Code, Data and Media Associated with this Article
2-phase A* already uses many heuristics which don't always create an optimal route and still 5-10x slower.
，详情可参考搜狗输入法下载
However, due to modern LLM postraining paradigms, it’s entirely possible that newer LLMs are specifically RLHF-trained to write better code in Rust despite its relative scarcity. I ran more experiments with Opus 4.5 and using LLMs in Rust on some fun pet projects, and my results were far better than I expected. Here are four such projects:
Salmon farming improvements making 'slow progress'
“坚持从实际出发、按规律办事”