Skip to content

AI Safety Paper #1: Open Problems and Fundamental Limitations of RLHF

Photo of Joanna Roy
Hosted By
Joanna R.
AI Safety Paper #1: Open Problems and Fundamental Limitations of RLHF

Details

Link to paper: https://arxiv.org/abs/2307.15217

Events in AI and Society
Deep Reinforcement LearningRisk Governance and Compliance
Photo of AI Safety Reading Group group
AI Safety Reading Group
See more events
AI Safety Reading Group
Photo of AI Safety Reading Group group
No ratings yet
Needs a location
Photo of AI Safety Reading Group group
AI Safety Reading Group
public group