| Making software is no longer very hard. It's becoming a few steps up from burger flipping. Maybe somewhere around line chef. There's still some skill involved, but the skill is mostly in manual testing, and accurately phrasing what went wrong. The AI is better at debugging than people are, and the code isn't great, but perfectly adequate for pretty much everything. And it's even fine at system design these days. It's interesting realizing how mind numbingly thoughtless my job has become. Don't get me wrong, I wouldn't mind it if this was skilled work, but it just isn't. |
| |
| ▲ | a2ff6eeb0 5 hours ago | parent [-] | | Since you apparently work on this kind of software, here's a challenge for you: take the last several bugs that were reported and paste them into Fable, pointing it at your code. How long does it take? Does it find the issue? In more or less time than the engineers took? Ask it to review your code for design and cohesiveness issues. How does it do? | | |
| ▲ | tripledry 2 hours ago | parent | next [-] | | Fun example I've had (some weeks ago), Agent completely dismissed the lack of strong consistency in our db system, this tiny bug would have caused a massive problem in the future. A bug that is not immediately obvious, no syntax error, logic is sound, works as expected on local and QA envs. But let it run in prod for 2 months and you have a massive problem. I'm not dismissing LLM's here btw, just pointing out that there is probably a lot of things that go into the category "you don't know what you don't know". These kinds of issues may or may not be a problem depending on the business you are in. Most of the time the latest models perform better than I expect. | | |
| ▲ | ethin an hour ago | parent [-] | | Ouchy. That isn't as bad as the slop I've seen: one example I saw a few weeks ago from vibe-coded software had this absolutely mind-blowing bit of Rust code: pub(crate) fn zeroed_safe<T>() -> T { unsafe { std::mem::zeroed() } } pub(crate) fn read_unaligned_safe<T: Copy>(src: const T) -> T { unsafe { std::ptr::read_unaligned(src) } } pub(crate) fn box_from_raw_safe<T>(ptr: mut T) -> Box<T> { unsafe { Box::from_raw(ptr) } } pub(crate) fn isize_to_wndproc_safe(value: isize) -> WNDPROC {
unsafe {
Some(std::mem::transmute::<
isize,
unsafe extern "system" fn(HWND, u32, WPARAM, LPARAM) -> LRESULT,
>(value))
}
} No, I'm not joking either, this is actual code that Claude wrote (and I'm pretty sure it's the latest models too but I don't actually know for certain, since the "dev" never specified). This idiom is repeated about 238 more times through that one file. I have tried repeatedly to help this person out but they're the kind of vibe-coder who thinks they know best, and who will take your advice and drop it into CLAUDE.md verbatim, and then Claude will go off and do the most literal interpretation of that text and not best practice. To be clear, I don't hate LLMs. They're really useful for very specific things or where you know the domain very well. But then I see slop like this (and the dependency many people have on them -- I have literally heard my own close acquaintances say that they could not see themselves without a Claude subscription) and it really hammers home that software quality is not at all going to get better because of these things unless something changes. Edit: grammar/spelling | | |
| ▲ | a2ff6eeb0 29 minutes ago | parent [-] | | Yeah, trying too hard to guide with hard rules, instead of asking the LLM for self-review, is going to go wrong. The LLM is much better at code review than it is at writing code. Use a high effort model and let the llm review it's output and figure it out on its own. The code still won't be great, but it'll be good enough. |
|
| |
| ▲ | ethin 4 hours ago | parent | prev [-] | | Sorry, but we aren't talking about me here. You were the one who made the claim that AI pretty much makes making software trivial nowadays. Specifically, you wrote: > Making software is no longer very hard. It's becoming a few steps up from burger flipping. Maybe somewhere around line chef. You did acknowledge that "some" skill was required: > There's still some skill involved, but the skill is mostly in manual testing, and accurately phrasing what went wrong. The AI is better at debugging than people are, and the code isn't great, but perfectly adequate for pretty much everything. And it's even fine at system design these days. All I asked was for you to back this up, since the burden of proof is on you to prove your claim, not on me to prove it for you. | | |
| ▲ | a2ff6eeb0 4 hours ago | parent [-] | | Oh. So, because I said I work in software you assumed I worked in safety critical systems? Interesting. A little unhinged, but interesting. Anyways, as I said elsewhere, I don't code for fun, and my employer would be unhappy if I sent you their proprietary code. You can decide to do some experiments yourself, or you can decide that you don't want to hear it. No skin off my back either way. | | |
| ▲ | ethin 3 hours ago | parent | next [-] | | > Oh. So, because I said I work in software you assumed I worked in safety critical systems? No, I didn't. I asked you to provide me an example of code that you had generated via AI that might survive in such an environment. But if you re-read my original post, I also gave you an escape hatch: just code that was correct. Not even formally. I'd say your refusal to provide any examples of your original claim is pretty telling, and your reasoning is pretty convenient for you, now isn't it? Edit: also, I'd like to point out that it was you who used the word "software" as a general claim. You never specified what kind of software. Since you continue to expect me to derive the proof for you instead of you providing the evidence, I don't see any need to continue this discussion since nobody is obviously going to learn anything. I'm sure many of us here would love to learn what secret sauce your using that makes software engineering so trivial, but you don't seem willing to actually provide that. | | |
| ▲ | a2ff6eeb0 2 hours ago | parent [-] | | As I said, feel free to experiment, I gave you some hints where to start. Or not. I don't win any prizes either way. |
| |
| ▲ | jibal 2 hours ago | parent | prev [-] | | They simply asked you to support your claims, as an ethical person would. Without that, your words are just noise. And I see that this isn't the only comment you made where someone asked to provide supporting evidence and you dodged. | | |
|
|
|
|
