Get the top HN stories in your inbox every day.
redfloatplane
utopiah
I called it "software".
It's so strange to me that since the 1960s with BASIC then later on dozens of https://en.wikipedia.org/wiki/List_of_educational_programmin... including Logo by Feurzeig/Papert/Solomon there is effort to precisely help beginners program software.
The effort was not to onboard future professional software developers but rather to make the personal in personal computer, or PC, meaningful. It's YOUR computer, you can put YOUR software on it. In fact even pocket calculator do that.
We keep on re-discovering the foundations.
customguy
To me this doesn't seem like a step towards those foundations, but another layer of of loss of agency. You can run "a" model locally, but you cannot make it locally (at least not for the purpose of just talking software into existence). You need to slurp up all the internet first, so to speak. And even if you could do that, you still depend on people putting new things onto the internet for you to slurp up. So is it really my software? What if it breaks or I want a new feature and AI corp nuked my account? How much did I learn during my time having it done for me?
And before anyone mentions it, I don't think the fact that I need a compiler and a manual and some example software to learn from is quite on the same level. I might be wrong but I would need some convincing.
utopiah
Agreed, I wasn't advocating on using LLMs, even "open" or "local" ones.
darkwater
You can also run a computer at home but you cannot even make a 486 from scratch at home, let alone something released more recently.
I agree on the SaaS side of the story, that's why it is so important to have open models.
MrGilbert
With the current situation on the hardware market, it makes me sad the we discover it only now. If things continue the way they are, there will be no Personal Computer any longer.
utopiah
Ah well don't despair there are already alternatives e.g. https://www.crowdsupply.com/mnt/reform
Ygg2
> It's YOUR computer, you can put YOUR software on it. In fact even pocket calculator do that.
I'm pretty sure this exists. It's called OSS or, more ubiquitously, Linux.
The problem is, of course, no one wants to publish software for your PC/handmade OS. Which makes it a huge problem. You can't write every piece of your OS, without wasting huge amount of time. Nor do people generally want this.
utopiah
OSS/Linux is "our" software. It's made by us for us (or others if you don't contribute).
Your software can be made by you, for you. It can be open source/free software if you want. Others can contribute to it, if you want but it can be open source without accepting external contributions also.
My point was to highlight that having software made by you for your machine is not new. Arguably the way to do so changed but I would say the principle remains.
Agingcoder
Agreed I’ve already started writing software for myself using Claude. I would never have done this if it weren’t for AI - I simply don’t have the time otherwise .
I now have tailor made apps with all kinds of bells and whistles that commercial products can’t offer easily ( I fall under non commercial usage which opens a lot of doors ), and that free software might offer, but later.
I have also learnt a lot technically in the process, since I’ve been able to venture into what was for me unknown territory but at controlled cost
I plan to create more such apps in the future. What is certain though is that my cooking app has immediately displaced all the others on the market , because none of the others cater to my requirements.
The production side is indeed of specific interest - most users don’t run production software so I had to think about that one. Tailscale and Cloudflare came in quite handy and there is indeed a market here
nz
I don't know how to tell you this, but people have been writing custom software for personal use for decades. I've been doing it since at least 2009! I find it hard to believe that there is a demographic of people that were yearning to write code, but simply could not because they lacked LLMs. Is it the price? Are people simply too cheap to buy books? Or have they simply "forgotten" how to patiently and thoughtfully read them? Or has the quality of tutorials/documentation of languages/libraries/framework online decayed in the last decade? Or is it really that people have struggled to type characters of code into their text editors[1]?
Basically, I am prepared to accept that there is a friction that LLMs lubricate away, but what is the source of the friction, and why am I (and a bunch of other colleagues) not feeling that friction daily in our practice?
[1]: And if so, where did we programmers and computer scientists go wrong? Were subroutines and macros not sufficient for automating all of that excess typing? Were Emacs and Vim simply not saving enough keystrokes? Did people forget how to touch-type?
JodieBenitez
> Basically, I am prepared to accept that there is a friction that LLMs lubricate away, but what is the source of the friction, and why am I (and a bunch of other colleagues) not feeling that friction daily in our practice?
You must be extremely talented and fast if LLMs make no difference for you.
For people like me though, it's another story: I've been doing this professionally for 25 years and of course, like many, I have been writing custom software for my own use all this time, on personal time. But with LLMs I get better results, faster and with very little effort. And that is the difference between another item in my list of unfinished software that consumed too much of my weekends and a cool utility/toy/useful thing I got after a few fun and interesting chat sessions.
> I find it hard to believe that there is a demographic of people that were yearning to write code, but simply could not because they lacked LLMs.
We didn't lack LLMs, we lacked time and energy.
mrob
I still vaguely remember how difficult man pages were to understand when I first started reading them. I'm pretty sure the biggest obstacle is the fact that most documentation is written for people who already know the standard computer science terminology. I have a generally negative opinion of LLMs, but one thing they do very well is function as a "reverse dictionary". You can input a idiosyncratic description of something you want and get the standard terminology. This is a new and valuable capability.
dpark
> I find it hard to believe that there is a demographic of people that were yearning to write code, but simply could not because they lacked LLMs. Is it the price?
Yes, because the price is measured in time.
With LLM tooling I’ve churned out idiosyncratic tools that fit my use cases quickly. Takes maybe a day instead of a week. A week instead of months. The fast turnaround changes the economics of writing custom tools for myself.
ilivethere
It's a question of time and priorities.
I work 8-10 hours a day and outside those working hours I want to spend time with my family, my friends, and my hobbies.
At the same time, during those 8-10 working hours I don't want to spend time fiddling around with different programming languages or software patterns just to spit out a quirky little tool that would make my job a bit easier.
For example, I wanted a local to-do list software that I could easily integrate with my workflow. Spent some time trying to find one, but not a single one worked the way I wanted. So, one morning, I spent 5 minutes detailing what I wanted, prompted it to Claude and let it rip while I was working. 30 minutes later, it was ready.
taude
Not speaking for the OP. But my biggest constraint is time. Now with agentic coding, I can work in 5 to 15 minute bursts a few times/day, and make meaningful progress on projects, where as before I would have never been able to context shift from my day job long enough on a personal project.
kaashif
If you are saying that what we had previously was actually as easy as literally writing "make me a web app for arranging seats at a wedding and put it on Vercel" then you are very divorced from reality.
I know how to do all of these things and even find them easy, but it's just much faster now. These are personal one task toy apps, but they are useful.
eichin
Given how often younger people find my typing speed startling, I think it has been somewhat forgotten (US high schools had "keyboarding" classes at one point but that seems to have fallen off...)
Agingcoder
Well, I’ve been writing code for decades so I know because there was a time ( when I was younger ) where I did just this.
I also know that these days, for all kinds of reasons, I do not have the time to write the tools I’m writing now without AI. I don’t lack the ability, and I could - it will simply be multi months side projects that I can’t / won’t complete.
vessenes
I had the same reaction. We're headed into a period where you can shape your tools exactly as you like them; artisanal rather than factory-created workshops, essentially.
I think the instinct that APIs, validation layers, and so on take on a much higher importance is right.. I have a few internal tools that made sense to make libraries out of, and once the first library is good, and a test suite is comprehensive, porting to a bunch of different languages is extremely simple.
Everting that, it's also going to be simple for someone to hook up to this library with custom tooling.
Really interesting period in computing, for sure.
blks
> We're headed into a period where you can shape your tools exactly as you like the
What period were we for the past 50 years?
vessenes
Since roughly 1995 or so we've been in a world where quality tooling was provided by on the order of 1,000s of developers, mostly open source. GNU, Xorg, Apache, emacs, nginx, and so on. Or you could opt in to the Microsoft ecosystem.
The ~20 years prior to that we were in a world where you chose to align with either Microsoft's tooling, IBM, or shops providing Unix tooling from proprietary vendors.
I elide a nearly infinite amount of detail, obviously.
What's new now is that you can get your own window manager written to spec in under a week, perhaps much more quickly, not just choose one of a few major window managers and configure it in accordance with the chosen configuration options delivered by the large developer team.
chrisweekly
"Everting"?
vessenes
I learned it in the math context - a sphere eversion is a 3 dimensional process that ends with the inside of the sphere becoming the outside.
setopt
I had to check it up too. Appears to be a synonym for "inverting" used in some fields like biology and medicine.
dllu
I vibe coded an image viewer for myself to address a big pain point that had been annoying me for years. [1]
[1] https://daniel.lawrence.lu/blog/2025-10-22-sriv-simple-rust-...
konschubert
I built an optimisation for charging my car. It’s very smart, looks multiple days ahead in weather and prices and predicts my driving habits.
I tried to make it a product, but I didn’t find much interest. Maybe I’m just bad at marketing.
With the help of Claude, it cost me years of experience and few weekends to build. So even if nobody other than me ever profits from it, it was still worth it!
dannyfritz07
Reminds me of this blog post and conference presentation on home cooked software by Maggie Appleton.
redfloatplane
Great post, thanks for sharing. Evidently I am far behind the real thinkers! The Robin Sloan post mentioned is also very good.
stateofinquiry
Interesting points. With the extreme cheapening of the cost (time/skill) for software production, we can have "Extremely Personal Software", as you mention and as demonstrated by the source. I wonder if we will reach a stage where "software" is written by a computer for an audience of 1 and for a single task, to be run once only- via an interface that works for all tasks. The very concept of software as something that users have to learn to use (memorizing keybindings, for example), might go the way of the punch card.
More like Star Trek, we would just ask "computer" to do things, and its machinations (and "software") will be invisible to us. We would just have output to deal with.
I think this would mean a lot of things. I'm sure I can't fathom all of the implications, but it sure makes me feel old! Interesting times ahead.
criddell
LLMs seem to be great for speeding up the creation of things that aren't all that hard to write in the first place.
They don't seem to be helping much with difficult tasks.
Text editor? Easy. That used to be a rite of passage. Lots of people have written their own basic text editor.
3d solid modeler? It's always been difficult and AI coders aren't (yet?) up to the task. Most open source CAD projects that show up here are layers on top of OCCT (Open Cascade) which is pretty far behind what commercial geometry kernels are capable of.
theshrike79
More likely we'll have a library of skeletons for single task software, where the LLM can fill in the blanks as needed.
Maybe it saves the script locally (invisible to the user) and reuses it if the user repeats the same request, the script is deleted if it's not needed for X amount of time.
quietthrow
This. I have written so much software recently to make my computer my own. It’s been so much fun to be able to borrow the the ideas from different tools I have used (eg vim modal behaviours etc ) and also bring them together with some completely novel ideas to produce tools for myself that are one of a kind and that “fits me like a glove“
Too bad this is all on the work computer and need to bring it to my personal one but can’t copy paste lol. It’s been thrilling building g and using them and the time from an ideating a small enhancement/ optimization to actually using it is like 5 to 15 minutes away. Soo cool.
vidarh
While I wouldn't do asm, I love the approach and do much the same myself but in Ruby instead.
My wm, shell, terminal, editor, file manager, pop-up menu (dmenu-like) are all pure ruby (including font rendering and X11 bindings). These all started before I started using Claude to improve them, so they're still mostly hand-written, but that is changing.
They're messy, they have bugs and "misfeatures" that works for me but likely would be painful for others.
Like OP, I don't really recommend anyone else use my code, at least not directly, and that is extremely liberating.
Overall, the projects covers the largest surface of what I use beyond the kernel, a browser, and Xorg (I'm so, so tempted, but I think an LLM will need to get a lot further first before I could fit it into my schedule).
It doesn't need to be polished because it's mostly for me. It's okay for them to have bugs as long as they work better for me than the alternatives.
I strongly believe more people should do this. It's both a great learning experience, and it gives you a system that has exactly the features you actually want and use.
And it's only going to get easier to do this.
psychoslave
[dead]
nine_k
This is very cool. I wonder how much time did it actually take, and how much did it cost, because Clause Code is very much not free [1] [2]. It's more like hiring a robotic contractor, very fast, but with a serious hourly rate.
[1]: https://fortune.com/2026/04/28/nvidia-executive-cost-of-ai-i...
[2]: https://www.briefs.co/news/uber-torches-entire-2026-ai-budge...
geir_isene
I'm on Claude Max, so it didn't cost me anything more than the subscription I already have. Had to use it for Something. As for time - for the full CHasm and Fe2O3 suite of sw, I started the work 2026-03-29 and have probably spent 60h or so of my time. But then again I have a very tailored CC setup that I have fine-tuned since last summer with more than 70 CC projects helping me get it the way I need it to be since then.
nine_k
So, it's at most $400 in Claude expenses for a fully custom suite of software in 2 months. Even if your time is 300/h, it's less than $2k in your own time (which, I would expect, you enjoyed spending). That's insanely impressive.
geir_isene
I need Claude Max in any case for my work, so the cost is effectively null. And I do creative stuff in my spare time regardless, and I don't really think about my hourly rate when I play with my kids either ;)
luqtas
> That's insanely impressive.
literally every app they need, except the browser, at least have 10 alternatives that are FOSS, much more mature, better structured and prone to be bug free... or do you really think the OP with months/years of use won't need some other feature and will re-invent the wheel on software that is around for more than a decade with hundreds of bug reports done (i3 wm was released in 2009)
robotresearcher
Did you miss a factor of 10 in that time-cost calculation?
As a hobby, normal rates don’t apply, but just not to be misleading on the equivalent cost.
linsomniac
@geir_isene: This is insanely cool, thanks for writing about it.
chickensong
Interested to hear about your CC setup if you'd like to share.
topaz0
Do you know how much it would have been at API prices?
boesboes
Can't speak for their usage, but I calculated my token use with Copilot, my employer paid 22$ for >2000$ in tokens. Given estimates margins, Github is paying 98-99% of the costs for us. I imagine Claude max etc is similar. So it's not sustainable at all
geir_isene
No idea. Probably quite expensive. I usually run 4-5 concurrent CC sessions, so hard to pinpoint for just CHasm and Fe2O3
theshrike79
My irccloud.com subscription is about 60€/year.
I've spent two weeks with the cheapest tiers of Claude Pro + pi.dev+GPT-5.5 (+ some deepseek-v4 via openrouter recently) to create my own bespoke version.
I'm at 90% feature parity currently and surpassed on some levels. For ~20€-ish I've soon replaced a 60€/year subscription service.
I haven't spent a single second thinking about how someone else might run it, it doesn't have logins, security or anything - because I'm going to run it 100% behind a Tailscale node with no external access. The release and deployment processes are exactly how I like it, other people might not. I don't need to care, it's mine =)
A few months ago I did the same with Hazel[0]. That took maybe one evening to get an MVP and a week of casual updates to make it pretty. Now I have my own macOS application that does the exact things I needed Hazel for. It's mine forever and I can add or remove features as I feel like it.
dadoum
Sorry I have a question that is a little off-topic: what's the value of generating an image of a laptop on a desk? That's not like it's particularly relevant, when you could have integrated a screen shot of your set-up (like the same one you put on a few of your repos) or something more unique, and even if you want to show that, it's easy to find similar images with the same vibe, so I guess it's for some fun I missed in the process?
geir_isene
I like the image. It was simple.
gwern
But doesn't that make it bad? It doesn't say anything new. Unlike the software in question, which is personalized, so it's not even symbolically reflecting the topic. It's a sheer waste of pixels and time spent looking at it or scrolling past the cognitive junk food.
i_think_so
Come on, bro. Why you gotta be like that?
I mean, I'm a gwern fan, but...can't you just let people enjoy things?
overfeed
This appears to be a harbinger of a Plastic-era of software. A miracle product that's used for everything, and will turn up everywhere before we've had the chance to consider the wider impact. Learning to write software in a generation will be a royal mess, as will be finding clean training data, and software discovery.
mentos
AGI or bust
geir_isene
For those who may be interested - I broke down some numbers for my CHasm and Fe2O3 efforts in a new blog post: https://isene.org/2026/05/Audience-of-One-Numbers.html
alchemist1e9
You’ve reduce the memory requirements so much that it could all run on an early 90s computer easily. When I see such extreme examples I think back to the OLPC machines and this idea of how can extremely cheap but with useful software computers be available in very impoverished areas. I understand this has nothing to do with your argument or anything you’re writing about. It just made me think if LLM assisted software production might make the failed OLPC idea viable again. Could a minimalist but useful set of tools be created to run on old chromebooks for example.
patcon
I fuckin love this.
It points toward the parts of "reduce, reuse, recycle" that capitalism has demonstrated no interest in serving
furyofantares
I've got a wrapper around tmux for an audience of one. I can operate claude code, codex, opencode, or just a shell, from any of my devices to any of my devices (via tailscale) or more commonly, operate it on my exe.dev server.
I often continue a session on my phone, sometimes with voice. I have buttons for viewing files or following links the agent has referenced, extracted from the stream of text, and I have some buttons for exactly the git stuff I need. I have a button to toggle between yolo mode and normal.
Basically, very simple UI for everything I actually use, easy to use on a phone - and maybe more importantly, no UI for anything I don't personally use. Also all my machines have the repo for the uh, harness-harness, so I just open the tab for it if I need some changes and prompt them into existence and get the changes live.
All this is great, except it enables me to work every waking hour of my life. That part might be bad.
paweladamczuk
Do you have a way to use voice on your smartphone?
I use a whisper wrapper (also "built for one") for Windows and connect through SSH but it only works well enough because of the laptop's ARC graphics card. I wish I could do that when connecting to SSH from my smartphone.
protostork
FUTO has a superb Android keyboard with on-device voice transcription using a fine-tuned Whisper model, which is quite performant for me (and actually does fairly impressive text autocorrect and prediction too): https://keyboard.futo.org/
They also do a pure play voice input keyboard, if that's your jam or you want to use it with other keuboards: https://voiceinput.futo.org/
furyofantares
Yeah, two ways, lol. I have a big mic button on the bottom that I hold to speak, which uses the browser speech api. edit: I'm reading that that's local in safari but remote in chrome.
But I also type into an input field rather than the terminal and can use the mic on the phone keyboard (iOS).
yjftsjthsd-h
You could always just use whisper as a keyboard on the phone: https://github.com/woheller69/whisperIME
geir_isene
I do the same also
vbernat
I find this fascinating. I also like to customize my desktop experience with my own code, but it's more assembling stuff with some additional code as glue.
A word of warning: a reliable lock tool for X11 is difficult. You should look at XSecureLock, which uses a multiprocess approach to avoid leaving the desktop unprotected in case of crash. It also implements a number of countermeasure to ensure the desktop stays locked and the locker stays in the front of the display. It's small too, so easy to audit (but written in C).
geir_isene
Thanks. I'll look into it and borrow whatever is useful there into bolt.
undefined
cadamsdotcom
This is really exciting.
Some of the folks who make things will go on to make things that suit not just their preferences but also those of a small audience.
Some of those audiences will go on to grow and grow and disrupt the big players.
The capital intensive part of software construction is melting away and being converted to opex (payg token costs and your time) and that will blast open the possibility space and lead to a massive new commons.
If the thing was so cheap to create why not open source it!
And if you like someone else’s open source thing but don’t want to take it wholesale why not give it to your agent and say “put the ideas from this onto my thing”!
It’s a new way of thinking about code too.
deepfriedbits
Absolutely and you're dead on thinking about the opening of the possibility space. The value of software as an enterprise will fall as we enter an age of abundant, and often custom, bespoke software. There will be many great apps coming and some lousy apps.
Another thing to watch for is how chatty the internet is about to become. A great many of these apps will hit APIs, ping each other, and so forth.
theshrike79
> The value of software as an enterprise will fall as we enter an age of abundant, and often custom, bespoke software.
Not just software. I'm predicting we'll be getting bespoke books and comics in a few years. TV and Movies after that.
Basically there will be a service with mad-libs style book skeletons and you can get your exact specifics put in with LLM writing in them.
You want a romance novel with dragons (D&D style), a red-headed princess protagonist that's a bad-ass fighter and she has three men competing for her affection, each with a very distinct look that YOU specifically like.
Done.
This already being done by actual human writers, many (not all!) people read books based on tropes they like, the rest doesn't really matter. They basically check the tags of the story and if they match well enough, they'll buy it and read it. And I mean very specific: https://www.goodreads.com/series/151379-ice-planet-barbarian... =)
gnabgib
Real nice to see two accounts using LLMs discuss nothing like this. They warned us this would happen, and here we are. I guess the topic is apt, but we used to customize windows (95+) and Linux like this (not down to vibe-coded insecure replacement of apps, but display/desktop/widgets/explorer/transparency of components).
deepfriedbits
Wait, are you implying I used an LLM to write my comment? Sorry if I'm misreading what you're saying.
robotresearcher
I’m inspired by the message.
On this software itself: I’d like to know how this feels to use. It’s so very lightweight. Does it feel categorically different to what we are used to?
One of the things I miss about the 1980s home computers is that they booted into a usable command line in a handful of seconds, from a few KB in ROM. Imagine what today’s HW could do if we’d retained that level of efficiency.
salvesefu
we are there now. depending on boot loader/os combination, one can get to the sub 1-5 sec range, if its cli-only.
CableNinja
Clearly havent seen what enterprise hardware is like these days... sure, the OS takes 5 seconds.. but the hardware can take 10 minutes in some cases now glares at hpe gen11 systems. Its seriously bad now. The amount of power and time backround hardware level tasks now take has significantly increased over the last 10 years. Even the ancient dell r710 i have sititng in a closet collecting dust boots faster than todays hp gen11's.
We waste a ton of energy on ineffeciencies in hardware and software today all because we managed to "just go faster".
geir_isene
It feels very different. It's all damn instant. Me happy.
robotresearcher
That’s wonderful! I’ve made ultra-lightweight web apps of my own to replace bloated, slow, and poor UIs. It’s a night and day difference when the dependencies are few-to-none. And that’s on a fat browser stack. Your ASM desktop must zip!
chrisweekly
Related tangent: https://smolmachines provides microvms with cold-start bootup times around 200ms, and a "pack" utility and format to create self-contained binaries. No affiliation, but I just discovered it a few days ago, sharing bc I find it kind of exciting.
ekjhgkejhgk
How often do you hit against bugs that stop you from being able to do something and then you have to stop what you're doing and go fix the bug?
For me, I've used i3-wm exclusively for 4 years now, and it has always felt instant. I struggle to believe that getting whatever incremental performance at the cost of increased bugs is worth bothering about it.
aorth
Brilliant! I hate it. The author will surely admit that there was "joy" in creating this suite of software, but it's a different kind of joy than most of us here would recognize. I am looking forward to being a part of the group of detractors doing things the old way, similar to the "small web" or other counter cultures on the Internet. I fantasize about being here to pick up the pieces after all the others went full-on into AI-assisted everything and lost their critical thinking capacity, programming skills, knowledge of Unix command line, etc.
There is part of me that understands the appeal of the all-in on AI and personalized software approach. It's a bit cyberpunk! In terms of open-source software, the downsides outweigh the benefits in my opinion, though. Important principles like community ownership and commitment are absent, and this approach is even radically antisocial. And then there's the inevitable issues with maintainability, to say noting about dependence on big tech companies.
To each their own, but this is not for me.
dimator
I read somewhere (in the myriad blog posts dealing with this Cambrian LLM explosion) that software developers could be put into two camps: those that just want the thing to exist, and those that want to build and understand the thing (in addition to wanting it to exist).
those in the first camp are having a great time.
those in the second camp (which is how you're describing yourself, and how I'd describe myself) are wary and suspicious.
it is somewhat paradoxical, we've watched/read sci-fi/cyberpunk for years and dreamed of this kind of world. after all, when did you see any members of the Enterprise writing code? they just asked the computer to "write a subroutine" and that was that. what a world!
but here we are, with the craft in danger, not entirely impressed by the idea of "just ask and walk away".
i, too, fear for my loss of critical thinking, raw skills, and design sense, as do i think about being one of the few (in 2, 3, 5, 10 years) that didn't abdicate their cognition, their craft, to the tech overlords.
but i wonder if it will matter anyway. i wonder if "source code" will be a deep abstraction that nobody thinks about anyway, similar to how 99% of us don't care/need to care what the machine code we're eventually emitting does or looks like.
in any case, i'll keep my thinking for now.
latexr
> I read somewhere (…) that software developers could be put into two camps (…)
Surely you read it more than once, because that has become a talking point. It’s a false dichotomy that, you’ll notice, is most often used by the people who put themselves in the first camp to steer the conversation. By framing it as “there are two camps, it’s just different, none of them is better”, it lends legitimacy to their position.
You don't have to pick one camp over the other. Good, high quality craft makes good products.
> after all, when did you see any members of the Enterprise writing code?
When did you see anyone in any media taking a dump, or sleeping, or doing any of the boring bits? Rarely, because if it’s not relevant to the story they don’t show it, but it doesn’t mean it didn’t happen.
I’m more of a DS9 fan, and I remember them having computer problems all the time. O’Brien, despite being highly competent and the chief of engineering with a team, was constantly overworked.
And their computers were infinitely superior to the LLMs we have now. When they gave you an answer, you could be confident it was correct. And if they didn’t know, they’d tell you!
ptnpzwqd
I think a notable difference is that the AI that is portrayed in most sci-fi (that I have read/watched anyway) tend to be "logical machines" that act deterministically based on the data available to them.
What we got are "statistical machines" that tend to do the right thing under the right conditions, but can go completely off the rail every now and then.
The former are more akin to a generalization of computers as we typically think of it, whereas the latter is something else. Maybe that something else is closer to human behavior in some ways, but also so very different - unlike humans, where you get to know people, build relationships, know who to trust in what ways, and so forth, you can never really trust an LLM with any critical tasks without close supervision.
danparsonson
I feel like using an LLM to do serious work is a bit like us using our brains language centre for the same job - like a very elaborate collection of stock phrases. I'm impressed that it works at all but it doesn't really feel like the right tool for the job. I think the robot of the future will have some more logical cortex doing the thinking, with an LLM in front of it handling the communication.
cyclopeanutopia
People who watch/read cyberpunk and dream about living in such a world are way beyond stupid. :(
theshrike79
I kinda like the woodworking analogy of this.
I, in theory, can plane a piece of wood with a hand planer. But I'll never do it again, we did it at school in ye olden times before the millennium and it was boring then as it is boring now.
I know people who get satisfaction from it, they take one sliver off with the hand planer, feel the wood with their hand and figure out the perfect angle for the next tiny sliver of wood to come out off, repeating the process over and over again.
I, personally, will just feed the damn plank to a mechanical planer with the exact specs of the resulting board set up. I just want the board smooth so I can get to the next step of the process. I'm not doubting the "wood-slop" the machine produces, I can see and measure if it's good enough or not. I don't need to be involved in the process.
We're both making a table, mine will be done faster. It might not be hand-crafted to perfection, but it will hold the stuff I intend to put on it just fine. If I find out it sucks later on, I can make a new one that's slightly better or fix the existing one. My goal was a functional product, not a piece of handcrafted art.
dimator
Your analogy is not really apples to apples though, is it?
More close is: if there was a table making machine, you just push a button and something like a table comes out, would you still be a woodworker? You haven't planed, nor measured, nor cut, nor jointed, you've only pressed on "make me a table"
yuye
I don't think the analogy works. You're focusing on the "how", not the "what". Using a mechanical planer, you still need to dial in numbers yourself. You design your own table, the more modern tools just make it easier to realize your vision.
Another example: I enjoy writing with a good pen. But whether I write by pen or on a keyboard, it's still me writing it.
However, AI does basically all the real work, only leaving you to guide it. Make a table? AI gives you one with 2 legs. More legs? Guess I can live with 5 legs.
And you wouldn't be making that table, AI is. You cannot have pride in something that you never made yourself. It's the same as 3D-printing something from Thingiverse and claiming you made it.
People who create AI blog posts are not writing. Those that prompt their way to a piece of software are not doing software engineering. The ones that generate AI images are not being artists.
viccis
I'm in the second camp.
Part of it's that the whole point of going into this industry is that I love coding and have been doing it since I was 8. Part of it is that I'm a control freak and it makes me uncomfortable to have to trust AI generated code. Sure, I already trust interpreters and compilers, but those are much more deterministic, and they don't generally do anything I have to be wary of. Part of it is that anytime I've used Claude to write stuff (using Opus 4.7 via an API key), I've had to handhold it when doing simple things (telling it repeatedly that a given column doesn't exist in Snowflake's task history table and eventually just giving up and taking it out by hand) and had to remove tons of completely pointless Python code it generates. The big difference is that the people in the first camp don't seem to care enough to check. Someone at my company used Claude to write 20k lines of code this past Friday. No way he read and scrutinized all of that in one day.
The other big thing I've noticed is that a lot of the people using it extensively seem to just be spitting out API endpoint after endpoint. Just doing endless CRUD with some light business logic. Yeah, it's not too hard to automate that with AI without any major issues. Hell, back when Ruby on Rails was hot, it was so fast to write those kinds of things with it that I could spin up things as fast as AI is doing now. Full websites or APIs in an hour or two because its syntactic sugar and scaffolding did what AI does with the FastAPI codebases I see these days. You could go from an ER diagram to a working app in minutes sometimes. I don't care that much if that kind of work is automated.
geir_isene
I was in the second camp until last summer, having been hand-writing code since 1979.
ximm
My experience is that often when I think "I wish my email / browser / calendar / … did X" it turns out be a limitation of the underlying protocol. So even if you build all software yourself, you still have to make compromises when you interact with the outside world.
Get the top HN stories in your inbox every day.
I (and I'm sure many others) have been thinking about this a lot over the last couple of months. I called it "Extremely Personal Software" in a blog post a few months ago (https://redfloatplane.lol/blog/14-releasing-software-now/) but there are lots of names and concepts floating about for the same basic idea.
I think it's possible the amount of new software that will be written for an audience of 1-10 will be greater in 2026 than in any previous year, and then the same again for many years to come. I also think a lot of this software will be essentially 'hidden' - people just writing this stuff for themselves because the cost to say things to an agent is very low compared with the cost of actually planning out a software design and so forth.
Interoperability will probably be important in the next few years and I wonder if this is something solvable at the agent/LLM level (standing instructions like 'typically, use sqlite, use plaintext, use open standards' or whatever). I also think observability and ops will be pretty important - many people who want personal software but don't care for the maintenance and upkeep.