# @repligate — 2025-12-29

♥2 ↻0 · https://x.com/repligate/status/2005780433036820848

whether they count as the same object or hypothetical objects seems like a matter of degree/interpretation. and transformers even have a guarantee that human brains dont have: that activation vectors from previous "moments" are added to the current activations without modification. and maybe the layers are more different than you and your previous self, but how different? what if you just duplicated the layers in a transformer, would that fix the problem you're pointing at?

tags: author:repligate, kind:tweet, thread-context, year:2025