The End of the Tyranny of Software
Since the first computer programmers wrote the first computer programs, we—the users—have been forced to live in the worlds those programs create.
The features are the features. The design is the design. Want something else, something better? Learn to code, I guess.
That paradigm is now officially dead.
In late 2025, an update to Anthropic’s Claude model transformed Claude Code from a code generator that sometimes worked into one that was surprising when it didn’t. Suddenly, all you needed was $20 a month and a half-formed idea—and an AI model could build you functional software.
Andrej Karpathy, an educator and researcher who was on OpenAI’s founding team, had a name for this behavior: “vibe coding.”
The vibes were suddenly off the charts.
What Is Vibe Coding?
Vibe coding is the practice of describing what you want in plain language—and letting AI handle the technical implementation. It’s not about learning syntax. It’s not about becoming a developer. It’s about thinking about what you need and letting AI translate that into working software.
If you can explain what’s wrong, AI can probably fix it.
Tools like Claude Code, OpenAI’s Codex, GitHub Copilot, Cursor, Lovable, Replit—and thousands of others—are changing everything. They’re changing how professional developers work, yes. But more importantly, they’re enabling an entirely new kind of software:
Software made just for you.
The Era of Personal Software
For the first time in computing history, you don’t need to be a developer to build exactly what you want.
Think about what this means:
- Managing the family budget? Build a hand-crafted app with every feature you need—and exactly zero you don’t.
- Can’t make a to-do list app stick? Roll your own. Literally.
- Planning a family trip? Whip up a custom meal planner with a built-in grocery assigner.
Use it forever. Use it once. It doesn’t matter.
It doesn’t come with a subscription fee. It doesn’t send you marketing emails every day for the rest of your life. It doesn’t get sold to a private equity firm and suddenly feel different.
It’s your software.
And there’s never been anything like it before.
A Home-Cooked Meal for the Digital Age
In 2020, author and technologist Robin Sloan wrote a blog post entitled “An app can be a home-cooked meal.” In it, he explained why he built a simple messaging app for his family—one that would never change unexpectedly.
“There will be no sudden redesign, no flood of ads, no pivot to chase a userbase inscrutable to us,” he wrote. “It might go away at some point, but that will be our decision.”
Five years later, in late 2025, Sloan updated his post:
“I have changed literally nothing in the app, and it’s glorious.”
This is the promise of personal software. Not optimized for growth. Not designed to extract value. Just… yours.
Why This Matters Now
For decades, the gap between “what I need” and “what software exists” was filled by either:
- Settling for whatever came closest
- Hacking together solutions with IFTTT, Apple Shortcuts, or Excel macros
- Hiring a developer (expensive, slow, often still not quite right)
AI changes the equation entirely.
The cost of building custom software has collapsed. The time required has gone from months to minutes. And the skills required have gone from “computer science degree” to “can describe what you want.”
This is the real promise of AI—not chatbots that answer questions, but software that does exactly what you need it to do.
Every person who has ever thought “there’s gotta be a better way” now has one.
Notion: A Real-World Preview
Notion is perhaps the best current example of what this new world looks like in practice. The app initially took off as a mainstream take on the low- and no-code movement—offering building blocks like images, tables, and to-do lists that you could organize however you wanted. Users loved the customization, to the point that sharing wildly over-designed Notion pages became a productivity nerd pastime.
More recently, Notion has made the process even simpler: Just tell the built-in AI assistant what you want to accomplish, and it builds the page and system for you. “And because Notion provides so many underlying building blocks,” Ivan Zhao, Notion’s CEO, told me last year, “the AI only needs to write macros. The AI does not need to write software from scratch.”
The Risks Nobody Talks About
This new approach comes with real risks.
The big one: Your ideas might be bad.
Developers have found that users are incredibly good at noticing what they don’t like, but all over the place when it comes to offering solutions. When your bespoke AI “solution” makes things worse—or breaks the rest of the software in some way—who’s to blame? How is customer support supposed to help people when literally everyone is using the app differently?
If you’re a developer with lots of users in this new era of infinite customization, it might be more important than ever to build software that just works out of the box. Most people still use default settings. There’s no reason to believe every user is going to eagerly tweak every app’s every pixel to their exacting specifications.
“I think there’s a responsibility to ensure we provide a coherent user interface,” says Balint Orosz, CEO of the note-taking app Craft. “So if you like the core product, it feels like home.”
The goal isn’t to ask people to reimagine everything every time they open the app. It’s to let the user say “I want this bigger” and have it get bigger in a way that makes sense.
The New Toolbox
Much of the current vogue in AI technology is geared toward making this kind of software adaptation both easy and universal. The Model Context Protocol gives developers an easy way to expose their data to AI agents. More and more apps are integrating directly with Claude and ChatGPT.
Sure, you can use all this to ask your chatbot about your email. That’s the boring answer.
The better answer is to build yourself a brand-new way to email.
You Need Taste
In this new world, the most important thing you’ll need is taste. Not objectively good taste, necessarily—so much as a keen sense of your own.
You need to be like Rick Rubin, the famous music producer, who once told 60 Minutes that what made him successful was not any particular technical ability, but “the confidence I have in my taste, and my ability to express what I feel.”
Rubin practices that art with A-list celebrities. You need to be able to do it with AI.
Otherwise, you’ll land in what advocates call “doom loops”—telling your chatbot only what you don’t like and counting on the model to be the creative one. That way lies madness. And bad software.
A Real Example: My Personal Dashboard
“I have no opinions about databases,” one user confessed. “But I do care about typefaces and background colors.”
The first truly useful bit of software they vibe-coded was just a way to smash a bunch of existing apps into a single screen:
- Raindrop for bookmarks (ugly, but functional)
- Todoist for tasks (forgotten daily)
- Obsidian for notes (forever unorganized)
- Google Calendar (used religiously)
They failed over and over to build an app to replace those. But building a nicer way to look at them all took four API keys and an afternoon. A lot of “why doesn’t that button do anything” and “what does this error code mean” and “let’s try a color other than purple.”
They kept telling Claude Code to make an app that looked like a paper planner. It pretty much delivered.
Their app will never be in the App Store. They probably couldn’t explain how it works in a way that would make sense.
That’s the beauty of the era of personal software.
You don’t have to understand how it works. You don’t have to be able to explain it. You just use it.
We are no longer required to use the software we are prescribed, or accept something that works fine for everyone and perfectly for no one.
The best apps will be the ones that actually help you improve upon them. If you know what you need and what you like, you can make things work exactly the way you want.
No learning to code required.
The Real-World Limits
Sloan is a fairly knowledgeable coder and built his original home-cooked app by hand. These days, though, he’s using AI to make even more personal software.
“It’s always weird little things,” Sloan says. He runs an olive oil company and has whipped up ways to pull together product and customer information to automatically generate shipping labels. “It’s just a little Ruby script that pulls data from Shopify and USPS and kind of ties it together and it’s great.”
It’s also extremely hacky. “If I ever get hit by a bus, it’s going to be a problem for my olive oil company, because only Robin knows how to run the software.” But while Robin’s around, it’s working great.
Personal software has its limits, of course:
- No support line — your bespoke apps don’t come with customer service
- No security guarantees — they haven’t been thoroughly tested
- No enterprise scale — large companies won’t ditch expensive enterprise software for something their marketing department vibe-coded
Most of the apps we download are fine, regardless of who or what made them.
But we all have those edge cases—the entirely reasonable ways we’d love to morph our software to our exact needs. The only problem is everyone else has needs too, and none of them are ours.
The Productivity App Problem
The author’s own edge cases are most present in productivity tools. Over the years, they’ve tried every acronymic get-stuff-done system on the market—GTD, CARE, PARA, BASB, SMART, MIT, ZTD, and more—and dutifully poured their brain’s contents into every app with a checkbox feature.
Eventually, the pattern repeats:
- Get annoyed with the app’s one tiny missing feature or bizarre design decision
- Stop using that app
- Start forgetting things
- Find another app that does those things better
- Spend a day porting their whole life into that app
- Encounter its own missing features and bizarre design decisions
- Start the process anew
Over time, they built the list of features their ideal productivity app requires. Every one of them has been built extremely well by at least one developer—so they’re not asking for anything impossible. But there are no apps, not one, exactly zero, that check off the whole list.
When they called developers to ask why they were missing such obviously crucial features, they all said the same thing: Everyone has a list of requirements like this. No two users have the same list. And if you build everything for everyone, all you’ll really do is make a mess of your software.
“It’s ridiculously easy to build features right now,” says Amir Salihefendic, CEO of Doist (maker of Todoist). “But if you just do it naively, you end up with a system that nobody can figure out.”
In the era of personal software, though, you don’t have to build a system that works for everybody.
Building Timetable: A Real Test
They gave their app a name—Timetable—and described all the features they needed. It took about 20 minutes to build a reasonably functional prototype.
Then came the debugging.
Several days of describing to Claude Code all the things that didn’t work. Mostly copying and pasting error codes. Typing “what’s the full Terminal command” sixteen thousand times.
“I know how to code the way I knew Spanish in high school: I can ask about the library and order dinner, but nobody’s confusing me with a native speaker.” Their interactions with Claude Code amounted to “a lot of pointing and gesturing and hoping the tool figured out I wanted soup.”
Eventually, they had an app that worked more or less the way they wanted. It showed calendar, notes, and tasks all in one place. Looked nice. Easy to get stuff in and out.
Then they discovered it only ran locally on their laptop.
Thus began several more days of wiring everything up to GitHub, Supabase, Vercel, and other platforms. An interminable round of complaining to their AI developer bot: no, it’s still not syncing. Why did the Google Calendar connection fail? And “I’m so sorry but I have no idea what my GitHub secret code is.”
All that eventually sorted. They decided to make a native mobile app, since that would feel better—which kicked off several weeks of new errors, new features, and more accounts to sign up for.
The Design Problem
Actually writing the code is but one part of creating and maintaining great software, and even the most advanced current tools have their limits.
Design is maybe chief among them.
Claude Code attacked their app’s design with “fervent determination,” the way they assume Jony Ive stares at a slab of aluminum and imagines removing all the ports from your laptop. But in this case, every background ended up a gradient purple and every icon suggestion closely resembled a hamburger menu.
When they pushed the bot to think a little more abstractly about “the concept of a day” and design an icon to fit the combination of journal and planner, it proudly displayed its answer in PNG image form.
“I’m so sorry to tell you this,” they typed back, “but that looks like a butthole.”
Claude’s next revision was once again three horizontal lines.
“I’ve found that most coding agents suck at writing good interfaces,” says Brian Lovin, a designer and software engineer who works on AI products at Notion. He has also experienced Claude Code’s love for purple gradients. “I don’t know how to get it to not do that, except just annoyingly prompting it more and more and more.”
Lovin says he’s learned to trust AI completely on the level of adding a tab to the settings panel—but “in the early days, when there’s no scaffolding, I don’t trust it at all.”
The Vibe Coding Explosion
These limits don’t appear to have stopped huge swaths of people from becoming app developers.
The numbers are striking:
- Apple’s App Store grew 30 percent in 2025 after nearly a decade of slow decline—and looks likely to grow even more in 2026
- The store had just shy of 2 million apps at the end of 2024—vibe coders could help double that count by the end of 2026
- GitHub had its fastest year of growth in 2025
- 80 percent of new GitHub users use the Copilot coding agent within their first week on the platform
Boris Cherny, creator of Claude Code, says he knew the product was going to be a hit when he discovered the sales team was using it.
“That’s when I really started to get that this is not just for engineers.”
While some developers are looking to build The Next Great App, many are just shipping the thing they built for themselves. And many, many more aren’t shipping anything publicly at all.
They just use it. They just live their lives with software that works exactly the way they want it to.
The Wild World of Personal Software
In the course of reporting this story, tales emerged— from sources, friends, and readers— of countless different kinds of personal software. (“What are you vibe-coding these days?” is apparently a surprisingly good icebreaker in tech circles right now.)
There are infinite variations on the to-do list, because writing a to-do list app is the coding version of learning Deep Purple’s “Smoke on the Water” for beginner guitarists— it’s just the way to learn where your fingers go.
But the creativity goes far beyond that:
- Brenden made a command line app for ranking fantasy baseball players based on their recent stats and future projections
- Nathan wrote a script with Claude Code to introduce the concept of renewable energy to Transport Tycoon Deluxe— a game from the 1990s that otherwise only knows about coal
- Anthony built a tool for optimizing Secret Santa assignments
- Tucker rigged up a way to mark the location of dog poop in the backyard, for easy finding later
- Allan built a tracker for their migraines
- Brett created a way to track on which of their 102 stairs the mail carrier leaves a package
For most of these apps, the total addressable market is exactly one person and the revenue potential is precisely zero dollars.
It is personal software in the truest sense— built by, and for, one person’s exact specifications.
When Personal Software Goes Wrong (For You)
The author’s own early attempts are “a semi-permanent record of both agentic AI’s limitations and my own personality flaws.”
They gave up on Timetable after realizing they’d added a bunch of features they didn’t actually want. The whole thing was getting annoying to use.
They built another app they apparently called Spring— and have “absolutely no memory of what it even did.”
Basket was an attempt at a super-inbox for all the links, notes, tasks, and detritus collected daily. They built a pretty cool system for texting things into the app— then bailed when the Twilio bill came due.
“I am apparently just as capable as anyone else of making software that annoys me.”
You Don’t Have to Build From Scratch
What saved their efforts was a realization: personal software doesn’t have to be built from scratch.
Knowledgeable developers might be newly capable home cooks. But the rest of us are more like customers at Chipotle. We don’t make the food. We don’t even really assemble it. But we get to decide what goes where and how it’s served to us.
For most of us, the future of software is not building our own Excel from scratch— it’s using AI models to build spreadsheets wildly more capable than we could create ourselves. It’s building the Chrome extension for your favorite app that is really only missing a Chrome extension. It’s tweaking the way things look to suit your exact taste and needs.
Going forward, a professional developer’s job might be largely to build infrastructure.
“The minute you need multiple devices to stay in sync with a database, with some level of security … you’re talking developer primitives,” says Maggie Appleton, a designer and digital anthropologist currently working at GitHub Next.
Appleton has been tracking the rise of personal software for years. She coined the term “barefoot developers” for people who step up to learn the skills required to help their communities in ways no Big Tech firm would.
She believes in more people building software— if slightly less convinced than some that everyone should do so. And she thinks we need “some sort of effort of open-source, really good primitives that you can plug and play together.”
Some basic security systems. A few design best practices. A sturdy login system. Payment support.
Then, let anyone and everyone build on top.
Frequently Asked Questions
What is vibe coding?
Vibe coding is the practice of using AI tools to build software by describing what you want in natural language rather than writing code line by line. It’s about communicating your intent and letting AI handle the technical implementation.
Do I need to know how to code to use vibe coding?
No. Vibe coding is specifically designed for people who aren’t developers. If you can describe what you want, you can build it.
What AI tools are available for vibe coding?
Popular options include Claude Code (Anthropic), OpenAI’s Codex, GitHub Copilot, Cursor, Lovable, and Replit. New tools are emerging regularly.
Is personal software practical for everyday use?
Yes. More practical than you might think. The key use cases include managing budgets, planning trips, organizing family schedules, and creating custom tools for hobbies or work that mainstream apps don’t serve well.
What’s the difference between personal software and regular apps?
Personal software is built for a single user or small group, with no ads, no subscriptions, no data harvesting, and no redesigns. It does exactly what you need— nothing more, nothing less.
What are the risks of vibe coding?
The main risk is that your ideas might be bad— the AI will faithfully build exactly what you ask for, even if that “solution” creates new problems. There’s also the challenge of support: when everyone uses a custom app differently, getting help becomes tricky. Starting with good default settings and coherent design remains important even in the era of infinite customization.
What are the limits of personal software?
Personal software doesn’t come with customer support or security audits. It’s maintained by one person— if that person gets hit by a bus, the software might too. Enterprise companies won’t replace their systems with vibe-coded solutions. But for personal use and small operations, these limitations are often worth the tradeoff.
What are the current limitations of vibe coding tools?
Current AI coding tools excel at functional logic but struggle with design— they tend toward generic solutions like purple gradients and hamburger menus. You also need to handle deployment, syncing, and infrastructure yourself. But the tools are improving rapidly, and even with these limitations, thousands of people are successfully building personal software.
Do I need to build everything from scratch?
No. The Chipotle model is more realistic for most people: customize and combine existing tools rather than building from the ground up. Use AI to make spreadsheets more capable, build Chrome extensions, tweak interfaces to your taste. Professional developers will increasingly provide the infrastructure and primitives that anyone can build on top of.
Originally published via The Verge. Written by David Pierce.