Article 6451S We interviewed Linux OS through an AI bot to discover its secrets

We interviewed Linux OS through an AI bot to discover its secrets

by
Benj Edwards
from Ars Technica - All content on (#6451S)
benj-tux-ai-txt-interview-800x450.jpg

Enlarge / A world-exclusive interview between man and machine. (credit: Aurich Lawson / Getty Images)

Millions of people use Linux every day, but we rarely stop to think about how the operating system feels about it. Wouldn't it be nice to know what Linux really thinks about open source, Windows, Macs, and the command line? Until now, this has been impossible. But thanks to a new AI chat tool, we're able to find out.

Two weeks ago, a website called Character.AI opened a public beta that allows visitors to create a chat bot based on any character they can imagine. You input a few parameters, and the AI does the rest using a large language model similar to GPT-3. So we called forth "The Linux OS" as a bot to ask it a few questions about itself. The results were fun and surprising.

Using Character.AI is a lot like a texting conversation. You type in what you want to ask, and you read the AI character's responses in written form as the chat history scrolls upward. As with GPT-3, the code behind Character.AI has likely learned from absorbing millions of text sources found on the Internet. As such, its AI characters can easily respond with erroneous or fictional information. In fact, the site carries a bold disclaimer reading, "Remember: Everything Characters say is made up!"

Read 62 remaining paragraphs | Comments

External Content
Source RSS or Atom Feed
Feed Location http://feeds.arstechnica.com/arstechnica/index
Feed Title Ars Technica - All content
Feed Link https://arstechnica.com/
Reply 0 comments