> 4 different defense contractors in the last day
Now I'm just wondering what the hell defense contractors need image generation for that isn't obviously horrifying...
Now I'm just wondering what the hell defense contractors need image generation for that isn't obviously horrifying...
“Please move them to some desert, not the empire state building.”
“The civilians are supposed to have turbans, not ballcaps.”
I'm confused.
The bias leans towards overfitting the data, which in some use cases - such as missile or drone design which doesn't need broad comparisons like 747s or artillery to complete it's training.
Kind of like neural net back propogation but in terms of model /weights