LLMs can read and write executables byte by byte from a hex dump (sgiannopoulos.github.io)

137 points by fortran77 3 days ago

pier25 6 hours ago

I've suspected for years that AI companies have been using commercial software to train their models including games, audio plugings, DAWs, etc. It would not surprise me one bit if we find out they used torrented pirated apps like they did with books and music.

There's certainly eg open source audio dev material out there but not nearly as much as web dev. How else do you explain all the avalanche of vibe coded audio plugins and DAWs appearing this year?

dachris 4 hours ago

And (from a training material point of view) it makes perfect sense.

I would assume that to a LLM, a binary executable is not much worse than actual source code. And it's much denser, just missing the semantics of human-written identifiers. It's the code's pure logic, condensed into machine language.

And there's tons of it, many vendors supply it "freely" (you don't need license keys to train on a binary) It's often battle-tested code that you wouldn't get hold of otherwise, and compared to ingested source code its unlikely that Codex regurgitates a recognizable part of a Windows 2000 DLL into your C++ source code.

Earw0rm an hour ago

That's not quite right - source expresses the idea relative to a language syntax and grammar, whereas machine code (or assembler) implements the idea against a specific target machine, for a specific set of circumstances.

So as an example, there are a bunch of different ways a for or while loop can be implemented in compiled code, but there are also situations where two quite different source constructs can result in the same machine code sequence.

Machine code certainly won't teach an LLM much about how to write good source code.

mycall 4 hours ago

Being deterministic, a binary executable is just a compressed version of source code.

azornathogron 3 hours ago

vardump 2 hours ago

shermantanktop 3 hours ago

xnx 6 hours ago

My hunch is that one of the handicaps Google is dealing with (vs. OpenAI and Anthropics) is that Google is not training on pirated media. They are using YouTube, Google book project scans, and purchased copies of media.

jarjoura 7 minutes ago

I suspect that Anthropic, being public, and under scrutiny, will get sued into compliance from all over the world. It's not a foregone conclusion that the data they trained on remains fair game over the long term.

walthamstow 4 hours ago

Perhaps they are not actively collecting it like Ant/OAI but YouTube and Google Books are full of user-uploaded pirated media.

mike_hearn an hour ago

kakacik 4 hours ago

mixtureoftakes 6 hours ago

There is zero chance models are not trained on pirated media and games, especially most popular ones.

Makes complete sense to study things people actually want to use and consume

jarjoura a minute ago

At least for Google, they have almost every game worth playing documented in precise frame by frame detail on YouTube. They don't need access to the source code, or compiled binaries to reverse engineer game mechanics. They built vision models perfectly capable of ingesting those game play videos and derive game play understanding from them.

Plus, there's so much open source, and game engine SDKs, freely available, that with a few game engineers at Deep Mind, they can write training systems that connect the dots.

It's definitely a gray area because these models are doing what an indie game dev would do, but at a scale and precision that's basically pirating the game, and getting around the rules of copyright to do it legally.

basilgohar 6 hours ago

I agree 100% with sentiment. It is inconceivable to me that models were not trained, either directly, or indirectly through other aggregates, on code and binaries and, of course, media, fetched from torrent or other filesharing sites.

Keyframe 6 hours ago

wouldn't that information leak out or somehow found out? too many people already involved. With some, like Seedance it's obvious of course.

docshock 5 hours ago

georgemcbay 2 hours ago

singpolyma3 6 hours ago

Not saying you're wrong, but LLMs can work in areas they've never been exposed to in languages they've never been exposed to. Training is not needed for something to be possible

WarmWash 5 hours ago

They also use synthetic generated data to train on too

If it works and it's verified in nine different ways, throw it in the training pile, and then automate the process.

blazarquasar 2 hours ago

devmor 5 hours ago

There is absolutely no way to prove that this claim is true because no model advanced enough to do so at a useful level has any fine grained report of its training data that could be used to verify this.

docshock 2 hours ago

djleni 4 hours ago

docshock 5 hours ago

Earw0rm 2 hours ago

Audio plugins are something that lots of people wanted to try making, but few (until now) could. Now they all can, and they do.

They're about to learn the hard way that the market wasn't profitable even without 10x the number of new entrants.

And that a third of the paying customer base (which was not that large to begin with) gave up on plug-ins anyway to generate finished music tracks from prompts.

petu 6 hours ago

> How else do you explain all the avalanche of vibe coded audio plugins and DAWs

By them being nothing special?

> appearing this year?

Vibe coding in general became viable last year, Opus 4.5 is Nov 24, 2025.

MomsAVoxell 33 minutes ago

Yes, plus there is the fact that there is a HUGE amount of open source audio code out there, many, many DAW’s and so on.

I chalk it up to synth and audio guys being among the more innovative users, personally - its a market of folks who have always wanted to design their own DSP/audio-graphs, and were primed for the opportunity that AI/ML presented to do so.

The same goes for the vibe-coded game communities, and as well all the retro guys.

Folks tend to not realize just how much open source is out there in fields/subjects they’re not really familiar with.

SyneRyder 5 hours ago

Also the 1 Million token context window helped make it more viable.

I've made a bunch of unreleased vibe-coded VST plugins to replace the hundreds that I've bought over the years - and many of the barriers to development weren't the model. Just having belief that the model was capable of the work, a bit like the 4-minute mile. Also knowing to persevere and iterate with the model, not giving up because the first UI is inevitably so amateurish.

There's also a flywheel happening. If you make permanent notes on the process, your rules for UI design, a library of re-usable components and algorithms, tools so the model can judge its own work... the whole process for the next VST just gets much faster & much easier. Same goes for any software you make with AI too.

whateveracct 5 hours ago

so weird how AI boosters act like it hasn't been less than a year, isn't it?

bitwize 5 hours ago

rhdunn 6 hours ago

It should be theoretically possible to use C/etc. source code, assembly output, and compiled output in the training set with equivalence mapping between them. That would make it possible for the LLM to learn disassembly and decompiling to some degree.

You don't need software for that aside from the compiler/linker tools (which are free for C/C++ compilers, rust, etc.). You can then permutate/generate the source code using tools/techniques like fuzzing.

There's also things like Intel's instruction set documentation.

cedws 6 hours ago

An LLM trained on decompilation would be a game changer, but there's no way they'd allow us to use it.

ape4 5 hours ago

dreamcompiler 4 hours ago

sorokod 4 hours ago

torrented pirated apps may contain all sorts of nasties, it would be amusing if the nastiness gets embedded in the LLMs

riggsdk 6 hours ago

In that case it would be movie-plot worthy when the LLM was trained on all those embedded viruses and malware. "Believing" it is intentional and then start embedding it into all software it creates for us.

goodmythical 3 hours ago

report shows AI botnet is using your fridge as distributed command and control server

"Hello, we're here to see whether or not your fridge is runni-Hey, no not like that, this is serious!"

saagarjha 5 hours ago

AIs are quite good at using existing binary analysis tools; they usually do not just operate on binaries in “prompt space” like this

rossy 4 hours ago

Like the weight space stuff, I think there's a small misdirection in how this is presented: Phrases like "write directly in machine code" seem to imply that ordinary LLMs intuitively understand machine code as just another language, like English or JavaScript, that they read from context and write directly as tokens, and that this intuitive understanding could mean increased efficiency or capabilities if you ask the LLM to just use the bytes rather than asking it to use the tools that human reverse engineers use.

If that's what you assumed, the DeepSeek reasoning trace shatters that illusion. It's just disassembling by hand like what a human reverse engineer would do if you (sadistically?) denied them a disassembler. Yeah, the human reverse engineer would need an excellent memory of the x86_64 instruction reference, but we already know LLMs can recall a breadth of information. What we don't know, that this article also provides no evidence for, is if there will be any benefit in using the LLM for this over objdump.

The article seems to intentionally conflate disassembly (computationally cheap) with decompilation (can be computationally expensive) to imply that there's some benefit to asking the LLM to work with machine code (seems impressive to the RE layman) rather than working in assembly (something you probably already assumed LLMs can do,) but the DeepSeek trace has a disassembly in it, and it's hard to imagine that inference will ever be cheaper or more reliable per-token than objdump is at producing the same output.

Farmadupe 28 minutes ago

Ooh I'm not sure that I would buy into that! I've been experimenting with giving small binaries without strings or other direct clues, and asking them "So tell me what you think this does" in a bare container without disassembly tools.

So I'm actually fairly confident that the ability does come straight from the ability to read the bytes into context (usually as hex bash/perl/python3 is almost always available), and Then to directly interpret what the binary does from the code. And yes, when I do use open models, I can see from their reasoning traces that they do "hand-translate" the hex into assembly, but I kind of suspect that the translation stage into assembly may just be a narration, and the "understanding" of what is going on is actually a pure latent skill. That's just my guess, though.

The reason that I think this is because I've been using minimal implementations of inference engines. And frontier closed-weight models and open-weight models are able to observe a binary with no strings and the weights not attached, and they can infer the exact architecture and model (eg qwen3 0.6b, qwen3.5-0.8b, whatever) from the fixed shape of the inference kernels.

So in effect, over the course of 30 seconds, they go from looking at 500 instructions of x86 code and reply, “I know what this is. It's an inference engine for Qwen 3 0.6B!”

And I'm fairly sure that 30 seconds or not, it's a skill that no single human has.

bita_nidir 5 hours ago

I don't think it'll make sense for an LLM to program directly on the cpu opcode level due to the overhead.

But I hope you all realize that the programming language of the future is going to be for LLMs. It'll tightly optimized for LLMs and we'll get nice tools to understand them. They'll probably be great, with loads of fancy tooling.

amelius 5 hours ago

The programming language of the future will be a purely functional language, where the LLM acts as the compiler using correctness preserving transforms.

Any other way of coding will be considered ridiculous (except maybe if you do it for a hobby).

Better start learning Haskell, folks.

WarmWash 5 hours ago

In its purest form there would be no programming at all, you would just be interacting directly with the AI model. The interface would be like an amorphous digital goo that can instantly shape-shift into any state.

massysett 4 hours ago

hollowturtle 2 hours ago

Haskell, future, pure and LLMs in the same sentence can only describe a good joke. But that wasn't one. So I guess you're serious. It's basically a useless language that hasn't been used for doing anything meaningfull, I tried using functional languages for doing "pure game programming" performance and type gymnastic was a total disaster. Spaghettified code even before LLMs

bonesss 4 hours ago

OCaml, F#, or even Rust have functional cores that verify correctness. They’re wire token efficient, too.

Sufficiently massaged OCaml/F# approaches straightforward readability in plain English.

And, for people who have been doing it for a minute, the other ways of programming do seem a little ridiculous ;)

sevenzero 5 hours ago

Yea lets just trash all these legacy codebases the world depends on, I'm sure this will work out

raincole 5 hours ago

amelius 5 hours ago

behringer 5 hours ago

duskdozer 4 hours ago

bitwize 5 hours ago

andai 4 hours ago

What overhead? More tokens for same result?

I haven't looked into it properly but, it looks like it might actually be the same amount of tokens? (Excepting stdlib boilerplate etc.)

haolez 5 hours ago

It depends. If you design and train a tokenizer for that, I don't see why it wouldn't work, and I'm not even an "AI psychosis" victim :D

dezgeg 4 hours ago

Emitting a executable binary (eg. ELF) will never make sense over using assembly language. Adding/removing some code to the middle of a large program shifts tons of addresses like jump targets and variables. It makes no sense to have LLM spend tokens on making edits to (potentially) every single call instruction in an existing binary, instead of letting assembler do it.

MomsAVoxell 6 hours ago

Back in the day, thats how we got executables from one system to another, over ASCII-tuned serial lines. I had a colleague in the 80’s who could muscle-memory a “hx.c” which would produce the requisite hex listing given an input, and if that input was a hex listing, reproduce the binary. It was something like 12 lines of C code and it saved our asses so many times, he eventually made a DOS compatible equivalent that could be piped into DEBUG.com to produce the same results.

Exmoor an hour ago

Not quite sure if this was the same thing, but I recall getting small utilities off some FidoNet echo for dos users which used DEBUG.com to turn it from ASCII into an executable binary.

MomsAVoxell 42 minutes ago

As far as I know my colleagues tools were never pushed online, we were air-gapped from Fido and USENET and so on back then, but they might’ve made it out there .. he was mighty good at typing it in anew when it was needed though, literally a minute and we’d have bins available to do the rest. I used to use it to get zmodem.exe and kermit.exe onboard remotely managed DOS systems that didn’t have compilers .. I also had a 20 line debug.com assembly program that would do sector copies of floppy disks that I kept around/retyped when needed for such purposes. Those were fun times…

euroderf 5 hours ago

IIRC there was a bastard mini version of uudecode that was written so that all the opcodes were printable ascii, so you could save the text block, mark it as executable, and off you went... to get a uuencode of the full uudecode binary, decode it with your bastard mini uudecode, and then you were all set.

mfuzzey 6 hours ago

This can be useful in the reverse engineer / malware analysis case where there is existing machine code and no source but I don't think that AI "writing machine code directly rather than high level languages" makes sense. Code generation by LLMs is a non deterministic process so it makes far more sense to generate higher level compilable source code once and then compile it with a deterministic compiler for each target rather than generate machine code non deterministically several times seperately for each target.

saagarjha 5 hours ago

We also have more or less deterministic tools to lift code as well, which are usually more efficient to use.

orbital-decay 40 minutes ago

Yeah sure, people have experimented with giving them binaries since the first instruction-tuned models. They do it poorly though, compilers and decompilers are still necessary.

bitexploder 38 minutes ago

They keep getting better. And they know the system. They can literally build and validate reverse engineering tools all by themselves, and they know enough of the machine to literally extrapolate. You could basically tell them machine format and he’ll climb them to a completely valid C compiler for it. That’s the power of Them speaking in machine code. It’s just another language. It’s actually a bounded and somewhat consistent language… and they speak it.

orbital-decay 27 minutes ago

My point is that the data is much worse for machine code than for high-level languages, and it will always stay that way unless you generate more. Which doesn't make much sense as HLLs are just more efficient, being designed around more expressive semantics and formal constraints that can be automatically verified. LLMs are always going to suck at machine code compared to HLLs for the same reason as humans do.

Everything that can be offloaded to dumb tools should be offloaded. You don't do long division when you have a calculator. It's a neat trick, you should know how to do it, but it's not very practical.

jrmg 3 hours ago

This has been true for some time now. I can't remember details, but about a year ago, I was debugging some boot issues on an AVR microcontroller, and just pasting the HEX of the bootloader (that I didn't have access to the source of) into Claude's web interface got me the answers I needed.

plastic3169 3 hours ago

It feels like image models which create images and video by bitbanging pure pixels. This is almost never the way people would approach the task of creating images barring pixel graphics. It also means that using image models is inconvinient. I always likened it to having programming AI that would go from prompt to binary. I thought we don’t program like that because programmers understand the problem area better and like to go through source code.

goodmythical 3 hours ago

000000?

Nope.

000001?

Nope.

...

000000 00001 00010 00110 00000 100000?

Hey, we've got addition!

JKCalhoun 6 hours ago

An uninteresting case I am sure, but I have been leaning on LLMs to disassemble 6502 hex dumps and it's no doubt easy-lifting for them.

And the proof of course is that I can reassemble/link, with "modern" tools, their presented assembly and it combines right back into a hex dump mirroring the original.

Anyway, it's been a joy to take the long-out-of-print book, "The First Book of KIM", and re-typeset it (re-assemble it?) for modern hobbyists like myself. LLMs have allowed me to clean up the poor OCR-extracted text from the original. Claude has not only done that, but found missing labels and "equates" in the assembly, as legitimately printed in the book—not OCR errors.

Heck, Claude latched on to a bug in the classic "WUMPUS" game that apparently the author was not even aware of. (But I left that bug in for hobbyists to find—or exploit.)

itsquiteamazing 2 hours ago

Funny I was doing this the other day. Write an HTTP server and some routes directly as a FreeBSD binary, no intermediaries, no tools. It works and you know what, I am not even surprised.

nubinetwork 5 hours ago

A hex dump is just extra bytes of ascii filling up context... having to deal with "20 e3 8f" is 8 characters of text, compared to 3 bytes. LLMs can already parse binary files without the text overhead.

bitexploder 40 minutes ago

Yeeeeep. Been saying this for months. Go paste them Base 64…. Dozens of other formats. Use an open model. Watch thinking traces: “i am now mentally decoding X” O_o

Now think about homomorphism and safety filters……

Neywiny 3 days ago

Wow. It can read bytes from a byte output? That's incredible

plqbfbv 5 hours ago

The incredible part is that an LLM that wasn't explicitly trained for this, can analyze bytes as if they were natural language, and surgically modify and/or insert bytes directly without going through intermediate steps (source -> ASM -> ...).

This process would normally require a human to lift bytes -> ASM, ideally ASM -> obfuscated source, making sense of it, and doing the chain backwards, and it requires coordinating a lot of knowledge. Which of course is no problem for an LLM.

saagarjha 5 hours ago

People can do this in some limited circumstances, LLMs are just better at it

pipes 2 hours ago

I could be wrong, but this is really silly: 1. Read byte by byte, well yes, executables are files how else do you want them to read and write them.

2. Binaries are 1 to 1 direct representations of the assembly code they are created from. If you know the instructions set it isn't black magic to figure what byte means what.

Why on earth would it be better for llms to program in binary or assembly. We have optimizing compilers so the effort doesn't need to be spent there.

Maybe my assumptions are wrong, so please correct me.

Edit: but yes, in general it's utterly amazing I can ask computer to tell what a computer program does, even a binary file.

Buttons840 41 minutes ago

I wonder if you trained a LLM on the data that has passed through my router throughout my whole life how smart it would be.

I mean decrypted data of course, because it surely couldn't learn directly from encrypted data, right? Right?

andai 4 hours ago

Couldn't they do this before?

They don't list any model size or version that failed, right?

layer8 6 hours ago

I wonder if prompt injection via an executable is possible. Especially in the context of having AI perform malware analysis.

saagarjha 5 hours ago

Yes but models are fairly resistant to simple prompt injection these days. Having them hit guardrails is a more common strategy

flohofwoe 5 hours ago

Hmm, is this new or surprising? When testing my home computer emulator code for correctness, Opus had no trouble taking C64 .prg files apart and analyse them the same way it would analyse .asm source files.

PS: and it also has no problem writing a simple 'bouncing sprite' C64 demo without going through assembly and wrap that in a .prg file (of course this is basically the 'hello world' of C64 demos and could be as-is in the training set).

Let's see if the data URL survives HN:

https://floooh.github.io/tiny8bit/c64.html?file=data%3Aappli...

secondcoming 6 hours ago

I recently watched a video of a guy trying to unbrick his Harley Davidson Livewire electric motorbike. Harley Davidson were unable to do it. Perplexity created an app to sniff the canbus and talk to the battery and other components on the bike. Soon it'll be possible to write your own firmware for things like this.

[0] is the episode I'm referring to, but the whole series of videos about his woes with this bike are quite interesting.

[0] https://www.youtube.com/watch?v=Z4Ty0oqA_Bk

tliltocatl 5 hours ago

So can I. CD 20

dreamcompiler 5 hours ago

Since disassembly is a solved problem and it's deterministic with a 1:1 solution, why throw a nondeterministic LLM at it? Why not give the disassembly output to the LLM and let it do the decompilation, which is not 1:1?

Pet peeve: Using AI to solve problems that existing algorithms can dependably solve with 10^-6 the CPU resources.

adrian_b 3 hours ago

Disassembly is not 100% solved, at least not in a way that is easy for an LLM to use.

Disassembling directly an executable program, especially when it is some proprietary program for which there is no debugging information, is likely to produce a lot of garbage that does not correspond to correct assembly instructions.

Correct disassembly can be obtained only by simulating the execution of the program and disassembling only the instructions that are reached in this way. This is still not completely foolproof, because during simulation some parts of the code might be reached only for some specific input data, which is unknown. Sometimes one may guess all the possible inputs and disassemble anything reached in this way, but in reality some of those inputs can never occur, which can lead to erroneously disassembling parts that should not be disassembled, as they are not instructions.

That said, most executable programs are easy to disassemble, but some may be intentionally or unintentionally very obfuscated, and for such cases any disassembling tool would have to be guided by a human to achieve a complete disassembly.

g-b-r 40 minutes ago

Disassembly means going from bytes to assembly, it's not only "solved" but trivial.

In your comment you're talking about reverse engineering.

WhereIsTheTruth 4 hours ago

The point is you no longer need expertise as a prerequisite