Robotics Data Trends
Jeremy and Seth discuss the trend of using previous work to generate data for robotics, highlighting the challenge of building proprietary datasets. Seth shares insights on the exciting advancements in robotics due to foundation models capturing common sense, leading to more flexible and generalized logic in robots' actions. The conversation delves into the potential of model distillation to address the size issue in robotics models, hinting at future directions in the field.In this clip
From this podcast
Last Week in AI
#132 - FraudGPT, Apple GPT, unlimited jailbreaks, RT-2, Frontier Model Forum, PhotoGuard
Related Questions