AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Make Neural Nets Suspect of Text
The training data set is a very weirdly undefined thing in this case which is sort of like the weirdest cases humans can come up with. And once you start training the model on like adversarial examples that people have found where it was making mistakes then it gets a lot more suspicious of stuff like that. It's funny I said someone posted about this to Facebook I didn't realize this was your project where they were like giving an examples like of a parent slowly and lovingly suffocating their childhood death right? ExactlyYes, we're currently pushing for the goal of no false negatives and 60% false positive rate.