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

Vibe coding and agentic engineering are getting closer than I'd like

simonwillison.net

Post reply on HN
Print view View original

831–840 of 958 posts

Re: Vibe coding and agentic engineering are getting closer than I'd like

#831

Post by g3f32r »

kiba wrote: post #784
therealpygon wrote: post #757

Earlier quoted context omitted.

Or at least, aware that this argument continues to be made with tenuous evidence and anecdotes. And yet, people are being more productive (actually productive) with AI. Release schedules are increasing, bugs are getting fixed faster, security issues identified and patched sooner, so on and so forth. I’m not denying (at all) that unused skills languish. I take issue with AI being characterized as a magic eraser that m…

Can AI make developers lazy in new ways? Of course! Why wouldn’t it? I don’t write things in ASM because I can be “lazy” and write 50x more useful instructions with a few lines of a modern language. I doubt I’d be able to write working ASM anymore without a serious refresher. Did newer languages erase my memory of ASM and make me “lazy”, or did my efforts evolve to make use of the newest technology regardless of “los…

> You wouldn't trust an engineer a bridge that an engineer vibe-engineered would you?

If it was as easy to stress test/battery test/materials test/etc a bridge as it is to test code - then yes. I'd trust an engineer who vibe-engineered a bridge.

---

The problem with mapping digital problems into meat-space is that there is inherently a few orders of magnitude of cost automatically added to anything that happens in meat-space.

I can spin up an arbitrary number (10, 10k, 500k) docker instances, X with fuzzed inputs, Y with explicit edge cases, Z with tolerance testing, etc etc. And if that doesn't work - I can fix and push a button and it just happens again.

If a bridge engineer could do that with bridges - yes I'd expect them to be vibing just as hard as we are now.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#832

Post by munksbeer »

allthetime wrote: post #490
u8 wrote: post #440

The disconnect for AI is that it is a jagged frontier and it only really shines when one of its jagged frontiers extends counter to one of your valleys. If you've been writing Perl for 30 years, you might not want to learn JavaScript just to make a little fun idea in your head to show your wife. Vibe code that shit man. Who cares? Your wife does not care about LOC or those internal design decisions you made. If you'r…

AI is just revealing the two types of people in this line of work. Those who don’t actually like software and just do it because it’s lucrative, and the actual nerds who care.

There are more types of people. I do it because it is lucrative, because it turns out I'm good at being a professional software engineer, but I also enjoy it more than other things I could be doing.

However, ultimately, I got into software because I was intellectually curious and programming was a tool I could use to explore that curiosity. When I stop working professionally, I will stop caring about the sorts of stuff I care about today and go back to using programming for what I love. A tool to explore.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#834

Post by lmeyerov »

dodu_ wrote: post #608
lmeyerov wrote: post #548

Earlier quoted context omitted.

Maybe a failure to automate? The volume of people successfully adopting agentic engineering practices suggests this stuff isn't rocket science, but it is a learned skill and takes setup. A year later into heavy AI coding, my experience is what you're describing should aid in being able to run 5+ agents simultaneously on a project because you know what you're doing, you set it up right, and you know how to tell agents…

Maybe you're the exception and are actually doing it right and actually getting good results, but every time I have heard this, it has been an ignorance-is-bliss scenario where the person saying it is generating massive amounts of code that they don't understand, not because they're incapable but because they don't care to, and immediately wiping their hands of it afterward. To give an example of where I hear this, i…

Yes and no

I've seen productivity surveys of senior programmers that share the reverse, and that matches our experience. A common finding is that gardening projects are a lot cheaper now when they're just a few extra terminal tabs running in parallel - security, refactoring, more testing, etc. Non-feature backlog items that senior developers value around tech debt are less of a discussion now. They're often essential now: to make AI coding work well, there is an effective automation poverty line around verification, testing, and specification that needs to be reached.

The understanding code thing is tough. Eg, when a non-senior fullstack developer manually edits frontend css code and didn't start from pixel-perfect designs across all form-factors, do they really understand what they did? I wrote the first formal mechanized specification of the CSS standard, and would claim 95%+ of web developers do not understand core CSS layout rules to beginwith: it was a struggle to semantically formalize even a tiny core of the box model as soon as you have floats. If the AI generates live storybooks and in-tool screenshots of all these things as part of the review process, and doing code review "looks good", what's the difference?

I don't truly think this way - my point is to challenge basic claims of manual coding to be good to begin with and whether AI coding is being held to an artificial standard. What I see in commercial and defense software is a joke compared to what we do in the verification world. AI coding automating review iteration fixes in areas like security engineering and test coverage+amplification has been a blessing for quality improvement.

More fundamentally, we require developers by default to be responsible for knowing what the code does and having tested it. Every case of relaxing that rule has to be explicit, eg, clear that something is a prototype, or an area is vibed with what alternate review/test flow, and we are learning as a team what that means in different situations. In practice, our senior ai coders are doing more quality engineering work than the manual coders, both per-pr and in broader gardening contributions.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#835

Post by avgDev »

allthetime wrote: post #490
u8 wrote: post #440

The disconnect for AI is that it is a jagged frontier and it only really shines when one of its jagged frontiers extends counter to one of your valleys. If you've been writing Perl for 30 years, you might not want to learn JavaScript just to make a little fun idea in your head to show your wife. Vibe code that shit man. Who cares? Your wife does not care about LOC or those internal design decisions you made. If you'r…

AI is just revealing the two types of people in this line of work. Those who don’t actually like software and just do it because it’s lucrative, and the actual nerds who care.

I am a nerd who cared. Caring is not putting my food on the table though, delivering stuff is.

I still enjoy diving into documentation but AI has transformed how I work. I can quickly get code examples I can debug. I learn new things as sometimes AI generates approaches I haven't used before.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#836

Post by cindyllm »

sothatsit wrote: post #823
ori_b wrote: post #820

Earlier quoted context omitted.

You can keep telling yourself that. I have seen the results from others making the same arguments. The result is invariably trash.

Well you have obviously already made up your mind, so have fun with your confirmation bias. We'll all be over here having a good time, getting more work done. Feel free to come over when you put down your grudge.

[dead]

Re: Vibe coding and agentic engineering are getting closer than I'd like

#837

Post by Schiendelman »

nozzlegear wrote: post #551
eric_cc wrote: post #406

Earlier quoted context omitted.

You can also just talk it out loud to Claude while you’re on a walk getting some sunshine. Done.

Now you're working when you should be taking a break and enjoying your surroundings. Not good!

Maybe instead you get twice as much walking in the sunshine.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#838

Post by Schiendelman »

asa400 wrote: post #467
hnuser123456 wrote: post #399

Earlier quoted context omitted.

I see you haven't encountered an API where a GET command can modify the database.

Similarly, I once worked somewhere that had an HTTP API that returned status code 200 {“error”: “ok”} to indicate an error occurred.

A lot of GraphQL APIs are like this! They return a 200 just to mean the damn GraphQL is well formed, and the call can totally fail underneath.

Re: Vibe coding and agentic engineering are getting closer than I'd like

#839

Post by robotresearcher »

gspr wrote: post #560
bulbar wrote: post #531

Earlier quoted context omitted.

Giving a precise description of what the computer is supposed to do is exactly what programming is. The more specific your requirements the closer you get to natural language not being useful anymore.

This is actually my biggest gripe with vibecoding. The single best feature of any programming language is that it is precise. And that is what we throw out?! I favor of natural language , of all things?! We're insane!

Historically we almost entirely moved from ASM to C, a language with lots of undefined behavior, because precision is not the most valued feature of languages.
Post reply on HN