I want to note that we weren't the first to come up with "let's think step by step",https://arxiv.org/abs/2205.11916 this paper might be the origin but I wouldn't be surprised if a lot of people discovered it independently before, it's not that hard to notice if you play around with models.
It's not special either, other prompts that mean the same also seem to work.
What's novel is that as far as I know nobody had tried to use it to reduce biases or in the inverse scaling price datasets.
(And in general the effects of using let's think step by step style prompts seems pretty unexplored so far in general).