I think it’ll be used to push everything I to the cloud since they can “no longer trust putting code on user’s local machines” and we will all have to rent streamed software experienced for the rest of our lives or be unable to function in society.

Honestly fuck capitalism for taking us down this road.

Yeah, this is all over tech news for the past month. The entire Adobe creative suite got reverse engineered. Someone reverse engineered Skate and combined it with Call of Duty or something.

The big companies are suddenly talking about how bad AI is...

https://github.com/songshikang0111/awesome-REA-cases

I tested REA with Qwen 3.8 27B with a narrow solver capability from some commercial 3d software and it was quick to extract 20,000 lines of Ghidra C-like pseudocode, but painfully slow to turn it into actual C++. It struggled interpreting all the matrix math and making something that actually worked. I stopped after a couple days of it churning, figuring it could spend a couple weeks and end up with worthless slop. I’m a software engineer and don’t have a background in RE, so maybe someone with more experience would do better.

De-obfuscation is probably one of the few ok uses for a ethically trained LLM

Given what is happening to Project Zombiod right now... I think it working pretty darn well.

The advantage of decompilation as a task is that you have a reference output you can validate against.

I would assume the approach, mechanisms, and quality of produced code is similar to general/prompted code generating.

I assume the produced code (and its quality) depends on the compiled code; how much was stripped or obfuscated, and what runtime are we talking about which may or may not have language constructs that guide structure. With little metadata or code structure left AI would shift more into it's general patterns than if there is more metadata available that already defines structures or names.

The thought of integrating a deterministic decompiler and then use AI to structure it and make it more readable while verifying the output remains the same seems like an interesting extension or alternative workflow and toolchain.

I have not used these kinds of AI decompilation tools or workflows, but thinking purely from my background and general experience.

I think for the long term success, they need to write better readable code. But this only comes after the legal part is solved, in example how copyright is handled if an Ai is involved.