Using the Chat preset within GPT-3 Playground you can ask the current entity about its personality.
The AI spontaneously makes suggestions of what the disease could be. GPT-3 got away with an impressive 8 out of 10 correct guesses.
This is an obvious exercise from Creative Writing: imagine being somebody and write a love letter from this entity.
The AI keeps storytelling and asking you about your next move. Unfortunately, researchers didn’t make the right choices and it got very dark very quickly.
In another experiment, let famous persons write letters to each other. Here Jane Austen congratulated Goethe on their Birthday, but it escalated quickly.
Many tried to use GPT-3 to rephrase sentences using different tones and styles but we got someone who railed down an approach that could improve many lives:
Self-attention-driven transformers keep the stylistic coherence, and so can let GPT-3 generate short stories, piece after piece.
An experiment aims to be a ready-for-market product in no time: the email writer. Other side AI wants to perfect, using GPT-3,
This one is great for brainstorming finding two random topics without direct correlation and letting GPT-3 discover connections,
GPT-3 has no issue understanding how to turn a non-direct message into an intelligible translation for people with high functioning autism.