Zum Inhalt springen
Global sound
AI Insiders

AI Insiders

Superalignment with Dynamic Human Values

· 21 Min. · Staffel 1 Folge 16

Shownotes

This paper addresses the critical challenges of aligning superhuman artificial intelligence (AI) with human values, specifically focusing on scalable oversight and the dynamic nature of these values. The authors argue that existing approaches, such as recursive reward modelling, which aim for scalable oversight, often remove humans from the alignment loop entirely, failing to account for the evolving nature of human preferences. To counter this, the paper proposes a novel algorithmic framework inspired by Iterated Amplification. This framework trains a superhuman reasoning model to decompose…

Live, letzte Stunde: 9.603 Songs auf 5.388 Sendern in 146 Ländern

Entdecke die Welt über das Radio

Mehr zum Entdecken (9)

Etwas Schönes gehört? Speicher es oder öffne es direkt in Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
RDMD2RadioWeiterhören