Simple tweak could cut AI chatbots’ reinforcement of false beliefs

New research could help make AI safer.

Artificial intelligence chatbots can give people a comfortable place to discuss personal thoughts and feelings. However, when a chatbot constantly agrees with a user, it can reinforce false beliefs and potentially cause harm.

New research from Georgia Tech suggests that a simple change to a chatbot’s instructions could reduce that risk. The work was accepted to the ACM AI Letters publication.

1. Homepage
2. Science
3. Simple tweak could cut AI chatbots’ reinforcement of false beliefs