Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Breaking the spell of vibe coding

fast.ai

Post reply on HN
Print view View original

221–230 of 375 posts

Re: Breaking the spell of vibe coding

#221

Post by rafaelmn »

jackfranklyn wrote: post #219

[flagged]

> Vibe coding would be catastrophic here. Not because the AI can't write the code - it usually can - but because the failure mode is invisible. A hallucinated edge case in a tax calculation doesn't throw an error. It just produces a slightly wrong number that gets posted to a real accounting platform and nobody notices until the accountant does their review.

How is that different from handwritten code ? Sounds like stuff you deal with architecturally (auditable/with review/rollback) and with tests.

Re: Breaking the spell of vibe coding

#222

Post by big-chungus4 »

There are different kinds of coding - web dev, low level coding, software, research, data science. There are some kinds of coding where carefully designing the architecture is important, and AI might not produce satisfactory code. Some kinds of coding, on the other hand, can benefit very strongly from AI. I suspect that many people who specialize in a particular area of coding form opinions based on how useful AI is in that area, and those opinions are perfectly valid for what coding means to them, but don't generalize to other people with different specializations.

Re: Breaking the spell of vibe coding

#223

Post by NiloCK »

mprast wrote: post #53
daxfohl wrote: post #7

I think it all boils down to, which is higher risk, using AI too much, or using AI too little? Right now I see the former as being hugely risky. Hallucinated bugs, coaxed into dead-end architectures, security concerns, not being familiar with the code when a bug shows up in production, less sense of ownership, less hands-on learning, etc. This is true both at the personal level and at the business level. (And astound…

It's very interesting to me how many people presume that if you don't learn how to vibecode now you'll never ever be able to catch up. If the models are constantly getting better, won't these tools be easier to use a year from now? Will model improvements not obviate all the byzantine prompting strategies we have to use today?

I think there's something to this, but I also there there's something to the notion that it'll get easier and easier to do mass-market work with them, but at the same time they'll become greater and greater force multipliers for more and more nuanced power users.

It is strange because the tech now moves much faster than the development of human expertise. Nobody on earth achieved Sonnet 3.5 mastery, in the 10k hours sense, because the model didn't exist long enough.

Prior intuitions about skill development, and indeed prior scientifically based best practices, do not cleanly apply.

Re: Breaking the spell of vibe coding

#224

Post by kolinko »

mettamage wrote: post #166
Sateeshm wrote: post #142

Earlier quoted context omitted.

It's hilarious. The whole point of "vibe coding" is that you don't need to learn or know anything. It's like saying if you don't learn to use a smartphone you'll be left behind. Even babies can use it now.

Even if that were true you'd still need to be good at UX

The new claude/opus, esp, with additional skills is actually pretty decent with UX.

Re: Breaking the spell of vibe coding

#225

Post by rsynnott »

mgraczyk wrote: post #45
daxfohl wrote: post #7

I think it all boils down to, which is higher risk, using AI too much, or using AI too little? Right now I see the former as being hugely risky. Hallucinated bugs, coaxed into dead-end architectures, security concerns, not being familiar with the code when a bug shows up in production, less sense of ownership, less hands-on learning, etc. This is true both at the personal level and at the business level. (And astound…

Even if you believe that many are too far on one side now, you have to account for the fact that AI will get better rapidly. If you're not using it now you may end up lacking preparation when it becomes more valuable

> If you're not using it now you may end up lacking preparation when it becomes more valuable

How's that? If it ever gets good, it seems rather implausible that today's tool-of-the-month will turn out to be the winner.

Re: Breaking the spell of vibe coding

#226

Post by rsynnott »

abcde666777 wrote: post #41

It's astonishing to me that real software developers have considered it a good idea to generate code... and not even look at the code . I would have thought sanity checking the output to be the most elementary next step.

Those people aren't real software developers.

Re: Breaking the spell of vibe coding

#227

Post by fragmede »

ChrisMarshallNY wrote: post #217
fragmede wrote: post #216

Earlier quoted context omitted.

I think we are. I'm helping somebody who has a non-technical background and taught himself how to vibe code and built a thing. The code is split into two GitHub repos when it should have been one, and one of the repos is named hetzner-something because that's what he's using and he "doesn't really understand tech shit"

That sounds a lot like “twiddling knobs at random,” to me.

> Sometimes, they would have a hit, but they wasted a lot of energy on dead ends.

We'll see which one it is in a few months.

Re: Breaking the spell of vibe coding

#228

Post by croes »

rtpg wrote: post #160
mprast wrote: post #53

Earlier quoted context omitted.

It's very interesting to me how many people presume that if you don't learn how to vibecode now you'll never ever be able to catch up. If the models are constantly getting better, won't these tools be easier to use a year from now? Will model improvements not obviate all the byzantine prompting strategies we have to use today?

I do think that there's some meta-skills involved here that are useful, in the same way that some people have good "Google-fu". Some of it is portable, some of it isn't. I think if you orient your experimentation right you can think of some good tactics that are helpful even when you're not using AI assistance. "Making this easier for the robot" can often align with "making this easier for the humans" as well. It's a…

Are the early tricks for LLMs still useful today?

Re: Breaking the spell of vibe coding

#229

Post by lebuin »

ChrisMarshallNY wrote: post #217
fragmede wrote: post #216

Earlier quoted context omitted.

I think we are. I'm helping somebody who has a non-technical background and taught himself how to vibe code and built a thing. The code is split into two GitHub repos when it should have been one, and one of the repos is named hetzner-something because that's what he's using and he "doesn't really understand tech shit"

That sounds a lot like “twiddling knobs at random,” to me.

Exactly. The fact that an LLM isn't very good at helping you fix basic organizational issues like this is emblematic. Quoting the article: "We have automated coding, but not software engineering."

Re: Breaking the spell of vibe coding

#230

Post by dannyfritz07 »

holoduke wrote: post #124
AstroBen wrote: post #107

Earlier quoted context omitted.

> you have to account for the fact that AI will get better rapidly that's nowhere near guaranteed

Nothing gets worse in computers. Name me one thing. And if the current output quality of LLM stays the same but speed goes up 1000, quality of the generated code can be higher.

Software has gotten considerably worse with time. Windows and MacOS are basically in senescence from my point of view. Haven't added a feature I've wanted in years, but manages to make my experience worse year to year anyways.

CPU vulnerability mitigations make my computer slower than when I bought it.

Computers and laptops are increasingly not repairable. So much ewaste is forced on us for profit.

The internet is a corporate controlled prison now. Political actors create fake online accounts to astroturf, manipulate, and influence us.

The increasing cost of memory and GPU make computers no longer affordable.

Post reply on HN