Explore the inner workings of Chat-GPT and delve into crucial AI safety considerations in this thought-provoking TEDx talk by computer scientist Blaine Rogers. Gain insights into the mechanics behind Chat-GPT's functionality and understand the importance of addressing AI safety through technical alignment, interpretability research, and effective AI governance policies. Drawing from his expertise in formal verification, Bayesian statistics, and computer vision, Rogers presents a compelling case for proactive engagement with AI safety measures. Discover the potential implications of AI development and learn about the ongoing efforts to ensure responsible AI implementation in this engaging 16-minute presentation.
Overview
Syllabus
Is Chat-GPT trustworthy? | Blaine Rogers | TEDxOtemachi
Taught by
TEDx