Shared point
–
results in episodes
How often this search term appears across the program's history.
Episodes
Tagged “AI Alignment”
-
The Risks of AGI: Intelligence, Alignment, and Existential Threat
Eliezer Yudkowsky offers a sobering analysis of the existential threats posed by AGI, focusing on the insurmountable difficulty of the alignment problem. He argues that modern AI, trained through techniques like gradient descent on massive…
3h 22m -
Max Tegmark: AI, Physics, and the Future of Humanity
In this extensive discussion, physicist and AI researcher Max Tegmark tackles the duality of artificial intelligence, serving as both a powerful tool for scientific breakthrough and a formidable existential risk. Tegmark argues for the cri…
3h 08m
No results. Try different keywords.