News for hackers. Stuff that matters.
Re:The Universal Weight Subspace Hypothesis by energy123 on Monday December 08, 2025 @11:34PM (#46201260)
Every vision task needs edge/contrast/color detectors and these can be all mostly the same across ViTs.

The surprising thing is inter-modality shared variation. Not intra-modality which is quite obvious and expected.

I would like to see interpretability work into whether these high variance components are low level or high level abstractions.

Re:The Universal Weight Subspace Hypothesis by TheOtherHobbes on Tuesday December 09, 2025 @03:33PM (#46210247)
It hints there may be common higher-level abstraction and compression processes in human consciousness.

The "human" part of that matters. This is all human-made data, collected from human technology, which was created to assist human thinking and experience.

So I wonder if this isn't so much about universals or Platonic ideals. More that we're starting to see the outlines of the shapes that define - perhaps constrict - our own minds.