There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.
The #VibeCoding checklist nobody talks about:
☐ Does it have error handling beyond try/catch everything?
☐ Are secrets in env vars, not hardcoded?
☐ Is there at least one integration test?
☐ Does the README match what the code actually does?
Check all four and you're ahead of 90% of AI-built projects.
« Le RECEL est le fait de dissimuler, détenir ou transmettre une chose ou une personne […] ou de faire office d'intermédiaire afin de la transmettre, en sachant que cette chose provient d'un crime ou d'un délit […]
Le recel peut également résulter du fait, en toute connaissance de cause, de bénéficier d'une chose provenant d'un crime ou d'un délit. »
Cf. https://fr.wikipedia.org/wiki/Recel
On est donc bien d'accord qu'utiliser l'#IA pour générer texte/image/son ou le #VibeCoding c'est du recel ? 🤔
re software "laundering": I just call it “sampling” software now. I have a great collection of samples for many situations I built up crate digging, and now I can make tracks pretty quickly, layering on a little solo when I feel like it. Depending on the situation (say, who this software is for, how much I "transformed" the samples) it'll feel like something I just straight out borrowed, but it'll also feel like mine at some point.
It feels eerily similar in terms of its ethical and creative implications. We'd lose a lot of music if we straight out banned sampling. And sampling royalties are now mostly corporate owners of catalogs pushing money amongst each other.
Ich versteh nicht, wie Leute beim #Vibecoding in einen Flow kommen... Ich sitze ständig rum und warte auf die #KI.
Trotzdem schneller und weniger Frustration, als wenn ich mich von Hand durch den Code wühlen müsste.
Programmieren ist einfach nicht meine Sprache. Ich kann in Formeln denken, aber nicht in Code.
So I now have "render surfaces" which are basically a render loop around a runtime session and it's loading a runtime bundle which is javascript which was generated by dropping the render surface into the AI chat and it turned into a reflection tool call and then you can also mount the render surface into a documentation render surface to show its docs and also make a kanban render surface.
I don't even know what I'm saying, but it's more and more starting to resemble familiar concepts, so I know I'll get there.
Lots more updates on my vibe-coded “News with Wes Fryer” website:
https://news.wesfryer.com
I used ‘regular’ Claude AI as well as Claude Code for the first time. PHP and html only, no backend database. GitHub code and documentation on:
https://github.com/wfryer/news-with-wes
Please check it out and share your feedback!
#ReclaimOurNewsFeeds #VibeCode #VibeCoding #MediaLit #edtech #edtechSR #news
Check out the video from my March 5th presentation at the #Thrive2026 Democracy conference: “Reclaiming Our News Feeds” (22.5 min)
https://www.youtube.com/watch?v=8v4UL9W2dFA
More session resources are on:
https://wiki.wesfryer.com/Home/thrive2026
#openweb #SocialMedia #Fediverse #Mastodon #Flipboard #VibeCoding #BlueSky #RSS
we have liftoff!
the inkling of a shell, separation of render surfaces, code bundles, hypercard sessions, raw js sessions, a full repl with autocomplete, reflection on docs, code editor.
If only i had persistence...
starting to get a bit more worried about llm supply chain attacks so took a few of the best practice articles I could find out there and of course vibecoded a little validation framework.
I use the SICP idea of using language as an abstraction builder, so use go to do the annoying scaffolding, provide GH API primitives, workflow yaml parsing primitive, and output format rendering, then pass those to a JS VM and do the actual work there.
I get full separation, and the abstraction layer makes the code small and easy to review.
Now obviously I will need some time to read the articles and understand what this is all about, but I have a serious toolset (including a REPL!) to get work done.
#TIL that, again, #Djikstra was a ahead of his time, saying that what we call #VibeCoding is flawed because a language is a less precise tool than a formal representation:
'On the foolishness of "natural language programming"' (late 1970s)
https://www.cs.utexas.edu/~EWD/transcriptions/EWD06xx/EWD667.html
One of the funny things about #vibecoding is that making a note of a bug takes as long as typing that same info into the AI. The only issue is that you don't know what can of worms that fixing the bug will open so I always struggle with do I just make a note or try and fix it really quick. Today... its the latter.
Die ganze Widersprüchlichkeit des #LernenmitKI auf meiner Startseite: Im #FediLZ wird #vibecoding als Next Level Werkzeug gefeiert und Amazon fährt AWS damit vor die Wand.
"Amazon plans to address a string of recent outages, including some that were tied to AI-assisted coding errors"
> Amazon said in a statement at the time that the outage was the result of “user error” and not AI
Translation: "It's not AI if there was a human somewhere that clicked on the 'vibecode this for me' button". 🤡
I tried #vibeCoding my election visualizations. #ClaudeCode did well, but considering that my #generativeAI assistant didn't have eyes or fingers, I had to give it a lot of guidance to make something readable and usable.
https://weill.org/2026/03/09/vibe-coded-visualizations/
#dataviz #electionViz
Your LLM Doesn't Write Correct Code. It Writes Plausible Code https://lobste.rs/s/dnqcvh #vibecoding
https://blog.katanaquant.com/p/your-llm-doesnt-write-correct-code
I just spent the last 24 hours building... a free tool to create your very own handwriting font quickly within the browser (no logins, all local processing):
https://arcade.pirillo.com/fontcrafter.html
Having tested it extensively on my own manuscript, I can definitely say that it works. ;) Download the OTF and/or TTF when done!
I have way too many items in my Nextcloud Tasks app. Fun #selfhosting stuff, #AntennaPod and #OpenPodcastAPI things and simply annoying household tasks. Would love to have an Android app that goes through them, asks me how much time and energy I have, and then proposes some things I could do.
So if anyone's looking for a (vibe)coding project…
#Nextcloud #development #vibecoding #durftevragen #AI cc @selfhst
Was tun, wenn falsche Einträge im #Marktstammdatenregister die Auswertung ruinieren?
Das Register ist berüchtigt für Fehleinträge durch Anlagenbetreiber. Fehlerhafte Stammdaten können #Diagramme massiv verzerren – besonders bei Ausreißern. Für meine #Windkraft-Auswertungen musste ich bereits eine Korrekturlogik in das #Python-Skript einbauen. Zugegeben, ich habe es sehr primitiv umgesetzt. 🫣🤭
https://tino-eberl.de/vibe-coding/fehler-im-marktstammdatenregister-fehlerkorrektur-zur-laufzeit/
true #vibecoding gives you no copyright to the end result, and at the same time exposes you for unknown liability for #copyright infringement. and if you promised to transfer copyright to the results to a client of yours, there's also a legal defect.
using #llms as dumb-ish auto-complete is mostly fine, but giving it autonomy is like copypasting random stuff from the internets and hoping for the best.
Voxtral Memos — My First iOS App
Voxtral Memos — a privacy-first voice memo app for iOS, powered by Mistral AI.
Is it still the case with #vibeCoding? Now the code is done by machines, for machines. It's too much for humans to validate anyway. The only criterion is passing tests / does its job.
So why even bother with #programming languages? They are for humans too!
#ai
