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

Ask HN: Worth leaving position over push to adopt vibe coding?

news.ycombinator.com

Post reply on HN
Print view View original

81–90 of 99 posts

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#81

Post by SftwrSvior81 »

Ancapistani wrote: post #21

I’ve been doing this for 20 years. I see it as you having two primary options. You should stay there, learn the new tech, and see what happens. If it works better than you expected, then your mind will be changed and you’ll be well positioned for the new economy. If it turns out how you expect, now you have experience working with this tooling to inform your positions at your next company. Either way, a few months in…

Agree with this wholeheartedly. Stay there for now while looking for a new job. If things work out ok at the current place, end your search and enjoy your current job. If they don't work out, hopefully you'll have some options to move into. Best of luck to you.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#82

Post by wrs »

edanm wrote: post #75
wrs wrote: post #73

Earlier quoted context omitted.

Were you around for the OOP craze? It definitely affected a lot of peoples’ day job. I mean, quite a few people use C++ and Java, no? In my list I didn’t even mention the internet, the web, smartphones, and the cloud, all of which had a very broad effect on programming and programmers, and had similar top-down edicts from the C-suite, e.g., declaring you must be “all-in on cloud”. Turns out those things were indeed q…

I've been programming professionally since around 2003. I'd say I caught the late-stages OOP craze (or maybe after-craze) though not really the origin or rise of OOP. My first job was in a C++ codebase, and I spent a lot of time learning the OOP design patterns (or really, the "how do we make C++ behave well" patterns). That said, the rise of OOP is probably measured in a decade or two. It eventually "spawned" whole…

I’m not comparing anything blindly; that is in fact the exact opposite of my advice. Nor am I saying all big hypes are equivalent, just that there’s always a big hype about something, and you need a strategy to stay levelheaded about them despite the irrational polarized yelling you hear.

I use LLMs every day in my work (both to help write code and as a component of the thing I’m coding). They’re pretty cool. But as an engineer you need to make decisions based on what they actually do, in your empirical observation, not what people tell you they will do, eventually, in their fantasies. Speculating about that is just noise. The engineer’s job is to find the signal.

In my observation, I can trust an LLM to write code way more than last year, but I still have to keep it on a very short leash. Will it be better next year? I don’t know. Nobody does.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#83

Post by wrs »

RaftPeople wrote: post #79
wrs wrote: post #73

Earlier quoted context omitted.

Were you around for the OOP craze? It definitely affected a lot of peoples’ day job. I mean, quite a few people use C++ and Java, no? In my list I didn’t even mention the internet, the web, smartphones, and the cloud, all of which had a very broad effect on programming and programmers, and had similar top-down edicts from the C-suite, e.g., declaring you must be “all-in on cloud”. Turns out those things were indeed q…

> Were you around for the OOP craze? In the early 90's I was working for a large ERP company that went all in on OOP and distributed objects. I was talking to one of the guys from the new team they created to re-write the entire system and had an entertaining conversation: Tech guy that had drunk the kool-aid (TGTHDTKA): "...and the objects can just automatically interact with each other, like I can drop this person…

Now the MCP kool-aid is about how we’re finally going to make that work, because the computer on either end can literally read the field descriptions and intuit the interaction. MCP uses LLMs to supply the magic that the WSDL folks never admitted was necessary.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#84

Post by edanm »

wrs wrote: post #82
edanm wrote: post #75

Earlier quoted context omitted.

I've been programming professionally since around 2003. I'd say I caught the late-stages OOP craze (or maybe after-craze) though not really the origin or rise of OOP. My first job was in a C++ codebase, and I spent a lot of time learning the OOP design patterns (or really, the "how do we make C++ behave well" patterns). That said, the rise of OOP is probably measured in a decade or two. It eventually "spawned" whole…

I’m not comparing anything blindly; that is in fact the exact opposite of my advice. Nor am I saying all big hypes are equivalent, just that there’s always a big hype about something , and you need a strategy to stay levelheaded about them despite the irrational polarized yelling you hear. I use LLMs every day in my work (both to help write code and as a component of the thing I’m coding). They’re pretty cool. But as…

Yes, agreed on basically everything.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#85

Post by flowerthoughts »

I've recently started using Claude Code, and also expected to not like it (based on using Claude Web to generate some code). I have 17 years of experience.

But it's actually been fantastic. It's challenging in a new way: splitting things down into small enough descriptions that the LLM don't go down a rabbit hole it can't get out of. While also giving high-level guidance to plan for the whole project.

I like UI design, but implementing it is tedious and slow. With Claude I can get a dashboard page done in less than 1 min, from a spec, that I can iterate on. Instead I can focus on the parts I care about, like backend. I need to nudge it to always care about security and storage concerns. I've seen O(n²) loops where O(n) would be sufficient. It keeps making enough mistakes that I'm not exactly out of a job.

The best way to use Claude Code is to write those descriptions and use examples of what you want the output to look like, so take it in small steps and do manual corrections.

However, you need to have seen some good code before using it to make something good. It's just a tool, like compilers and IDEs. I'm pretty happy I don't have to input programs using eight data switches and a latch switch on an Altair 80. And I'm now pretty happy I don't have to care so much about internal API boundaries, because doing a refactoring is one sentence away.

However, I do keep running out of quota after 2-2.5h out of 5h. If I had a company sponsoring this, it would be a no-brainer to use it more.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#86

Post by majora2007 »

flowerthoughts wrote: post #85

I've recently started using Claude Code, and also expected to not like it (based on using Claude Web to generate some code). I have 17 years of experience. But it's actually been fantastic. It's challenging in a new way: splitting things down into small enough descriptions that the LLM don't go down a rabbit hole it can't get out of. While also giving high-level guidance to plan for the whole project. I like UI desig…

This is similar to how I use Claude (bought a Pro sub this year). I like to group up context into the UI and have it either look over my approach or write some skeleton code, then I do the heavy lifting myself.

It's faster for me to do it manually (and I still learn) than having to find hard to spot bugs from the AI output (as it always outputs some weird stuff).

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#87

Post by danielbln »

kasey_junk wrote: post #29
NotAnOtter wrote: post #7

Earlier quoted context omitted.

>You should remain open to new things in this industry I'm open to new things. I've seen demo's, attended presentations, and spent a long time toying around with it myself. I have not been convinced there is any meat there, not in it's current iteration. LLM's are designed to make things that "look" like human output and thus are very good at hiding bugs. It's ok at getting the first 20% of the project done, but that…

Feel free to make your own decisions about this stuff but know that there are people with lots of experience and success in the industry using llm coding tools successfully (I’m one). I am in a situation where ai was mandated, I was skeptical, but took it as a chance to try it out. I now can’t imagine going back.

Yep, if you know what you're doing, if you have good software dev and review practices and if you manage to aim the AI foot gun away from the body, then the productivity boost is absolutely gigantic.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#88

Post by AnimalMuppet »

A software engineer's job is to design and create programs that adequately meet their need (including performance, reliability, and maintainability). That's your job. Your job is not "type out the code".

If an AI helps you do that (all of it, including the "maintainability" part), then sure, use it. If not, don't (or only use it in limited places where it can help).

How do you know? You almost certainly have to experiment. So look at your company's push as a chance to experiment. But when you do, make sure you have your "software engineer" hat on, not your "code monkey who cranks through Jira tickets" hat.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#89

Post by mattmanser »

rogerthis wrote: post #37

I can't stop thinking what happened when CASE tools, WYSIWIG, UML, Model Driven Architecture/Development, etc was pushed into devs. I know, it's a different phenomenon (that was a graphical visual push, this keeps the text).

We've had it on code as well. The factory pattern, workflow engines, SOA, lo-code, cloud computing, serverless, a billion different templating engines for js, js the right way, jQuery, not jQuery, SPAs, noSQL, graphQL, micro services, event sourcing and on and on.

Every couple of years there's something that if you aren't using you're apparently doing it wrong.

I think maintaining this AI code is going to turn out to be a nightmare and everyone will tone down on it, not letting agents run off on their, but we'll see.

Re: Ask HN: Worth leaving position over push to adopt vibe coding?

#90

Post by more_corn »

Theres vibe coding and there’s ai assisted coding. The former is bullshit and causes more problems than it fixes. The latter is great and you should lean into it. There was a post a few days ago about a rule file for using Claude code effectively. (I never bothered to learn the hn rules on linking so google it up with site:)

You should start building a rule file listing every way it screws up and a) warning it not to b) watching for it. Errors I’ve seen: failure to follow best security practices, failure to plan properly, failure to update variable names, lies, bad tests, stuck in a rut flip flopping between two possible paradigms Get into it, get better at it than your CEO and CTO, save them from the worst of their folly.

And simultaneously start looking for another job because you clearly don’t like them and disagree with their strategy in important ways.

AI assisted coding is the future, but probably not the way they’re doing it. But pain is the best teacher so dive in and feel that pain.

Post reply on HN