Re:Quadrillion-parameter transformers and how to train them
by ACCount39 on Sunday November 08, 2026 @10:40AM
(#50414205)
This becomes more true the deeper you look.
LLMs used to "fail at spatial reasoning forever". But each new generation would fail a little less. Then we got the likes of Astra, and ARC-AGI-3 straight up died.
LLMs used to "fail at spatial reasoning forever". But each new generation would fail a little less. Then we got the likes of Astra, and ARC-AGI-3 straight up died.