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

541–550 of 958 posts

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

#541

Post by Daishiman »

eli wrote: post #514
allthetime wrote: post #490

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.

A much more charitable framing: people who enjoy the process vs people who enjoy the result. (Though, granted, the results are a lot better if you craft it by hand)

I am not really sure. I wrote some scripts that aggregated data from several APIs with an LLM and the LLM had the foresight to create a caching layer for the API responses as it properly inferred that I would need the results over and over again as well as using asyncio to accelerate fetch speed. This would have been a v2 or v3 and it one-shotted it perfectly.

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

#542

Post by Daishiman »

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 care a lot about software and I use LLMs extensively. There are some things I deeply understand yet I don't care for doing anymore because I've done them for years and there's nothing to be gained from doing them manually.

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

#543

Post by okdood64 »

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 take software engineering and production reliability very seriously. But coding is just a small part of my job. It's not really the meat and potatoes. I'll vibe code (responsibility) where I can.

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

#544

Post by imrozim »

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…

100% aggred, i learn coding by building stuff and breaking it when you let ai do everything you skip that pain and also skip the understanding.

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

#545

Post by ori_b »

sothatsit wrote: post #487
ori_b wrote: post #357

Earlier quoted context omitted.

It's deeper. We used to mock architects that stepped back and stopped coding, because they generated trash. There's a cycle that is needed for good system design. Start with a problem and an approach, and write some code. As you write the code, you reify the design and flesh out the edge cases, learning where you got the details wrong. As you learn the details, you go back to the drawing board and shuffle the puzzle…

You don’t need to write code by hand to learn from iterations and experiments. I run more experiments and try out more different solutions than I ever could before, and that leads to better decisions. I still read all the code that gets shipped, and don’t want to give that up, but the idea that all craft and learning is lost when you don’t is a bit silly. The craft/learning just moves.

How much calculus do you think you could pick up skimming a textbook without doing exercises?

We mocked these "architects" from experience. We knew that if you weren't feeling the friction yourself, you wouldn't learn enough to do good design.

Maybe you don't care about engineering great systems. Most companies don't. It's good for profit. This isn't new, though AI enables less care.

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

#546

Post by ofrzeta »

"I want professionally managed software companies to use AI coding assistance to make more/better/cheaper software products that they sell to me for money.” (Simon Willison herein quotes Matthew Yglesias) - this is such a naive and sloppy take. What do you want? "better software"? not going to happen. "cheaper software"? not going to happen either. "more software"? for sure, but is it really what you want?

If I hire a plumber it's certainly not cheaper than doing it myself but when I am paying money I want to make sure it is better quality than what I am vibe plumbing myself.

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

#547

Post by charcircuit »

ditchfieldcaleb wrote: post #495
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…

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…

>No one can type at the speed AI can code

You can definitely be faster than frontier models. The number of tokens per second is not that high and they require a lot of tokens for thinking and navigating things.

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

#548

Post by lmeyerov »

notnullorvoid wrote: post #528
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…

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…

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 to leverage that properly.

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

#549

Post by Daishiman »

gck1 wrote: post #359
mleo wrote: post #332

Earlier quoted context omitted.

I can’t understand this. The first thing I do with new agent driven project is set up quality checks. Linters, test frameworks, static analysis, etc… Whatever I would expect a developer to do, I would expect an agent to do. All implementation has to go through build success and mixed agent reviews before moving on. I might not do this with initial research/throwaway prototype, but once I know what direction to go and…

> The first thing I do with new agent driven project is set up quality checks. Linters, test frameworks, static analysis, etc I do this too, but then I sit and observe how agent gets very creative by going around all of these layers just to get to the finish line faster. Say, for example, if I needlessly pass a mutable reference and the linter screams at me, I know it's either linter is wrong in this case, or I shoul…

> Same story with tests. Who decides when it's the test that should be changed/deleted or the implementation?

Claude is remarkably good at figuring this is out. I asked it to look at a failing test in a large and messy Python codebase. It found the root cause and then asked whether the failure was either a regression or an insufficiently specified test, performed its own investigation, and found that the test harness was missing mocks that were exposed by the bug fix.

It has become amazingly good at investigating.

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

#550

Post by rgbrenner »

jmalicki wrote: post #434
rgbrenner wrote: post #387

Earlier quoted context omitted.

ok "series of context windows spread across many agents".. sure much clearer. Doesn't change my point: the amount of code the agent can operate on is very large, if not unlimited, as long as you put even a little bit of thought into structuring things so it can be divided along a boundary. If you let the codebase degrade into spaghetti, then the LLM is going to have the same problem any engineer would have with that.…

Context windows don't necessarily cleanly divide. Getting each agent to be able to task within a context window is a hard problem. It's like like if your context window with one agent is n, your context window with 10 agents is n/10. It is some skill, but that is also where a lot of the advances are coming in.

300k tokens--the useable context window of a single agent--is about 40k lines of code and you can't figure out a natural breakpoint within that code to divide up the task?
Post reply on HN