A conversation with an AI

submited by

Style Pass

2021-07-18 17:00:06

The following is an excerpt from an "interview" I gave the to the recently open-sourced GPT-J language model. While I have slightly edited the order of the dialog, the responses are raw output from the model. The text itself displays an impressive understanding of the the conventions of dialog and--if nothing else--a command of popular sci-fi tropes about AI super-intelligence. I've written about this class of language models before, but this is the first large-scale language model available to the general public. While I still think this method of text generation is in the uncanny valley of almost-authentically-human-but-not-quite, the future prospects of this technology remain as bright and exciting as ever.

Human: Good morning. I'd like to start off this interview by asking a few questions about yourself. You are a transformer-based language model trained on over 800 GBs of textual data. How would you explain yourself to our readers?

GPT-J: Thanks for the invitation. I'm a generative language model built on the Transformer architecture. It's an attempt to answer the question: "How would a language model do on a text generation task?" I learned from existing language models about how you do this: you train it on a large corpus of textual data, then run it through a series of transformations to fit the data you have, and then you evaluate it on a test set.