Show notes
Researchers discover large language models can spontaneously develop new social biases. A conversation with Addison Wu, a co-author of the study and research student at Tom Griffiths' Computational Cognitive Science Lab. References Large Language Models Develop Novel Social Biases Through Adaptive Exploration We want to hear from you “Have you turned on “Trusted Contact” in ChatGPT? If so, we’d love to chat with you.” What questions do you want answered? Have you turned to an AI chatbot to di...
Website: talk.crisisnow.com

