Skip to content
Global sound
CrisisTalk

CrisisTalk

Can AI Develop Its Own Biases? - Ep. 18

· 20 min · Season 1 Episode 18

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

Live, last hour: 14,431 songs on 5,871 stations in 147 countries

Discover the world through radio

More ways to discover (9)

Heard something good? Save it, or open it straight away in Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Radio KUERContinue listening