663: Astonishing CICERO negotiates and builds trust with humans using natural language
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Building a Competitive Chess Computer Against Humans
The chapter explores the process of training a chess computer to compete against humans in real-time, starting from playing against other bots to nearly perfect performance challenging top human players. It delves into the differences between game algorithms, focusing on the complexities of diplomacy games like negotiating and forming alliances. The chapter also discusses the challenges faced by large language models in outputting high-quality responses and the adaptation of a language model to handle correlated behavior and create individualized plans for different players.
Play episode from 28:53
Transcript
