News for hackers. Stuff that matters.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @08:34AM (#43470449)
I see the keynote next year; 'vibing isn't coding isn't programming isn't ...; a pyramid of shite that sometimes works a bit'. I am happy Dijkstra doesn't have to see this; he was angry in the 80s in my parents living room; I cannot even imagine what he would be with 'vibe coding'.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by frou_dh on Tuesday March 25, 2025 @08:48AM (#43470552)
"Vibe coding" seems like one of those things where there's way more people complaining about the concept than there ever were people actually promoting it in the first place.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @08:54AM (#43470608)
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ziddoap on Tuesday March 25, 2025 @09:03AM (#43470687)
Yes, there are results for people saying "vibe coding" on HN. I don't feel like reading the ~500 or so mentions of it to tally which ones are people promoting it vs. which are people complaining about it. Do you have a summary of your results?

The first page seems mostly to be people complaining.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by intuitionist on Tuesday March 25, 2025 @09:13AM (#43470794)
you know you could probably put them into some kind of language model to tally promotion vs complaints

you could probably even knock together a script to do that

in fact you might be able to get a language model to knock together such a script with a bit of iteration

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by Cthulhu_ on Tuesday March 25, 2025 @09:16AM (#43470828)
It's going to be rage bait at this point.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by api on Tuesday March 25, 2025 @09:12AM (#43470777)
> ... seems like one of those things where there's way more people complaining ... than there ever were people actually promoting it in the first place.

The entire social and political discourse since around 2016.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by alabastervlog on Tuesday March 25, 2025 @09:03AM (#43470691)
> he was angry in the 80s in my parents living room

Yikes, how bad was your parents’ living room?

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @09:06AM (#43470717)
My father was a commercial guy (and a good programmer) who wanted to sell development services to companies, Dijkstra didn't really like this idea, especially if it was done in a way that badly educated (...) people would write not proven correct code was distributed to the clients, making the world worse.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by jonnycat on Tuesday March 25, 2025 @09:11AM (#43470775)
Looking back, they were both right!
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by desdenova on Tuesday March 25, 2025 @09:12AM (#43470783)
That's exactly what ended up happening.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by eikenberry on Tuesday March 25, 2025 @01:16PM (#43473622)
> wanted to sell development services to companies

So he wanted to start a contracting service? Contractors are famous for writing piles of untested, spaghetti code that only kind of works but they've finished it by then and the contract is over. Then some poor sap gets stuck trying to maintain it. Probably one of the worse ways businesses acquire custom software.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Wednesday March 26, 2025 @02:20AM (#43479340)
It is how most software is written and indeed, often badly. But how do 'businesses acquire custom software' otherwise? Most in house employees suck as well. So what's the other ways?
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by tmpz22 on Tuesday March 25, 2025 @08:41AM (#43470498)
Vibe coding is analogous to programming while high with identical results.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by latexr on Tuesday March 25, 2025 @09:11AM (#43470769)
At least if you’re programming high (or drunk) you get a different kind of fun and the next day you know you have to recheck your work. The one thing that bothers me about LLM coding¹ is that the vast majority of people doing it don’t understand the issues. Those who do check their work and believe everyone else also does are immensely naive and will one day be severely bitten² by bad unreviewed code written by an LLM.

¹ Not calling it “vibe coding” to not go into pedantic definition discussions.

² As will we all.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ge96 on Tuesday March 25, 2025 @11:21AM (#43472421)
Funny while getting high would make me creative in the past (draw) I could not do anything hard like writing logic, I also used to think my dumb ideas were good so yeah I don't do it anymore
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by baq on Tuesday March 25, 2025 @08:50AM (#43470574)
Vape coding, maybe. Vibe coding react interfaces for backoffice tools is very real, speaking first hand.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @08:58AM (#43470645)
Is it though; what does the term mean; are we talking to our computers, not reading anything and just judging the non-coder endresult? Or are you just using it to help coding. Vibe coding would be the former and while it sometimes works, it doesn't in many cases, including LoB tools if the backoffice is large and complex enough. Unless you have some interesting tooling to help out, in which case it is possible, but that's not really vibe coding at the moment.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by Workaccount2 on Tuesday March 25, 2025 @10:14AM (#43471622)
I now have 5 "vibe coded" programs in our production chain at my non-tech company. Some have been running for over two years now.

I think what tech companies miss is that customers buy these expensive feature packed software suites and then use 3% of the functionality. Cutting edge LLM's, and especially the newer thinking ones, are incredibly talented at creating programs that offer 3% the functionality of software suites.

Just a few weeks ago we skipped out on a $1k/mo CAD package because claude wrote a program with a simple GUI that enabled our engineers to do the one task we needed the custom CAD software for (Manually creating part placement files from 90's era manufacturing files).

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Wednesday March 26, 2025 @02:24AM (#43479357)
I think throwaway programs are fine here; you make them, ship them and that's it. But i'm quite sure you didn't vibe code them; you used an LLM to write a lot of code but helped it along; vibe coders cannot do that because they don't actually understand what the LLM did. It just worked, or didn't work, so they copy back and forth errors (if there are any) until it works. Using LLMs to assist writing software, sure, we do that every day and it ships. But if we don't help the LLMs when they are stuck, they don't get unstuck. They cannot solve some surprisingly trivial things which vibe coders will be stuck with.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by baq on Tuesday March 25, 2025 @10:42AM (#43471946)
> are we talking to our computers, not reading anything and just judging the non-coder endresult?

more or less this, yes. a quick glance, maybe skimming through a tricky part. otherwise, if it works, it ships.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ramesh31 on Tuesday March 25, 2025 @09:07AM (#43470730)
>Is it though; what does the term mean; are we talking to our computers, not reading anything and just judging the non-coder endresult? Or are you just using it to help coding. Vibe coding would be the former and while it sometimes works, it doesn't in many cases, including LoB tools if the backoffice is large and complex enough. Unless you have some interesting tooling to help out, in which case it is possible, but that's not really vibe coding at the moment.

I spent 10 years of my life as an FE with a total obsession for the field, and took huge pride in my hand tuned HTML/CSS interfaces and well architected JS. I was "the UI guy" that anyone would come to with questions, as it was my expertise and what I loved to do all day.

Now I'll never write a line of that stuff ever again as long as I live.

I do not write code anymore. Everything goes through an agent. Occasionally I will flip a config value here or there, or clean up some leftover logs or whatever, but I don't type code at all anymore. My job is now to guide the agent and review its' PRs. Yet, I now easily have the productivity of an entire team from a few years ago.

You can keep your head in the sand over this stuff for a little while longer maybe, but you will be completely obsolete if you don't adapt soon.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by guappa on Tuesday March 25, 2025 @09:21AM (#43470900)
Yeah not every developer does html templates for wordpress.

Of course if your job is extremely simple and generic, AI can kinda figure it out.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ramesh31 on Tuesday March 25, 2025 @09:24AM (#43470940)
>"Yeah not every developer does html templates for wordpress. Of course if your job is extremely simple and generic, AI can kinda figure it out."

Keep telling yourself this. It's only hurting you.

I think anyone who isn't working heavily with agentic systems right now has absolutely no clue about the revolutionary things that have happened in the last six months or so. Our industry is going to be in a completely different universe this time next year.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by stickfigure on Tuesday March 25, 2025 @09:59AM (#43471400)
"Past performance does not guarantee future results"

You can't extrapolate from the last 6 months, especially with technologies this new. There's no Moore's Law of LLMs. Context windows are still tiny and the codebases that actually run our world are still huge.

This time next year I expect you're going to be disappointed.

Let me rephrase that. This time next year I expect that I will be disappointed but you will still be predicting a completely different universe... next year.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by guappa on Tuesday March 25, 2025 @09:35AM (#43471109)
> Keep telling yourself this. It's only hurting you.

I don't tell myself this. I just read your comment.

You're welcome to be hired in my team, we're hiring. Then you can sit there and ask claude or copilot and be fired when your trial period ends.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ramesh31 on Tuesday March 25, 2025 @09:38AM (#43471149)
>You're welcome to be hired in my team, we're hiring. Then you can sit there and ask claude or copilot and be fired when your trial period ends.

I see this attitude a lot. As if "uses AI" === "can't program". Keep swinging that hammer, John Henry.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by guappa on Tuesday March 25, 2025 @10:12AM (#43471585)
Reading your comment, regardless of AI I think that.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by mattmanser on Tuesday March 25, 2025 @10:46AM (#43471990)
You're obviously getting a lot of pushback, do you think people here haven't used these tools?

Yes it's great at React/Frontend. Because that is mainly boilerplate. Hooking up click handlers and validators and submit buttons and fetch calls is boilerplate. It's just busy work. There can be complicated FE work, like making something like google maps, but how many of us ever need to do that? Most of the time if you did need to do something complicated, you get a library to do it ALL for you. Charts, maps, etc.

If you've worked on more niche languages/tools/problems you start seeing behind the curtain. The trick. It's essentially just copying someone else's code and replacing the variables. I've inherited some robot framework tests. I tried it to fix a problem, the code it spat out (v1) was nonsense. I told it. It spat out some different code, v2. It's still wrong. It then spat out v1 again! It seemed to only have these two "templates" to use. No matter how I framed the questions, v1, v2, v1, v2, v1, v2. They didn't even compile.

Hence why it's great at React, there are millions of examples for it to combine and refine.

I'd love AI to take away a lot of boring coding. But in my honest experience anything much longer than 100/200 lines and the AI starts screwing it up. It can't work on a full codebase. It even does incredibly irritating things like remove code that's needed, forgetting code changes it's already made, and worse still deleting code updates or fixes you've made.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @09:34AM (#43471101)
... next year

Maybe... Why are you so sure? It's incredible what these models do but now it's all incremental and it's pretty clear LLMs are as bad at complexity as humans. If a system is of a realistic size of a business system, the llm will fuck up things mostly all the time unless you are a good coder with patience. It saves a lot of time, but it saves a lot of time of stuff that is 'just typing'; that is more than many programmers in this world can claim, but that's really another case. You are not doing anything that requires anything more than hello world context, because LLMs now really break down there.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by tom_ on Tuesday March 25, 2025 @10:07AM (#43471523)
I remember hearing this about self driving cars.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Wednesday March 26, 2025 @02:58AM (#43479533)
Don't worry; Elon says it's coming end of the year.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by pphysch on Tuesday March 25, 2025 @10:32AM (#43471821)
The large models are as good as their data, and there's a lot of data for common technologies and tasks, i.e. web stuff.

Step out of that bubble, though, and it's a different world.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @09:10AM (#43470758)
I am aware, I just don't see this. I too write a lot of code like this, but the LLMs cannot figure out many things. If you are on that track, it will sometimes just loop forever. But sure, most humans are pretty bad too so many fail at the same things the llms do and then the llms are a lot cheaper.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by whatamidoingyo on Tuesday March 25, 2025 @09:20AM (#43470889)
Most of the time, yes. But there are certain times where I prompt an AI to build X, and it delivers a seriously neat project. It's not all of the time, though.

It has only happened like twice where I saw the full power of LLMs. I don't understand it. It's like there's a switch to dumb these things down, but if you catch them at the right time, they will blow your mind. But yes, most times, they are horrible.

Or maybe I'm just crazy, i dunno.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by guappa on Tuesday March 25, 2025 @09:22AM (#43470907)
I think he writes HTML pages and some JS occasionally.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by confooseddd on Tuesday March 25, 2025 @09:49AM (#43471281)
Frontend is a low bar for anyone and is the exact job which will be wiped out by AI. You are trapped in your own skillset prison that you don't understand what more complex engineering looks like.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by zmgsabst on Tuesday March 25, 2025 @09:25AM (#43470967)
My experience is that around 200-300 lines, the LLM is no longer able to understand the context of its own work. At that point, it also usually contains a significant mistake.

And around that scale, you’ll get much better code if you refactor it yourself and clean up its logic (which tends to be verbose, at best).

Someday, it will be better; today, none of them (Grok, ChatGPT, Claude) are good enough for what you describe.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ramesh31 on Tuesday March 25, 2025 @09:31AM (#43471049)
>Someday, it will be better; today, none of them (Grok, ChatGPT, Claude) are good enough for what you describe.

You're living in 2023. Try Cline with Sonnet 3.7.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by stickfigure on Tuesday March 25, 2025 @10:12AM (#43471593)
How big is your project (LOC)? How big are your individual source files? What language(s)?
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by smusamashah on Tuesday March 25, 2025 @09:04AM (#43470697)
What exactly was he angry at?
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @09:11AM (#43470773)
People writing software without proper foundations of logic and proofs. Which was by then quite 'common' (now it's normal of course).
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by miroljub on Tuesday March 25, 2025 @09:18AM (#43470857)
> a pyramid of shite

Why do some people use such abominations like "shite" or "shoot" instead of just using "shit"? C'mon lads, everyone knows what you want to say, why not just say it?

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by JimDabell on Tuesday March 25, 2025 @09:28AM (#43470998)
“Shite” isn’t a minced oath. It’s a different word to “shit” with a different etymology. Same as “feck” is a different word to “fuck”, even if they are used in the same way.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by umanwizard on Tuesday March 25, 2025 @01:43PM (#43473920)
That’s not true at least according to etymonline. Got a source?
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by ChrisRR on Tuesday March 25, 2025 @10:53AM (#43472096)
Shite is a perfectly normal use in the UK, especially in Scotland. It has a slightly different effect to shit
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by anonzzzies on Tuesday March 25, 2025 @09:21AM (#43470904)
Some people don't live in the US woooow... In the UK and especially certain parts, shite is the actual word to use. Shite is definitely not the same as gosh or shoot. It's (more) vulgar as shit but our own.

I personally also don't like gosh or shoot as we all know what you mean, but this is not that case, look it up.

Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by osigurdson on Tuesday March 25, 2025 @09:20AM (#43470885)
People can use whatever word they want.
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by bena on Tuesday March 25, 2025 @09:24AM (#43470939)
I'd imagine he's British. "Shite" seems to be the spelling favored by the British. Much like arse/ass
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by voidUpdate on Tuesday March 25, 2025 @10:18AM (#43471672)
We use both, in different circumstances
Re:Closing Keynote with Leslie Lamport at Scale 22x: Coding ... by dpassens on Tuesday March 25, 2025 @09:23AM (#43470924)
Shite isn't a euphemism like shoot, it's a synonym of shit.