Live data from Hacker News

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

simonwillison.net

561–570 of 958 posts

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

#561
post #538

Earlier quoted context omitted.

I don’t think it’s going to burst like how other people expect. The technology is already out there, when it loses steam people aren’t suddenly going to stop using it. I predit it’ll be more like the dot come crash where companies that can survive the downturn come out dominant.

It ends like this: all codebases become unmaintainable spaghetti after agentic AI spends years on it. Then after every agent in existence will spend minimum 24 hours reading the codebase to add a simple feature, the software is abandoned.

I believe most codebases were "unmaintainable spaghetti" even before LLMs: depends on how you define it though.

To be, it means expensive to evolve.

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

#562
post #389

Earlier quoted context omitted.

This is very true, I've found these tools that I am highly encouraged to use very hit and miss, which they are by nature. After using Matt Pocock's skills, I've come around to the idea that LLM's main utility is to act as the ultimate rubber ducky. The `grill-me` feature is honestly the most useful, not for guiding the follow up writing of code, but to make me write down and explore the idea I have more quickly. It's…

The first time i used LLMs it was to try and refactor behind a solid body of tests i trusted. I figure if it cant code when it has all of the necessary context available and when obscure failures are easily detected then why would i trust it when building features and fixing bugs? It never did get good enough at refactoring.

I agree, the mechanical refactoring of modern IDE tooling, especially with typed languages is so much faster and safer, it's not even close. These tools can be useful for sure, but I think in general they are being wayy over prescribed to different tasks.

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

#563
post #396

Earlier quoted context omitted.

> If I know the answer to all these questions, wiring it together takes me LESS time than passing it to Claude Code How so?

Like writing code to me is not slower than writing text? When I write code every character I type in my computer has less ambiguity than when I write it in human language? I also have the help of LSPs, Linters and Auto-completes.

You're still typing? I don't know how fast you can type, but I can speak way faster than I can type. Somewhere in the neighborhood of 300 wpm. Speech-to-text is pretty good now, and prompting an AI means I'm not trying to speak curly brace semicolon new line.

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

#564
The more I use AI, the more I find it’s great for anything trivial and uninspired. Need help with some predictable glue code? AI. Need help with something insightful and new to the world? Not AI. Need help with an important task that’s been done a 1000 times? AI with scrutiny. Need to invent something new to the world and core to your business? Probably not AI.

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

#565

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…

Some of us do actually have intimate knowledge in certain areas where guidance of an AI takes longer than doing it yourself. It's not about typing speed, it's that when you know something really really well the solution/code is already known to you or the very act of thinking about the problem makes the solution known to you in full. When that happens it's less text to write that solution than it is to write a suffic…

Care to explain which particular intimate knowledge allowed you in the last 6-9 months to be faster than AI in certain area?

Honestly, I'm still faster than AI cooking scrambled eggs, but definitely not faster than neither AI (or compiler) in translating stuff into code.

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

#566
post #560
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!

It turns out an awful lot of precision (plenty for many things) lives in library and web APIs, documentation, header files and dependency manifests. Language can literally just point at it without repeating it all. Avoidance of mistake through elimination of manual copying in things like actuarial and ballistics tables was what the original computers were built for.

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

#567
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…

Except those are the same people that will decide who is getting hired, and who gets layoff because of increasing productivity.

And no, this isn't playing what ifs.

I have seen it happening with offshoring, migration to cloud, serverless, SaaS and iPaaS products, and now AI powered automations via agents.

Less devops people, less backend devs , no translation team, no asset creation team,...

I have been layoff a few times, having to do competence transfer to offshoring teams, the quality of the output is something c suites don't care all.

Do you wanna bet what is behind Microslop, Apple Tahoe bugs and so forth?

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

#568
post #565

Earlier quoted context omitted.

Some of us do actually have intimate knowledge in certain areas where guidance of an AI takes longer than doing it yourself. It's not about typing speed, it's that when you know something really really well the solution/code is already known to you or the very act of thinking about the problem makes the solution known to you in full. When that happens it's less text to write that solution than it is to write a suffic…

Care to explain which particular intimate knowledge allowed you in the last 6-9 months to be faster than AI in certain area? Honestly, I'm still faster than AI cooking scrambled eggs, but definitely not faster than neither AI (or compiler) in translating stuff into code.

Not the parent but I've had this happen when debugging for sure. Sometimes I ask Claude Code to help me debug something and it makes a wrong assumption and just churns in circles burning tokens. While it's doing that I realize the problem and fix it.

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

#569

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…

You seem to have missed OP's point: some things are only encoded in our brains when you are sufficiently experienced. Translating that into code can happen directly by you, or into prompt iterations that need to result in the same/similar coded representation. In other words, when it matters how something works and it is full of intricate details, you do not need to specify it, you just do it (eg. as an example which…

I think there's a level above that where the words to describe such structure are familiar and readily available and hey guess what? The model understands those too. Just about every pattern has a name. Or a shape. Or an analog or metaphor in other languages or codebases. All work as descriptors.

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

#570

Earlier quoted context omitted.

> 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…

This. There is definitely a ratio. A year ago, it was 50/50. It felt better because the hard things it did fast while I sipped coffee outweighed in my mind the negatives.

Now that ratio is swinging way over towards the LLMs favor.

Post reply on HN