This is a refreshingly practical demonstration of an LLM adding value. More of this please.
The unexpected effectiveness of one-shot decompilation with Claude
11–20 of 133 posts
Re: The unexpected effectiveness of one-shot decompilation with Claude
#12Makes me wonder if decompilation could eventually become so trivial that everything would become de-facto open source.
Re: The unexpected effectiveness of one-shot decompilation with Claude
#13Re: The unexpected effectiveness of one-shot decompilation with Claude
#14Makes me wonder if decompilation could eventually become so trivial that everything would become de-facto open source.
This deserves a discussion
Re: The unexpected effectiveness of one-shot decompilation with Claude
#15If you aren't using LLMs for your reverse engineering tasks, you're missing out, big time. Claude kicks ass. It's good at cleaning up decompiled code, at figuring out what functions do, at uncovering weird assembly tricks and more.
Makes sense because LLMs are quite good at translating between natural languages. Anyway, we're reaching the point where documentation can be generated by LLMs and this is great news for developers.
I stumbled across a fun trick this week. After making some API changes, I had CC “write a note to the FE team with the changes”.
I then pasted this to another CC instance running the FE app, and it made the counter part.
Yes, I could have CC running against both repos and sometimes do, but I often run separate instances when tasks are complex.
Re: The unexpected effectiveness of one-shot decompilation with Claude
#16Makes me wonder if decompilation could eventually become so trivial that everything would become de-facto open source.
This deserves a discussion
I've used LLMs to help with decompilation since the original release of GPT-4. They're excellent at recognizing the purpose of functions and refactoring IDA or Ghidra pseudo-C into readable code.
Re: The unexpected effectiveness of one-shot decompilation with Claude
#17I've been experimenting with running Claude in headless mode + a continuous loop to decompile N64 functions and the results have been pretty incredible. (This is despite already using Claude in my decompilation workflow). I hope that others find this similarly useful.
This is super cool! I would be curious to see how Gemini 3 fares… I've found it to be even more effective than Opus 4.5 at technical analysis (in another domain).
Re: The unexpected effectiveness of one-shot decompilation with Claude
#18Earlier quoted context omitted.
This deserves a discussion
I've used LLMs to help with decompilation since the original release of GPT-4. They're excellent at recognizing the purpose of functions and refactoring IDA or Ghidra pseudo-C into readable code.
How does it do on things that were originally written in assembly?
Re: The unexpected effectiveness of one-shot decompilation with Claude
#19If you aren't using LLMs for your reverse engineering tasks, you're missing out, big time. Claude kicks ass. It's good at cleaning up decompiled code, at figuring out what functions do, at uncovering weird assembly tricks and more.
The article is a useful resource for setting up automated flows, and Claude is great at assembly. Codex less so, Gemini is also good at assembly. Gemini will happily hand roll x86_64 bytecode. Codex appears optimized for more "mainstream" dev tasks, and excels at that. If only Gemini had a great agent...
Re: The unexpected effectiveness of one-shot decompilation with Claude
#20Earlier quoted context omitted.
This deserves a discussion
I've used LLMs to help with decompilation since the original release of GPT-4. They're excellent at recognizing the purpose of functions and refactoring IDA or Ghidra pseudo-C into readable code.
Someone please try this on an original (early 1980s) IBM-PC BIOS.