101–110 of 168 posts
Earlier quoted context omitted.
> It's like hiring a plumber then trying to tell them how to fix the toilet. I never faced or witnessed that in software dev.
Us testers have been dealing with that crap forever. Every non-tester thinks they know how a professional tester should work, and imagines our work is just writing test cases.
We’re in the geocities phase of LLM, mostly trash, very basic, but eventually, people will either get bored and go back to whatever it is they were doing or actually use the tools for useful and productive work. As for the feelings that using LLM has when it one shots your project start (and does a pretty good job), have a German word: Automatisierungskummer (automation sorrow) • Kummer is emotional heaviness, a mild…
Put it into Google and you will see.
Been writing software for like 20 years now and I love it. I am also a fan of AI-assisted coding, but I only just started using Cursor. Gosh I do not like it at all for a simple reason: since I didn't write the code, in order to understand it I have to read it. But gaining understanding that way takes longer than writing it myself does. When you write the code, you understand it. When you read the code produced by an…
You raise a great point here: > since I didn't write the code, in order to understand it I have to read it. But gaining understanding that way takes longer than writing it myself does. I remember reading Joel Spolsky's blog 25 years ago, and he wrote something like: "It is harder to read code than to write code." I was quite young at that stage in my programming journey, but I remember being simultaneously surprised…
Earlier quoted context omitted.
Us developers are experiencing what designers have had to deal with for decades. 2009 anyone? https://theoatmeal.com/comics/design_hell
Devs too, this one is at least 30 years old: https://www.pcuf.fi/~pjt/pink/software-architecture.html
This article is not about vibe coding per se, it's about not having strong boundaries between you as the developer, and your client. You should not be allowing the client to dictate how you work, much less them having the permissions to merge in code. This was true before AI too, where clients might say, do X this way, and you should simply say no, because they are paying for your expertise*. It's like hiring a plumb…
> It's like hiring a plumber then trying to tell them how to fix the toilet. I never faced or witnessed that in software dev.
The result was a piece of shit, but it was his piece of shit and he loved it.
For me vibecoding has a similar feeling to a big bag of Doritos. It's really fun at first to slap down 10k lines of code in an afternoon knowing this is just an indulgence. I think AI is actually really useful for getting a quick view of some library or feature. Also, you can learn a lot if you approach it the right way. However, every time I do any amount of vibecoding eventually it just transitions into pure lethar…
This. First I try it just a little to do a boring part. It feels great. The boring part that was holding me is gone and all it took was a little instruction. The dopamine hit is real. So of course I will try it again. But not so fast. It needs to be corrected to make everything aligned with the architecture. And as my requests get bigger, it needs more and more corrections. Eventually correcting everything becomes to…
It's a language mode with finite context and the ability to use tools. Whatever it can fit into its context, it can usually do pretty well. But it does require guidance and documentation.
Just like working with actual humans that aren't you and don't share your brain:
1) spec your big feature, maybe use an LLM in "plan" mode. Write the plan into a markdown file.
2) split the plan into smaller independent parts, in github issues or beads or whetever
3) have the LLM implement each part in isolation, add automatic tests, commit, reset context
Repeat step 3 until feature is done.
If you just use one long-ass chat and argue with the LLM about architecture decisions in between code changes, it WILL get confused and produce the worst crap you've ever seen.
We’re in the geocities phase of LLM, mostly trash, very basic, but eventually, people will either get bored and go back to whatever it is they were doing or actually use the tools for useful and productive work. As for the feelings that using LLM has when it one shots your project start (and does a pretty good job), have a German word: Automatisierungskummer (automation sorrow) • Kummer is emotional heaviness, a mild…
This is not a German word. Pseudo-German at best. Put it into Google and you will see.
Earlier quoted context omitted.
Video/audio production here and the exact same rules apply. You can’t let clients dictate your tools any more than you feel you should tell your plumber what they can use to fix your sink. “We use Premiere.” Cool. I use Resolve. If we aren’t collaborating on the edit then this is an irrelevant conversation. You want a final product , that’s what you hired me for my dude. If you want me to slot into your existing edit…
Not all freelancers are good, sometimes you just ask these questions to understand how good the freelancer is.
If you pay me for a 30s highlight, you get a 30s highlight. If you don’t like the highlight itself that’s a different discussion.
Earlier quoted context omitted.
I have yet to find the niche where it is "good at the beginning". So far I've mostly tried asking to build C tools that use advanced linux API. Me: hey make this, detailed-spec.txt AI: okidoki (barfs 9k lines in 15 minutes) all done and tested! Me looks at the code, that has feature-sounding names, but all features are stubs, all tests are stubs, and it does not compile. Me: it does not compile. AI: Yes, but the code…
Holy shit, I feel the same. I was arguing with an LLM one day about how to do Kerberos auth on incoming HTTP requests. It kept giving me bogus advice that I could disprove with a tiny snip of code. I would explain. It would react just like yours. After a few rounds, it would give the first answer again. Awful. So infuriating. I had a similar issue with GNU plot. The LLM-suggested scripts frequently had syntax errors.…
Been writing software for like 20 years now and I love it. I am also a fan of AI-assisted coding, but I only just started using Cursor. Gosh I do not like it at all for a simple reason: since I didn't write the code, in order to understand it I have to read it. But gaining understanding that way takes longer than writing it myself does. When you write the code, you understand it. When you read the code produced by an…
You raise a great point here: > since I didn't write the code, in order to understand it I have to read it. But gaining understanding that way takes longer than writing it myself does. I remember reading Joel Spolsky's blog 25 years ago, and he wrote something like: "It is harder to read code than to write code." I was quite young at that stage in my programming journey, but I remember being simultaneously surprised…
Also:
Everyone knows that debugging is twice as hard as writing a program in the first place. So if you're as clever as you can be when you write it, how will you ever debug it?
— Brian Kernighan: The Elements of Programming Style, 2nd edition, chapter 2
In summary: write simple code, it's easy to read and understand - by future you who forgot why you did something and others.