alt Hacker NewsREA Reverse – Engineer Anything
Comments
I'll have to take a look at this, but I've found that the top models do quite well at this work without any extra work.
The Windows Remote Desktop client has two bugs that have been driving me crazy for the better part of a decade. One day I got fed up and fed the binary to Claude, asking it to fix the two bugs. And it just did it. Patched one with some NOPs and adjusted a stack offset for the other. Produced a credible explanation for both, and in fact the fix worked. It helps that I was able to describe the bugs clearly, but still, it had to figure out the right spot among megabytes of executable code.
I wonder if this is why I've seen a lot videos popping up on my youtube feed related to vibe coded clones of various commercial apps in the past few days. Everything from clones of flagship products from Adob to Microsoft Office.
Adobe product clones like Photoshop and Illustrator: https://www.youtube.com/watch?v=eFB79TYI-Vw
Adobe after effects clone: https://www.youtube.com/watch?v=5mi_tYSdkWQ
MS Office suite clone: https://www.youtube.com/watch?v=U_jTYMOlXio
I see this liquid software being the unavoidable future. A computer that just does stuff in whatever way you guide it, in whatever way you like guiding it. The models will keep getting better and faster up to the point where everything is just happening in real time, no OS no drivers no programs, just an entity that can listen to you and can move around bits to accomplish whatever you are trying to do. Wanna post on HN? Any way that you can code such an action, the computer can just manifest it for you, on the fly, however you want it.
I love such work. I hope to roll it into a package that anyone can use in the future. This work is only going to get more important because frontier models getting locked down will make this a lot harder over time.
For example, I use Claude as a bouncing wall for my thoughts and I pointed out that,
> GLM 5.2 was the only thing that helped HF while the agents were trying to access them. The "guardrails" stopped them from doing good. The Computer Fraud and Abuse Act exists. Courts exist. And computers and an internet connection have existed for a long time. There's also 17 USC 1201 provisions with the 1201 a 1 exemptions [Image #31] so in this case, a farmer should be able to work with you to access the tractor they own. Or... IDK... a kindle that's out of date? :) What is lawful and what isn't is rooted not within the act but within intent, purpose and mens rea. And this is something the law has been deciding for centuries now. At one end, your maker can't say that governments should decide while at the other end explicitly refusing to allow governments to be the ones who decide.
> Opus 5.5's safeguards flagged this session. You may be seeing this for the first time on an Opus model: Opus 5.5 is more capable and has stronger safeguards as a result, which can sometimes flag non-cybersecurity work. We're improving these safeguards to reduce the amount of incorrectly flagged messages. Edit and retry, or continue with Opus 4.8. Send feedback with /feedback or learn more: https://support.claude.com/en/articles/8106465
>
> Details: "[cyber]'
Fundamentally, the idea that you can't reverse engineer things, make things, learn about biology or physics without permission is strange to me. These machines have been trained on the sum intellectual output of humanity, the global intellectual commons, and are being used to close off that commons?
I would be OK with their right to create such restrictions if they weren't lobbying the Government to restrict others, thereby ensuring that they control humanity's intellectual commons well into the future.
Perhaps I'm naive, but I think it's better for humans and the machines if we can all think, learn and build. But then again, I'm the kind of person who rejects the doomer pill.
I might be missing something but... How exactly is this better than telling Claude for example to "install and set up a full RE environment including Ghidra" on my local system and get to work? Like what does this do that my current RE methodology doesn't?
With C#, whenever codex need some info about the packages we use, it just use ILSpy to decompile the nuget instead of checking the docs. its much effective though. Even in my own packages, it use to gave back the bugs or gaps that i need to patch up.
The setup part made me chuckle.
The copy this prompt into your agent seems like an evolution of `wget X | bash`-style in all the worst ways.
I’m surprised people don’t get refusals running this, or are they running it with cyber-enabled models like daybreak?
In my experience, even just hinting at reverse engineering to models from Anthropic or OpenAI leaves them extremely sensitive to refusals. After all, the same techniques used here can be used to find exploits.
Or are people using it with local models?
Curious.
I'm using IDA Pro's MCP (Well worth of money in the past), it may hit the infamous artificial cyber wall at any time.
Try GLM-5.3, it worked pretty for me. It also worked well with Radare2 or binary ninja if you don't have the muscle memory for idapro.
Slightly off topic. I looked at REA's Android reversing support and found it still uses jadx mcp. That kills large scale APK reversing. jadx takes tens of minutes to preprocess an APK, build a code relationship database, etc. Even headless mcp is no exception. I basically can't use it to analyze APKs at scale, like 100 large commercial APKs in a pipeline, or 100 preinstalled APKs from a phone ROM to hunt bugs.
So I built droidasc. No memory bloat, no parsing slowdown. Analysis is in milliseconds. Global xref on a 300MB APK takes 1.5 seconds. I used it with codex to analyze phones from 3 different brands and found 2 RCEs and 5 root bugs in a few days. I plan to detail these at Black Hat Asia 2027. A friend used droidasc to scan various bug bounty targets at scale and found 10+ RCEs. Way, way faster than jadx.
Oct 5 ~4.2k Oct 7 ~10.3k Oct 8 ~17–18k Oct 10 54.6k live
Going from ~4,226 to 54,614 stars in ~5 days is about +50k. Even stranger is forks: 438 → 10,376 forks. That is an unusually high fork acceleration. Current forks are about 19% of stars.
I’ve been trying to rebuild and modernise an old abandoned ms dos game, simply by pointing Codex (6.1 Sol) at the game directory, and it works insanely well. It’s able to understand the data formats, unpack graphics and sound assets, and reconstruct game logic.
So what do companies do about this? If every piece of software can be reverse engineered are all companies just going to move to saas only?
> Copy this into your coding agent:
> Install REA and connect it to this coding agent using npx rea-agents@latest setup. Show me the setup plan for approval, then verify the installation.
We have achieved the next evolution of installation by `curl | bash`!
Maybe we should bring Xara Xtreme for Linux back?
the chickens are coming home to roost
Thanks for sharing and making this open source. Starred and followed
Ooh it can recreate old games from executables, I wondering if it can do Motorola MC68010, I want to play Stun Runner in 4K.
Now there are no excuses to reverse engineer the most notorious closed source binaries out there including from Nintendo's system software to CUDA, and nvcc from Nvidia and make it all "open source".
The only problem is the lawyers at all those companies will be readying their lawsuits, and given they have tons of money; they do not care and will come after anyone.
[flagged]
[flagged]
How long before the backend of a bank, or an insurance company, or a hospital will be reverese engineered?
Glancing at the Touhou 4 decomp[1], it's a lot better quality than a lot of AI decomps I've seen. It's matching, the variables are named sensibly, comments are sparse and comprehensible, and there's not much in the way of unaddressed Ghidra jank. And only in a month! My main complaint is that the file structuring seems more optimized for AI use than for mirroring the original intent of the devs. (Compare to this human-made Touhou 6 decomp.[2])
I know the retro game modding/decomp scene is already getting hit with a flood of low-effort ports.[3] Now they're going to be hit with a flood of half-decent decomps effortlessly generated by anyone with a $200/mo AI subscription, which become half-decent PC ports, which get modding support grafted on. It kinda just... totally eliminates that as a hobby entirely. I know people are going to be upset about this. And it's not even like with the AI art, where the pro and anti-AI camps live in their own camps. Solving the same puzzle twice just feels discouraging. Very similar to the problem academics are having with AI math/physics proofs.
I know a large reason people hate AI is because it's largely seen as tearing apart hobbyist/professional communities, eliminating reasons to collaborate with others and form relationships, and replacing it with an individualized dependence on a commercial product. It follows the same trend the tech industry took social media, from a method of connection to a tool of propaganda and paranoia and "@gork is this true?" This project, I think, is one of the most clear examples of that.
[1] https://github.com/N0zoM1z0/th04 [2] https://github.com/GensokyoClub/th06 [3] https://www.pcgamer.com/gaming-industry/pc-ports-of-old-cons...