It is not worth my time. How anyone believes writing magic incantations to be interpreted by a non-deterministic black box of bullshit is better than writing the actual structured programming language is befuddling. Thinking there is an actual market for such an inane concept is naive.
When I was growing up, I was fascinated by good ol' combinatorial algorithms, the kind that Bob Tarjan was an expert in (like union-find, various kinds of crazy heaps, etc.). I loved the provable and deterministic nature of the guarantees. That's what I wanted to do research in, so when my PhD advisor, Philippe Flajolet, forced me to work on randomized algorithms—nasty non-deterministic monsters that always had some possibility of going completely off the rails—I was horrified and traumatized.
I don't know when I started feeling like randomization could be useful, but I think it's when I started to slowly realize that there are several kinds of randomness, different kinds of failures, different kinds of requirements. For instance a Bloom filter has false positives, but when it's job is to reduce the throughput of queries to a costlier computation, then the false positives don't matter so much, they don't matter to the exactness of the final computation.
It's commendable that you mention being in Internet marketing (i.e. sausage making :-) and I can imagine that the uses of models that you witness might make you cynical about them: The models can be collaborated in a variety of way, including cybernetic and epistemic. Cybernetic is when you ask models to do something for you. Epistemic is when you are trying to figure something out that you are curious about, and investigating with the model.
One of the most important aspects of the methodology is the Secondary Directive: Surface doubts. This means the magic incantations involve an extended conversation or round of question answering that narrow down anything that is unknown or that is underspecified. There are multiple opportunities in these interactions to constrain the final output of the model.
At any rate, I get and respect your skepticism. Assuming you know what falsification is: What would it take for you to change your mind about the usefulness of the "non-deterministic black box of bullshit"?
