DeepTweets: Generating Fake Tweets with Neural Networks Trained on Individual Twitter Accounts

Source: Deep Learning on Medium


I fine-tuned the GPT-2 language model (345 million parameters) on tweets from people’s Twitter accounts to create AI versions of them, and then had the bots rewrite real tweets. I’ve generated hundreds of the following images and picked my favorites. All are surprisingly representative of their corresponding real Twitter accounts. Some are funny, some are profound, some are dark in a way that gives me pause. Here’s a real tweet about tunnels from Elon Musk rewritten by AI versions of Justin Bieber, Kanye West, and Katy Perry:

So far I’ve trained AI versions of the following people (listed below). If you have more suggestions for who/what you would like to see, let me know. I’ll release the models, code, and more tweet bot rewrites and conversations when I have time. Everything together took ~4 hours of programming time and ~2 weeks neural network training time. List of fine-tuned language models (in alphabetical order) I’ve trained so far:

Barack Obama
 Bernie Sanders
 Conan O’Brien
 Deepak Chopra
 Donald Trump
 Dwayne The Rock Johnson
 Ellen DeGeneres
 Elon Musk
 Hillary Clinton
 Jimmy Fallon
 Joe Rogan
 Jordan Peterson
 Justin Bieber
 Kanye West
 Katy Perry
 Kevin Hart
 Lex Fridman
 Neil deGrasse Tyson
 Richard Dawkins
 Ricky Gervais
 Sam Harris

If you would like to learn about the basics behind the techniques used for this, you can watch my lectures on deep learning or watch my conversation with Greg Brockman (CTO, OpenAI) about the GPT-2 language model specifically:


Originally published at https://lexfridman.com/deeptweets.