News for hackers. Stuff that matters.
Re:Language Models Are Injective and Hence Invertible by sebastianmestre on Thursday October 30, 2025 @04:38PM (#45765027)
No, yeah, totally. Even assuming binary vectors 2^768 is a ridiculously huge number. The probability of collision even assuming a bad sampling that discards 75% of dimensions is still vanishingly small.

There are no comments on this comment yet.