That Goat wolf cabbage problem gpt-4 can solve already
If I ask it a leading question that intentionally relies on a wrong solution, will it recognize that?
In the canonical example it also remarks "This is a classic river crossing puzzle" before delivering the solution.
EDIT: I tried some variations with "two wolves and a rabbit" and "three wolves and a rabbit". ChatGPT started bullshitting about its solution that supposedly was "a bit more complex". It started with taking one wolf to the other side. After I pointed out the rabbit would be eaten by the remaining two wolves it apologized for the mistake but just kept going hallucinating "correct" solutions.