The Long Tail of LLM-Assisted Decompilation

Re:The Long Tail of LLM-Assisted Decompilation by seddonm1 on Tuesday February 17, 2026 @12:11AM (#47043911)

My test harness loads up the original DLL then executes that in parallel against the converted code (differential testing). That closes the feedback loop the LLM needs to be able to find and fix discrepancies.

I'm also doing this on an old Win32 DLL so the task is probably much easier than a lot of code bases.

[ Parent | on HN ]

Re:The Long Tail of LLM-Assisted Decompilation by measurablefunc on Tuesday February 17, 2026 @12:22AM (#47043988)

What are you tracking during the runtime tracing? Or is that written up in your link?

[ Parent | on HN ]

Re:The Long Tail of LLM-Assisted Decompilation by seddonm1 on Tuesday February 17, 2026 @12:36AM (#47044070)

I am applying differential/property based testing to all the side effects of functions (mutations) and return values. The rust code coverage is also used to steer the LLM as it finds discrepancies in side effects.

It is written up in my link - please bear in mind it is really hard to find the right level to communicate this level of detail at - so I'm happy to answer questions.

[ Parent | on HN ]

Re:The Long Tail of LLM-Assisted Decompilation by measurablefunc on Tuesday February 17, 2026 @12:38AM (#47044082)

That's fine, that answers my question.

[ Parent | on HN ]