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

471–480 of 958 posts

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

#471

Post by jmilloy »

sumeno wrote: post #438
jmilloy wrote: post #418

Earlier quoted context omitted.

I think most people are finding the opposite. Claude Code is not only reducing how many projects get abandoned, it's also resurrecting projects from the graveyard.

The number of Show HNs recently that have a days worth of commits and are never touched again disagrees. It's creating a lot of projects that are immediately abandoned

There is a difference between a project that is eventually abandoned out of annoyance because you couldn't accomplish what you wanted and a project that gets a day or two of attention and then gets aborted because you figured out it wasn't worth it or got interested in something else. I think the parent comment is talking about the former and I'm responding to that, while you're talking about the latter.

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

#473

Post by Xeronate »

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…

When I started spending 40-60 hours a week programming and wanted to spend my remaining time doing other things.

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

#474

Post by cindyllm »

ytoawwhra92 wrote: post #423
GistNoesis wrote: post #157

The real paradigm shift is not here yet, but not very far away. I'm talking about the single unified codebase. Agents building a unique codebase for all your software needs. Because most of the complexity in software comes from interfacing with external components, when you don't need to adapt to this you can write simpler and better code. Rather than relying on an external library, you just write your own and have f…

> Standardize data and services and you don't need that much software. We've known this since close to the advent of computing and yet every generation of has taken us further away from this goal. Largely driven by jealous resource-guarding, particularly when it comes to data. Why don't I have a generic media player app that can stream Netflix, Disney, Hulu, etc? Those brands want control over my experience. They wil…

[dead]

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

#475

Post by jesterson »

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…

> Why is it a bad thing to know all the ins and outs of a programming language? To write and make all the decisions yourself? That shit is fun.

It's not just fun (i agree it is), but it is also essential for creation.

What we have done with the 'AI' is to create a lot of ignorant morons who think they can create a lot of things without knowledge. This is not gonna end well.

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

#476

Post by brentcrude »

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

#477

Post by kelnos »

Yup, the normalization of deviance here is a real thing. I still review all the code the LLM generates (well, really, I have it generate very little code: I use it more for planning, design, rubber-ducking, and helping track down the causes of bugs), but as time goes on without obvious errors, it gets more and more tempting to assume the code is going to be fine, and not look at it too closely.

But resisting that impulse is just another part of being a professional. If your standards involve a certain level of test coverage, but your tests haven't flagged any issues in a long time, you might be tempted to write fewer tests as you continue to write more code. Being a professional means not giving in to that temptation. Keep to your quality standards.

Sure, standards are ultimately somewhat arbitrary, and experience can and should cause you to re-evaluate your standards sometimes to see if they need tweaking. But that should be done dispassionately, not in the middle of rushing to complete a task.

And hell, maybe someday the agents will get so good that our standards suggest that vibe coding is ok, and should be the norm. But you're still the one who's going to be responsible when something breaks.

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

#478

Post by xmprt »

apsurd wrote: post #451
xmprt wrote: post #431

Earlier quoted context omitted.

I'll go in the other direction and say that if you're spending a lot of your time learning to prompt better then you're wasting it because LLMs are only going to get better at understanding your intent regardless of "prompt engineering". The JSON API example to wire up a database can be one-shot pretty easily by the latest models without much context and without setting up any harness. The more time you spend perfect…

but then how can the parent comment land? "you're just not prompting right"

I don't think it does. If I had to guess, the top comment was using an older version of AI or a local model which wouldn't be able to solve the JSON API task. A lot of AI skepticism comes from people who used it once a while back and decided not to keep up with the latest developments. If I only had experience with gpt-3.5 then I'd also assume what the original commenter said.

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

#479

Post by majormajor »

eddieroger wrote: post #416
jwpapi wrote: post #373

> I know full well that if you ask Claude Code to build a JSON API endpoint that runs a SQL query and outputs the results as JSON, it’s just going to do it right. It’s not going to mess that up. You have it add automated tests, you have it add documentation, you know it’s going to be good. I feel like this is just not true. An JSON API endpoint also needs several decisions made. - How should the endpoint be named - W…

> If I know the answer to all these questions, wiring it together takes me LESS time than passing it to Claude Code. That's just not true, and if it is in your case, then you're not great at writing prompts yet. > Take the todo_items table in Postgres and build a Micronaut API based around it. The base URL should be /v1/todo_items. You can connect to Postgres with pguser:pgpass@1.2.3.4 That's about all it takes these…

Every day I do something where the llm writes it ten times faster than I would with twice the test coverage.

And every day I do something else where the LLM output is off enough that I end up spending the same amount of time on it as if I'd done it by hand. It wrote a nice race condition bug in a race I was trying to fix today, but it was pretty easy for me to spot at least.

And once a week or so I ask for something really ambitious that would save days or even weeks, but 90% of the time it's half-baked or goes in weird directions early and would leave the codebase a mess in a way that would make future changes trickier. These generally suggest that I don't understand the problem well enough yet.

But the interesting things are:

1) many of the things it saves 90% of the time on are saving 5+ hours

2) many of the things I have to rework only cost me 2+ hours

3) even the things that I throw away make it way faster to discover that 'oh, we don't understand this problem well enough yet to make the right decisions here yet' conclusion that it would be just starting out on that project without assistance

so I'm generally coming out well ahead.

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

#480

Post by AndrewKemendo »

BoorishBears wrote: post #405
AndrewKemendo wrote: post #344

Earlier quoted context omitted.

Some of my favorite peer engineers work exactly like that People used to like them and they used to be legends (even if not everyone liked them) Notch, Woz, Linus and Geohot come to mind The Metasploit creator Dean McNamee worked for me and he was just like that and a total monster at engineering hard tech products

No they don't because they have brains. I have no strong idea why people can't accept that intelligence formed separately of a human brain can truly be alien: not in the hyperbolic sense of "that person is so unique it's like they're a different species", but "that thing does not have a brain, so it can have intelligence that is not human-like". A human without a brain would die. An LLM doesn't have a brain and can d…

I think these are reasonable questions but it assumes that everything is actually a black box instead of being treated as such.

Despite what the headlines say, these systems aren’t inscrutable.

We know how these things work and can build around and within and change parameters and activation functions etc…and actually use experience and science and guidance.

However those are not technical problems those are organizational social and quite frankly resource allocation problems.

Post reply on HN