Decompiling 2024: A Year of Resurgance in Decompilation Research

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by wzdd on Thursday January 30, 2025 @09:23AM (#42877925)

> Decompilation, seen as a translation problem, is by any means a job that suits AI methods.

Compilation is also a translation problem but I think many people would be leery of an LLM-based rust or clang -- perhaps simply because they're more familiar with the complexities involved in compilation than they are with those involved in decompilation.

(Not to say it won't eventually happen in some form.)

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by chrisco255 on Thursday January 30, 2025 @10:30AM (#42878655)

LLMs are not deterministic, and I want deterministic builds from compiled code to assembly. I also do not want the LLM to arbitrarily change the functionality, I have no such guarantees.

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by sitkack on Thursday January 30, 2025 @11:20AM (#42879238)

Compilers aren't deterministic in the ways that people would think matter.

We will have LLM based compilers in the near future. Determinism is a property of the system, not the components.

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by LowLevelMahn on Thursday January 30, 2025 @12:09PM (#42879752)

"near" like never :)

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by sitkack on Thursday January 30, 2025 @02:07PM (#42880996)

You want to put money on it?

You set the criteria.

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by pjc50 on Friday January 31, 2025 @05:30AM (#42886396)

Let me know when an LLM compiler is licensed for use on critical infrastructure. Admittedly Java doesn't meet this bar (see "You acknowledge that Licensed Software is not designed or intended for use in the design, construction, operation or maintenance of any nuclear facility" https://www.oracle.com/technetwork/java/javase/downloads/jdk... )

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by IshKebab on Thursday January 30, 2025 @05:47PM (#42882973)

I wouldn't be at all leery of LLM-based compilers (as long as their output is verified to be correct and reasonable).

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by pjc50 on Friday January 31, 2025 @05:31AM (#42886405)

Verification is the hard bit! That's why sel4 is so unique.

[ Parent | on HN ]

Re:Decompiling 2024: A Year of Resurgance in Decompilation R... by IshKebab on Friday January 31, 2025 @08:49AM (#42887614)

That's a different kind of verification entirely.

[ Parent | on HN ]