Loading original post…Open on X ↗
Giving an LLM maze-solving judgment only at junctions while code holds the DFS stack and visited set solved a 14×14 braided maze in 22 calls and 56 steps (2.2× optimal), versus 60 per-step calls that just paced a 7-cell corridor at 96% confidence.
Original post
Loading original post…Open on X ↗
jev
Start typing to find a use case.