Not 14 different things. 14 different approaches to solve the same image recognition problem. Please do not jump to conclusions. I did not say TDD is not useful at a _later_ stage, but at the research phase it is simply more of a burden than help, because the "refactor" step ends up as "drop everything".

> Not 14 different things. > 14 different approaches

So... if you are trying to take 14 different approaches... TDD isn't there to solve it for you. That's what I said.

But then that's planning. And when you've found your approach, you write it with TDD.