- cross-posted to:
- technology@lemmy.ml
- cross-posted to:
- technology@lemmy.ml
You must log in or register to comment.
How many more years are going to be wasted with this crap?
Everyone knows that both in theory and practice, AIs are shit are producing code; the only ones who don’t are the ones who are themselves unable to produce decent code and refuse to see the problem.
But yes, let’s keep on pushing more and more until everything is drowned in worthless crap, as if we didn’t already have enough issues with humans producing crap like web technologies, now they’ll be riddled by even more crap.
I think people are too polite to call shitty programmers out on being shitty. It’s probably not a fair assumption, but whenever I see someone admit they use some AI coding tool, I immediately assume they’re either a junior, or one of those people who just were never intelligent enough to be a good developer, and ended up getting filtered into some low skill web dev job. Those are the kinds of people who probably feel threatened by AI, and I feel are more likely to use it.
We need to make elitism and public shaming cool again.
Capitalism is happy to have cheap code that works “well enough” to sell, and mostly prefers it to expensive code that works “really well.”
The future is full of buggy ass code that runs most services and devices, who’s main priority is vacuuming up data about its users and everyone and everything around them, and then a few high quality products and services only the rich can afford.
Man if you’re not faster with AI I dunno what to say.
If you’re faster with “AI”, all I can say is, learn to fucking code, scrub. If you cannot spot that shit as shit from a mile away, you SUCK at coding and shouldn’t be doing code reviews either way.
You are literally the kind of ignorant people I’m talking about.
It’s like telling a guy who makes wooden jewelry that “dude if u not faster with chainsaw I dunno what to say”, or to someone trying to take down a wall between two rooms that a bulldozer would be faster.
I still cannot comprehend that some people would be “smart” enough to understand basic programming, but then be absurdly lacking understanding of the matter to end with the conclusion that coding “skill” is about speed.
I just don’t know how to even make an example that explains how absurd that is. It’s like having a random naked dude in an archery competition screaming that he won because he shot his arrows faster than all the other contestant, even though most of them landed in the crowd.
I am really at a loss for words for how absurdly stupid that kind of vision of programming and technology is.
I’m literally slower with AI, because I have to waste my time review slop generated code that looks convincing rather than actually works.
If they tried at least to write the code themselves they would get better over time
how many more years
As many as possible running down the clock on climate change and putting our whole economy towards less-than-useless bullshit.
Killing truth, sloppifying everyone is the point.
This quote from the article very much sums up my own experience of Claude:
In my recent experience at least, these improvements mean you can generate good quality code, with the right guardrails in place. However without them (or when it ignores them, which is another matter) the output still trends towards the same issues: long functions, heavy nesting of conditional logic, unnecessary comments, repeated logic – code that is far more complex than it needs to be.
AI coding tools definitely helpful with boilerplate code but they still require a lot of supervision. I am interested to see if these tools can be used to tackle tech debt, as often the argument for not addressing tech debt is a lack of time, or if they would just contribute it to it, even with thorough instructions and guardrails.
These might be of interest to software developers but it’s all just style nothing here actually effects the computation. The problem I encounter with LLMs is that they are incapable of doing anything but rehearsing the same algorithms you get off of blogs. I can’t even successfully force them to implement a novel algorithm they will simply deny that it is valid and revert back to citing their training data.
I don’t see LLMs actually furthering the field in any real way ( even if by accident, since they can’t actually perform deductive reasoning).
I am interested to see if these tools can be used to tackle tech debt, as often the argument for not addressing tech debt is a lack of time, or if they would just contribute it to it, even with thorough instructions and guardrails.
From my experience working with people who use them heavily, they introduce new ways of accumulating tech debt. Those projects usually end up having essays of feature spec docs, prompts, state files (all in prose of course), etc. Those files are anywhere from hundreds to thousands of lines long, and there’s a lot of them. There’s no way anybody is spending hours reading through enough markdown to fill twenty encyclopedia-sized books just to make sure it’s all up-to-date. At least, I can promise that I won’t be doing it, nor will anyone I know (including those using AI this way).
I am interested to see if these tools can be used to tackle tech debt
Having it rewrite existing functioning code seems like a terrible idea. QA would at least have to re-test all functionality.
My brief experience is similar, even if conditions are perfect (you treat it like an editor, like this exactly the change you should make, flow exactly this naming and testing styles, run the tests so it’s clear you didn’t screw anything) it will still screw things up here and there.
