663: Astonishing CICERO negotiates and builds trust with humans using natural language
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Enhancing Language Models with Reinforcement Learning and Planning Techniques
This chapter delves into the application of reinforcement learning and planning methods to improve the performance of language models, focusing on grounded and intentional language model outputs. The speakers talk about the implementation of value-based filtering techniques to avoid strategic messaging and highlight the potential of AI models like Cicero for generating more realistic and nuanced interactions in settings such as the metaverse and video games.
Play episode from 51:20
Transcript
