zlacker

[return to "The unexpected effectiveness of one-shot decompilation with Claude"]
1. ACCoun+eao[view] [source] 2025-12-06 13:55:23
>>knacke+(OP)
If 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.

◧◩
2. ameliu+sfo[view] [source] 2025-12-06 14:43:29
>>ACCoun+eao
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.

◧◩◪
3. saagar+2po[view] [source] 2025-12-06 15:59:44
>>ameliu+sfo
Documentation is one place where humans should have input. If an LLM can generate documentation, why would I want you to generate it when I can do so myself (probably with a better, newer model)?
◧◩◪◨
4. simonw+dzo[view] [source] 2025-12-06 17:19:29
>>saagar+2po
I definitely want documentation that a project expert has reviewed. I've found LLMs are fantastic at writing documentation about how something works, but they have a nasty tendency to take guesses at WHY - you'll get occasional sentences like "This improves the efficiency of the system".

I don't want invented rationales for changes, I want to know the actual reason a developer decided that the code should work that way.

[go to top]