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

311–320 of 375 posts

Re: Breaking the spell of vibe coding

#311

Post by ragall »

ryan_n wrote: post #244
rafaelmn wrote: post #221

Earlier quoted context omitted.

> 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 s…

It’s shocking to me that people even ask this type of question. How do you not see the difference between a machine that will hallucinate something random if it doesn’t know the answer vs a human that will logic through things and find the correct answer.

Almost all current software engineering practices and projects rely on humans doing ongoing "informal" verification. The engineers' knowledge is integral part of it and using LLMs exposes this "vulnerability" (if you want to call it that). Making LLMs usable would require such a degree of formalization (of which integration and end-to-end tests are a part), that entire software categories would become unviable. Nobody would pay for an accounting suite that cost 10-20x more.

Re: Breaking the spell of vibe coding

#312

Post by fcantournet »

KronisLV wrote: post #220

> However, it is important to ask if you want to stop investing in your own skills because of a speculative prediction made by an AI researcher or tech CEO. Consider the case where you don’t grow your software engineering or problem-solving skills, yet the forecasts of AI coding agents being able to handle ever expanding complexity don’t come to pass. Where does this leave you? The current Claude Code setup with Opus…

Do you think your organisation as a whole is doing more ? Is the more being done actually useful ? i.e: is the outcome better ?

Re: Breaking the spell of vibe coding

#313

Post by skydhash »

lelanthran wrote: post #196
zozbot234 wrote: post #90

Earlier quoted context omitted.

> if you nail everything down hard, the specs get unwieldy - large and overly detailed That's a rather short-sighted way of putting it. There's no way that the spec is anywhere as unwieldly as the actual code, and the more details, the better. If it gets too large, work on splitting a self-contained subset of it to a separate document.

> There's no way that the spec is anywhere as unwieldly as the actual code, and the more details, the better. I disagree - the spec is more unwieldy, simply by the fact of using ambiguous language without even the benefit of a type checker or compiler to verify that the language has no ambiguities.

People are keen to forget that programming languages are specs. And a good technique for coding is to build up you own set of symbols (variables, struct, and functions) so that the spec become easier to write and edit. Writing spec with natural language is playing russian roulette with the goals of the system, using AI as the gun.

Re: Breaking the spell of vibe coding

#314

Post by kody »

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…

Coaxed into dead-end architecture is the exact issue I have had when trying agentic coding. I find that I have the greatest success when I plan everything out and document the implementation plan as precisely as possible before handing it off to the agent. At which point, the hard part is already done. Generating the code was not really the bottleneck.

Using LLMs to generate documentation for the code that I write, explaining data sheets to me, and writing boilerplate code does save me a lot of time, though.

Re: Breaking the spell of vibe coding

#315

Post by skydhash »

habinero wrote: post #115
CBarkleyU wrote: post #61

Earlier quoted context omitted.

With all due respect, but if you actually wasted hours (multiple) each (!) day on those issues, then yeah, I can fully believe that AI assisted coding 10 or even 100x'd you.

I uncharitably snarked that AI lets the 0.05X programmers become 0.2X ones, but reading this stuff makes me feel like I was too charitable. I've never had problems with any of those things after I learned what a code editor was.

Yep, it may be an issue in notepad, which does not have helper like syntax highlighting, auto indent, and line numbers. But I started with IDLE which has all those things. So my next editor was notepad++ and codeblock.

Re: Breaking the spell of vibe coding

#316

Post by anthonypasq96 »

vidarh wrote: post #295
jackfranklyn wrote: post #219

[flagged]

If the failure mode is invisible, that is a huge risk with human developers too. Where vibecoding is a risk, it generally is a risk because it exposes a systemic risk that was always there but has so far been successfully hidden, and reveals failing risk management.

i agree, and its strange that this failure mode continually gets lumped onto AI. The whole point of longer term software engineering was to make it so that the context within a particular persons head should not impact the ability of a new employee to contribute to a codebase. turns out everything we do to make sure that is the case for a human also works for an agent.

As far as i can tell, the only reason AI agents currently fail is because they dont have access to the undocumented context inside of peoples heads and if we can just properly put that in text somehwere there will be no problems.

Re: Breaking the spell of vibe coding

#317

Post by anthonypasq96 »

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?

knowing how to properly use AI is a skill, there are new tools, new patterns, new primitives etc. you will be unpracticed.

Re: Breaking the spell of vibe coding

#318

Post by firemelt »

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…

using ai too little is never wrong I think

Re: Breaking the spell of vibe coding

#319

Post by tqian »

rafaelmn wrote: post #221
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 s…

Humans make such mistakes slowly. It's much harder to catch the "drift" introduced by LLM because it happens so quickly and silently. By the time you notice something is wrong, it has already become the foundation for more code. You are then looking at a full rewrite.

Re: Breaking the spell of vibe coding

#320

Post by anthonypasq96 »

eddythompson80 wrote: post #97
mgraczyk wrote: post #63

Earlier quoted context omitted.

I don't think so. That's a good point but the capability has been outpacing people's ability to use it for a while and that will continue. Put another way, the ability to use AI became an important factor in overall software engineering ability this year, and as the year goes on the gap between the best and worst users or AI will widen faster because the models will outpace the harnesses

That’s the comical understanding being pushed by management in software companies yes. The people who never actually use the tools themselves, but the concept of it. It’s the same AGI nonesense, but dumped down to something they think they can control.

why does every AI skeptic assume that everyone is lying to them. theres millions of developers using AI to be more productive and you just keep plugging your ears and screaming, claiming its only dumb managers, meanwhile Linus Torvalds is vibe coding stuff.
Post reply on HN