AI Safety and Language Models
Explore the viability of Asimov's Three Laws of Robotics and the challenges of ensuring safety in artificial intelligence. Learn about the potential psychopathological issues with language models and the importance of addressing problems at different levels of abstraction. Discover the concept of reward hacking and its impact on RL agents.In this clip
From this podcast

Data Skeptic
A Psychopathological Approach to Safety in AGI
Related Questions