Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- I remember how just 5 years ago the majority of speakers were saying how absolutely everyone should learn computer programming. Already many years ago VBA was built to bridge the gap between engineers and other professions. Well, the gap is completely closed now, everyone can do what has been talked about for decades: programming computers. And I suspect even markdown will become obsolete very soon, eliminating this very last remnant of what programming used to be.by aledem
- Maybe it's a good idea for SWEs to consider using LLMs to train themselves into new careers -- just in case.
Most other "knowledge" professions -- by which I mean teaching, programming, some engineering, and the arts -- are even further along into obsolescence. That said, you can still use the knowledge gained in a knowledge profession to convert into a more hands-on profession. We might have a bit longer before humanoid robots destroy all hands-on job opportunities as well. Once that happens, every person will be equally poor and destitute.
by ogogmad - Enjoyable article. I've had the same feeling about native software becoming more accessible with the help of llms. However, I tried the app and opened a large-ish markdown file and immediately had scroll hangs and then the app crashed. Making a small proof of concept is easy, but performance and reliability are still hard.
edit: typo
by kettlez - "the terminal itself, which is almost always monospaced and thus fatiguing to read"
It is? Why? I read monospaced text all day long. I don't find it fatiguing in the least. In fact, I think I might prefer it to non-monospaced text.
by bananamogul - I know the article is mostly about making stand-alone software, but this type of thing is why one of the things I value most when looking workflow tools I will be using heavily is extensibility. I can try put someone's neovim plugin for a second, figure out if it's something I actually need, and if so make my own personal version that matches my mental model perfectly, adds all the dumb little bells I want, and removes all the useful features I don't personally care about. Plus I no longer need to worry nearly as much about supply chain issues.
Over the years I've replaced 90% of the plugins I used when I started. Plus I get a nice outlet from any pesky NIH symptoms.
by simoesd - I'm the same.
In all honesty, when you start up emacs for the first time with a blank config, it looks terrible. But then you start building it up with plugins and adding code to support your own quirky workflows and slowly it becomes too powerful in your life to ignore. I have not been able to drop it for 13 straight years. With AI taking over the development experience, emacs and neovim have only become even better, because now you can get AI to bake your custom workflows into the config for you.
Emacs/neovim should be the gold standard for all workflow tools.
by disinterred - This article hints at what I feel is one of the not-yet-realized transformations that LLM coding brings: can we finally drop Electron/React Native and just have LLMs automate the work of transforming Figma/wireframes and behavior specs into truly native apps for each platform?
For CRUD apps, the API spec and UI mockups -- or even a photo of how it looks on the already coded platform -- would go a long way. That's exactly the kind of well defined task work LLMs do well with. It should be possible to automate a lot of the equivalence testing too.
Is there still an excuse for "maybe we'll add Android someday" or "not enough Mac/Linux users"? And is there still a justification for not building those less-used flows like password reset into the iOS app instead of throwing up random WebViews?
For those apps that do have non-trivial logic on device, LLMs have shown a lot of promise at rewriting to cross-compiling-is-easy languages like Go or Rust.
- Yes. You can do that. It works right now. It works really well.
My original spicy take is: why learn SwiftUI at all at this point? It's a skill that, for most tasks, falls into the same kind of bucket as "learning Microsoft Word really, really well". I appreciate people who take the time to do that, but the outcomes are within millimeters of each other whether or not we do that.
I don't think that's true of programming generally. But I think there are languages now where the rationale in specializing in them has gotten, hrm, more complicated.
by tptacek - I feel as though the author really missed an opportunity here: "The Emacsulation of Software"
- Your Emacs (or my VIM) config was simple text file, that you can open in a simple text editor, and customize it as needed, and you know where is what. My VIM config is 20 year old. A year or 2 ago, I just dumped the manual package management, and started using a plugin manager.
There are no gatekeepers, no dependencies!
This, require you to have pay $20-$200 to a 3rd party corporation, or have a kind of beefy GPU (to run locally), run some instructions on text file, keep editing till it might does what you intend it to.
You are knowingly adding a dependency, which probably will become a hard dependency when everything goes jumbled up for human reviews, either on a beefy GPU or sending your data to a shareholder pleasing corporation.
Let's distinguish, how these are not the same, and the real price we pay
by t_mahmood - You mean no gatekeepers besides whatever the people who build the UI applications decide the limits should be.by tptacek
- "Personal Software" i.e. programs that one writes for oneself, was the original vision of home computing back in the 1960s. The PC wasn't really anticipated, but the thought was that everyone would have a computer terminal at home, and write programs to do whatever was needed. It was imagined that programming would become easy enough that anyone could learn to do it. We're not there yet but with LLMs we're getting closer.by SoftTalker
- It’s exactly what I use LLMs for as a non-computer professional.by lobf
- That's going to be huge thing in the future I think
Everyone having their own hyperspecific apps or even different UIs/visualization in the same app
The whole idea of an application becomes a much more fluid thing
If your app is built with a dynamic language why not let users re-write the code themself and add whole new features
by ex-aws-dude - My fears with the situation you are describing is that we end up without a common file format, if everyone has a propietary app and/or file system then that makes transition or collaboration a pain.
We probably won't end there due to how lazy most of us are, but it's certainly something to consider
- LLMs are great for problem exploration. Especially with the decline of Google I think we're at a point where it's less difficult to get an LLM to spit out something that'll accomplish a task sorta compared to actually finding that on the internet. But if the task is going to be repeated or modified then I think LLMs are at a permanent disadvantage to prebuilt software. Even if that prebuilt software is just someone else running an LLM and then passing the output through acceptance testing most people just don't want the headache of debugging weird edge cases and the novelty of "I'm a developer too!" wears off pretty quickly.
I'm excited that the weird grey-zone of excel sheets with business critical logic is likely going to disappear as LLMs slowly make the logic driving those too complex to be comprehended and managed and those get foisted off onto actual engineering resources. It'll be painful but probably for the best... but for actual tools people need to use day-to-day I think the assurance that the tool will work has a lot more value than the AI hype has comprehended.
by munk-a - > We're not there yet but with LLMs we're getting closer.
I feel I'm there. Whenever I have a problem I definitely ask "should I vibe code an app for that?"
My current Swift app has 15K LoC (5K in tests, 10K implementation) and it is finished. Like, there are minor improvements now, but it does what it needs to do. It took me 20 hours. I think the actual thing would personally take me 500 hours as I haven't programmed in Swift.
by mettamage - > It was imagined that programming would become easy enough that anyone could learn to do it.
Arguably LLMs take us further away from that than we've ever been. All they do is automate copying and pasting in shit from StackOverflow.
We were closer to everyone being able to learn how to program computers in the mid-80s when everyone had one and they started up with a BASIC prompt.
- I have told this to many friends who scoff at me, but using a computer is very clearly going to also mean "having the computer create programs for you". We won't even think or know about it.
To me, it isn't a matter of if, and the matter of when is also very clearly in "at most 10 years, probably much, much earlier", given that I have relatives already doing this without knowing how to code.
This is a future of computing I am absolutely in love with, and is so incredibly empowering!
by jorl17 - The road not (yet?) taken is the full flowering of the HyperCards, the Visual Basics, the Macromind Directors and Flashes...
That is, the idea that a non-expert might create interesting software in an authoring environment with good, well-thought-out building blocks and easy-to-grasp metaphors, shorn of layers of accidental or over-engineered complexity.
In this vision software still requires careful logical thinking, but it makes it much less cumbersome to translate that thinking into running code, with no tooling and build system nightmares.
Instead, we've invented such powerful models that they can regurgitate and recombine complex incantations on our behalf. The complexity is still there, though, and it's still inscrutable to non-experts.
But maybe they can help us eliminate some of it?
I think that path is still possible, and it may even nicely complement the LLM world, where LLMs help generate software that individual humans can still easily comprehend and manually modify.
- Emacs has this property because it uses Lisp. The general tendency for programmers to start writing everything themselves was noted, for Lisp, but was named “The Lisp Curse”¹. It is a curse because programmers stop collaborating. Everyone becomes their own wizard in their own tower, and overall progress stops, and a dark age sets in.
1. <https://www.winestockwebdesign.com/Essays/Lisp_Curse.html#ma...>
by teddyh - Is you actually look at the Lisp ecosystem as it exists today (even just Emacs by itself) you'll quickly realize that none of this is true in practice. Other people have pointed this out.[0]
[0] https://applied-langua.ge/posts/lisp-curse-redemption-arc.ht...
by Antibabelic - I've absolutely engaged in making personal software [0] thanks to the age of LLMs.
But to be honest, my time using Emacs didn't teach me to "build personal software". My Emacs set up was extremely brittle, and it was a nightmare when I tried to use it across Windows & macOS. My university project was written using an unholy combination of org-mode & some workflow to create a beautiful LaTeX file, and I couldn't tell you how to recompile it (if I were to try, I'd probably get an LLM to literally translate it to LaTeX).
I want my life to have as little maintenance as possible, and making my own software for everything isn't always compatible with that.
[0]: A rewrite of a NETFX application in Rust, simply because the 20 minute installation time irked me: https://github.com/bevan-philip/wlan-optimizer
by shaokind - “Those who say they lack time to build tools are precisely the ones who cannot afford not to.”by d0mine
- > I want my life to have as little maintenance as possible
I honestly can't even relate to what that even means. I'm a programmer - my everyday job is all about changing the behavior of computer systems - local, remote, cloud, embedded, etc. Requirements change, scope fluctuates, problem space evolves - grows and shrinks, accretion is unavoidable. I need to routinely move between language stacks, different data types, formats, CLI and web tools, protocols, paradigms, OSS and proprietary apps.
That means I have to constantly adapt, my control plane has to keep up with the flux. Automation is key - you must develop a mentality for that - every little annoyance can be and shall be automated. That is an endless, non-stop transformation of my workflow - continuous maintenance of my tooling. But that is not some toilsome, reactive maintenance.
Thinking that you're a programmer that doesn't want to constantly build software for your own sake is a delusion - it's like a cook that hopes to turn on the stove only in the restaurant, but won't touch a knife at home.
Emacs is the cook's home kitchen. I'd say there are two kinds of maintenance: reactive (fixing breakage, keeping up with churn) versus generative (shaping tools to match your evolving understanding). Programmers instinctively dislike the first and should be drawn to the second. Emacs is almost uniquely suited to generative maintenance because the tool and the work share the same substrate.
I get your complaint about Emacs specifically, it's a common: "too much work to set up", which usually means: "I don't want to invest before I get value", which honestly is not wise, strategic thinking. Treating Emacs as the universal tool for minimizing total maintenance burden over a career, over a lifetime is.
by iLemming - > I want my life to have as little maintenance as possible, and making my own software for everything isn't always compatible with that.
So LLMs are good enough to make personal software, but not good enough to maintain them?
- Have had the same emacs setup on linux, windows and macos for 15 years. Honestly, it's the best thing in my computing life.by e40
- Software that today is overwhelmingly prepackaged and usually professional, which I think at this point the nerds should reclaim:
* Podcast apps
* Music listening apps
* Feed readers
* Bluesky clients
* Note-taking apps
* Desktop bookmarking/read-later apps
* Chat and instant messaging
* Time trackers
* Recipe managers
These are all things that you can get better-than-replacement-grade results from Claude on --- not necessarily the best, not necessarily the most globally competitive, but certainly an application more closely tailored to exactly what you want it to do for your own idiosyncratic work style.
Music.app is a miserable experience, and I can just tell as I use it that it's miserable trying to serve me. But Apple long ago factored all the meaningful bits out of Music.app into MusicKit. Why am I still using Music.app? MusicKit is the real product now. This is new.
by tptacek - Music apps especially went downhill, spotify and tidal etc need to offer apis so we can integrate several sources in one app. They used to offer much more. I was able to import my library into spotify once (thoigh it could only hold 10k item back then). I want all my music in one place, not 4 appsby johanvts
- I'd add Email to the list.
Email is right there waiting for disruption.
by ijidak