[zwaps]

And yet, it might fail in actual application.

If every DGP could be captured by fast-tuning a sophisticated enough model, science probably would be solved even before DL.

[deeeeplearning]

We're talking about building useable products not solving science...

[zwaps]

My point being that the reason many products end up not usable, ref. accounts in this thread, is the same reason why science isn’t solved and doing ML correctly isn’t easy.