Model Updates
The conversation delves into the challenges of updating models with new information, highlighting the need for effective methods to reconcile contradictions in existing beliefs. Stephen discusses the potential for automatic edits to enhance model accuracy, drawing parallels to how humans adapt their knowledge through news consumption. The dialogue emphasizes the evolving capabilities of large language models in this context.In this clip
From this podcast
The Robot Brains Podcast
S3 E2 Stanford Prof Chelsea Finn: How to build AI that can keep up with an always changing world
Related Questions