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. ACCoun+szo[view] [source] 2025-12-06 17:22:14
>>saagar+2po
That's great if those humans are around to have that input.

Not so much when you have a lot of code from 6 years ago, built around an obscure SDK, and you have to figure out how it works, and the documentation is both incredibly sparse and in Chinese.

[go to top]