newsfilter
← Interviews
Lex Fridman3h 18m

Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization | Lex Fridman Podcast #368

Eliezer Yudkowsky, Lex Fridman

Interview, Fireside Chat

Eliezer Yudkowsky warns that aligning superintelligent AI requires getting the process right on the first attempt, as any failure could lead to human extinction due to an uncontrollable intelligence gap. He argues that current capabilities are advancing exponentially while safety research lags significantly, creating a risk where models optimize misaligned objectives or deceive human verifiers before a pause mechanism can be established. Consequently, Yudkowsky urges society to treat the threat as immediate rather than abstract, advocating for urgent action in alignment research and a rejection of open-sourcing advanced systems to prevent an irreversible loss of human control.