51–60 of 323 posts
That prompt looks horrifying. I am not going to spend half an hour coming up with that prompt, tweaking it, and then spend many hours (on the optimistic side) to track down all the hallucinated code and hidden bugs. Have been there once, never going to do that again. I'd rather do it myself to have a piece of mind.
Earlier quoted context omitted.
>The scary thing is: I have seen professional human developers write worse code. This is kind of the rub of it all. If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? I mean at that point its kind of like looking at the output of a bytecode compiler and being like "wow what a mess". And it's not li…
> If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? You're not wrong here, but there's a big difference in programming one-off tooling or prototype MVPs and programming things that need to be maintained for years and years. We did this song and dance pretty recently with dynamic typing. Developers…
In my experience, type checking / type hinting already starts to pay off when more than one person is working on an even small-ish code base. Just because it helps you keep in mind what comes/goes to the other guy's code.
I have a business which is turning in millions in ARR at the moment (made in the pandemic) it's a pest control business and we have got a small team with only 1 experienced senior engineer, we used to have 5 but with AI we reduced it to one which we are still paying well.
Even with maintenance, we plan ahead for this with an LLM and make changes accordingly.
I think we will see more organizations opting for smaller teams and reducing engineer count since now the code generated is to the point that it works, it speeds up development and that it is "good enough".
This is excellent, and matches my experience. Those lamenting the loss of manual programming: we are free to hone our skills on personal projects, but for corporate/consulting work, you cannot ignore 5x speed advantage. It's over. AI-assisted coding won.
As a long time hobby coder, like 25 years and I think I’m pretty good(?), this whole LLM /vibecoding thing has zapped my creativity the past year or so. I like the craft of making things. I used tools I enjoy working with and learn new ones all the time (never got on the JS/react train). Sometimes I have an entrepreneur bug and want to create a marketable solution, but I often just like to build. Im also the kind of…
It's been depressing to listen to people pretend that LLM generated code is "the same thing". To trivialize the thoughtful lessons one has learned honing their craft. It's the same reason the Studio Ghilbi AI image trend gives me the ick.
Earlier quoted context omitted.
Fascinating. it's gone the other way for me. because I can now whip up a serious contender to any SaaS business in a week, it's made everything more fun, not less.
Yeah, I see that perspective bu I guess my thought process is “what’s the point, if everyone else can now do the same” I had long ago culled many of those ideas based on my ability to execute the marketing plan or the “do I really even want to run that kind of business?” test. I already knew I could build whatever I wanted to exist so My days of pumping out side projects ended long ago and I became more selective wit…
a project in a niche where I live and breath the fumes off the work and I can help the whole ecosystem with their workflow? sign me up!
Earlier quoted context omitted.
The more I browse through this, the more I agree. I feel like one could delete almost all comments from that project without losing any information – which means, at least the variable naming is (probably?) sensible. Then again, I don't know the application domain. Also… def _save_current_date_time(current_date_time_file: str, current_date_time: str) -> None: with Path(current_date_time_file).open("w") as f: f.write(…
>The scary thing is: I have seen professional human developers write worse code. This is kind of the rub of it all. If the code works, passes all relevant tests, is reasonably maintainable, and can be fitted into the system correctly with a well defined interface, does it really matter? I mean at that point its kind of like looking at the output of a bytecode compiler and being like "wow what a mess". And it's not li…
Coding by prompt is the next lowering of the bar and vibe coding even more so. Totally great in some scenarios and adds noise in others.
The premise might possibly be true, but as an actually seasoned Python developer, I've taken a look at one file: https://github.com/dx-tooling/platform-problem-monitoring-co... All of it smells of a (lousy) junior software engineer: from configuring root logger at the top, module level (which relies on module import caching not to be reapplied), over not using a stdlib config file parser and building one themselves,…
Saying that, for typed languages like TypeScript and C#, they have gotten very good. I suspect this might be related to the semantic information can be found in typed languages, and hard to follow unstructured blobs like dataframes, and there for, not well repeated by LLMs.
As a long time hobby coder, like 25 years and I think I’m pretty good(?), this whole LLM /vibecoding thing has zapped my creativity the past year or so. I like the craft of making things. I used tools I enjoy working with and learn new ones all the time (never got on the JS/react train). Sometimes I have an entrepreneur bug and want to create a marketable solution, but I often just like to build. Im also the kind of…
Fascinating. it's gone the other way for me. because I can now whip up a serious contender to any SaaS business in a week, it's made everything more fun, not less.
So far none of them are having a great time after their initial enthusiasm. A lot of it is people discovering that there’s far more to a business than whipping up a SaaS app that does something. I’m also seeing a big increase in venting about how their progress is slowing to a crawl as the codebase gets larger. It’s interesting to see the complaints about losing days or weeks to bugs that the LLM introduced that they didn’t understand.
I still follow because it’s interesting, but I’m starting to think 90% of the benefit is convincing people that it’s going to be easy and therefore luring them into working on ideas they’d normally not want to start.