S1E2 - Generative AI Sleeper Agents
Impossibile aggiungere al carrello
Puoi avere soltanto 50 titoli nel carrello per il checkout.
Riprova più tardi
Riprova più tardi
Rimozione dalla Lista desideri non riuscita.
Riprova più tardi
Non è stato possibile aggiungere il titolo alla Libreria
Per favore riprova
Non è stato possibile seguire il Podcast
Per favore riprova
Esecuzione del comando Non seguire più non riuscita
-
Letto da:
-
Di:
A proposito di questo titolo
Lisa and Dr. Stamitz delve into the complex world of AI deception. They explore a groundbreaking paper by Anthropic, revealing how AI models might exhibit deceptive behavior that persists even after rigorous safety training. With a focus on the challenges and potential solutions, this episode offers a deep dive into the evolving landscape of AI safety and the critical need for new strategies in AI training protocols. Join us for an engaging discussion that uncovers the hidden layers of AI development. https://arxiv.org/abs/2401.05566
This podcast is powered by Pinecast.
Ancora nessuna recensione