Live data from Hacker News

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

simonwillison.net

781–790 of 958 posts

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

#781
post #769

Earlier quoted context omitted.

You are probably talking about people who just crunch out some half baked solutions for the sake of getting somewhere. But there are other nerds who care, just not about the code quality, but about conversion, testing out business ideas quickly, getting to know their customers better. There are nerds who care about business strategy. There are nerds who care about accounting principles and clean financial reporting.…

This resonates with me. I'm a Mechanical Engineer who loves the process of coding. I did take an intro to business class in undergraduate though, and my professor said one thing that has stuck with me for 30+ years - 'The fundamental goal of a business is to make profit now and in the future'. Vibe coded slop might get some traction and make money now, but high quality code will reduce technical debt and allow it to…

But also time to market matters.

While Company A is building their product in perfect hand-coded Rust with zero defects, Company B is on their third iteration of vibe'd "slop" and getting actual customer feedback - which helps them iterate further.

It's mostly a matter whether Company B is smart enough to refactor the code to a stabler and more maintainable form or do they run headlong into a vibeslop wall.

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

#782
post #707

Earlier quoted context omitted.

> Also, when did we stop liking to learn? I suspect it happened when we achieved a level of such constant stimulation (there is a pocket computer always on us with infinite effortless distraction) that we’re never bored and never engage the default mode network. https://en.wikipedia.org/wiki/Default_mode_network https://www.youtube.com/watch?v=orQKfIXMiA8 When you’re bored, your mind goes to places it wouldn’t otherw…

> 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.

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

#783
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.

Your category of "nerds who care" is actually "nerds who only want to be coders" and not "nerds who care about solving problems".

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

#784

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…

Can AI make developers lazy in new ways? Of course! Why wouldn’t it? I don’t write things in ASM because I can be “lazy” and write 50x more useful instructions with a few lines of a modern language. I doubt I’d be able to write working ASM anymore without a serious refresher. Did newer languages erase my memory of ASM and make me “lazy”, or did my efforts evolve to make use of the newest technology regardless of “lost” skills?

I would argue that's a misuse of AI. If the point of an engineer is to know how things work behind a piece of software, then shipping code without an understanding how it all works is a failure.

You wouldn't trust an engineer a bridge that an engineer vibe-engineered would you?

So instead of focusing on AI as a productivity tool, focus on AI as a means of adding rigor and understanding to your workflow.

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

#785
post #591

Earlier quoted context omitted.

bro is probably using a local LLM at 2 tokens/sec

Ad hominem

Extremely relevant as that’s the only way it would make sense that your experience with agentic coding is still so slow and so poor

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

#786
post #707
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…

> Also, when did we stop liking to learn? I suspect it happened when we achieved a level of such constant stimulation (there is a pocket computer always on us with infinite effortless distraction) that we’re never bored and never engage the default mode network. https://en.wikipedia.org/wiki/Default_mode_network https://www.youtube.com/watch?v=orQKfIXMiA8 When you’re bored, your mind goes to places it wouldn’t otherw…

We also stopped learning when someone had the idea to put unrealistic deadlines in projects and tackling tech debt has been denied and the most hated activity from management.

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

#787
post #759

Earlier quoted context omitted.

> 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. I promise you that is incorrect. People who actively participate on HN are a group more diverse than is often given credit, and I strongly believe there is nothing “everyone knows” here. https://xkcd.com/1053/ Just nine days ago, someone on HN was vaguely aware of the…

Fair enough. It's always tricky to generalize like this, so I wont defend that position. However, for those who know, I don't think this is blaming the victim. I think victim blaming is a form of debate simplification in this case, just like "this is life" or "shit happens". Sure there are billions of dollars invested in attention stealing mechanisms, just as there are billions of dollars invested in gambling sites,…

We do all what we can as individuals, but it's not enough. The obesity crisis is going unabated except GLP-1 drugs to clean up the mess.

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

#788

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…

> successfully adopting agentic engineering practices What's your definition of "successfully"? More LOC committed per day is probably the only one that's guaranteed when you let spicy autocomplete take the wheel. I don't think it's at all possible to reason about the other more meaningful metrics in software development, because we simply don't have the context of what each human is working on, and as with the WYSIW…

If you are on the right team with the right professionals you can measure. when we first started using LLMs we decided to run the same process as if they did not exist, same sprint planning meetings, same estimation. we did this for 6 months and saw roughly 55% increase in output compared to pre-LLM usage. there are biases in what were tried to achieve, it is not easy to estimate something will take XX hours when you know some portion (for example writing documentation or portions of the test coverage) you won’t have to write but we did our best. after we convinced ourselves of productivity gains we stopped doing this. saying you can’t measure something is typical SWE BS like “we can’t estimate” and the other lies we were able to convince everyone off successfully

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

#789
post #622

Earlier quoted context omitted.

I care about solving problems for and delivering value to my users. The software is simply a means to that end. It needs to work well, but that does not mean every line of code requires an artisanal touch and high attention to detail.

I think there's some ambiguity in the discussion around what people mean when they say "good code". Good code for a business is robust code, that's functionally correct, efficient where it needs to be and does not cost too much. I believe most developers who care about good code are trying to articulate this, they care about a strong system that delivers well, which comes from good architecture. LLMs actually deliver…

But the trick is that if / when you can define "good code" in a deterministic manner, then the LLM can also deliver "good code".

But if it's just based on feels, then of course it can't do it because it's not a mind reading machine.

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

#790

Earlier quoted context omitted.

It's about responsibility. If I get pwned because my AI agent wrote code that had a security vulnerability, none of my users are going to accept the excuse that I used AI and it's a brave new world. I will get the blame, not Anthropic or OpenAI or Google but me. The same goes for if my AI generated code leads to data loss, or downtime, or if uses too many resources, or it doesn't scale, or it gives out error messages…

On the other hand, I don’t need to review carefully every line of code in my thumbnail generator and associated UI. My nonexistent backend isn’t going to be pwned if there is a bug in the thumbnail generation. After the QA testing on my device, a quick scroll through of the code is enough. Maybe prompt „are errors during thumbnail generation caught to prevent app crashes?“ if we‘re feeling extra cautious today. And j…

I assume you're talking about a local application? You don't care if a malicious image you downloaded pwns your PC then? Like CVE-2016-3714
Post reply on HN