I love programming for a lot of reasons but one of them is just that it’s an entire field that dedicates an incredible amount of energy to discovering more useful abstractions. That’s very in my wheelhouse of compulsions. But…
-
-
TLDR: Your favored abstraction is one abstraction among many that all vary in quality with respect to heterogeneous loss functions. Most of the time you assert that your abstraction is better, you’re making a statement about your loss function, not the abstraction.
Show this thread -
Except we're rarely stating loss functions explicitly, were just inducing them on-demand. And the difference between yours and mine manifests as generalized trust or distrust.
Show this thread
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.