How Do You Find Flaky Tests?

When developers do find these flaky tests, what do we do? How do we stop them? Some of that process is going to necessarily be manual in nature. There are testing techniques that are called metamorphic testing techniques. And if I expected changing the input shouldn't change the behavior of the machine learning algorithm, but it does, that's a means by which I can often find bugs in my system without having to come up with fancy test articles.