I've taken the test multiple times, and ended up with my boundary being both greener than >70% of the population and bluer than >70% of the population in separate attempts. And I know my color perception to be good at distinguishing hue - it's just that I don't have strong opinions about categorizing it in this space.
I'm pretty sure there's some hysteresis going on - if we randomly end up in the ambiguous zone on the bluer side, we'll be pressing "blue" every time a small change happens, because it's basically the same color. Until the changes add up so much that we're out of the ambiguous zone on the green side - and now our "border" is far on the green side. But if we started on the other side, entering the ambiguous zone from the green side, it'd take a big cumulative change before we press "blue".
"but does it only make these because there already exist hundreds of examples and tutorials? fear not, there's an entire library of other projects it made all of which also have hundreds of examples and tutorials"
don't get me wrong, it's interesting, but the response here didn't answer the question
I'm pretty sure there's some hysteresis going on - if we randomly end up in the ambiguous zone on the bluer side, we'll be pressing "blue" every time a small change happens, because it's basically the same color. Until the changes add up so much that we're out of the ambiguous zone on the green side - and now our "border" is far on the green side. But if we started on the other side, entering the ambiguous zone from the green side, it'd take a big cumulative change before we press "blue".