@aidaxbaradari This is a losing game. GANs are literally a method to train AI.
To create the best ai image detector is to also create the best image generator trainer
Anyone else notices this problem with Astra?
Astra: I have done X
Me: This is wrong, you should do Y instead
Astra: You're right. I should do Y
Me: ...
Why doesn't it just go and do Y, like the other models??
It's been 4 months since WeaveHacks 4 and I still haven't received my prize money???
They refuse to simply send me a check, claiming that they are unable to.
@theo i've found myself needing to ask it to "yes, so do it" a lot. it would come to a conclusion but never act upon it. so much so that I literally had to add "When you say you'll implement something, actually do it." as an instruction