Giving GPT-3 a Turing Test

I’ve been playing around with OpenAI’s new GPT-3 language model. When I got beta access, the first thing I wondered was, how human is GPT-3? How close is it to passing a Turing test?


How It Works

Let me explain how exactly I’m generating these conversations. GPT-3 is a general language model, trained on a large amount of uncategorised text from the internet. It isn’t specific to a conversational format, and it isn’t trained to answer any specific type of question. The only thing it does is, given some text, guess what text comes next.