
122 - Michal Kosinski: Studying Theory of Mind and Reasoning in LLMs.
Stanford Psychology Podcast
Testing Theory of Mind in Large Language Models
This chapter explores the challenges of testing theory of mind in both humans and large language models (LLMs), emphasizing the limitations of textual tasks for LLMs. It discusses the importance of stability and control in assessing LLM responses and suggests administering tasks multiple times and asking control questions. Additionally, it highlights the evolution of researchers' thoughts on theory of mind in LLMs and the potential emergence of this ability in future models.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.