When I was a kid, I was interested in a number of professions that are now either outdated, or have changed completely. One of those dreams involved checking out books and things to patrons, and it was focused primarily on pulling out the little card and adding a date-due stamp.
Of course, if you’ve been to a library in the last 20 years, you know that most of them don’t work that way anymore. Either the librarian scans special barcodes, or you check materials out yourself simply by placing them just so, one at a time. Either way, you end up with a printed receipt with all the materials listed, or an email. I ask you, what’s the fun in that? At least with the old way, you’d usually get a bookmark for each book by way of the due date card.
As I got older and spent the better part of two decades in a job that I didn’t exactly vibe with, I seriously considered becoming a programmer. I took Java, Android, and UNIX classes at the local junior college, met my now-husband, and eventually decided I didn’t have the guts to actually solve problems with computers. And, unlike my husband, I have very little imagination when it comes to making them do things.
Fast forward to last weekend, the one before Thanksgiving here in the US. I had tossed around the idea of making a personal library system just for funsies a day or so before, and I brought it up again. My husband was like, do you want to make it tonight using ChatGPT? And I was like, sure — not knowing what I was getting into except for the driver’s seat, excited for the destination.
Vibing On a Saturday Night
I want to make a book storage system. Can you please write a Python script that uses SQL Alchemy to make a book model that stores these fields: title, author, year of publication, genre, and barcode number?
So basically, I envisioned scanning a book’s barcode, pulling it up in the system, and then clicking a button to check it out or check it back in. I knew going in that some of my books don’t have barcodes at all, and some are obliterated or covered up with college bookstore stickers and what have you. More on that later.
First, I was told to pip install sqlalchemy, which I did not have. I was given a python script called books_db.py to get started. Then I asked for code that looks up all the books and prints them, which I was told to add to the script.
Then things were getting serious. I asked it to write a Flask server and a basic HTML front end for managing the books in the system. I was given the Flask server as app.py, and then some templates: base.html to be used by all pages, and index.html to view all the books, and add_book.html to, you know, add a new book. At that point, I got to see what it had created for the first time, and I thought it was lovely for a black and white table. But it needed color.
Check It Out
I asked the chat-thing for features and implemented them piecemeal, as you do if you’re not a masochist. First up was a cute little trash-can delete-button for every entry. Then it was time to set up the CheckoutEvent. Each of these events records which book it belongs to, whether it’s a check-out or check-in event, and the timestamp of said event. Of course, then it was time to get the checkout history wired to the front-end and accessible by clicking a book’s title.
All I really had to do was add a history route to app.py, update index.html to make the titles clickable, and create the book_history.html it spat out. Then I had it add the buttons for checking in and out on the new checkout history page, which involved adding routes to app.py as well as a helper to compute the current status.
Then it had me modify the history route and update book_history.html with the actual buttons. And they’re super cute, too — there’s a little red book on the checkout button, and a green book on the check-in.
Barcode Blues
On the index.html page, can you add a barcode number-based search box? And when the user searches, redirect them to the book page for that barcode?
Now it was time to get the barcode scanning situation up and running. I was sure at some point that ChatGPT would time me out for the night since I use the free model, but it just kept helping me do whatever I wanted, and even suggesting new features.
I wanted the barcode handling to be twofold: one, it should definitely pull the checkout page if the book exists in the system, and it should also definitely go to the book-entering page if not.
Yes — that’s a great workflow feature.We’ll add a barcode search box to your index page, and when someone submits a barcode, the app will:
-
Look up the book by barcode -
Redirect straight to that book’s checkout history page -
Show a nice error if the barcode doesn’t exist
I did what it told me, adding a barcode search route in app.py and updating the index() route to use it. I then added its barcode search form to index.html. It was at this point that I had to figure out a way to generate barcodes so I could make little stickers for the books that lack them entirely, or have otherwise obliterated ones.
I have a pretty basic 1D barcode scanning gun, and it won’t scan everything. As I soon found out, it prefers fake EAN barcodes to UPCs altogether. I finally found an online barcode generator and got to work, starting with a list of randomly-generated numbers I made with Excel. I decided I wanted all the fake barcodes to start with 988, which is close enough to the ISBN 978 lead-in, and happens to use my favorite number twice.
We took a brief detour as I asked the chat-thing to make the table to have ascending/descending sorting by clicking the headers. The approach it chose was to keep things server-side, and use little arrows to indicate direction. I added sorting logic to app.py and updated index.html to produce the clickable headers, and also decided that the entries should be color-coded based on genre, and implemented that part without help from GPT. Then I got tired and went to bed.
The Long, Dark Night of the Solo Programmer
I’m of a certain age and now sleep in two parts pretty much every night. In fact, I’m writing this part now at 1:22 AM, blasting Rush (2112) and generally having a good time. But I can tell you that I was not having a good time when I got out of bed to continue working on this library system a couple of hours later.
There I was, entering books (BEEP!), when I decided I’d had enough of that and needed to try adding more features. I cracked my knuckles and asked the chat-thing if it could make it so the search works across all fields — title, author, year, genre, or barcode. It said, cool, we can do that with a simple SQLAlchemy or_ query. I was like, whatever, boss; let’s get crazy.
Can you make it so the search works across all fields?
It had me import or_ and update the search route in app.py to replace the existing barcode search route with a generalized search using POST. Then I was to update index.html to rename the input to a general query. Cool.
But no. I messed it up some how and got an error about a missing {% endblock %}. In my GPT history it says, I’m confused about step 2. Where do I add it? And maybe I was just tired. I swear I just threw the code up there at the top like it told me to. But it said:
Ah! I see exactly why it’s confusing — your current index.html starts with the <h1> and then goes straight into the table. The search form should go right under the <h1> and before the table.
Then I was really confused. Didn’t I already have a search box that only handled barcodes? I sure did, over in base.html. So the new search code ended up there. Maybe that’s wrong. I don’t remember the details, but I searched the broader internet about my two-layer error and got the thing back to a working state many agonizing minutes later. Boy, was I proud, and relieved that I didn’t have to ask my husband to fix my mistake(s) in the morning. I threw my arms in the air and looked around for the cats to tell them the good news, but of course, I was the only one awake.
Moar Features!
I wasn’t satisfied. I wanted more. I asked it to add a current count of books in the database and display it toward the top. After that, it offered to add a count of currently-checked-out vs. available books, to which I said yes please. Then I wanted an author page that accepts an author’s name and shows all books by that author. I asked for a new page that shows all the books that are checked out. Most recently, I made it so the search box and the column headers persist on scroll.
I’m still trying to think of features, but for now I’m busy entering books, typing up check-out cards on my IBM Wheelwriter 5, and applying library pockets to the inside back covers of all my books. If you want to make your own personal library system, I put everything on GitHub.
On the Shoulders of Giants (and Robots)
I couldn’t have done any of this without my husband’s prompts and guidance, his ability to call shenanigans on GPT’s code whenever warranted, and ChatGPT itself. Although I have programmed in the past, it’s been a good long time since I even printed “Hello, World” in any language, though I did find myself recalling a good deal about this and that syntax.
If you want to make a similar type of niche system for your eyes only, I’d say this could be one way to do it. Wait, that’s pretty non-committal. I’d say just go for it. You have yourself and the broader Internet to check mistakes along the way, and you just might like some of the choices it makes on your behalf.
I usually enjoy reading your articles just for your writing style, but this one just raised the bar. Great start to my morning!
She had me at ……. 2112!
Absolutely agree,
the writing style is great!
Did the same thing but for: cd,dvd,bluray,book management + ereader + jellyfin integration, isbn lookup, lable generator, currency, i18n, reading stats wishlist the whole 9 yards. works great!
The problem with these tools is though, you are easilly the only one using it + maintaining it. so do not create too many AI side projects!
I vibe coded a real simple Flask app with python last week. I knew in general how it should work, but have never used Flask before. It’s a one page file server that lets me upload emulator saves and download them from a central location so I can manage saves across multiple devices. Maybe I can browse it when I have down time and actually learn flask. But it was neat to get something personal done so fast.
A vibe coded server facing the net? Oof.
Where exactly did it say it was facing the net?
Let’s hope it’s behind a VPN and not raw dogging it.
Depending on the devices this seems like something that could be handled by Syncthing or a WebDAV server more easily.
Ya know what? If this is what Hackaday is about now, I’m done. I started reading this site when it was about creativity, and slop machines ain’t that.
But this is appropriate, as this is a hack in the sense that adequate use of technology helped her gain a huge amount of time on achieving her project. Of course this is subjective, because some may enjoy spending the time to do everything by themselves, but still a hack, because she did it faster than most people could. There are use cases where AI is not wrong.
Interesting take. I enjoyed the article, and have found myself in a similar situation (where vibe coding helped me hit an impossible deadline at the cost of tight code, but that met the requirements here).
If every HAD article was about this, yeah eventually I’d stop coming, but I appreciate the varied assortment of articles, provided none of the actual articles are written by AI.
Why?
Do you even understand what ai slop originally referred to, or do you blindly apply it to every single usecase?
Do you feel the same way about other automated tools?
Was the industrial revolution full of ‘slop machines’ as well?
Clara, I’ve seen your name enough to recognize it, and your projects on hackaday.io, and think you’re making a mistake. Our plucky author “programmed” a personal project while sleep deprived and it still worked. She even mentions that she couldn’t cut is as a professional programmer. But she did it. I think this article is about ambition more than cutting corners.
Yeah I have to join the others and gently challenge this position.
A few decades ago, a certain curmudgeon of a similar viewpoint would have said “ I can believe this was done on a turnkey consumer packaged all in one personal computer and not on a real mainframe and terminal with real mechanical relays. Pfft”
Just because they’re using new tools to achieve and outcome, learn something it doesn’t invalidate the journey they took.
Should we all go back to scribbling on cave walls with charcoal, because anything more is using the tools of those upon whose shoulders we stand?
AI, Reeeeeeee!!!
I vibe coded a flask app to display co2 level and temperature from mqtt and allowing voting on thermal comfort back to mqtt and to a influxdb via node-red
All of the books in my personal library (1000+) have had Dewey Decimal codes on them since i was a kid decades ago. I use a program called Tellico to inventory both my book as well as my massive multimedia (vinyl LPs, DVDs, BluRays, VHS, Beta, LaserDisc, SelectaVision, etc). Most everything has a barcode you can scan, but if not, it’s simple to enter the title by hand and do a search. Makes finding a single item MUCH easier in a large collection.
Standing on the shoulders of $20 month to regurgitate stack overflow code
She never coded.
Now she did this.
Now she will learn about ‘life cycle’ and effort ratios.
In the end, she will finally learn to code, fixing this Rube Goldberg Lego mess.
To preserve the sunk effort of scanning all her books.
Either that or her husband will get stuck with ‘maintenance’ (read find decent library manager and import data).
What I’m saying is ‘vibe coding’ is a trap unless you immediately throw the thing away.
Like typing in games from computer magazines when I was a kid.
Also: ‘Library Science’ is a thing.
Predates CS by centuries.
You (well not YOU, you’re an idiot) could get a PhD in Library Science.
I never knew Library Science was a thing until I met my wife who has a master’s degree in it. It’s pretty cool stuff.
“She never coded.
Now she did this.”
Whatever else you want to say, AI and vibe coding is democratizing the interest in and creation of software tools by people who might not have gotten on the right on-ramp early enough. This is good (unless gatekeeping).
There are a ton of possible futures for this person (and project), none of which could likely ever have existed 3 years ago.
Actually she mentions that it was a free account ;) I use API access (mostly through openrouter) myself, keeps me way below that $20/month. And since we use these tools, i can see that AI generated code from the top models surpasses stack overflow in 99% of the cases. The quality has improved immensely for the last 12 months. Probably because frontier labs see coding as a number one business case.
Article fun and v non cynical – loved it
Not vibe-coded, but… For barcode scanning on a mobile device on an intranet site, I built a browser client function to take a pic to upload, with viewfinder to preview and position w/ vid overlay, then Zebra Xing to decode server side and return to client to validate. Not what I’d call the greatest, but free lib and did work.
I have no objection to this, why should I? To me the question is, and this seems to be a regular thing in these parts, why specifically ask for Python? I understand that it’s the current hotness. Years ago I built a PHP/MySQL database that I have used over and over, extending and altering as needed. It’s how I learned (some) PHP and (some) mySQL. But let a thousand different strokes bloom. On the plus side, now that I know the writer lives in the U.S. I feel free to criticise writing and spelling! Bonus!
I’m a fan of PHP but the PHP job market is rapidly declining. Fad JS servers are the rage now. Python remains popular for beginners and in its niches like data science or CUDA-wrapper. That popularity really helps the LLM write correct code.
I was by no means giving or intending to give advice. Anyway I worked in PHP 5 so I’d have some learning to do to get up to speed with whatever’s current (8? 9? I dunno) because it’s not backwards compatible. Paraphrasing something I heard in another context, “The good thing about Python is anyone can use it. The bad thing about Python is that anyone can use it.” Can’t figure out how to put “Established track record of learning no Python” on a resume.
This is a great article and library is a great project. I also (Nov 2025) put together a library application. I used phone camera to get the titles into the software, and AI lookup to create a card catalog entry with a description and everything. I used the Library of Congress API to lookup the LOC call number rather than using Dewey decimal. Soon, I hope to add a checkout-by-photo feature which uses AI to scan a phone camera photo to fill in all the fields for checking out a book. That bypasses any barcode requirement. I also used book pockets and book cards to go into the pockets. I added acid free stickers onto the pockets to show the title, author, and call number.
LLM coding is so legit when you follow the other coding best practices. Mentally, I go from programmer to supervisor. If you’re reading the results and committing to git you’re doing better than most vibe coders. You’re breaking the problem into small enough chunks for the LLM, so you understand the big picture. That’s so much better than “my LLM deleted the production database” lmfao.
Definitely use an IDE. VS Code + Github Copilot works for me. That will let the LLM read the existing code and avoid so many contextual issues.
Same. I use Claude and opencode with a plethora of models (openrouter can be great for that as well), from the terminal in my editor (Zed). OpenSpec can help preparing the chunks and document your project so agents can stay within sane bounds. You just check the bigger picture, coding practices and style, and the rest is done. Sometimes a problem is too complex, of course, but even then, most of the time feeding some pseudocode and smaller chunks fixed that too.
Wow. Another rabbit-hole, worth reading. Someone else who had some time. i’m finally retired and for fun try to keep working my PCLinuxOS laptops and desktop compu. So, recently have used ChatGPT to solve this and that computer problem instead on posting on the forum and … waiting for someone to comment. Besides, it’s kinda fun. So, we’ve been working up from short questions to longer ones to finally – we have a collection of 200 Bahá´í Writings in Spanish and wanted a way to use Chat or some other LLM to ask it questions but having everything locally housed on the desktop. Thus began the journey… we switched to Claude after a while – it’s just better in some inexplicable way. We have a little script that we can use on the collection and hope to be able to make it internet-facing in kind of limited way eventually. But it’s been a pain. First we didn’t have near enough RAM, much less and GPU – lol. Our son gave us his old Fatboy and we found some more RAM in the proverbial drawer and … this particular XFX Fatboy 590 is not recognized – not even by the OS. So, it’s been a trip. Trying to make things that might be of use to others is just rewarding – if conducive to hair-pulling behavior at times, but it’s worth it to me. Whenever Chat 5 would conk out, we’d just go do something else ’till it decided we could use it again – so no biggie there. Thanks for the chance to share. Have a beautiful evening and be happy :)
“Vibe coding” is just “I can’t be bothered doing this, but I want credit for having done it regardless.”
I’ve been wanting to dip my toes into LLM assisted coding, but I can’t stand the thought of giving sam altman my money or attention. Is there a slightly less unethical solution out there? Have folks had any luck with self hosted models?
Yes, people do use self-hosted LLMs for vibe coding. You do need a decent computer (preferrably with a GPU), though. Just try Googling something like “localllm coding” .
Self-hosted models are not necessarily always ethical…but at least those corporates won’t be able to collect your data.