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

791–800 of 958 posts

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

#791

Post by eloisant »

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…

Exactly, I'm a back-end engineer and I vibe-coded that in a couple of hours: https://erwan.github.io/sovereign-cards-database/

I could have learn all the frameworks to make it, but honestly I wouldn't have bothered.

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

#792

Post by swsieber »

latexr wrote: post #782
theshrike79 wrote: post #775

Earlier quoted context omitted.

> When you’re bored, your mind goes to places it wouldn’t otherwise go. Curiosity kicks in. Curiosity is a precursor to learning. Learning engages the brain and is fun. But it’s not fun all the time, some of it is challenging and frustrating (which is good, that’s the process that teaches you). And I love how I can go from a curious brainfart "hmm, could I do a movie catalogue app that uses a web page + phone camera…

I don’t see what that has to do with “when did we stop liking to learn”, which is the only point I’m addressing. My point has nothing to do with AI and it doesn’t seem like you actually learned anything from that experiment.

I read it more as response to your argument that it was a lack of curiosity due to over stimulation, which they responded to by citing an example of a time when they were curious while stimulated and chucked something at a vibe-coding agent to satisfy that curiosity.

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

#793

Post by r_lee »

jwpapi wrote: post #596
dreambuffer wrote: post #443

Earlier quoted context omitted.

This assumes: - that you spend no amount of time looking things up, reorganising, or otherwise getting stuck - that you have a solution to the problem ready to go at all times - that your solution is better than the LLM's solution I highly, highly doubt that all 3 of these are true. I doubt even 1 of them is true, I think you just don't know how to use LLMs in a focused way.

I use AI to look things up and I try to learn. That part is speed up, but once I know how X works I’m faster doing it myself. My assumption is that most people seeing things differently, compare their performance of not knowing how X works with Claude, but not with someone who’s really good at X. Which makes a lot of sense given LLMS are prediction generators. My take is that the best use of AI is to get you to the p…

what my experience says is that, when you get "really good" with X, then you can easily write a prompt that says exactly how it needs to be done and you'll be able to do it much faster than writing it all yourself because you know the important parts and the rest is just glue.

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

#795

Post by throwaway613746 »

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…

[dead]

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

#796

Post by skydhash »

theshrike79 wrote: post #778
stingraycharles wrote: post #712

Earlier quoted context omitted.

Custom written code can also point at those APIs and libraries without repeating it all? Or am I missing your point?

API Glue is the easy and boring part in programming. Nobody really enjoys wiring API A to API B, combining the results and using API C to push it forwards. Any semi-competent AI Agent can do that with a plan you've written in 5 minutes.

I would love to see an AI try to make sense of GTK API.

I may be wrong, but it seems when people are talking about easy glue code, they’re talking about web services API, not OS API, not graphics or sound API, not file formats libraries,…

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

#797

Post by eloisant »

erfgh wrote: post #583
ditchfieldcaleb wrote: post #495

Earlier quoted context omitted.

I agree with you on everything you said here except: > when you know how the thing works and have that mental context, you will always be faster than an AI That's just plain false, honestly. No one can type at the speed AI can code, even factoring in the time you need to spend to properly write out the spec & design rules the AI needs to follow when implementing your app/feature/whatever. And that gap will only incre…

Where does this certainty that LLMs will get more intelligent stem from?

They progressed very quickly in the past year. Not just models, but all the harness around them to code.

When they start plateauing, then we can assume they're done progressing.

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

#799

Post by strken »

Kiro wrote: post #653
Turskarama wrote: post #529

Earlier quoted context omitted.

In my experience AI can write _something_ from scratch, but often edge cases won't be handled until I go through and read the results or test it. Usually when I'm writing by hand I will naturally find the majority of edge cases as I go. By the time I've read through the results and fixed said edge cases, I usually would have been faster just doing it myself.

My experience is the opposite: AI takes too many edge cases into account and guard against even the most unlikely thing. The upside is that it often handles edge cases that I either didn't think about or was too lazy to implement. I can with full confidence say that the code AI writes is more robust and safe than if I would have done it myself. The code definitely becomes more bloated though.

My experience has been that it wraps all the obvious things, and even some obscure things, in error handling. In this sense it is safer.

It also fails to write abstractions unless they're carbon copies of a well established pattern, and when abstractions already exist, it needs babysitting to ensure it will use them appropriately. It won't introspect about its current direction unless forced to by the user or by an error, and when forced it will happily "fix" non-issues just because you pointed them out, since it's a happy little yes-man.

Because of this, code written by a good engineer is more likely to start out broken but converges towards correctness as more abstractions get built, while code written by AI duplicates abstraction layers, leaks between them, and never converges towards anything.

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

#800

Post by swsieber »

therealpygon wrote: post #757
gchamonlive wrote: post #732

Earlier quoted context omitted.

> it happened when we achieved a level of such constant stimulation (...) that we’re never bored and never engage the default mode network. I don't know... I don't disagree, but I think this has been repeated so much that I believe everyone, at least everyone that is actively participating in HN discussions is aware of this. So if we are aware of this and we consciously choose to keep engaging in dopaminergic activit…

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…

> 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 didn't see anything in parent chain that implied this. Nor did I see it "characterized as a magic eraser"; I saw it framed as something that impedes learning, and that was tied back to constant simulation.

> Or at least, aware that this argument continues to be made with tenuous evidence and anecdotes

The arguments I read and the argument you seem to be replying to seem to be different things.

Post reply on HN