[HN Gopher] Perfect Software - Software for an Audience of One
___________________________________________________________________
Perfect Software - Software for an Audience of One
Author : ggauravr
Score : 196 points
Date : 2025-12-20 07:14 UTC (4 days ago)
(HTM) web link (outofdesk.netlify.app)
(TXT) w3m dump (outofdesk.netlify.app)
| tidderjail2 wrote:
| I feel the same, I'm now building more side projects with the
| help of AI even if they're only for me
| jesse__ wrote:
| By the authors definition, I've been writing perfect software for
| over a decade.
|
| It's never required LLMs. In fact, I think the idea that "LLMs
| allow us to write software for ourselves" borders on missing the
| point, for me at least. I write software for myself because I
| like the exploratory process .. figuring out how do do something
| such that it works with as little friction as possible from the
| side of the user; who is of course myself, in the future.
|
| I like nitpicking the details, getting totally side-tracked on
| seemingly frivolous minutiae. Frequently enough, coming to the
| end of a month long yak-shave actually contributes meaningful
| insight to the problem at hand.
|
| I guess what I'm trying to say is "you're allowed to just program
| .. for no other reason than the fun of it".
|
| As evidence for my claims: a few of my 'perfect' projects
|
| https://github.com/scallyw4g/bonsai
|
| https://github.com/scallyw4g/poof
|
| https://scallywag.software
| rolfus wrote:
| I get what you're saying - I personally scratch that itch by
| doing woodworking and hobby electronics; I just love doing it
| and the end product is often just a means to an end; to craft
| something and enjoying the process of it.
|
| But programming doesn't give me that same feeling, and
| honestly; the scope of doing and learning everything needed to
| make my projects without LLM's are just way out of reach.
| Learning these things would not be relevant to my career or my
| other hobbies. So, for me I use LLM's the way a person who's
| not into carpentry might buy the services of a carpenter,
| despite the possibility of them doing the project themselves
| after investing tons of time into learning how.
| skydhash wrote:
| These days, I spend my personal coding time on building
| personal interfaces either as a shell script or as emacs
| packages. So many tools and applications hinders power usage.
| redhale wrote:
| Both can be true.
|
| Some people enjoy cooking. Some people enjoy eating great food.
| Some people enjoy both. Some people enjoy cooking certain
| things, and also like eating things they would never bother
| cooking themselves.
|
| There is nothing wrong with any of these perspectives.
| rolfus wrote:
| This resonates with me. I'm not a programmer, and before LLM's I
| could only make basic hello world apps and simple websites. Now I
| am developing my own versions of various apps that I've used but
| maybe have limitations that I've become frustrated with. For
| example, I didn't like how the fitness tracker Strava didn't
| allow me to customize audio announcements, so now I have my own
| (and in my own eyes) better version of Strava that I use instead.
| It's absolutely blowing my mind that this is possible and
| available today, and not some tech-optimists wet dream about an
| impossible future.
| reconnecting wrote:
| Here is the demo of my perfect software.
|
| https://play.tirreno.com
|
| However, I'm skeptical about AI, because what I've understood
| about agentic processes is more about cheap dopamine.
|
| When it comes to medium-sized software development (over 50k
| LOC), there is much less fun and much more pain, because a
| growing codebase doesn't allow you to make new features easily.
|
| I believe it is important not to mix up a dose of dopamine gotten
| from agentic results, as in the article, with achievement from
| longstanding work, even if it's not so attractive from a short-
| term perspective.
| breckenedge wrote:
| I use Claude Code on a 900kloc Rails/JS monolith and it's still
| pretty pleasant. However if it wasn't already structured well,
| I could see that being a worse experience.
| reconnecting wrote:
| The article is about the pleasure of creating new software
| (occasionally with AI help), so I hope that the 900k LOC in
| your case doesn't come from Claude Code.
| 1313ed01 wrote:
| Someone just discovered why some of us enjoy shell scripts and
| Emacs so much. No need for LLM, just small hacks to solve
| specific problems in limited contexts that works well enough,
| most of the time, for one user.
| criddell wrote:
| Even phones these days have pretty good scripting environments
| (thinking of Shortcuts on iOS).
|
| I've had really good luck with Claude helping me write shortcut
| scripts. For example, I wore a CGM this year for a bit and I
| couldn't find an easy way to get the raw data. It did log
| everything to Apple Health and a shortcut was able to extract
| it and append it to a spreadsheet where each row was a reading.
| zingar wrote:
| I've written so much more elisp and bash this year because of
| LLMs.
| lll-o-lll wrote:
| This article triggers all my "written by an LLM" spidey senses.
|
| Which is ironic considering the subject matter. "Perfect", but
| artificially constructed. "Just for me", but algorithmic slop.
|
| I agree that you can do so much more custom tailoring of bespoke
| software with the speed an LLM brings. But something inside of me
| still revolts at calling this anything other than "convenient".
|
| "Perfect" I will reserve for things I've made myself. However
| "imperfect" they may really be.
| golemotron wrote:
| Look at it this way. The carver doesn't have to grow the tree.
| Using an LLM for coding is a lot like being a carver. You can
| take broad or small strokes and discard what you don't like.
| lll-o-lll wrote:
| > Using an LLM for coding is a lot like being a carver.
|
| It's nothing like being a carver. It's like being a director;
| "Once more! With feeling!". "Perfect, brilliant, just one
| more take, and I want you to consider..."
|
| A sculptor shapes with their hands, and there is pleasure in
| that. A director shapes with someone else's hands.
| ares623 wrote:
| It's like being a master, really. You're getting output
| from something that can't say no and that was built from
| the works of millions of unknowing and unconsenting
| contributors.
| golemotron wrote:
| Yet we see directors as artists. Kubrick, Coppola (both of
| them), Hitchcock, etc.
| bitwize wrote:
| We also see actors as artists, and pay them gorillions of
| dollars. AI is about using distilled human knowledge,
| while cutting the human out of the loop (and out of the
| payroll).
| imiric wrote:
| This has always been possible, even if you weren't a programmer.
| You just needed to have the desire to customize your computing
| environment, and the time and patience to do it.
|
| There is so much software out there, written by people who wanted
| to solve their particular problem, just like you. Chances are
| that some of it will fit your needs, and, if the software is
| flexible enough, will allow you to customize it to make that fit
| even better.
|
| This is why the Unix philosophy is so powerful. Small independent
| programs that do one thing well, which can be configured and
| composed in practically infinite number of ways. I don't need to
| write a file search or sorting program, nor does the file search
| program need to implement sorting. But as a user, I can compose
| both programs in a way to get a sorted list of files by any
| criteria I need. This is possible without either program being
| aware of the other, and I can compose programs written decades
| ago with ones written today.
|
| You can extend this to other parts of your system as well.
| Instead of using a desktop environment like GNOME, try using a
| program that just manages windows. Then pick another program for
| launching applications. And so on. This is certainly more work
| than the alternative, but at the end of the day, you feel like
| you are in control of your computer, instead of the other way
| around.
| eterm wrote:
| I like this article, I think it taps into something real.
|
| I find myself scratching real itches that would otherwise have
| gone left un-scratched, because the hurdle to just getting
| started on something was too damn high.
|
| For example I had need for an image contact-sheet. I'm sure there
| exist a lot of contact sheet generators out there, but I was able
| to just as quickly get claude to write me a set of scripts that
| took a bunch of raw images, resized them down to thumbnails,
| extracted their meta-data, and wrote a PDF (via Typst) with
| filenames and meta-data, in date order.
|
| I got lost perfecting it, hand-picking fonts etc, but it still
| only took an hour or so from start to finish.
|
| It's perfect for my need, I can customise it any time I want by
| simply asking claude to modify it.
|
| Did I need to be a developer to do that? Arguably yes, to know
| the capabilities of the system, to know to ask it to leverage
| image-magick and typst, to understand what the failure-modes
| looked like, etc.
|
| But I dind't need to be programmer, and over time people like the
| OP will learn the development side of software development
| without learning the programming side.
|
| And that's okay.
| mgaunard wrote:
| The comparison to coffee is bad, since it's obvious the best
| coffee is with no sugar and no milk.
| pedrogpimenta wrote:
| I agree, but it is there: perfect amount of sugar: 0, perfect
| milk-to-coffee ratio: 0 to 1.
|
| What really gets on my nerves is the justified text...
| mgaunard wrote:
| My point is that it's not a personal amount, but an absolute
| constant.
|
| If you need to mix other things with it, then the coffee
| isn't good.
| CharlieDigital wrote:
| > The Extended Mind Theory argues that our tools are not just
| accessories, but literal extensions of our cognitive process.
| Viewed this way, a generic tool like a one-size-fits-all app,
| feels like a prosthetic that doesn't quite fit.
|
| Three years back now, my wife and I were planning a two-week long
| trip and found it really difficult to simply move day-places
| around (e.g. shift a whole day in a schedule with all of the
| places planned for the day) as we were planning a multi-city
| route.
|
| We started with Google Sheets (way too cumbersome), then Docs
| (cumbersome in a different way), then a simple app using Firebase
| + the Google Maps embedded API built over a weekend, and then
| ended up building a full blown planning app and eventually a
| Chrome extension[0] that hooks directly into Google Maps (our
| preferred tool for exploring).
|
| We are _meticulous_ planners so I totally get the author 's
| sentiment here. Many people see the app the first time and feel
| overwhelmed, but for us, it's hard to imagine using other tools
| now because this one fits "just right" having been built
| specifically for our planning process.
|
| [0] For anyone interested:
| https://chromewebstore.google.com/detail/turasapp/lpfijfdbgo...
| qbit wrote:
| I've always been somewhat dissatisfied with image
| viewing/browsing software. Gqview and Sequential came close to
| being what I wanted, but there were things about both that I
| didn't like. I finally just wrote my own custom viewer using
| pyqt. For me, it is perfect software!
| Lyngbakr wrote:
| I was nodding along enthusiastically right up until LLMs and that
| point we sharply diverge.
|
| For me, part of creating "perfect" software is that _I_ am very
| much the one crafting the software. I 'm learning while creating,
| but I find such learning is greatly diminished when I outsource
| building to AI. It's certainly _harder_ and perhaps my software
| is worse, but for me the sense of achievement is also much
| greater.
| grugagag wrote:
| You can still create what you already know how to, by hand, but
| also extend to areas you previously where shy about with the
| help of LLMs.
| dotancohen wrote:
| Just today I gave an LLM the task of porting some Python
| modules to rust. I then went back and learned enough rust to
| understand these modules. This would have taken me days
| without the LLM. And I learned a lot.
| analogpixel wrote:
| I find that most of the time, programming is just
| procrastination, and having the LLM there breaks through that
| procrastination and lets me focus on the idea I was thinking on
| without going into the weeds.
|
| A lot of the time, the LLM outputs the code, I test my idea,
| and realize I really don't care or the idea wasn't that great,
| and now I can move on to something else.
| dotancohen wrote:
| I'm now using an LLM to write a voice note organisation
| application that I have been dreaming about for two decades.
|
| I did vibe code the first version. It runs, but it is utterly
| unmaintainable. I'm now rewriting it using the LLM as if it
| were a junior or outsourced programmer (not a developer, that
| remains my job) and I go over every line of application code.
| I love it, I'm pushing out decent quality code and very
| focused git commits. I write every commit message myself, no
| LLM there. But I don't even bother checking the LLM's unit
| and integration tests.
|
| I would have never gotten to this stage of my dream project
| without AI tooling.
| Antibabelic wrote:
| > I would have never gotten to this stage of my dream
| project without AI tooling.
|
| Why not? People have been writing successful personal
| projects without LLMs for years.
| rolisz wrote:
| Not grandparent, but I'm in the same boat. I've been
| dreaming for almost 10 years of building a sort of
| digital bullet journal. I had some feeble attempts to
| start, but never got to the point where I could actually
| use it. Last year I started again, heavily LLM assisted.
| After 1-2 weeks (this was before agents), I had something
| usable, from which I could benefit, which wanted to make
| me improve it more, which made me want to use it more.
|
| By now it's grown to 100k lines of code. I've not read
| all of them, but I do have a high level overview of the
| app, I've done several refactorings to keep it
| maintainable.
|
| This would not have happened without AI agents. I don't
| have the time, period. With AI agents, I can kickoff a
| task while I'm going to the park with my kids. Instead of
| scrolling HN, I look every now and then to what the agent
| is doing.
| lelanthran wrote:
| > By now it's grown to 100k lines of code
|
| Did you add an extra zero there? A journal with 100k
| lines of code, presumably not counting the framework it
| is built on?
|
| That doesn't sound correct.
| dotancohen wrote:
| > With AI agents, I can kickoff a task while I'm going to
| the park with my kids. Instead of scrolling HN, I look
| every now and then to what the agent is doing.
|
| How does that work? Are you running the agents on a
| server? Are you using gnu screen and termux? Can you
| respond to prompts asking for permission to e.g. run ls
| or grep?
| deaux wrote:
| All the big providers offer this. Usually they just work
| on your Github repo.
| dotancohen wrote:
| I see. So you're running an agent on a server against
| your github repo. Not working on your local machine.
| Thanks.
| 6510 wrote:
| I have at least two projects that I estimated to take a
| week or two but aren't finished after years. There might
| be others that just got abandoned that should be included
| in the count.
|
| Then there are things that work but aren't polished
| enough or should really have documentation.
| Antibabelic wrote:
| Why did you abandon them? Every time I ask this question,
| I get lots of sob stories, but not a single explanation.
| cgriswald wrote:
| I can't (due to other priorities) give consistent time to
| a project unless it is very important. That lack of
| consistency means I have to spend time re-learning what I
| was thinking and doing which is both inefficient and not
| fun. Since the projects are either experimental or not
| that important, I'm generally more motivated to do
| something else.
|
| Over time I've learned to not even start such projects,
| but LLMs have made it easier to complete such projects by
| making the work faster reducing the time variable in time
| over importance and easing the refamiliarization problem,
| adding to the set of such projects I'm willing to tackle.
| 6510 wrote:
| lack of character, distracted by other things for to
| long, drowning in unforeseen complexity, much slower
| progression than expected, bored with it, force majeure,
| etc
| resonious wrote:
| I hope at some point people don't feel the need to justify
| using or not using LLMs. If you feel like using them, use
| them. If you regret doing that, delete the code and write it
| yourself. And vice versa - if you are in a slog and an LLM
| can get you out, just use it.
| meysamazad wrote:
| I love this answer
|
| I really do
| 6510 wrote:
| You have to break down the problem into manageable chunks
| anyway, might as well feed those into a code agent while
| you write it yourself. If you don't like what it did
| explain what it did wrong. Shouldn't take long to figure
| out what parts are the biggest waste of time to write
| yourself. Do still have to hop tools and adjust your
| confidence as they improve.
| conartist6 wrote:
| What!
|
| Why is this, idunno a better way to say it, good?
|
| So ok you don't get into the weeds and you're proud of that,
| but also nothing you can think of wanting to do turns out to
| be worth doing.
|
| Those things are wholly related. Opportunity never comes
| exactly the time and the way you expect. You have to be open
| to it, you have to be seeking out new experiences and new
| ideas. You have to get into the weeds and try things without
| being entirely sure what the outcome might be, what insight
| you might gain, or when that insight might become useful.
| 6510 wrote:
| A friend of mine has a hilarious method for breaking though
| procrastination. His one trick is to spend money on the
| task/project, buy all kinds of things to make the job easier.
| It has to be useful but it is more about paying the unlock
| fee.
|
| Github is full of half forgotten saved games waiting for
| money to be thrown at them.
| browningstreet wrote:
| IMO LLMs/AI alone neither make nor break anything.
| sigmarule wrote:
| Are you writing software for the sense of accomplishment or to
| create software you wish you had?
| Lyngbakr wrote:
| The two aren't mutually exclusive.
| mckn1ght wrote:
| Conversely, one is not necessarily a prerequisite for the
| other.
| anon7000 wrote:
| That's really not the point of the post!
|
| The author is saying that "perfect software" is like a perfect
| cup of coffee. It's highly subjective to the end user. The
| perfect software for me perfectly matches how I want to
| interact with software. It has options _just for me_. It's fine
| tuned to my taste and my workflows, showing me information I
| want to see. You might never find a tool that's perfect for you
| because someone else wrote it for their own taste.
|
| LLMs come in because it wildly increases the amount of stuff
| you can play around with on a personal level. It means someone
| finally has time to put together the perfect workflow and
| advanced tools. I personally have about 0 time outside of work
| that I can invest in that, so I totally buy the idea that LLMs
| can really give people the space to develop personal tools and
| workflows that work perfectly for them. The barrier to entry
| and experimentation is incredibly low, and since it's just for
| you, you don't need to worry about scale and operations and all
| the hard stuff.
|
| There is still plenty of room for someone to do it by hand, but
| I certainly don't have time to do that. So I'll never find
| perfect software for some of my workflows unless I get an
| assist from LLMs.
|
| I agree with you about learning and achievement and fun -- but
| that's completely unrelated to the topic!
| ggauravr wrote:
| Thanks for this. This is exactly the spirit in which I wrote
| it.
|
| You hit on the key constraint: time. The point isn't that the
| use of LLMs specifically provides agency, but that it lowers
| the barrier, allowing us to build things that bring it.
| "Perfect software" is perfect not just because of what they
| do, but because of what it lacks (fluff, tracking, features
| we don't need).
| saagarjha wrote:
| Sometimes it's nice to have other people cook you a tasty meal.
| PunchyHamster wrote:
| I definitely made software for me with zero desire to learn,
| zero learning happening, just to scratch an itch.
|
| _that being said_ calling it "perfect" is on the nose, at
| least for my own, it does a thing, it does it good enough, and
| that's all. It could be better but it won't be because it's not
| worth it, because it's good enough
| ggauravr wrote:
| That is a fair distinction.
|
| However, I don't think using LLMs has to be an all-or-none
| proposition. You can still choose to build the parts you most
| care about yourself (where the learning happens) and delegate
| the other aspects to AI.
|
| In the case of the text justifier, it was a small nuisance I
| wanted solved with very little effort. I didn't care about the
| browser APIs, just the visual outcome, so I let the LLM do it
| all.
|
| If I were building something more complex, I would use LLMs
| much more mindfully. The value is in having the choice to
| delegate the chores so you can focus on the craft where it
| matters to you.
|
| While we might value the process differently, the broader point
| remains that these tools enable people to build things they
| otherwise wouldn't have the time or specific resources to
| create, and still feel a sense of agency and ownership.
| bitwize wrote:
| What's alarming to me is this:
|
| I remember some of the early phases of home computing. The
| whole point of owning a home computer was that in addition to
| using other people's software, you could write your own and put
| the machine to whatever use you could think of. And it was a
| machine you _owned_ , not time on some big company's machine
| which, ultimately, was controlled, and uses approved, by that
| company. The whole _point_ of the home computing market was to
| create an environment where people managed the machines, not
| the other way around. (Wozniak has said that this was one of
| his motivations for creating the Apple I and II.)
|
| Now we have people like this guy who say we finally have
| autonomy in computing--by purchasing time on some big company's
| machine doing numberwang to write the software for you.
| Ultimately the big company, not you, controls the machine and
| the uses to which it may be put. What's worse is these
| companies are buying up all the manufacturing capacity,
| starving the consumer market and making it more difficult to
| acquire computing hardware! No, this is not the autonomy
| envisioned by Wozniak, Jobs, or even a young shithead Bill
| Gates.
| PaulRobinson wrote:
| Hard agree.
|
| The first time I saw a computer, I saw a machine for making
| things. I once read a quote from actor Noel Coward who said
| that television was "for appearing on, not watching", and I
| immediately connected it to my own relationship with computers.
|
| I don't want an LLM to write software or blog posts for me, for
| the same reason I don't want to hire an intern to do that for
| me: I enjoy the process.
|
| Everything else, I'm in agreement on. Writing software for
| yourself - and only for yourself - is a wonderful superpower.
| You can define the ergonomics for yourself. There's lots of
| things that make writing software a little painful when you're
| the only customer: UX learning curves flatten, security
| concerns diminish a little, subscription costs evaporate...
|
| I actually consider the ability to write software for yourself
| a more profound and important right over anything the open
| source movement offers. Of course, I want an environment which
| makes that easier, so it's this that makes me more concerned
| about closed ecosystems.
| brap wrote:
| Great vision for 2030.
|
| But as for today, have we all just collectively decided to
| pretend that the LLMs we have are capable of writing good
| software?
|
| I use LLMs a lot in my workflow, I probably spend a whole day per
| week learning and fiddling with new tools, techniques, etc. and
| trying to integrate them in all sorts of ways. Been at it for
| about a year and a half, mainly because I'm intrigued.
|
| I'm sorry but it still very much sucks.
|
| There are things it's pretty good at, but writing software,
| especially in large brownfield projects, is not one of them. Not
| yet, at least.
|
| I'm starting to believe many are just faking it.
| habinero wrote:
| Most of them are, yeah. There are a _lot_ of Idea Guys on here,
| who are in love with the idea that they no longer need effort
| or skills to Create Their Vision. If they can just prompt hard
| enough, success will come rolling in.
| redhale wrote:
| Did either of you read the article? You seem to be arguing
| against a point it doesn't make. Tools like Claude Code are
| entirely capable today of one-shotting tiny bespoke web apps
| that do a narrow set of things for an audience of one.
|
| The article isn't talking about "large brownfield projects"
| or people wanting "success [to] come rolling in". It's about
| people making little apps for themselves, for personal
| enjoyment, not profit.
| zingar wrote:
| About 15 years ago I thought of writing custom software for
| friends and family instead of paying for gifts in order to save
| money (and give something more "meaningful"). For instance a fun
| guessing game using photos from a group holiday.
|
| I never did it because I imagined the pain of supporting every
| device or screen size, or dealing with someone who wants to know
| why their gift stopped working 6 months later.
|
| The gains I've seen from LLM code - making me personally more
| productive in languages I've never used before - don't erase the
| support burden so I think I'd still avoid this.
|
| Still, I wonder if soon ordinary people will find it easy enough
| to make software for their own amusement (not just us nerds doing
| side projects to stay current), and will my job ever morph into
| being a software "mechanic" who is paid to fix what someone else
| built? Not just "someone else working at the company who owns the
| software", but a different company or individual entirely?
|
| Will software maintenance become the job that big industry stops
| wanting to take because it's so cheap to write something new that
| they'll never fix this year's model?
|
| Or is software maintenance being democratised by LLMs such that a
| corner software shop could realistically offer maintenance for
| this one copy of a piece of software on this one device that the
| customer brings in?
|
| I think we've never discussed a "software right to repair"
| because changing software is expensive, but we might see that
| change.
| 2001zhaozhao wrote:
| What we really need is well-built open source software base with
| flexible and well-documented plugin SDKs where people can just
| vibecode their own extensions on top of them. The software needs
| to be designed from scratch expressly for the purpose of being
| extended in this way, and the SDK should place appropriate limits
| to allow multiple extensions to be combined easily.
|
| Otherwise, there is too much you have to do right before you have
| a suitable software base to start building your extra
| personalized features on. Building on existing open-source
| software (not designed to be extended on) isn't great either
| because you would need to merge any changes from the original
| software into your fork, as opposed to a purpose-built SDK that
| would better tolerate plugins on different base software
| versions.
|
| I'm working on this for gaming but the idea is really applicable
| to any kind of software, if the goal is to allow people to easily
| create and run personalized versions of them without as much
| effort and chance for things to go wrong.
| criddell wrote:
| So, something like Excel?
| zingar wrote:
| Interested in what you're doing with gaming. Are you literally
| extending game code?
| lwhi wrote:
| I disagree.
|
| How do we work together when we all have our own unilateral views
| of software?
| chickensong wrote:
| The article is about writing tools for yourself, not for
| collaborating with others. But if you must, open standards are
| the solution.
| andy99 wrote:
| I guess software is going to be like furniture - there was some
| (possibly imagined) period where it was very well made and bought
| for the long term, and (obvious where this is going) now there's
| lots of ikea crap that is easy and cheap but doesn't survive a
| move or getting water spilled on it, and is essentially Formica
| over cardboard.
|
| Overall both are net positives, I have some nice wood furniture
| and also a $7 Lack bedside table, and of course I rely on some
| industrial long term software (Linux e.g.) but almost every day
| vibe code some throwaway thing for a specific task.
| zingar wrote:
| I have the same furniture analogy in mind. If we imagine that
| more people have more agency when it comes to extending
| software, what does the software equivalent of repair look
| like? What does dumpster diving or a second hand software store
| look like?
| eszed wrote:
| Cloning and extending someone's long-abandoned github
| project?
| mgfist wrote:
| Most "good" software like you speak of was written long ago.
| Slop has dominated long even before LLMs.
| Pepp38 wrote:
| I see it as just another tool. Like any other tool, you have to
| learn it and integrate it into your workflow.
|
| And as a learning tool, it's extraordinary. Not because it
| replaces understanding, but because it accelerates it: you can
| explore unfamiliar domains, compare approaches, and iterate with
| feedback that used to take days or weeks.
|
| The responsibility to think, judge, and decide still sits
| entirely with the developer.
| sombragris wrote:
| Very OT, and this betrays my age, but...
|
| When I saw "Perfect Software" in the title, I thought it referred
| to Perfect Software, the developer who produced the Perfect
| Writer word processor, Perfect Calc spreadsheet, and Perfect
| Filer database. These were a suite of office software products
| developed in the early '80s for CP/M and MS-DOS computers.
| jauntywundrkind wrote:
| What seems perfect is the adaptability & changeability, the
| suiting to fit.
|
| We see LLMs as a huge opportunity here, to self define.
|
| And existing software as too limberous & weighty.
|
| But there are so many other dimensions and levels of how and why
| the past hasn't let us situate our software and us together
| effectively. The architecture of software doesn't have this grow-
| in-ability to it.
|
| I love the Home-cooked Software and Barefoot Developers material.
| But neither of those ideas nor perfect software nor audience of
| one actually appeal to me that strongly. They are all very
| positive enormous breaks from bad software and bad times where we
| didn't have basic liberty over systems. But they all strike me as
| valorizing a particularly isolated rejectionist view of software,
| that ultimately is rude to the protocols & affordances building
| that a good healthy _and_ connected form of software that we
| might and perhaps SHOULD aspire to.
|
| But anything unjamming is from the inflexible unarticulated
| illegible mess of systems we can at best endure today is doing
| great work. Many positive steps into greater beyonds out of bad
| tar pits. 2025 has amazing hope amid _all this_.
| guoxudong wrote:
| Yes, that's exactly what I'm doing right now--building my own
| software to restructure my work and life.
| bgwalter wrote:
| _Before LLMs, "perfect software" was largely a myth._
|
| We know, your blog is the first static webpage in existence.
|
| _Third, it brings back autonomy._
|
| This is the new talking point. Musk claims that cars that are
| always connected provide "autonomy", vibe coders claim that the
| stolen code distributed by Anthropic provides "autonomy".
|
| War is peace, freedom is slavery.
| rpdillon wrote:
| > vibe coders claim that the stolen code distributed by
| Anthropic
|
| You could approach these topics with more nuance, and your
| posts would be stronger.
|
| The current legal status is murky, and evolving!
|
| https://ipwatchdog.com/2025/12/23/copyright-ai-collide-three...
| leonflexo wrote:
| I only read this because while messing around with learning some
| basic VPS and NGINX, I used Claude to spin up some quick
| frontends. One ended up being a geocities hackernews clone. Then
| while getting some basic process and terminal experience, I piped
| into Codex CLI to generate a summary modal to my visual liking.
| All of that to say that while I could have done it on my own, I
| likely wouldn't have because it allowed me a low friction path to
| implementing the bits that weren't crucial for what I was trying
| to learn.
| bitwize wrote:
| Before LLMs, software wasn't just some artifact like a painting,
| a ladder, or a bloviating Facebook post--something ordinary
| humans made to suit their own purposes. It could only be made by
| the mutant lizard people from space who walk among us, wearing
| human skins, yet somehow having the innate ability to program.
| But by good old fashioned human ingenuity and manipulation
| tactics (aka marketing), we managed to trick the lizard people
| into building LLMs! Think of an LLM as an electronic genie that
| has, among other abilities, the lizard person's ability to write
| computer programs--and puts that power in the hands of ordinary
| human beings like you! Finally, after eight decades of computers
| --infernal machines built by the lizard people to enslave us all
| --the computer now does exactly what _you_ want!
| MostlyStable wrote:
| Of all the topics to judge LLM use, this seems the least
| appropriate. This is about people making software _for themselves
| and no one else_. Your opinion on the quality of _their_ software
| is entirely beside the point. No one is ever going to force you
| to use an LLM to make personal software. And no one is ever going
| to force you to use LLM-generated software that was explicitely
| made and intended to be used only by the one person.
|
| There are a lot of contexts where I can understand arguing
| against LLM use (even in cases where I might not entirely agree,
| I can _understand_ the objection), but this is not one of them.
|
| Don't think this will improve your life? Great, don't do it. But
| this is also the most classic case of "don't yuck other people's
| yum". If someone tells you they used an LLM to make some piece of
| software for themselves and they like it or that it improved some
| aspect of their life or workflow, what on earth is gained by
| trying to convince them that no, actually, it's not good and
| isn't improving their lives and is in fact garbage?
| jmathai wrote:
| Thanks to LLMs, I have revived personal projects that became
| too time consuming and complex to familiarize myself with
| again.
|
| While I enjoy the challenge of writing software, I more enjoy
| having the thing which does exactly what I want.
|
| LLMs are amazing for this.
| j45 wrote:
| Cosigned. Vibe coding for a senior developer is just ...
| coding - except developing software while walking around with
| your phone talking to it.
| chowells wrote:
| I would die of embarrassment if I had bad code in a project
| _for me_. I am at my limit for tolerating bad code in projects
| for others, where the economics don 't support taking the time
| that would be required to fix the deep problems. Code _for me_
| is going to be good. I won 't accept anything less. I need a
| countervailing force, reminding me of the beauty of clear
| expression of complex ideas.
| jdright wrote:
| 100% agree with this.
|
| I have years of experience, but I never had the time (or will) to
| take on some _very minor nuisances_ or different areas of dev far
| from my day job expertise.
|
| LLMs solved this. I produced about 12 different things that "I
| needed" to improve aspects of my life.
|
| Each single took between a few hours to 3 days, and most of them
| I use daily, they are the most used applications (mobile, desktop
| and web) for my family.
|
| It is a game changer.
|
| Personalized custom software would never really reach critical
| mass, LLM enabled it, this is the age of personalized software,
| egosoftware, llmware.
| deaux wrote:
| > Each single took between a few hours to 3 days, and most of
| them I use daily, they are the most used applications (mobile,
| desktop and web) for my family.
|
| How have you done distribution and auth? I'm interested in
| doing something similar but not sure of the best way to
| approach that part, especially with the family/multiplatform
| angle as well.
| jdright wrote:
| as basic as needed, most of them don't even require this.
| They are not products and we know their limitations.
| asgr wrote:
| "sufficient software"
| phendrenad2 wrote:
| I think we're going to see a lot more of this thanks to coding
| assistants, and it's going to get complicated when people start
| forking open-source programs and modifying them for their own
| personal use cases. I can see someone adding Feature X to their
| own fork of Project Y in a way that's incompatible with Project
| Y's roadmap, leading to drama between people who use the new fork
| vs people who are willing to wait for the "official" version.
___________________________________________________________________
(page generated 2025-12-24 23:02 UTC)