"Software is Over": Someone Vibe-Coded All of Adobe’s Products And Open-Sourced Them

[LevelUP]

"Software is Over": Someone Vibe-Coded Open-Source Adobe Clones
https://futurism.com/future-society/adob...e-artcraft

Adobe:


Somebody vibe-coded free open-source clones of basically the whole Adobe suite in Rust and dropped them a few days ago.

The guy (Brandon Thomas, @echelon) used Claude Opus agents to build PhotoCraft (Photoshop), VectorCraft (Illustrator), FilmCraft (Premiere), LightCraft (Lightroom), EffectCraft (After Effects), DesignCraft (InDesign), and PrintCraft (Acrobat). Mostly clean-room from public docs and watching the real apps, no decompiling.

He got the first versions out over a weekend. PhotoCraft alone is around 250k lines of Rust already, has real PSD support, a GPU compositor, and runs on Mac/Windows/Linux + browser.

[DegreeNerd]

Closed source is dead.

Everything can be reverse-engineered now!

[LevelUP]

I remember when this AI coding stuff first started to take off in the fall of 2024. I tried Cursor AI, and while it was cool at first, it completely fell apart once a project hit 1,000 to 2,000 lines of code.

Back then, asking the AI for a tiny CSS tweak meant watching it refactor your entire codebase, strip out core dependencies, and completely crash the program. You’d have to prompt it five times just to get a color change right. It would have been ten times faster to just do it manually.

Seeing what AI can do now is mind-blowing. It genuinely feels like going from an Intel 8088 chip to Apple Silicon in just two years.

[SteveFoerster]

AI-supported coding is getting better. So on the one hand, given that the software in this article is described as "pre-alpha" quality, I'll hold off a little longer on Adobe's eulogy. But on the other hand, Adobe and companies like them better have a plan for what's coming.

As an experiment, I tried to get the free Nemotron models to vibecode a browser-based version of the old Star Raiders game for the 8-bit Atari. It was... well, partially successful.

[Maltus]

Oh well if you read the articleyou get that they didn't "reverse engineer" Adobe, they created apps that can do the same for free as the shitty subscription-Adobe-stuff. But it is all still in early developement, so at this time you have to stick with Adobe...

The title of the article is a bit clickbaity...

[bluebooger]

a youtuber (The Cherno) asked claude to create 3D game engine

this is what it came up with
https://www.youtube.com/watch?v=R_uf5OfMGio&t=2580s

its pretty impressive

he told it to use this file as a prompt
https://gist.github.com/TheCherno/ccf5d7...9474c7af5d

The Cherno is an experienced C++ programmer and said he will do a code review of the engine once he's had time to look over the whole thing

[LevelUP]

Here's another article that describes the process a bit better. 

According to Ars Technica, developer Brandon Thomas used Anthropic’s Claude Opus 5.5 and Rust to reverse-engineer Adobe’s core software suite into an open-source clone called ArtCraft.

https://www.vice.com/en/article/everythi...ally-work/

He used a clean room implementation, which is a method used to recreate a competitor's product through reverse engineering without infringing on copyrights.

[DegreeNerd]

I remember when this AI coding stuff first started to take off in the fall of 2024. I tried Cursor AI, and while it was cool at first, it completely fell apart once a project hit 1,000 to 2,000 lines of code.

Back then, asking the AI for a tiny CSS tweak meant watching it refactor your entire codebase, strip out core dependencies, and completely crash the program. You’d have to prompt it five times just to get a color change right. It would have been ten times faster to just do it manually.

Seeing what AI can do now is mind-blowing. It genuinely feels like going from an Intel 8088 chip to Apple Silicon in just two years.

I've heard it described as the industrial revolution (which lasted roughly a century) compressed into less than a decade. 
Too many people write-off AI as irrelevant overhyped nonsense based on their personal experiences from a year ago, which is totally irrelevant to today! Or they just tried out a free AI chat service, which again is also totally irrelevant to what's cutting edge tonight. 

Anyway, Fireship on YouTube as always made a good video about this tech news: 
https://www.youtube.com/watch?v=wajoP_5Cpw8

---

As an experiment, I tried to get the free Nemotron models to vibecode a browser-based version of the old Star Raiders game for the 8-bit Atari. It was... well, partially successful.

Get yourself a Claude subscription (or anything else that gives you a generous quota of SOTA models, such as Cursor/GrokBot/etc)
It will do that then without breaking a sweat.

[SteveFoerster]

Get yourself a Claude subscription (or anything else that gives you a generous quota of SOTA models, such as Cursor/GrokBot/etc)
It will do that then without breaking a sweat.

Thank you for assuming the model was the issue and not my prompting! It did mostly work, and I could have refined it to improve but I wasn't really going to play it, so I was satisfied with it as a demo.

For now I'm happy playing around with the free ones to get a feel for what various models can do.

Besides, frontier models may be a little smarter, but I'm not trying to solve Millennium Prize-style problems here.

[LevelUP]

I've heard it described as the industrial revolution (which lasted roughly a century) compressed into less than a decade. 
Too many people write-off AI as irrelevant overhyped nonsense based on their personal experiences from a year ago, which is totally irrelevant to today! Or they just tried out a free AI chat service, which again is also totally irrelevant to what's cutting edge tonight. 

Yes, I agree. This is definitely a revolution unlike anything we've ever seen before.  I think the AI revolution will unfold in two phases: a massive gold rush followed by rapid commoditization.  Take video games, for example. Roughly 20,000 games were released on Steam in 2025, with estimates of 25,000 in 2026 and projections as high as 60,000 in 2027!

When AI dramatically lowers the cost and time required to create something, the supply of that thing explodes. And when supply explodes, differentiation becomes increasingly difficult.

In a world where anyone can build almost anything, the scarcest resources won't be code or technical skills. They'll be good judgment, attention, trust, and distribution.

As an experiment, I tried to get the free Nemotron models to vibecode a browser-based version of the old Star Raiders game for the 8-bit Atari. It was... well, partially successful.

Get yourself a Claude subscription (or anything else that gives you a generous quota of SOTA models, such as Cursor/GrokBot/etc)
It will do that then without breaking a sweat.

Thank you for assuming the model was the issue and not my prompting!  It did mostly work, and I could have refined it to improve but I wasn't really going to play it, so I was satisfied with it as a demo.

For now I'm happy playing around with the free ones to get a feel for what various models can do.

Besides, frontier models may be a little smarter, but I'm not trying to solve Millennium Prize-style problems here.

There's a huge demand for nostalgia-driven games and simple, fun experiences. Not everyone is trying to build the next GTA 6. Plenty of people just want to experiment, tinker with ideas, recreate childhood favorites, or bring a small creative vision to life. That's where AI is becoming a real game changer.

As for why AI struggled to recreate Star Raiders, I suspect the biggest issue was a lack of context. AI can analyze text and images, but depending on the tools being used, it may not be able to directly watch and understand videos. That means it's missing critical information about the original game's mechanics, controls, timing, and overall feel.