Hacker News Reader

I wonder if embeddings could be created from open source and library code and then used to convert back the code with all the correct variable and function names.

View on HN

It's not AI but Ghidra has a cool feature called BSim which does something similar. Each function get's a "feature vector" which now that I think about it has some clear parallels to embeddings.

Wow that is cool, I bet with that feature and a huge database of known "feature vectors" from open-source libraries so you can focus on the actual business logic of the binary instead of trying to reverse external library functions

BSim is a hash machine, right? (BSim uses feature vectors, and locality-sensitive hashing.)

Embeddings could be derived from reconstituted hash.

I've been wondering the same thing. However you would have to have a very large database of embeddings for this to be useful, right?

Otoh I can see this being disproportionately helpful with reverse Engineering Rust and Go binaries, which usually include many opensource dependencies

Reply on news.ycombinator.com