Live data from Hacker News

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

simonwillison.net

581–590 of 958 posts

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

#581

Earlier quoted context omitted.

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.

It goes for all professions really, people who do it for work and people who care. Apply to any profession, plumbers, doctors, carpenters, cleaners, etc etc. Most of us have experienced both types and I haven’t heard of anyone preferring the ”do it for work” over the ones who care. And like those other professions, in software we accept the worse of the two because finding people who care is both time consuming and o…

>in software we accept the worse of the two

and the whole world suffers for it.

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

#582

Earlier quoted context omitted.

You can direct LLMs to do test-driven development, though. Write several tests, then make sure the code matches it. And also make sure the agent organizes the code correctly.

The LLM obliges and writes a lot of useless tests. I have asked devs to delete several tests in the last day alone.

Well, yeah, you don't just make it bang out a bunch of useless code without monitoring it.

You instruct it to write the code you want to be written. You still have to know how to develop, it just makes you faster.

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

#583
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…

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?

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

#584

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…

Yeah it’s when you go off the happy path that it gets difficult. Like there’s a weird behaviour in your vibe-coded app that you don’t quite know how to describe succinctly and you end up in some back-and-forth.

But man AI is phenomenal for getting stuff out of your head and working quick.

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

#585
post #497
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…

This may have been a problem a year or two ago but any premium model will be exploring the codebase to check similar routes to answer all these questions, if you don't specify them.

Exactly. As long as the codebase is consistently following some given patterns, LLMs nowadays stick to it.

Understanding that limiting number of “design patterns” in a codebase made it better (easier to code and understand) was a good proxy for seniority before LLMs.

Now it’s even better: if all of a sudden “unusual code” is in a PR, either the person opening the PR or the one reviewing it has lost touch with the codebase. Very important signal, since you don’t want that to happen with code you care about.

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

#586
> The entire software development lifecycle was, it turns out, designed around the idea that it takes a day to produce a few hundred lines of code. And now it doesn’t.

No, it was never designed around that. All methodologies of software dev don't focus too much on writing the code, but on everything else: requirement definition, quality, maintenance, speed of integrating feature, scaling the work, ...

Personally with 20 years of experience, I never seen a single company were writing the code was a bottleneck

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

#587

Have you noticed that the coding agents get really close to the solution on the first one shot and then require tons of work to get that last 10% or 5%? If we shift the paradigm of how we approach a coding problem, the coding agents can close that gap. Ten years ago every 10 or 15 minutes I would stop coding and start refactoring, testing, and analyzing making sure everything is perfect before proceeding because a bu…

I can go long session with it making great code.

But the first time I say “No, it should be …” it’s nearly game over. If you say it 3+ times in a row, you’re basically doomed.

Sure, you can get it to fix the bug, but it comes at the cost of future prompts often barely working.

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

#588

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…

That's the failure to automate. The AI isn't telepathic, so agentic engineers not automating this stuff is skipping out on the engineering part.

You setup the environment and then you do the work. Unless you are switching employers every week, you invest in writing that stuff down so the generation is right-ish and generate validation tooling so it auto-detects the mistakes and self-repairs.

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

#589
The gap between "vibe coding" and "agentic engineering" is the same gap between asking someone to do a task and being able to prove they did it correctly. One is vibes. The other is accountability. We keep building more powerful agents without building the audit infrastructure to verify what they actually did.

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

#590

Earlier quoted context omitted.

> 2000 lines is 10x more time consuming to review than 200 Very far from the truth in practice, every line of code isn't as difficult/easy to review as the other.

But why would the lines in the 2000 case be easier to review per line?

Which of these programs is easier to review

  {x{x,sum -2#x}/0 1}
or

  def f(n):
      if n 
They're both the same program
Post reply on HN