Tony Technology
https://arstechnica.com/?p=1774477
Now OpenAI researchers say they’ve found a way to curtail GPT-3’s toxic text by feeding the program roughly 100 encyclopedia-like samples of writing by human professionals on topics like history and technology but also abuse, violence, and injustice.Yejin Choi, an associate professor at the University of Washington and leader of a group studying common sense at the Allen Institute for AI, has put GPT-3 through dozens of tests and experiments to document how it can make mistakes.
Found via Ars Technica RSS Feed :
https://feeds.arstechnica.com/arstechnica/index
Check it out for this and other awesome articles
#Shorts