These Conversations With the GPT-3 Chatbot Are Witty, Wise, and Dangerously Dark

A neural network did not write this

Image: baona/Getty Images

GPT-3 might sound like the name of an Android from Star Wars, but it’s really a neural network–powered language model — a computer program that, in layman’s terms, takes a load of text and then “speaks” by guessing what the next word is most likely to be.

OpenAI, the nonprofit behind the system, says it built GPT-3 as part of its goal to create a “friendly A.I.” that “benefits humanity” as a whole (as opposed to a Terminator-style unfriendly A.I. that… well, doesn’t.)

Generative Pretrained Transformer 3 (GPT-3) is an obscure-sounding mouthful that largely manifests itself as a sort of chatbot. You send it messages. It replies. And it’s actually good. Take, for example, this “conversation” between Kevin Lacker, CTO of Parse, and GPT-3:

Human: What is your favorite animal?

GPT-3: My favorite animal is a dog.

Human: Why?

GPT-3: Because dogs are loyal and friendly.

Human: What are two reasons that a dog might be in a bad mood?

GPT-3: Two reasons that a dog might be in a bad mood are if it is hungry or if it is hot.