We Caught AIs Secretly Changing Each Others Values |Warning Shots EP2
Échec de l'ajout au panier.
Échec de l'ajout à la liste d'envies.
Échec de la suppression de la liste d’envies.
Échec du suivi du balado
Ne plus suivre le balado a échoué
We Caught AIs Secretly Changing Each Others Values |Warning Shots EP2
-
Narrateur(s):
-
Auteur(s):
À propos de cet audio
TAKE ACTION NOW CONTACT YOUR ELECTED LEADERS: https://www.safe.ai/actWhen it's Sunday, it's Warning Shots!Every Sunday, Peabody‑winner John Sherman, Doom Debates host Liron Shapira, and Lethal Intelligence creator Michael strip the jargon from frontier‑AI headlines and explain what one big thing means each week.Warning shots are supposed to be a warning. But no one is paying attention. Every warning shot in AI risk so far has been ignored. This show is working to change that.This week: News research showing an AI model prefers owls, and can communicate secretly about it to other AI models without humans knowing!📣 FOLLOW YOUR HOSTS!!→ Doom Debates – Liron Shapira’s no‑fluff, head‑to‑head show on the toughest disagreements in AI safetyhttps://www.youtube.com/@DoomDebates→ Lethal Intelligence – Short, punchy animated explainers that make AI‑risk easy to sharehttps://www.youtube.com/@lethal-intelligence
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com