Safety
Neurosymbolic rising!
Neurosymbolic rising! I've wanted to work on deep neurosymbolic integration for a while: if you make an 800k transformer reason *like* a logical solver, you get 100% on sudoku-extreme w. 15m of train
Neurosymbolic rising! I've wanted to work on deep neurosymbolic integration for a while: if you make an 800k transformer reason like a logical solver, you get 100% on sudoku-extreme w. 15m of train compute. Happy that I finally got chance to focus on this at @axiommathai https://x.com/albe_alfa/stat…
Source: Gary Marcus (X) | 2026-06-01