kescusay

That's fair. I guess what I hate is what the term represents, rather than the term itself.

I actively hate the term "vibe coding." The fact is, while using an LLM for certain tasks is helpful, trying to build out an entire, production-ready application just by prompts is a huge waste of time and is guaranteed to produce garbage code.

At some point, people like your coworker are going to have to look at the code and work on it, and if they don't know what they're doing, they'll fail.

I commend them for giving it a shot, but I also commend them for recognizing it wasn't working.

You should read the community info on the sidebar. In short, this is a humorous community that shares real news stories that seem like they could be from The Onion.

So posts should be actual links to news reports with their original headlines, but only news stories that are weird enough that they read like headlines from The Onion are appropriate.

The name "Not The Onion" is a joke, because the news stories here are supposed to be real but make you think you're reading satire.

Are you using agent mode?

That's still not actually knowing anything. It's just temporarily adding more context to its model.

And it's always very temporary. I have a yarn project I'm working on right now, and I used Copilot in VS Code in agent mode to scaffold it as an experiment. One of the refinements I included in the prompt file to build it is reminders throughout for things it wouldn't need reminding of if it actually "knew" the repo.

• I had to constantly remind it that it's a yarn project, otherwise it would inevitably start trying to use NPM as it progressed through the prompt.
• For some reason, when it's in agent mode and it makes a mistake, it wants to delete files it has fucked up, which always requires human intervention, so I peppered the prompt with reminders not to do that, but to blank the file out and start over in it.
• The frontend of the project uses TailwindCSS. It could not remember not to keep trying to downgrade its configuration to an earlier version instead of using the current one, so I wrote the entire configuration for it by hand and inserted it into the prompt file. If I let it try to build the configuration itself, it would inevitably fuck it up and then say something completely false, like, "The version of TailwindCSS we're using is still in beta, let me try downgrading to the previous version."

I'm not saying it wasn't helpful. It probably cut 20% off the time it would have taken me to scaffold out the app myself, which is significant. But it certainly couldn't keep track of the context provided by the repo, even though it was creating that context itself.

Working with Copilot is like working with a very talented and fast junior developer whose methamphetamine addiction has been getting the better of it lately, and who has early onset dementia or a brain injury that destroyed their short-term memory.

Uh, re-read the post. Political news stories aren't banned here, they just have to have headlines that read like they're from The Onion. Lots of political posts here haven't been Onion-like at all. That's what's against the rules.

Like I said, I do find it useful at times. But not only shouldn't it replace coders, it fundamentally can't. At least, not without a fundamental rearchitecturing of how they work.

The reason it goes down a "really bad path" is that it's basically glorified autocomplete. It doesn't know anything.

On top of that, spoken and written language are very imprecise, and there's no way for an LLM to derive what you really wanted from context clues such as your tone of voice.

Take the phrase "fruit flies like a banana." Am I saying that a piece of fruit might fly in a manner akin to how another piece of fruit, a banana, flies if thrown? Or am I saying that the insect called the fruit fly might like to consume a banana?

It's a humorous line, but my point is serious: We unintentionally speak in ambiguous ways like that all the time. And while we've got brains that can interpret unspoken signals to parse intended meaning from a word or phrase, LLMs don't.

Experienced software developer, here. "AI" is useful to me in some contexts. Specifically when I want to scaffold out a completely new application (so I'm not worried about clobbering existing code) and I don't want to do it by hand, it saves me time.

And... that's about it. It sucks at code review, and will break shit in your repo if you let it.

"Scientists"

You keep using that word. I do not think it means what you think it means.

Yep. But it's important to remember that Republicans are utterly incapable of feeling shame. They can't do it. They know they're hypocrites of the highest order and do not care. For them, the ends justify literally any means, even if that includes utter betrayal of every moral precept they claim to hold dear.

Yes, the Bible says explicitly not to bear false witness. No, it's not effective to point that out to supposed conservative Christians who happily lie and flip-flop on every single damn topic if they think it'll give Republicans more power.

It's true, although the smart companies aren't laying off workers in the first place, because they're treating AI as a tool to enhance their productivity rather than a tool to replace them.

The fact that he ever had an approval rating with Gen Z is mind-boggling.