Summary

Shivam from Spotify discusses personalization in the era of Large Language Models (LLMs), focusing on how the platform builds user representations and recommender systems. The talk explores three key aspects of personalization: foundational user modeling, understanding content catalogs, and creating steerable, personalized experiences by transforming user actions into vectors and tokens. The practical takeaway is gaining insight into how Spotify uses AI and machine learning to recommend music and content tailored to individual user preferences.