jama211

Writing to express yourself sure. Using an llm for a birthday card would be a terrible sin. However if someone used it for, I dunno, drafting an email because you’re in a dispute with an evil real estate agent and you’re trying not to get screwed, I wouldn’t have any qualms about it.

IMO it’s lazy and bad for expressive writing, but for certain things it’s totally fine.

Generating art is worse than generating code though IMO. It’s more personal. Everything exists on a spectrum, even slop.

Code _can_ be expressive but it also can not, it depends on its purpose.

Some code I cobbled together to pass a badly written assignment at school. Other code I curated to be beautiful for my own benefit or someone else’s.

I think the better analogy in writing would be… using an LLM to draft a reply to a hawkish car dealer you’re trying to not get screwed by is absolutely fine. Using it to write a birthday card for someone you care about is terrible.

As opposed to literally anything else? Not doing that?

You ok?

Oh look another article of “this works for me therefore it must work for everyone else”

Fascinating reading about that bug, thanks for sharing

Sure! I don’t personally think it’s necessary, but whatever makes you happy yo.

> seems pretty naive

I had cereal for breakfast this morning

> is splitting hairs

I’m a chocolate ice cream guy myself, over strawberry that is.

—

Sorry, just wanted to join the “quote random parts of a comment and then state completely unrelated statements for unknown reasons” club.

Not even sure what you’re trying to say here mate. Sure, some people aren’t gonna do their work. That’s not really relevant here

I’ve rarely seen this happen personally but it does happen from time to time. Even thorough code reviews don’t take anywhere near as long as the writing though.

I err, don’t think you’re saying what you think you’re saying.

A fantastic read, even if it makes a lot of silly assumptions - this is ok because it’s self aware of it.

Who knows what the future will bring. If we can’t make the hardware we won’t make much progress, and who knows what’s going to happen to that market, just as an example.

Crazy times we live in.

Thursdays, unfortunately

Brilliant, thank you

Oh wow I see, great effort either way, thanks

Well, at least one of those statements is probably true.

Well said. It also causes a lot of bitterness among engineers too, not being able to follow the red string is maddening to some. This rage can prevent them from finding good prompting strategies also which would directly ease a lot of the pain, in a similar way to how it’s far harder to teach my mother how to do something on her phone if she’s already frustrated with it.

No, you don’t. This is a fundamental principle of cryptography, unless you’ve got a hidden proof of p=np up your sleeve.

Well said, you’re absolutely right. In practice code review is orders of magnitude faster than code creation and it always has been, baffling anyone is arguing otherwise. Perhaps they’ve never worked in a real organisation, or they’ve only worked on safety critical code,m or something?

Outside of life saving critical software or military spec software, no one needs to review so hard they understand it to the level you’re describing, and they do not.

There is a mathematical principle that verification of a proof is easier than any proof. The same is true in code.

Well said. Much like the self driving debate we don’t need them to be perfect, just better than us to be useful, and clearly they already are for the most part.

Indeed, a good summary.

Running it entirely unsupervised with “some refactoring principles” is the exact recipe for such a disaster, which supports my point.

That said, this is a very different kind of mistake to make compared to overwriting a file and then insisting it didn’t do that. Any modern model with reasoning would check the git history immediately if you mentioned this had happened, if it had somehow even made the mistake in the first place, but I digress.

Ah, so number 2. Thanks for answering!

Aww man you were doing so well

I dunno about the need for disclosure in this way. In my working life I’ve copied a lot of code from stack overflow, or a forum or something when I’ve been stuck. I’ve understood it (or at least tried to) when implementing it, but I didn’t technically write it. It was never a problem though because everybody did this to some degree and no one would demand others disclose such a thing at least in hobby projects or low stakes professional work (obviously it’s different if you’re making like, autopilot software for a passenger plane or something mission critical, that’s notwithstanding).

If it’s the norm to use LLMs, which I honestly believe is the case now or at least very soon, why disclose the obvious? I’d do it the other way around, if you made it by hand disclose that it was entirely handmade, without any AI or stackoverflow or anything, and we can treat it with respect and ooh and ahh accordingly. But otherwise it’s totally reasonable to assume LLM usage, at the end of the day the developer is still responsible for the final result, how it functions, just like a company is responsible for its products even if they contracted out the development of them. Or how a filmmaker is responsible for how a scene looks even if they used abobe after effects to content aware remove an object.

Genuinely curious, what’s your goal here? Disparage those who use LLMs? Or just express your unhappiness at the amount of ai content on the HN front page? Or just want to throw shade on LLM use in general?

This is impressive and cool but I don’t understand the bitterness here.

I mean it’s cool and all but it’s like making a painting entirely out of tiny dots with your hands tied behind your back. I’m happy for their achievement and it looks cool but it shouldn’t throw any shade on those of us who just like to use a paint brush instead.

I suspect this is like the invention of the car. Some people just love riding horses, so they’ll keep doing it as a hobby. The rest of us are fine with a car.

This article has some serious usage of either bad prompting, or terrible models, or they’re referencing the past with their stories. I have experience AI’s deleting things they shouldn’t but not since like, the gpt4 days.

But that put aside, I don’t agree with the premise. It doesn’t make the hard parts harder, if you ACTUALLY spend half the time you’d have ORIGINALLY spent on the hard problem carefully building context and using smart prompting strategies. If you try and vibe code a hard problem in a one shot, you’re either gonna have a bad time straight away or you’re gonna have a bad time after you try and do subsequent prompting on the first codebase it spits out.

People are terrible observers of time. If you would’ve taken a week to build something, they try with AI for 2 hours and end up with a mess and claim either it’s not saving them any time or it’s making them code so bad it loses them time in the long run.

If instead they spent 8 hours slowly prompting bit by bit with loads of very specific requirements, technical specifications on exactly the code architecture it should follow with examples, build very slowly feature by feature, make it write tests and carefully add your own tests, observe it from the ground up and build a SOLID foundation, and spend day 2 slowly refining details and building features ONE BY ONE, you’d have the whole thing done in 2 days, and it’d be excellent quality.

But barely anyone does it this way. They vibe code it and complain that after 3 non specific prompts the ai wasn’t magically perfect.

After all these years of engineers complaining that their product manager or their boss is an idiot because they gave vague instructions and demanded it wasn’t perfect when they didn’t provide enough info, you’d think they’d be better at it given the chance. But no, in my experience coaching prompting, engineers are TERRIBLE at this. Even simple questions like “if I sent this prompt to you as an engineer, would you be able to do it based on the info here?” are things they don’t ask themselves.

Next time you use ai, imagine being the ai. Imagine trying to deliver the work based on the info you’ve been given. Imagine a boss that stamped their foot if it wasn’t perfect first try. Then, stop writing bad prompts.

Hard problems are easier with ai, if you treat hard problems with the respect they deserve. Almost no one does.

/rant