slide from AI generated output. And rightly so. Plus, models routinely lead me down sub-optimal blind alleys while dreaming up really stupid ways to fix problems. The level of (re)prompting I have to provide to suggest to get decent quality results converges on a post-grad that has encyclopedic knowledge of software engineering as it exists online, but with zero real-world experience. It's both impressive and dangerous as a replacement for software engineering.

In the mode I describe above, I'm not losing the ability to do anything. I can see how one could surrender some coding chops or familiarity with a whole language or stack, in favor of automation. But all you have to do is not do that.

I will say that as a rapid-prototyping technology, It's nothing short of miraculous. I've watched junior engineers knock together medium-weight applications, complete with browser UI/UX and decent workflow, in less than a week. This is great for showing value or putting something semi-functional in front of management and/or customers. But pivoting those prototypes into something maintainable is an utter nightmare. Depending on how beholden to AI and forever prompt-looping with "skills" and MCPs you want to be, I suppose it's possible to just keep mashing the AI button. But at some point, you're going to need to get inside there to fix security problems or bugs that elude this workflow. What then?

Its a silver lining of AI that you can easily tell whos a big baby idiot and whos actually worth engaging with.

It feels like relying on GPS while driving around. If you know the roads well and just want some help with live traffic or somewhere you haven't been before, it's a decent tool.

If you rely on it because you don't want to think and just want to press the easy button, you're going to have a bad time sooner or later.

Back to software, I think there are a lot of people introducing concepts they don't understand or can't maintain (either from poor quality slop or it is just too advanced for their current level of understanding). You can do a few turns like this, until you're stuck burning tokens in a loop without moving forward in a meaningful way.

I try to avoid taking the easy route myself unless I've burnt too much time stuck on some small detail. Ultimately I feel it is super important to understand what you are delivering. Whether it is writing it yourself, copying a stack overflow post, or using an LLM. Once you commit and push to prod you've got to deal with that crap.

We have been interviewing for entry level positions and the new grads know less than ever before. I don't really care what they know, I am looking for evidence that they can think, but I usually ease them into thinking scenarios by asking easy foundational questions like how many bits in a byte. You would think I was asking for them to explain the Shrodinger wave equations... One candidate was waivering between 13 and 17...

Hot take: they had no ability to code in the first place.

is this much different than IT guys not knowing how to solder anymore? I started my career learning about individual components and doing math by hand, and shortly after I was told that all we did was swap cards. My job eventually turned into a more or less normal IT job (compared to what it was), and by the time I moved on, we weren't even using command prompts anymore.

I remember asking one of my instructors about how layer 1 can generate layer 2, and he had an idea, but couldn't really point at components and give an explanation. One could say that I represent that first step in the death of knowledge due to convenience and optimization, but it hasn't really negatively affected me outside of curiosity. Even when I'm working on legacy equipment and actually do have to bust out a soldering iron, that's usually because I'm being cheap and don't want to buy new cards.

So, this makes me wonder: is it really all that bad if someone can't sit down and write lines and lines of code, but can understand it well enough to direct AI? I've used AI to help me code in some unfamiliar languages and all of the outputs I got were utterly unusable. So, in my anecdote, it didn't make up for my lack of skill in the slightest.

I say this as someone who taught himself blacksmithing on principle, so it's not like i'm some techbro or something. Obligatory I think AI is overpromised, but this seems like one of the few things it can actually assist with, assuming the person using it is capable enough to be using it.

I notice getting lazier. Even adding a. gitignore file I ask Claude now. It takes longer than typing it myself and costs more probably. But I don't have to do anything but wait a few seconds.

Being able to call out a middle manager that if these tools are really so great he can just open the PR himself is pretty awesome though.

I just don't get it, even the purportedly best models screw things up so much that I can't just leave them to the job without reviewing and fixing the mess they made... And I'm also drowning in pull requests that turn out to be broken as it proudly has "co authored by Claude" in it... Like it manages to pass their test case but it's so messed up that it's either explicitly causing problems, or had a bunch of unrelated changes randomly.

I feel like I'm being gaslit as I keep reading that there are developers that feel they successfully offloaded the task of coding.

Closest I got was a chore that had a perfect criteria "address all warnings from the build". Then let it go and iterate. Then after 50 rounds each round saying "ok should be done now, everything is taken care of, just need to do a final check". It burned though most of my monthly quota doing this task before succeeding. Then I look at the proposed change... And it just added directives to the top of every file telling the tools to disable all the warnings... This was the best opus 4.6 could do...

Now sure, I can have it tear through a short boiler plate and it notice a pattern I'm doing and tab through it. But I haven't see this "vibe" approach working at all...