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

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: