River crossing puzzle 3

    problem statement

17 step solution 黃品勛

17 step solution 王智弘

Why LLM performs poorly with reasoning and planning

Claude Sonnet 4.5 reasoning did not work (It worked very very hard.)

Claude Sonnet 4.5 gen BFS but did not work (misinterpretation of problem)

Code gen (Python)

code gen python A* search for ::River Crossing Puzzle ...

Python on colab

Use REACT to visualize the steps

JS

change to js

run js

use React to visualize the steps

ChatGPT 5 create BFS to solve it. 17 step solution, visualize, visualizer

ChatGPT BFS

ChatGPT BFS

If BFS option is trurned off, ChatGPT has a hard time doing it manually.

ps:

I really like ChatGPT o1 reasoning performance.

Monologue is best.

reasoning mode in o1

Talking to itself

Running into difficulties? Cute

hours? Ha Ha Ha