,
8 tweets,
3 min read
Read on Twitter
I tried to use ganbreeder.app to illustrate the neural net racehorses, but apparently it wasn't trained on "horse" as a category. Closest thing I could find was "horse cart". which, um. 
who's a pretty horse?
do not pet.
and $100 on "Farthand" please
and $100 on "Farthand" please
realized that with ganbreeder.app i can actually subtract one category from another. so in theory if I start with "horse cart" and subtract "golf cart" i should get horse? right?
i tried to subtract "golf cart" from "horse cart" but everything ended up with dog faces. so i subtracted dog too.
well, the dog face is gone, i'll give it that.
well, the dog face is gone, i'll give it that.
another attempt to isolate "horse". this is
+ horse cart
- golf cart
+ golf ball
- basketball
---------------
= horsebasket? baskethorse?
+ horse cart
- golf cart
+ golf ball
- basketball
---------------
= horsebasket? baskethorse?
more attempts to combine ganbreeder.app categories to get "horse". letter-wise, this is the closest?
+ horse cart
- carton
-------------
= horse-on?
+ horse cart
- carton
-------------
= horse-on?
