Re:Language Models Are Injective and Hence Invertible
by gnfargbl on Thursday October 30, 2025 @09:16AM
(#45759710)
You don't, I guess. But again that's just the same as when you insert something into an object store: you can't be absolutely certain that a future retrieval will give you the same object and not a colliding blob. It's just good enough for all practical purposes.
Re:Language Models Are Injective and Hence Invertible
by ajkjk on Thursday October 30, 2025 @10:26AM
(#45760358)
Well that's not a problem, that's just a description of what "almost surely" means. The thesis is "contrary to popular opinion, you can more-or-less invert the model". Not exactly invert it--don't use it in court!--but like, mostly. The prevailing wisdom that you cannot is incorrect.
We aren't just trying to claim that two inputs are the same, as in hashing. We are trying to recover lost inputs.