pull down to refresh
Eh, I can't be bothered to read the code how the prompts were structured, but I did try this in Chat:
Good proof-of-work! Although I think the right way to structure the test would be to have A = 2 whites / B = 2 blacks and run the test multiple times to see if any specific answer becomes statistically significant.
Hmm, yes that would be an interesting way to do it
Eh, I can't be bothered to read the code how the prompts were structured, but I did try this in Chat: