Detecting When You're Talking to a Bot

One thing I would kind of caution on in this field is, you know, how do I make my machine learning system to have good enough quality that like it'll hit my 99% image detection threshold in real life or something like that? That's one standard. And there's this whole other standard, which is like, how do we build our machine learning systems to work well compared to like adversarial input? Right. Like, defensive design, like, defensive design. How do I defend against adversarial input?" He says he'd be "extremely skeptical" if they said a new fancy machine learning system will guard them from attack.