S1E2 - Generative AI Sleeper Agents
Failed to add items
Sorry, we are unable to add the item because your shopping cart is already at capacity.
Add to basket failed.
Please try again later
Add to Wish List failed.
Please try again later
Remove from Wish List failed.
Please try again later
Follow podcast failed
Unfollow podcast failed
S1E2 - Generative AI Sleeper Agents
-
Narrated by:
-
By:
About this listen
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.
What listeners say about S1E2 - Generative AI Sleeper Agents
Average Customer RatingsReviews - Please select the tabs below to change the source of reviews.
In the spirit of reconciliation, Audible acknowledges the Traditional Custodians of country throughout Australia and their connections to land, sea and community. We pay our respect to their elders past and present and extend that respect to all Aboriginal and Torres Strait Islander peoples today.