Re:The wall confronting large language models
by Ukv on Wednesday September 03, 2025 @08:49PM
(#45122154)
For a depth-first solution (backtracking), I'd assume mostly just the partial solutions and a few small counters/indices/masks - like for tracking the cell we're up to and which cells were prefilled. Specifics will depend on the solver, but can be made part of Markov chain's state regardless.
What are those variables exactly?