AI Scheming: Frontier Model Risks and Mitigation

Échec de l'ajout au panier.

Veuillez réessayer plus tard

Échec de l'ajout à la liste d'envies.

Veuillez réessayer plus tard

Échec de la suppression de la liste d’envies.

Veuillez réessayer plus tard

Échec du suivi du balado

Ne plus suivre le balado a échoué

AI Scheming: Frontier Model Risks and Mitigation

Écouter gratuitement

Voir les détails du balado

À propos de cet audio

This episode unpacks a recent article from AIModels.fyi focusing on the potential for "scheming" in frontier AI models. We delve into Google DeepMind's framework for evaluating AI stealth and situational awareness, vital capabilities related to AI safety. • Can current AI models exhibit "scheming" behavior? • What are the key elements of "stealth" in AI systems? • How does "situational awareness" impact AI risk? • What are the potential threat models of AI scheming? • How can the CAE framework be used to assess AI safety? • What kinds of AI actions are considered "code sabotage?" • What kinds of AI actions are considered "research sabotage?" • What kinds of AI actions are considered "decision sabotage?" • What does 'power-seeking behavior' in AI look like?

Pas encore de commentaire