research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
share
research
∙
05/26/2023
Twitter's Algorithm: Amplifying Anger, Animosity, and Affective Polarization
As social media continues to have a significant influence on public opin...
research
∙
03/16/2023
Characterizing Manipulation from AI Systems
Manipulation is a common concern in many domains, such as social media, ...
research
∙
02/20/2023
