This project is based on modified version of TextGenRNN, which is a module on top of Keras/TensorFlow for creating char-recurrent neural networks. The model is trained on scraped information from various public resources/job boards.
Using generative adversarial networks (GAN), we can learn how to create realistic-looking fake versions of almost anything, as shown by this collection of sites that have sprung up in the past month.
This website uses two datasets provided by NVIDIA, one of real people the other is generated using Machine learning, These people don't exist in real life. This website gives you the chance to test your ability to distinguish the two.
This is the ideal Silicon Valley website. You may not like it but this is what peak performance looks like. Plan your next vacation to DeepDreamland! Totally real listings that definitely weren't built by a GAN. It's thispersondoesnotexist.com but for airbnb listings.