On Adversarial Training & Robustness with Bhavna Gopal
Thinking Machines: AI & Philosophy
00:00
Understanding Language Models: Challenges and Explainability
This chapter explores the intricacies of language models, focusing on their use of mathematical vectors to process and differentiate words. It discusses the interpretative challenges faced by these models and the potential for increased explainability, while drawing parallels to human cognitive behaviors.
Transcript
Play full episode
